https://mw.hh.se/caisr/api.php?action=feedcontributions&feedformat=atom&user=Mohbou ISLAB/CAISR - User contributions [en] 2026-04-04T13:29:29Z User contributions MediaWiki 1.35.13 https://mw.hh.se/caisr/index.php?title=Mohamed-Rafik_Bouguelia&diff=5501 Mohamed-Rafik Bouguelia 2025-04-05T21:33:14Z <p>Mohbou: </p> <hr /> <div>{{Person<br /> |Family Name=Bouguelia<br /> |Given Name=Mohamed-Rafik<br /> |Title=PhD, Docent<br /> |Position=Associate Professor of Machine Learning<br /> |Email=mohamed-rafik.bouguelia@hh.se<br /> |Image=Rafiko.jpg<br /> |Country=Sweden<br /> |Office=F509<br /> |url=https://sites.google.com/view/bouguelia<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Machine Learning<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Deep Learning<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Artificial Intelligence<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Science<br /> }}<br /> [[Category:Staff]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> <br /> ==&#039;&#039;&#039;Publications&#039;&#039;&#039;==<br /> Google Scholar publication list [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= by clicking here]<br /> <br /> <br /> [[Category:staff]]</div> Mohbou https://mw.hh.se/caisr/index.php?title=File:Rafiko.jpg&diff=5500 File:Rafiko.jpg 2025-04-05T21:30:00Z <p>Mohbou: Mohbou uploaded a new version of &amp;quot;File:Rafiko.jpg&amp;quot;</p> <hr /> <div></div> Mohbou https://mw.hh.se/caisr/index.php?title=Mohamed-Rafik_Bouguelia&diff=5499 Mohamed-Rafik Bouguelia 2025-04-05T21:27:03Z <p>Mohbou: </p> <hr /> <div>{{Person<br /> |Family Name=Bouguelia<br /> |Given Name=Mohamed-Rafik<br /> |Position=Associate Professor of Machine Learning<br /> |Email=mohamed-rafik.bouguelia@hh.se<br /> |Image=Rafiko.jpg<br /> |Country=Sweden<br /> |Office=F509<br /> |url=https://sites.google.com/view/bouguelia<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Machine Learning<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Deep Learning<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Artificial Intelligence<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Science<br /> }}<br /> [[Category:Staff]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> <br /> ==&#039;&#039;&#039;Publications&#039;&#039;&#039;==<br /> Google Scholar publication list [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= by clicking here]<br /> <br /> <br /> [[Category:staff]]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Mohamed-Rafik_Bouguelia&diff=5212 Mohamed-Rafik Bouguelia 2023-05-25T11:20:23Z <p>Mohbou: </p> <hr /> <div>{{Person<br /> |Family Name=Bouguelia<br /> |Given Name=Mohamed-Rafik<br /> |Title=PhD<br /> |Phone=+46728368919<br /> |Cell Phone=+46728368919<br /> |Position=Associate Professor<br /> |Email=mohamed-rafik.bouguelia@hh.se<br /> |Image=Rafiko.jpg<br /> |Country=Sweden<br /> |Office=F509<br /> }}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignProjects<br /> |project=SeMI<br /> }}<br /> {{AssignProjects<br /> |project=BIDAF<br /> }}<br /> {{AssignProjects<br /> |project=SA3L - Situation Awareness for Ambient Assisted Living<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Machine Learning<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Artificial Intelligence<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Smart Energy<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Learning Systems (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Supervised Machine Learning (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Linux Administration (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Introduction to Linux and Python (7.5 credits)<br /> }}<br /> [[Category:Staff]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> <br /> ==&#039;&#039;&#039;Publications&#039;&#039;&#039;==<br /> See my Google Scholar publication list [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= by clicking here]<br /> <br /> <br /> [[Category:staff]]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Mohamed-Rafik_Bouguelia&diff=5211 Mohamed-Rafik Bouguelia 2023-05-25T11:19:55Z <p>Mohbou: </p> <hr /> <div>{{Person<br /> |Family Name=Bouguelia<br /> |Given Name=Mohamed-Rafik<br /> |Title=PhD<br /> |Phone=+46728368919<br /> |Cell Phone=+46728368919<br /> |Position=Associate Professor<br /> |Email=mohamed-rafik.bouguelia@hh.se<br /> |Image=Rafiko.jpg<br /> |Country=Sweden<br /> |Office=F509<br /> }}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignProjects<br /> |project=SeMI<br /> }}<br /> {{AssignProjects<br /> |project=BIDAF<br /> }}<br /> {{AssignProjects<br /> |project=SA3L - Situation Awareness for Ambient Assisted Living<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Machine Learning<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Artificial Intelligence<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Smart Energy<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Learning Systems (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Supervised Machine Learning (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Linux Administration (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Introduction to Linux and Python (7.5 credits)<br /> }}<br /> [[Category:Staff]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> <br /> ==&#039;&#039;&#039;Research Projects&#039;&#039;&#039;==<br /> {{InsertProjects}}<br /> <br /> ==&#039;&#039;&#039;Courses&#039;&#039;&#039;==<br /> {{InsertTeacherAndExaminer}}<br /> Some videos of my machine learning course(s) are also available at https://www.youtube.com/playlist?list=PLS8J_PRPtGfdnPf9QqT7Itnn2rAHsoWqY<br /> <br /> ==&#039;&#039;&#039;Publications&#039;&#039;&#039;==<br /> See my Google Scholar publication list [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= by clicking here]<br /> <br /> <br /> [[Category:staff]]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Mohamed-Rafik_Bouguelia&diff=4828 Mohamed-Rafik Bouguelia 2021-04-03T12:42:50Z <p>Mohbou: </p> <hr /> <div>{{Person<br /> |Family Name=Bouguelia<br /> |Given Name=Mohamed-Rafik<br /> |Title=PhD<br /> |Phone=+46728368919<br /> |Cell Phone=+46728368919<br /> |Position=Associate Professor<br /> |Email=mohamed-rafik.bouguelia@hh.se<br /> |Image=Rafiko.jpg<br /> |Country=Sweden<br /> |Office=F509<br /> }}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignProjects<br /> |project=SeMI<br /> }}<br /> {{AssignProjects<br /> |project=BIDAF<br /> }}<br /> {{AssignProjects<br /> |project=SA3L - Situation Awareness for Ambient Assisted Living<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Machine Learning<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Artificial Intelligence<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Smart Energy<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Learning Systems (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Supervised Machine Learning (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Linux Administration (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Introduction to Linux and Python (7.5 credits)<br /> }}<br /> [[Category:Staff]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> <br /> ==&#039;&#039;&#039;Research Projects&#039;&#039;&#039;==<br /> {{InsertProjects}}<br /> <br /> ==&#039;&#039;&#039;Courses&#039;&#039;&#039;==<br /> {{InsertTeacherAndExaminer}}<br /> Some videos of my machine learning course(s) are also available at https://www.youtube.com/playlist?list=PLS8J_PRPtGfdnPf9QqT7Itnn2rAHsoWqY<br /> <br /> ==&#039;&#039;&#039;Publications&#039;&#039;&#039;==<br /> See my Google Scholar publication list [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= by clicking here]<br /> <br /> &#039;&#039;&#039;The following is an automatically retrieved incomplete list of publications. [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= Please click here for a more complete list.]&#039;&#039;&#039;<br /> <br /> {{PublicationsList}}<br /> <br /> [[Category:staff]]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Mohamed-Rafik_Bouguelia&diff=4823 Mohamed-Rafik Bouguelia 2021-03-19T08:01:30Z <p>Mohbou: </p> <hr /> <div>{{Person<br /> |Family Name=Bouguelia<br /> |Given Name=Mohamed-Rafik<br /> |Title=PhD<br /> |Phone=+46728368919<br /> |Cell Phone=+46728368919<br /> |Position=Associate Professor<br /> |Email=mohbou@hh.se<br /> |Image=Rafiko.jpg<br /> |Country=Sweden<br /> |Office=F509<br /> }}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignProjects<br /> |project=SeMI<br /> }}<br /> {{AssignProjects<br /> |project=BIDAF<br /> }}<br /> {{AssignProjects<br /> |project=SA3L - Situation Awareness for Ambient Assisted Living<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Machine Learning<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Artificial Intelligence<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Smart Energy<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Learning Systems (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Supervised Machine Learning (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Linux Administration (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Introduction to Linux and Python (7.5 credits)<br /> }}<br /> [[Category:Staff]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> <br /> ==&#039;&#039;&#039;Research Projects&#039;&#039;&#039;==<br /> {{InsertProjects}}<br /> <br /> ==&#039;&#039;&#039;Courses&#039;&#039;&#039;==<br /> {{InsertTeacherAndExaminer}}<br /> Some videos of my machine learning course(s) are also available at https://www.youtube.com/playlist?list=PLS8J_PRPtGfdnPf9QqT7Itnn2rAHsoWqY<br /> <br /> ==&#039;&#039;&#039;Publications&#039;&#039;&#039;==<br /> See my Google Scholar publication list [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= by clicking here]<br /> <br /> &#039;&#039;&#039;The following is an automatically retrieved incomplete list of publications. [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= Please click here for a more complete list.]&#039;&#039;&#039;<br /> <br /> {{PublicationsList}}<br /> <br /> [[Category:staff]]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Mohamed-Rafik_Bouguelia&diff=4822 Mohamed-Rafik Bouguelia 2021-03-19T08:00:34Z <p>Mohbou: </p> <hr /> <div>{{Person<br /> |Family Name=Bouguelia<br /> |Given Name=Mohamed-Rafik<br /> |Title=PhD<br /> |Phone=+46728368919<br /> |Cell Phone=+46728368919<br /> |Position=Associate Professor<br /> |Email=mohbou@hh.se<br /> |Image=Rafiko.jpg<br /> |Country=Sweden<br /> |Office=F509<br /> }}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignProjects<br /> |project=SeMI<br /> }}<br /> {{AssignProjects<br /> |project=BIDAF<br /> }}<br /> {{AssignProjects<br /> |project=SA3L - Situation Awareness for Ambient Assisted Living<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Machine Learning<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Artificial Intelligence<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Smart Energy<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Learning Systems (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Supervised Machine Learning (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Linux Administration (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Introduction to Linux and Python (7.5 credits)<br /> }}<br /> [[Category:Staff]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> <br /> ==&#039;&#039;&#039;Research Projects&#039;&#039;&#039;==<br /> {{InsertProjects}}<br /> <br /> ==&#039;&#039;&#039;Courses&#039;&#039;&#039;==<br /> {{InsertTeacherAndExaminer}}<br /> Videos of my machine learning course(s) are also available at: https://www.youtube.com/playlist?list=PLS8J_PRPtGfdnPf9QqT7Itnn2rAHsoWqY<br /> <br /> ==&#039;&#039;&#039;Publications&#039;&#039;&#039;==<br /> See my Google Scholar publication list [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= by clicking here]<br /> <br /> &#039;&#039;&#039;The following is an automatically retrieved incomplete list of publications. [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= Please click here for a more complete list.]&#039;&#039;&#039;<br /> <br /> {{PublicationsList}}<br /> <br /> [[Category:staff]]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Anomaly_Detection_for_Predictive_Maintenance_with_Elvaco&diff=4770 Anomaly Detection for Predictive Maintenance with Elvaco 2020-10-26T16:12:47Z <p>Mohbou: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Anomaly Detection for Predictive Maintenance with Elvaco<br /> |Supervisor=Yuantao Fan, Mohamed-Rafik Bouguelia<br /> |Level=Master<br /> |Status=Internal Draft<br /> }}</div> Mohbou https://mw.hh.se/caisr/index.php?title=Anomaly_Detection_for_Predictive_Maintenance_with_Elvaco&diff=4769 Anomaly Detection for Predictive Maintenance with Elvaco 2020-10-26T16:11:27Z <p>Mohbou: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Anomaly Detection for Predictive Maintenance with Elvaco<br /> |Supervisor=Yuantao Fan, Mohamed-Rafik Bouguelia<br /> |Level=Master<br /> |Status=Draft<br /> }}</div> Mohbou https://mw.hh.se/caisr/index.php?title=Anomaly_Detection_for_Predictive_Maintenance_with_Elvaco&diff=4768 Anomaly Detection for Predictive Maintenance with Elvaco 2020-10-26T16:08:42Z <p>Mohbou: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Anomaly detection in sensor data for predictive maintenance purpose, in collaboration with Elvaco<br /> |TimeFrame=Fall 2020<br /> |Supervisor=Yuantao Fan, Mohamed-Rafik Bouguelia<br /> |Level=Master<br /> |Status=Draft<br /> }}<br /> Detect anomalies in sensor data for finding faults, e.g. sensor errors, water leakages in heating systems, in collaboration with Elvaco.</div> Mohbou https://mw.hh.se/caisr/index.php?title=Anomaly_detection_in_district_heating_data_-_with_the_Elvaco_company&diff=4767 Anomaly detection in district heating data - with the Elvaco company 2020-10-26T16:07:08Z <p>Mohbou: Created page with &quot;{{StudentProjectTemplate |Summary=Project around predictive maintenance in district heating |Supervisor=Yuantao Fan, Mohamed-Rafik Bouguelia, |Level=Master |Status=Draft }} T...&quot;</p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Project around predictive maintenance in district heating<br /> |Supervisor=Yuantao Fan, Mohamed-Rafik Bouguelia, <br /> |Level=Master<br /> |Status=Draft<br /> }}<br /> This project is defined around anomaly detection and predictive maintenance in district heating data. The project will likely use data from the Elvaco company, which includes measurements like the water flow, indoor-temperatures, and other temperatures. The goal is to analyze such data to identify challenges related to it and develop algorithms to detect anomalies, both for when the sensor(s) is bad and when something out of the ordinary (e.g. water leak) happens.</div> Mohbou https://mw.hh.se/caisr/index.php?title=Finding_patterns/motifs_in_time_series_data&diff=4765 Finding patterns/motifs in time series data 2020-10-26T15:33:05Z <p>Mohbou: Created page with &quot;{{StudentProjectTemplate |Summary=Finding patterns/motifs in time series data, for autonomous clustering or outlier detection |Supervisor=Thorsteinn Rögnvaldsson, Mohamed-Raf...&quot;</p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Finding patterns/motifs in time series data, for autonomous clustering or outlier detection<br /> |Supervisor=Thorsteinn Rögnvaldsson, Mohamed-Rafik Bouguelia, <br /> |Level=Master<br /> |Status=Draft<br /> }}<br /> The goal of this project is to find patterns/motifs in time series data. This can be applied for the purpose of autonomous clustering (to explore the data and better understand how a system works) or for the purpose of outlier detection (e.g. to detect faults in a given system).</div> Mohbou https://mw.hh.se/caisr/index.php?title=Mohamed-Rafik_Bouguelia&diff=4608 Mohamed-Rafik Bouguelia 2020-08-11T13:18:00Z <p>Mohbou: </p> <hr /> <div>{{Person<br /> |Family Name=Bouguelia<br /> |Given Name=Mohamed-Rafik<br /> |Title=PhD<br /> |Phone=+46728368919<br /> |Cell Phone=+46728368919<br /> |Position=Assistant Professor<br /> |Email=mohbou@hh.se<br /> |Image=Rafiko.jpg<br /> |Country=Sweden<br /> |Office=F509<br /> }}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignProjects<br /> |project=SeMI<br /> }}<br /> {{AssignProjects<br /> |project=BIDAF<br /> }}<br /> {{AssignProjects<br /> |project=SA3L - Situation Awareness for Ambient Assisted Living<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Machine Learning<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Learning Systems (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Introduction to Linux and Python (7.5 credits)<br /> }}<br /> [[Category:Staff]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> <br /> ==&#039;&#039;&#039;Research Projects&#039;&#039;&#039;==<br /> {{InsertProjects}}<br /> <br /> ==&#039;&#039;&#039;Courses&#039;&#039;&#039;==<br /> {{InsertTeacherAndExaminer}}<br /> Videos of my machine learning course(s) are also available at: https://www.youtube.com/playlist?list=PLS8J_PRPtGfdnPf9QqT7Itnn2rAHsoWqY<br /> <br /> ==&#039;&#039;&#039;Publications&#039;&#039;&#039;==<br /> See my Google Scholar publication list [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= by clicking here]<br /> <br /> &#039;&#039;&#039;The following is an automatically retrieved incomplete list of publications. [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= Please click here for a more complete list.]&#039;&#039;&#039;<br /> <br /> {{PublicationsList}}<br /> <br /> [[Category:staff]]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Learning_Systems_(7.5_credits)&diff=4607 Learning Systems (7.5 credits) 2020-08-11T13:16:12Z <p>Mohbou: </p> <hr /> <div>{{CourseTemplate<br /> |CourseCode=DT8008 <br /> |CourseShortDescription=The objective of the course is to provide an overview of machine learning systems for classification, regression, and self-organization, to study basic learning algorithms in detail.<br /> |CourseUrl=https://www.youtube.com/playlist?list=PLS8J_PRPtGfdnPf9QqT7Itnn2rAHsoWqY<br /> |CourseLevel=Advanced<br /> |isNativeISlab=true<br /> |SubjectArea=Learning Systems<br /> }}<br /> <br /> Videos of this course are also available at:<br /> https://www.youtube.com/playlist?list=PLS8J_PRPtGfdnPf9QqT7Itnn2rAHsoWqY</div> Mohbou https://mw.hh.se/caisr/index.php?title=Mohamed-Rafik_Bouguelia&diff=4588 Mohamed-Rafik Bouguelia 2020-05-06T18:46:54Z <p>Mohbou: </p> <hr /> <div>{{Person<br /> |Family Name=Bouguelia<br /> |Given Name=Mohamed-Rafik<br /> |Title=PhD<br /> |Phone=+46728368919<br /> |Cell Phone=+46728368919<br /> |Position=Assistant Professor<br /> |Email=mohbou@hh.se<br /> |Image=Rafiko.jpg<br /> |Country=Sweden<br /> |Office=F509<br /> }}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignProjects<br /> |project=SeMI<br /> }}<br /> {{AssignProjects<br /> |project=BIDAF<br /> }}<br /> {{AssignProjects<br /> |project=SA3L - Situation Awareness for Ambient Assisted Living<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Machine Learning<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Learning Systems (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Introduction to Linux and Python (7.5 credits)<br /> }}<br /> [[Category:Staff]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> <br /> ==&#039;&#039;&#039;Research Projects&#039;&#039;&#039;==<br /> {{InsertProjects}}<br /> <br /> ==&#039;&#039;&#039;Courses&#039;&#039;&#039;==<br /> {{InsertTeacherAndExaminer}}<br /> <br /> ==&#039;&#039;&#039;Publications&#039;&#039;&#039;==<br /> See my Google Scholar publication list [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= by clicking here]<br /> <br /> &#039;&#039;&#039;The following is an automatically retrieved incomplete list of publications. [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= Please click here for a more complete list.]&#039;&#039;&#039;<br /> <br /> {{PublicationsList}}<br /> <br /> [[Category:staff]]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Publications:Interactive_Clustering_:_A_Comprehensive_Review&diff=4587 Publications:Interactive Clustering : A Comprehensive Review 2020-05-06T18:21:15Z <p>Mohbou: </p> <hr /> <div>&lt;div style=&#039;display: none&#039;&gt;<br /> == Do not edit this section ==<br /> &lt;/div&gt;<br /> {{PublicationSetupTemplate|Author=Juhee Bae, Tove Helldin, Maria Riveiro, Sławomir Nowaczyk, Rafik Bouguelia, Göran Falkman<br /> |PID=1392785<br /> |Name=Bae, Juhee (0000-0002-2415-7243) (University of Skövde, Skövde, Sweden);Helldin, Tove (0000-0001-6245-5850) (University of Skövde, Skövde, Sweden);Riveiro, Maria (Jönköping University, Jönköping, Sweden &amp; University of Skövde, Skövde, Sweden);Nowaczyk, Sławomir (slanow) (0000-0002-7796-5201) (Högskolan i Halmstad (2804), Akademin för informationsteknologi (16904), Halmstad Embedded and Intelligent Systems Research (EIS) (3938), CAISR Centrum för tillämpade intelligenta system (IS-lab) (13650));Bouguelia, Mohamed-Rafik (mohbou) (0000-0002-2859-6155) (Högskolan i Halmstad (2804), Akademin för informationsteknologi (16904), Halmstad Embedded and Intelligent Systems Research (EIS) (3938), CAISR Centrum för tillämpade intelligenta system (IS-lab) (13650));Falkman, Göran (0000-0001-8884-2154) (University of Skövde, Skövde, Sweden)<br /> |Title=Interactive Clustering: A Comprehensive Review<br /> |PublicationType=Journal Paper<br /> |ContentType=Refereegranskat<br /> |Language=eng<br /> |Journal=ACM Computing Surveys<br /> |JournalISSN=0360-0300<br /> |Status=published<br /> |Volume=53<br /> |Issue=1<br /> |HostPublication=<br /> |Conference=<br /> |StartPage=<br /> |EndPage=<br /> |Year=2020<br /> |Edition=<br /> |Pages=<br /> |City=New York, NY<br /> |Publisher=ACM Digital Library<br /> |Series=<br /> |SeriesISSN=<br /> |ISBN=<br /> |Urls=<br /> |ISRN=<br /> |DOI=http://dx.doi.org/10.1145/3340960<br /> |ISI=<br /> |PMID=<br /> |ScopusId=<br /> |NBN=urn:nbn:se:hh:diva-41634<br /> |LocalId=<br /> |ArchiveNumber=<br /> |Keywords=Clustering;Interactive;Interaction;User;Evaluation;Feedback;Survey;Machine Learning;Data Mining<br /> |Categories=Datorsystem (20206)<br /> |ResearchSubjects=<br /> |Projects=<br /> |Notes=<br /> |Abstract=&lt;p&gt;In this survey, 105 papers related to interactive clustering were reviewed according to seven perspectives: (1) on what level is the interaction happening, (2) which interactive operations are involved, (3) how user feedback is incorporated, (4) how interactive clustering is evaluated, (5) which data and (6) which clustering methods have been used, and (7) what outlined challenges there are. This article serves as a comprehensive overview of the field and outlines the state of the art within the area as well as identifies challenges and future research needs. © 2020 Copyright held by the owner/author(s).&lt;/p&gt;<br /> |Opponents=<br /> |Supervisors=<br /> |Examiners=<br /> |Patent=<br /> |ThesisLevel=<br /> |Credits=<br /> |Programme=<br /> |Subject=<br /> |Uppsok=<br /> |DefencePlace=<br /> |DefenceLanguage=<br /> |DefenceDate=<br /> |CreatedDate=2020-02-10<br /> |PublicationDate=2020-02-10<br /> |LastUpdated=2020-02-14<br /> |diva=http://hh.diva-portal.org/smash/record.jsf?searchId=1&amp;pid=diva2:1392785}}<br /> &lt;div style=&#039;display: none&#039;&gt;<br /> <br /> == Keep all hand-made modifications below ==<br /> &lt;/div&gt;{{PublicationDisplayTemplate}}</div> Mohbou https://mw.hh.se/caisr/index.php?title=Mohamed-Rafik_Bouguelia&diff=4584 Mohamed-Rafik Bouguelia 2020-04-22T13:44:27Z <p>Mohbou: </p> <hr /> <div>{{Person<br /> |Family Name=Bouguelia<br /> |Given Name=Mohamed-Rafik<br /> |Title=PhD<br /> |Phone=+46728368919<br /> |Cell Phone=+46728368919<br /> |Position=Assistant Professor<br /> |Email=mohbou@hh.se<br /> |Image=Rafiko.jpg<br /> |Office=F509<br /> }}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignProjects<br /> |project=SeMI<br /> }}<br /> {{AssignProjects<br /> |project=BIDAF<br /> }}<br /> {{AssignProjects<br /> |project=SA3L - Situation Awareness for Ambient Assisted Living<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Machine Learning<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Learning Systems (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Introduction to Linux and Python (7.5 credits)<br /> }}<br /> [[Category:Staff]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> <br /> ==&#039;&#039;&#039;Research Projects&#039;&#039;&#039;==<br /> {{InsertProjects}}<br /> <br /> ==&#039;&#039;&#039;Courses&#039;&#039;&#039;==<br /> {{InsertTeacherAndExaminer}}<br /> <br /> ==&#039;&#039;&#039;Publications&#039;&#039;&#039;==<br /> See my Google Scholar publication list [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= by clicking here]<br /> <br /> &#039;&#039;&#039;The following is an automatically retrieved incomplete list of publications. [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= Please click here for a more complete list.]&#039;&#039;&#039;<br /> <br /> {{PublicationsList}}<br /> <br /> [[Category:staff]]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Mohamed-Rafik_Bouguelia&diff=4583 Mohamed-Rafik Bouguelia 2020-04-22T13:43:13Z <p>Mohbou: </p> <hr /> <div>{{Person<br /> |Family Name=Bouguelia<br /> |Given Name=Mohamed-Rafik<br /> |Title=PhD<br /> |Phone=+46728368919<br /> |Cell Phone=+46728368919<br /> |Position=Assistant Professor<br /> |Email=mohbou@hh.se<br /> |Image=Rafiko.jpg<br /> |Office=F509<br /> }}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignProjects<br /> |project=SeMI<br /> }}<br /> {{AssignProjects<br /> |project=BIDAF<br /> }}<br /> {{AssignProjects<br /> |project=SA3L - Situation Awareness for Ambient Assisted Living<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Machine Learning<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Learning Systems (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Introduction to Linux and Python (7.5 credits)<br /> }}<br /> [[Category:Staff]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> <br /> ==&#039;&#039;&#039;Research Projects&#039;&#039;&#039;==<br /> {{InsertProjects}}<br /> <br /> ==&#039;&#039;&#039;Courses&#039;&#039;&#039;==<br /> {{InsertCourses}}<br /> <br /> ==&#039;&#039;&#039;Publications&#039;&#039;&#039;==<br /> See my Google Scholar publication list [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= by clicking here]<br /> <br /> &#039;&#039;&#039;The following is an automatically retrieved incomplete list of publications. [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= Please click here for a more complete list.]&#039;&#039;&#039;<br /> <br /> {{PublicationsList}}<br /> <br /> [[Category:staff]]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Mohamed-Rafik_Bouguelia&diff=4582 Mohamed-Rafik Bouguelia 2020-04-22T13:41:28Z <p>Mohbou: </p> <hr /> <div>{{Person<br /> |Family Name=Bouguelia<br /> |Given Name=Mohamed-Rafik<br /> |Title=PhD<br /> |Phone=+46728368919<br /> |Cell Phone=+46728368919<br /> |Position=Assistant Professor<br /> |Email=mohbou@hh.se<br /> |Image=Rafiko.jpg<br /> |Office=F509<br /> }}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignProjects<br /> |project=SeMI<br /> }}<br /> {{AssignProjects<br /> |project=BIDAF<br /> }}<br /> {{AssignProjects<br /> |project=SA3L - Situation Awareness for Ambient Assisted Living<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Machine Learning<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Learning Systems (7.5 credits)<br /> }}<br /> {{AssignExaminer<br /> |Examiner=Introduction to Linux and Python (7.5 credits)<br /> }}<br /> [[Category:Staff]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> <br /> ==&#039;&#039;&#039;Research Projects&#039;&#039;&#039;==<br /> {{InsertProjects}}<br /> <br /> ==&#039;&#039;&#039;Publications&#039;&#039;&#039;==<br /> See my Google Scholar publication list [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= by clicking here]<br /> <br /> &#039;&#039;&#039;The following is an automatically retrieved incomplete list of publications. [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= Please click here for a more complete list.]&#039;&#039;&#039;<br /> <br /> {{PublicationsList}}<br /> <br /> [[Category:staff]]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Mohamed-Rafik_Bouguelia&diff=4574 Mohamed-Rafik Bouguelia 2020-04-16T09:59:15Z <p>Mohbou: </p> <hr /> <div>{{Person<br /> |Family Name=Bouguelia<br /> |Given Name=Mohamed-Rafik<br /> |Title=PhD<br /> |Phone=+46728368919<br /> |Cell Phone=+46728368919<br /> |Position=Assistant Professor<br /> |Email=mohbou@hh.se<br /> |Image=Rafiko.jpg<br /> |Office=F509<br /> }}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignProjects<br /> |project=SeMI<br /> }}<br /> {{AssignProjects<br /> |project=BIDAF<br /> }}<br /> {{AssignProjects<br /> |project=SA3L - Situation Awareness for Ambient Assisted Living<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Machine Learning<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> [[Category:Staff]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> <br /> ==&#039;&#039;&#039;Research Projects&#039;&#039;&#039;==<br /> {{InsertProjects}}<br /> <br /> ==&#039;&#039;&#039;Publications&#039;&#039;&#039;==<br /> See my Google Scholar publication list [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= by clicking here]<br /> <br /> &#039;&#039;&#039;The following is an automatically retrieved incomplete list of publications. [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= Please click here for a more complete list.]&#039;&#039;&#039;<br /> <br /> {{PublicationsList}}<br /> <br /> [[Category:staff]]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Publications:Large-scale_monitoring_of_operationally_diverse_district_heating_substations_:_A_reference-group_based_approach&diff=4562 Publications:Large-scale monitoring of operationally diverse district heating substations : A reference-group based approach 2020-03-31T11:13:46Z <p>Mohbou: </p> <hr /> <div>&lt;div style=&#039;display: none&#039;&gt;<br /> == Do not edit this section ==<br /> &lt;/div&gt;<br /> {{PublicationSetupTemplate|Author=Shiraz Farouq, Stefan Byttner, Rafik Bouguelia, Natasa Nord, Henrik Gadd<br /> |PID=1370681<br /> |Name=Farouq, Shiraz (shifar) (Högskolan i Halmstad (2804), Akademin för informationsteknologi (16904), Halmstad Embedded and Intelligent Systems Research (EIS) (3938), CAISR Centrum för tillämpade intelligenta system (IS-lab) (13650));Byttner, Stefan (stefan) (Högskolan i Halmstad (2804), Akademin för informationsteknologi (16904), Halmstad Embedded and Intelligent Systems Research (EIS) (3938), CAISR Centrum för tillämpade intelligenta system (IS-lab) (13650));Bouguelia, Mohamed-Rafik (mohbou) (0000-0002-2859-6155) (Högskolan i Halmstad (2804), Akademin för informationsteknologi (16904), Halmstad Embedded and Intelligent Systems Research (EIS) (3938), CAISR Centrum för tillämpade intelligenta system (IS-lab) (13650));Nord, Natasa;Gadd, Henrik<br /> |Title=Large-scale monitoring of operationally diverse district heating substations : A reference-group based approach<br /> |PublicationType=Journal Paper<br /> |ContentType=Refereegranskat<br /> |Language=eng<br /> |Journal=Engineering applications of artificial intelligence<br /> |JournalISSN=0952-1976<br /> |Status=submitted<br /> |Volume=<br /> |Issue=<br /> |HostPublication=<br /> |Conference=<br /> |StartPage=<br /> |EndPage=<br /> |Year=2020<br /> |Edition=<br /> |Pages=<br /> |City=Oxford<br /> |Publisher=Elsevier<br /> |Series=<br /> |SeriesISSN=<br /> |ISBN=<br /> |Urls=<br /> |ISRN=<br /> |DOI=<br /> |ISI=<br /> |PMID=<br /> |ScopusId=<br /> |NBN=urn:nbn:se:hh:diva-40962<br /> |LocalId=<br /> |ArchiveNumber=<br /> |Keywords=<br /> |Categories=Elektroteknik och elektronik (202)<br /> |ResearchSubjects=<br /> |Projects=<br /> |Notes=<br /> |Abstract=&lt;p&gt;A well-understood prior model for a District Heating (DH) substation is rarely available. Alternatively, since DH substations in a network share a common task, one can assume that they are all operationally homogeneous. Any DH substation that does not conform with the majority is an outlier, and therefore ought to be investigated. However, a DH substation can be affected by varying social and technical factors. Such details are rarely available.  Therefore, large-scale monitoring of DH substations in a network is challenging. Hence, in order to address these issues, we proposed a reference-group based monitoring approach. Herein, the operational monitoring of a DH substation, referred to as a target, is delegated to a reference-group which consists of DH substations experiencing a comparable operating regime along with the target. The approach was demonstrated on the monitoring of the return temperature variable for atypical\footnote{Here, &quot;atypical&quot; means that while it does not fit the definition of a normal operation, it is not faulty either and may also have some context.}  and faulty operational behavior in $778$ DH substations associated with multi-dwelling buildings. No target substation specific information related to its normal, atypical or faulty operation was used. Instead, information from the target&#039;s reference-group was leveraged to track its operational behavior. In this manner, $44$ DH substations were found where a possible deviation in the return temperature was detected earlier compared to models assuming overall operational homogeneity among the DH substations. In addition, six frequent patterns of deviating behavior in the return temperature of DH substations were identified based on the proposed reference-group based approach, which were then further corroborated by the feedback from a DH domain expert. &lt;/p&gt;<br /> |Opponents=<br /> |Supervisors=<br /> |Examiners=<br /> |Patent=<br /> |ThesisLevel=<br /> |Credits=<br /> |Programme=<br /> |Subject=<br /> |Uppsok=<br /> |DefencePlace=<br /> |DefenceLanguage=<br /> |DefenceDate=<br /> |CreatedDate=2019-11-16<br /> |PublicationDate=2020-02-4<br /> |LastUpdated=2019-11-18<br /> |diva=http://hh.diva-portal.org/smash/record.jsf?searchId=1&amp;pid=diva2:1370681}}<br /> &lt;div style=&#039;display: none&#039;&gt;<br /> <br /> == Keep all hand-made modifications below ==<br /> &lt;/div&gt;{{PublicationDisplayTemplate}}</div> Mohbou https://mw.hh.se/caisr/index.php?title=Interactive_Anomaly_Detection&diff=4374 Interactive Anomaly Detection 2019-10-03T14:29:10Z <p>Mohbou: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Anomalies can be relevant or irrelevant to the end-user. The goal of this thesis is to propose a new interactive anomaly detection method to leverage the user-feedback and learn to suggest more relevant anomalies.<br /> |Keywords=Interactive Anomaly Detection, Deviation Detection, Streaming Data, Data Mining, Machine Learning<br /> |TimeFrame=4th of November 2019 to 29th May 2020<br /> |References=- Lamba, H. and Akoglu, L., 2019, May. Learning On-the-Job to Re-rank Anomalies from Top-1 Feedback. In Proceedings of the 2019 SIAM International Conference on Data Mining (SDM), pp. 612-620. Society for Industrial and Applied Mathematics.<br /> https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69<br /> <br /> - Ding, K., Li, J. and Liu, H., 2019, January. Interactive anomaly detection on attributed networks. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp. 357-365. ACM.<br /> http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf<br /> <br /> - Arnaldo, I., Veeramachaneni, K. and Lam, M., 2019. ex2: a framework for interactive anomaly detection. In ACM IUI Workshop on Exploratory Search and Interactive Data Analytics (ESIDA).<br /> http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf<br /> <br /> - Zhu, Y. and Yang, K., 2019. Tripartite Active Learning for Interactive Anomaly Discovery. IEEE Access.<br /> https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963<br /> |Prerequisites=Requires very good understanding of ML and data mining techniques (especially for anomaly detection). Good programming skills (preferably in Python) are also required.<br /> |Supervisor=Mohamed-Rafik Bouguelia, Onur Dikmen<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> NOTE: please note that this thesis *requires* a strong prior knowledge of ML and data mining techniques (especially for anomaly detection). In addition, good programming skills (e.g. in Python) are also required.<br /> <br /> Contacts:<br /> * mohamed-rafik.bouguelia@hh.se<br /> * onur.dikmen@hh.se<br /> <br /> Description:<br /> <br /> Anomaly detection allows to find patterns that deviate significantly from the majority of reference data, indicating e.g. a system fault. Conventional anomaly detection methods focus on statistical features of the data; they are unsupervised (due to the expensive labeling costs of ground truth anomalies) and do not interact with a human-expert. However, from the user perspective, a detected anomaly can either be relevant (i.e. an actual anomaly) or irrelevant (e.g. an atypical but normal system behavior). In interactive anomaly detection, the goal is to maximize the true (relevant) anomalies presented to the human expert (user). This is done by allowing the algorithm to proactively communicate with the user and leverage the user-feedback to refine results and learn to suggest more relevant anomalies. Several challenges comes with this. For example, one want to learn to distinguish relevant from irrelevant anomalies, but without presenting a lot of irrelevant anomalies to the user. This raises the question of how to handle the exploration-exploitation dilemma when querying anomalies of different kinds.<br /> <br /> The goal of this thesis is to:<br /> # Perform a state-of-the-art literature review of existing methods for interactive anomaly detection.<br /> # Identify the advantages and limitations of these existing methods.<br /> # Propose a new interactive anomaly detection method wich solves some of the identified limitations.<br /> # Perform extensive experiments on artificial and real-world datasets to show the advantage of the proposed method over existing methods for interactive anomaly detection.<br /> <br /> Some relevant recent (2019) papers:<br /> <br /> * Lamba, H. and Akoglu, L., 2019, May. Learning On-the-Job to Re-rank Anomalies from Top-1 Feedback. In Proceedings of the 2019 SIAM International Conference on Data Mining (SDM), pp. 612-620. Society for Industrial and Applied Mathematics.<br /> [https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69 https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69]<br /> <br /> * Ding, K., Li, J. and Liu, H., 2019, January. Interactive anomaly detection on attributed networks. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp. 357-365. ACM.<br /> [http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf]<br /> <br /> * Arnaldo, I., Veeramachaneni, K. and Lam, M., 2019. ex2: a framework for interactive anomaly detection. In ACM IUI Workshop on Exploratory Search and Interactive Data Analytics (ESIDA).<br /> [http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf]<br /> <br /> * Zhu, Y. and Yang, K., 2019. Tripartite Active Learning for Interactive Anomaly Discovery. IEEE Access.<br /> [https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963 https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Interactive_Anomaly_Detection&diff=4373 Interactive Anomaly Detection 2019-10-03T14:28:47Z <p>Mohbou: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Anomalies can be relevant or irrelevant to the end-user. The goal of this thesis is to propose a new interactive anomaly detection method to leverage the user-feedback and learn to suggest more relevant anomalies.<br /> |Keywords=Interactive Anomaly Detection, Deviation Detection, Streaming Data, Data Mining, Machine Learning<br /> |TimeFrame=4th of November 2019 to 29th May 2020<br /> |References=- Lamba, H. and Akoglu, L., 2019, May. Learning On-the-Job to Re-rank Anomalies from Top-1 Feedback. In Proceedings of the 2019 SIAM International Conference on Data Mining (SDM), pp. 612-620. Society for Industrial and Applied Mathematics.<br /> https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69<br /> <br /> - Ding, K., Li, J. and Liu, H., 2019, January. Interactive anomaly detection on attributed networks. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp. 357-365. ACM.<br /> http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf<br /> <br /> - Arnaldo, I., Veeramachaneni, K. and Lam, M., 2019. ex2: a framework for interactive anomaly detection. In ACM IUI Workshop on Exploratory Search and Interactive Data Analytics (ESIDA).<br /> http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf<br /> <br /> - Zhu, Y. and Yang, K., 2019. Tripartite Active Learning for Interactive Anomaly Discovery. IEEE Access.<br /> https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963<br /> |Prerequisites=Requires very good understanding of ML and data mining techniques (especially for anomaly detection). Good programming skills (preferably in Python) are also required.<br /> |Supervisor=Mohamed-Rafik Bouguelia, Onur Dikmen<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> NOTE: please note that this thesis *requires* a strong prior knowledge of ML and data mining techniques (especially for anomaly detection). In addition, good programming skills (e.g. in Python) are also required.<br /> <br /> Contacts:<br /> * mohamed-rafik.bouguelia@hh.se<br /> * onur.dikmen@hh.se<br /> <br /> Anomaly detection allows to find patterns that deviate significantly from the majority of reference data, indicating e.g. a system fault. Conventional anomaly detection methods focus on statistical features of the data; they are unsupervised (due to the expensive labeling costs of ground truth anomalies) and do not interact with a human-expert. However, from the user perspective, a detected anomaly can either be relevant (i.e. an actual anomaly) or irrelevant (e.g. an atypical but normal system behavior). In interactive anomaly detection, the goal is to maximize the true (relevant) anomalies presented to the human expert (user). This is done by allowing the algorithm to proactively communicate with the user and leverage the user-feedback to refine results and learn to suggest more relevant anomalies. Several challenges comes with this. For example, one want to learn to distinguish relevant from irrelevant anomalies, but without presenting a lot of irrelevant anomalies to the user. This raises the question of how to handle the exploration-exploitation dilemma when querying anomalies of different kinds.<br /> <br /> The goal of this thesis is to:<br /> # Perform a state-of-the-art literature review of existing methods for interactive anomaly detection.<br /> # Identify the advantages and limitations of these existing methods.<br /> # Propose a new interactive anomaly detection method wich solves some of the identified limitations.<br /> # Perform extensive experiments on artificial and real-world datasets to show the advantage of the proposed method over existing methods for interactive anomaly detection.<br /> <br /> Some relevant recent (2019) papers:<br /> <br /> * Lamba, H. and Akoglu, L., 2019, May. Learning On-the-Job to Re-rank Anomalies from Top-1 Feedback. In Proceedings of the 2019 SIAM International Conference on Data Mining (SDM), pp. 612-620. Society for Industrial and Applied Mathematics.<br /> [https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69 https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69]<br /> <br /> * Ding, K., Li, J. and Liu, H., 2019, January. Interactive anomaly detection on attributed networks. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp. 357-365. ACM.<br /> [http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf]<br /> <br /> * Arnaldo, I., Veeramachaneni, K. and Lam, M., 2019. ex2: a framework for interactive anomaly detection. In ACM IUI Workshop on Exploratory Search and Interactive Data Analytics (ESIDA).<br /> [http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf]<br /> <br /> * Zhu, Y. and Yang, K., 2019. Tripartite Active Learning for Interactive Anomaly Discovery. IEEE Access.<br /> [https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963 https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Interactive_Anomaly_Detection&diff=4351 Interactive Anomaly Detection 2019-10-02T07:35:24Z <p>Mohbou: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Anomalies can be relevant or irrelevant to the end-user. The goal of this thesis is to propose a new interactive anomaly detection method to leverage the user-feedback and learn to suggest more relevant anomalies.<br /> |Keywords=Interactive Anomaly Detection, Deviation Detection, Streaming Data, Data Mining, Machine Learning<br /> |TimeFrame=4th of November 2019 to 29th May 2020<br /> |References=- Lamba, H. and Akoglu, L., 2019, May. Learning On-the-Job to Re-rank Anomalies from Top-1 Feedback. In Proceedings of the 2019 SIAM International Conference on Data Mining (SDM), pp. 612-620. Society for Industrial and Applied Mathematics.<br /> https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69<br /> <br /> - Ding, K., Li, J. and Liu, H., 2019, January. Interactive anomaly detection on attributed networks. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp. 357-365. ACM.<br /> http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf<br /> <br /> - Arnaldo, I., Veeramachaneni, K. and Lam, M., 2019. ex2: a framework for interactive anomaly detection. In ACM IUI Workshop on Exploratory Search and Interactive Data Analytics (ESIDA).<br /> http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf<br /> <br /> - Zhu, Y. and Yang, K., 2019. Tripartite Active Learning for Interactive Anomaly Discovery. IEEE Access.<br /> https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963<br /> |Prerequisites=Requires very good understanding of ML and data mining techniques (especially for anomaly detection). Good programming skills (preferably in Python) are also required.<br /> |Supervisor=Mohamed-Rafik Bouguelia, Onur Dikmen<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> NOTE: please note that this thesis *requires* a strong prior knowledge of ML and data mining techniques (especially for anomaly detection). In addition, good programming skills (e.g. in Python) are also required.<br /> <br /> Anomaly detection allows to find patterns that deviate significantly from the majority of reference data, indicating e.g. a system fault. Conventional anomaly detection methods focus on statistical features of the data; they are unsupervised (due to the expensive labeling costs of ground truth anomalies) and do not interact with a human-expert. However, from the user perspective, a detected anomaly can either be relevant (i.e. an actual anomaly) or irrelevant (e.g. an atypical but normal system behavior). In interactive anomaly detection, the goal is to maximize the true (relevant) anomalies presented to the human expert (user). This is done by allowing the algorithm to proactively communicate with the user and leverage the user-feedback to refine results and learn to suggest more relevant anomalies. Several challenges comes with this. For example, one want to learn to distinguish relevant from irrelevant anomalies, but without presenting a lot of irrelevant anomalies to the user. This raises the question of how to handle the exploration-exploitation dilemma when querying anomalies of different kinds.<br /> <br /> The goal of this thesis is to:<br /> # Perform a state-of-the-art literature review of existing methods for interactive anomaly detection.<br /> # Identify the advantages and limitations of these existing methods.<br /> # Propose a new interactive anomaly detection method wich solves some of the identified limitations.<br /> # Perform extensive experiments on artificial and real-world datasets to show the advantage of the proposed method over existing methods for interactive anomaly detection.<br /> <br /> Some relevant recent (2019) papers:<br /> <br /> * Lamba, H. and Akoglu, L., 2019, May. Learning On-the-Job to Re-rank Anomalies from Top-1 Feedback. In Proceedings of the 2019 SIAM International Conference on Data Mining (SDM), pp. 612-620. Society for Industrial and Applied Mathematics.<br /> [https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69 https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69]<br /> <br /> * Ding, K., Li, J. and Liu, H., 2019, January. Interactive anomaly detection on attributed networks. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp. 357-365. ACM.<br /> [http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf]<br /> <br /> * Arnaldo, I., Veeramachaneni, K. and Lam, M., 2019. ex2: a framework for interactive anomaly detection. In ACM IUI Workshop on Exploratory Search and Interactive Data Analytics (ESIDA).<br /> [http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf]<br /> <br /> * Zhu, Y. and Yang, K., 2019. Tripartite Active Learning for Interactive Anomaly Discovery. IEEE Access.<br /> [https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963 https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Interactive_Anomaly_Detection&diff=4350 Interactive Anomaly Detection 2019-10-02T07:34:21Z <p>Mohbou: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Anomalies can be relevant or irrelevant to the end-user. The goal of this thesis is to propose a new interactive anomaly detection method to leverage the user-feedback and learn to suggest more relevant anomalies.<br /> |Keywords=Interactive Anomaly Detection, Deviation Detection, Streaming Data, Data Mining, Machine Learning<br /> |TimeFrame=4th of November 2019 to 29th May 2020<br /> |References=- Lamba, H. and Akoglu, L., 2019, May. Learning On-the-Job to Re-rank Anomalies from Top-1 Feedback. In Proceedings of the 2019 SIAM International Conference on Data Mining (SDM), pp. 612-620. Society for Industrial and Applied Mathematics.<br /> https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69<br /> <br /> - Ding, K., Li, J. and Liu, H., 2019, January. Interactive anomaly detection on attributed networks. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp. 357-365. ACM.<br /> http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf<br /> <br /> - Arnaldo, I., Veeramachaneni, K. and Lam, M., 2019. ex2: a framework for interactive anomaly detection. In ACM IUI Workshop on Exploratory Search and Interactive Data Analytics (ESIDA).<br /> http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf<br /> <br /> - Zhu, Y. and Yang, K., 2019. Tripartite Active Learning for Interactive Anomaly Discovery. IEEE Access.<br /> https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963<br /> |Prerequisites=Requires very good understanding of ML and data mining techniques (especially for anomaly detection). Good programming skills in Python are also required.<br /> |Supervisor=Mohamed-Rafik Bouguelia, Onur Dikmen<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> NOTE: please note that this thesis *requires* a strong prior knowledge of ML and data mining techniques (especially for anomaly detection). In addition, good programming skills in Python are also required.<br /> <br /> Anomaly detection allows to find patterns that deviate significantly from the majority of reference data, indicating e.g. a system fault. Conventional anomaly detection methods focus on statistical features of the data; they are unsupervised (due to the expensive labeling costs of ground truth anomalies) and do not interact with a human-expert. However, from the user perspective, a detected anomaly can either be relevant (i.e. an actual anomaly) or irrelevant (e.g. an atypical but normal system behavior). In interactive anomaly detection, the goal is to maximize the true (relevant) anomalies presented to the human expert (user). This is done by allowing the algorithm to proactively communicate with the user and leverage the user-feedback to refine results and learn to suggest more relevant anomalies. Several challenges comes with this. For example, one want to learn to distinguish relevant from irrelevant anomalies, but without presenting a lot of irrelevant anomalies to the user. This raises the question of how to handle the exploration-exploitation dilemma when querying anomalies of different kinds.<br /> <br /> The goal of this thesis is to:<br /> # Perform a state-of-the-art literature review of existing methods for interactive anomaly detection.<br /> # Identify the advantages and limitations of these existing methods.<br /> # Propose a new interactive anomaly detection method wich solves some of the identified limitations.<br /> # Perform extensive experiments on artificial and real-world datasets to show the advantage of the proposed method over existing methods for interactive anomaly detection.<br /> <br /> Some relevant recent (2019) papers:<br /> <br /> * Lamba, H. and Akoglu, L., 2019, May. Learning On-the-Job to Re-rank Anomalies from Top-1 Feedback. In Proceedings of the 2019 SIAM International Conference on Data Mining (SDM), pp. 612-620. Society for Industrial and Applied Mathematics.<br /> [https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69 https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69]<br /> <br /> * Ding, K., Li, J. and Liu, H., 2019, January. Interactive anomaly detection on attributed networks. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp. 357-365. ACM.<br /> [http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf]<br /> <br /> * Arnaldo, I., Veeramachaneni, K. and Lam, M., 2019. ex2: a framework for interactive anomaly detection. In ACM IUI Workshop on Exploratory Search and Interactive Data Analytics (ESIDA).<br /> [http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf]<br /> <br /> * Zhu, Y. and Yang, K., 2019. Tripartite Active Learning for Interactive Anomaly Discovery. IEEE Access.<br /> [https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963 https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Interactive_Anomaly_Detection&diff=4349 Interactive Anomaly Detection 2019-10-02T07:33:14Z <p>Mohbou: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Anomalies can be relevant or irrelevant to the end-user. The goal of this thesis is to propose a new interactive anomaly detection method to leverage the user-feedback and learn to suggest more relevant anomalies.<br /> |Keywords=Interactive Anomaly Detection, Deviation Detection, Streaming Data, Data Mining, Machine Learning<br /> |TimeFrame=4th of November 2019 to 29th May 2020<br /> |References=- Lamba, H. and Akoglu, L., 2019, May. Learning On-the-Job to Re-rank Anomalies from Top-1 Feedback. In Proceedings of the 2019 SIAM International Conference on Data Mining (SDM), pp. 612-620. Society for Industrial and Applied Mathematics.<br /> https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69<br /> <br /> - Ding, K., Li, J. and Liu, H., 2019, January. Interactive anomaly detection on attributed networks. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp. 357-365. ACM.<br /> http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf<br /> <br /> - Arnaldo, I., Veeramachaneni, K. and Lam, M., 2019. ex2: a framework for interactive anomaly detection. In ACM IUI Workshop on Exploratory Search and Interactive Data Analytics (ESIDA).<br /> http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf<br /> <br /> - Zhu, Y. and Yang, K., 2019. Tripartite Active Learning for Interactive Anomaly Discovery. IEEE Access.<br /> https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963<br /> |Prerequisites=Requires very good understanding of ML and data mining techniques (especially for anomaly detection). Good programming skills in Python are also required.<br /> |Supervisor=Mohamed-Rafik Bouguelia, Onur Dikmen<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> NOTE: please note that this thesis *requires* a strong prior knowledge of ML and data mining techniques (especially for anomaly detection). In addition, good programming skills in Python are also required.<br /> <br /> Anomaly detection allows to find patterns that deviate significantly from the majority of reference data, indicating e.g. a system fault. Conventional anomaly detection methods focus on statistical features of the data; they are unsupervised (due to the expensive labeling costs of ground truth anomalies) and do not interact with a human-expert. However, from the user perspective, a detected anomaly can either be relevant (i.e. an actual anomaly) or irrelevant (e.g. an atypical but normal system behavior). In interactive anomaly detection, the goal is to maximize the true (relevant) anomalies presented to the human expert (user). This is done by allowing the algorithm to proactively communicate with the user and leverage the user-feedback to refine results and learn to suggest more relevant anomalies. Several challenges comes with this. For example, one want to learn to distinguish relevant from irrelevant anomalies, but without presenting a lot of irrelevant anomalies to the user. This raises the question of how to handle the exploration-exploitation dilemma when querying anomalies of different kinds.<br /> <br /> The goal of this thesis is to:<br /> # Perform a state-of-the-art literature review of existing methods for interactive anomaly detection.<br /> # Identify the advantages and limitations of these existing methods.<br /> # Propose a new interactive anomaly detection method wich solves some of the identified limitations.<br /> # Perform extensive experiments on artificial and real-world datasets to show the advantage of the proposed method over existing methods for interactive anomaly detection.<br /> <br /> Some relevant recent (2019) papers:<br /> <br /> * Lamba, H. and Akoglu, L., 2019, May. Learning On-the-Job to Re-rank Anomalies from Top-1 Feedback. In Proceedings of the 2019 SIAM International Conference on Data Mining (SDM), pp. 612-620. Society for Industrial and Applied Mathematics.<br /> [https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69]<br /> <br /> * Ding, K., Li, J. and Liu, H., 2019, January. Interactive anomaly detection on attributed networks. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp. 357-365. ACM.<br /> [http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf]<br /> <br /> * Arnaldo, I., Veeramachaneni, K. and Lam, M., 2019. ex2: a framework for interactive anomaly detection. In ACM IUI Workshop on Exploratory Search and Interactive Data Analytics (ESIDA).<br /> [http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf]<br /> <br /> * Zhu, Y. and Yang, K., 2019. Tripartite Active Learning for Interactive Anomaly Discovery. IEEE Access.<br /> [https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Interactive_Anomaly_Detection&diff=4348 Interactive Anomaly Detection 2019-10-02T07:30:34Z <p>Mohbou: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Anomalies can be relevant or irrelevant to the end-user. The goal of this thesis is to propose a new interactive anomaly detection method to leverage the user-feedback and learn to suggest more relevant anomalies.<br /> |Keywords=Interactive Anomaly Detection, Deviation Detection, Streaming Data, Data Mining, Machine Learning<br /> |TimeFrame=4th of November 2019 to 29th May 2020<br /> |References=- Lamba, H. and Akoglu, L., 2019, May. Learning On-the-Job to Re-rank Anomalies from Top-1 Feedback. In Proceedings of the 2019 SIAM International Conference on Data Mining (SDM), pp. 612-620. Society for Industrial and Applied Mathematics.<br /> https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69<br /> <br /> - Ding, K., Li, J. and Liu, H., 2019, January. Interactive anomaly detection on attributed networks. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp. 357-365. ACM.<br /> http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf<br /> <br /> - Arnaldo, I., Veeramachaneni, K. and Lam, M., 2019. ex2: a framework for interactive anomaly detection. In ACM IUI Workshop on Exploratory Search and Interactive Data Analytics (ESIDA).<br /> http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf<br /> <br /> - Zhu, Y. and Yang, K., 2019. Tripartite Active Learning for Interactive Anomaly Discovery. IEEE Access.<br /> https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963<br /> |Prerequisites=Requires very good understanding of ML and data mining techniques (especially for anomaly detection). Good programming skills in Python are also required.<br /> |Supervisor=Mohamed-Rafik Bouguelia, Onur Dikmen<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> NOTE: please note that this thesis *requires* a strong prior knowledge of ML and data mining techniques (especially for anomaly detection). In addition, good programming skills in Python are also required.<br /> <br /> Anomaly detection allows to find patterns that deviate significantly from the majority of reference data, indicating e.g. a system fault. Conventional anomaly detection methods focus on statistical features of the data; they are unsupervised (due to the expensive labeling costs of ground truth anomalies) and do not interact with a human-expert. However, from the user perspective, a detected anomaly can either be relevant (i.e. an actual anomaly) or irrelevant (e.g. an atypical but normal system behaviour). In interactive anomaly detection, the goal is to maximize the true (relevant) anomalies presented to the human expert (user). This is done by allowing the algorithm to proactively communicate with the user and leverage the user-feedback to refine results and learn to suggest more relevant anomalies. Several challenges comes with this. For example, one want to learn to distinguish relevant from irrelevant anomalies, but without presenting a lot of irrelevant anomalies to the user. This raises the question of how to handle the exploration-exploitation dilemma when querying anomalies of different kinds.<br /> <br /> The goal of this thesis is to:<br /> (1) Perform a state-of-the-art literature review of existing methods for interactive anomaly detection.<br /> (2) Identify the advantages and limitations of these existing methods.<br /> (3) Propose a new interactive anomaly detection method wich solves some of the identified limitations.<br /> (4) Perform extensive experiments on artificial and real-world datasets to show the advantage of the proposed method over existing methods for interactive anomaly detection.<br /> <br /> Some relevent recent (2019) papers:<br /> <br /> - Lamba, H. and Akoglu, L., 2019, May. Learning On-the-Job to Re-rank Anomalies from Top-1 Feedback. In Proceedings of the 2019 SIAM International Conference on Data Mining (SDM), pp. 612-620. Society for Industrial and Applied Mathematics.<br /> https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69<br /> <br /> - Ding, K., Li, J. and Liu, H., 2019, January. Interactive anomaly detection on attributed networks. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp. 357-365. ACM.<br /> http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf<br /> <br /> - Arnaldo, I., Veeramachaneni, K. and Lam, M., 2019. ex2: a framework for interactive anomaly detection. In ACM IUI Workshop on Exploratory Search and Interactive Data Analytics (ESIDA).<br /> http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf<br /> <br /> - Zhu, Y. and Yang, K., 2019. Tripartite Active Learning for Interactive Anomaly Discovery. IEEE Access.<br /> https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963</div> Mohbou https://mw.hh.se/caisr/index.php?title=Interactive_Anomaly_Detection&diff=4347 Interactive Anomaly Detection 2019-10-02T07:30:03Z <p>Mohbou: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Anomalies can be relevant or irrelevant to the end-user. The goal of this thesis is to propose a new interactive anomaly detection method to leverage the user-feedback and learn to suggest more relevant anomalies.<br /> |Keywords=Interactive Anomaly Detection, Deviation Detection, Streaming Data, Data Mining, Machine Learning<br /> |TimeFrame=4th of November 2019 to 29th May 2020<br /> |References=- Lamba, H. and Akoglu, L., 2019, May. Learning On-the-Job to Re-rank Anomalies from Top-1 Feedback. In Proceedings of the 2019 SIAM International Conference on Data Mining (SDM), pp. 612-620. Society for Industrial and Applied Mathematics.<br /> https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69<br /> <br /> - Ding, K., Li, J. and Liu, H., 2019, January. Interactive anomaly detection on attributed networks. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp. 357-365. ACM.<br /> http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf<br /> <br /> - Arnaldo, I., Veeramachaneni, K. and Lam, M., 2019. ex2: a framework for interactive anomaly detection. In ACM IUI Workshop on Exploratory Search and Interactive Data Analytics (ESIDA).<br /> http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf<br /> <br /> - Zhu, Y. and Yang, K., 2019. Tripartite Active Learning for Interactive Anomaly Discovery. IEEE Access.<br /> https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963<br /> |Prerequisites=Requires very good understanding of ML and data mining techniques (especially for anomaly detection). Good programming skills in Python are also required.<br /> |Supervisor=Mohamed-Rafik Bouguelia, Onur Dikmen<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> NOTE: please note that this thesis *requires* a strong prior knowledge of ML and data mining techniques (especially for anomaly detection). In addition, good programming skills in Python are also required.<br /> <br /> Anomaly detection allows to find patterns that deviate significantly from the majority of reference data, indicating e.g. a system fault. Conventional anomaly detection methods focus on statistical features of the data; they are unsupervised (due to the expensive labeling costs of ground truth anomalies) and do not interact with a human-expert. However, from the user perspective, a detected anomaly can either be relevant (i.e. an actual anomaly) or irrelevant (e.g. an atypical but normal system behaviour). In interactive anomaly detection, the goal is to maximize the true (relevant) anomalies presented to the human expert (user). This is done by allowing the algorithm to proactively communicate with the user and leverage the user-feedback to refine results and learn to suggest more relevant anomalies. Several challenges comes with this. For example, one want to learn to distinguish relevant from irrelevant anomalies, but without presenting a lot of irrelevant anomalies to the user. This raises the question of how to handle the exploration-exploitation dilemma when querying anomalies of different kinds.<br /> <br /> The goal of this thesis is to:<br /> (1) Perform a state-of-the-art literature review of existing methods for interactive anomaly detection.<br /> (2) Identify the advantages and limitations of these existing methods.<br /> (3) Propose a new interactive anomaly detection method wich solves some of the identified limitations.<br /> (4) Perform extensive experiments on artificial and real-world datasets to show the advantage of the proposed method over existing methods for interactive anomaly detection.<br /> <br /> Some relevent recent (2019) papers:<br /> - Lamba, H. and Akoglu, L., 2019, May. Learning On-the-Job to Re-rank Anomalies from Top-1 Feedback. In Proceedings of the 2019 SIAM International Conference on Data Mining (SDM), pp. 612-620. Society for Industrial and Applied Mathematics.<br /> https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69<br /> <br /> - Ding, K., Li, J. and Liu, H., 2019, January. Interactive anomaly detection on attributed networks. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp. 357-365. ACM.<br /> http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf<br /> <br /> - Arnaldo, I., Veeramachaneni, K. and Lam, M., 2019. ex2: a framework for interactive anomaly detection. In ACM IUI Workshop on Exploratory Search and Interactive Data Analytics (ESIDA).<br /> http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf<br /> <br /> - Zhu, Y. and Yang, K., 2019. Tripartite Active Learning for Interactive Anomaly Discovery. IEEE Access.<br /> https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963</div> Mohbou https://mw.hh.se/caisr/index.php?title=Interactive_Anomaly_Detection&diff=4346 Interactive Anomaly Detection 2019-10-02T07:27:53Z <p>Mohbou: Created page with &quot;{{StudentProjectTemplate |Summary=Anomalies can be relevant or irrelevant to the end-user. The goal of this thesis is to propose a new interactive anomaly detection method to ...&quot;</p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Anomalies can be relevant or irrelevant to the end-user. The goal of this thesis is to propose a new interactive anomaly detection method to leverage the user-feedback and learn to suggest more relevant anomalies.<br /> |Keywords=Interactive Anomaly Detection, Deviation Detection, Streaming Data, Data Mining, Machine Learning<br /> |TimeFrame=4th of November 2019 to 29th May 2020<br /> |References=- Lamba, H. and Akoglu, L., 2019, May. Learning On-the-Job to Re-rank Anomalies from Top-1 Feedback. In Proceedings of the 2019 SIAM International Conference on Data Mining (SDM), pp. 612-620. Society for Industrial and Applied Mathematics.<br /> https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69<br /> <br /> - Ding, K., Li, J. and Liu, H., 2019, January. Interactive anomaly detection on attributed networks. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp. 357-365. ACM.<br /> http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf<br /> <br /> - Arnaldo, I., Veeramachaneni, K. and Lam, M., 2019. ex2: a framework for interactive anomaly detection. In ACM IUI Workshop on Exploratory Search and Interactive Data Analytics (ESIDA).<br /> http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf<br /> <br /> - Zhu, Y. and Yang, K., 2019. Tripartite Active Learning for Interactive Anomaly Discovery. IEEE Access.<br /> https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963<br /> |Prerequisites=Requires very good understanding of ML and data mining techniques (especially for anomaly detection).<br /> |Supervisor=Mohamed-Rafik Bouguelia, Onur Dikmen<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> NOTE: please note that this thesis requires a strong prior knowledge of ML and data mining techniques (especially for anomaly detection).<br /> <br /> Anomaly detection allows to find patterns that deviate significantly from the majority of reference data, indicating e.g. a system fault. Conventional anomaly detection methods focus on statistical features of the data; they are unsupervised (due to the expensive labeling costs of ground truth anomalies) and do not interact with a human-expert. However, from the user perspective, a detected anomaly can either be relevant (i.e. an actual anomaly) or irrelevant (e.g. an atypical but normal system behaviour). In interactive anomaly detection, the goal is to maximize the true (relevant) anomalies presented to the human expert (user). This is done by allowing the algorithm to proactively communicate with the user and leverage the user-feedback to refine results and learn to suggest more relevant anomalies. Several challenges comes with this. For example, one want to learn to distinguish relevant from irrelevant anomalies, but without presenting a lot of irrelevant anomalies to the user. This raises the question of how to handle the exploration-exploitation dilemma when querying anomalies of different kinds.<br /> <br /> The goal of this thesis is to:<br /> (1) Perform a state-of-the-art literature review of existing methods for interactive anomaly detection.<br /> (2) Identify the advantages and limitations of these existing methods.<br /> (3) Propose a new interactive anomaly detection method wich solves some of the identified limitations.<br /> (4) Perform extensive experiments on artificial and real-world datasets to show the advantage of the proposed method over existing methods for interactive anomaly detection.<br /> <br /> Some relevent recent (2019) papers:<br /> - Lamba, H. and Akoglu, L., 2019, May. Learning On-the-Job to Re-rank Anomalies from Top-1 Feedback. In Proceedings of the 2019 SIAM International Conference on Data Mining (SDM), pp. 612-620. Society for Industrial and Applied Mathematics.<br /> https://epubs.siam.org/doi/pdf/10.1137/1.9781611975673.69<br /> <br /> - Ding, K., Li, J. and Liu, H., 2019, January. Interactive anomaly detection on attributed networks. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp. 357-365. ACM.<br /> http://www.public.asu.edu/~jundongl/paper/WSDM19_GraphUCB.pdf<br /> <br /> - Arnaldo, I., Veeramachaneni, K. and Lam, M., 2019. ex2: a framework for interactive anomaly detection. In ACM IUI Workshop on Exploratory Search and Interactive Data Analytics (ESIDA).<br /> http://ceur-ws.org/Vol-2327/IUI19WS-ESIDA-2.pdf<br /> <br /> - Zhu, Y. and Yang, K., 2019. Tripartite Active Learning for Interactive Anomaly Discovery. IEEE Access.<br /> https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8707963</div> Mohbou https://mw.hh.se/caisr/index.php?title=Uncertainty-based_fault_detection&diff=4050 Uncertainty-based fault detection 2018-10-17T13:33:12Z <p>Mohbou: Replaced content with &quot;Removed.&quot;</p> <hr /> <div>Removed.</div> Mohbou https://mw.hh.se/caisr/index.php?title=Mohamed-Rafik_Bouguelia&diff=3905 Mohamed-Rafik Bouguelia 2018-03-19T08:47:15Z <p>Mohbou: </p> <hr /> <div>{{Person<br /> |Family Name=Bouguelia<br /> |Given Name=Mohamed-Rafik<br /> |Title=PhD<br /> |Phone=+46729773581<br /> |Cell Phone=+46729773581<br /> |Position=Assistant Professor<br /> |Email=mohbou@hh.se<br /> |Image=Rafiko.jpg<br /> |Office=F509<br /> }}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignProjects<br /> |project=SeMI<br /> }}<br /> {{AssignProjects<br /> |project=BIDAF<br /> }}<br /> {{AssignProjects<br /> |project=SA3L - Situation Awareness for Ambient Assisted Living<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Machine Learning<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> [[Category:Staff]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> <br /> ==&#039;&#039;&#039;Research Projects&#039;&#039;&#039;==<br /> {{InsertProjects}}<br /> <br /> ==&#039;&#039;&#039;Publications&#039;&#039;&#039;==<br /> See my Google Scholar publication list [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= by clicking here]<br /> <br /> &#039;&#039;&#039;The following is an automatically retrieved incomplete list of publications. [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= Please click here for a more complete list.]&#039;&#039;&#039;<br /> <br /> {{PublicationsList}}<br /> <br /> [[Category:staff]]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Publications&diff=3805 Publications 2017-12-04T22:13:11Z <p>Mohbou: </p> <hr /> <div>&lt;css&gt;<br /> .mw-content-ltr a {color: #222222!important; font-weight: bold!important; }<br /> &lt;/css&gt;<br /> ==Annual Reports==<br /> CAISR Annual Report 2012[http://www.hh.se/download/18.149d6d3d13e19db3d27b58/1366797108619/CAISRarsrapport2012.pdf]<br /> <br /> CAISR Annual Report 2013[http://www.hh.se/download/18.6166dff4144dc6bbd02ea62/1395907798525/CAISR+årsredovisn+2013-webb-1.pdf]<br /> <br /> CAISR Annual Report 2014[http://www.hh.se/download/18.38e7400514bc4e0933aa046f/1425913322150/CAISR+2014+webb.pdf]<br /> <br /> CAISR Annual Report 2015[http://hh.se/download/18.fc95891549399f5ac599cc/1463128150079/CAISR+Annual+Report+2015.pdf]<br /> <br /> CAISR Annual Report 2016[http://www.hh.se/download/18.3826478315b179c438bde72f/1491305359726/CAISR+Annual+report+2016.pdf]<br /> <br /> == Intelligent systems lab journal publications ==<br /> {{#ask: [[Category:Publication]] [[PublicationType::Journal Paper]]<br /> | ?Year<br /> | ?Title<br /> | ?Author<br /> | ?Journal<br /> | ?diva<br /> | limit=100<br /> | sort=Year,Author<br /> | order=descending,ascending<br /> | format=template<br /> | named args=yes<br /> | template=TestPubOutput<br /> }}<br /> <br /> == Intelligent systems lab conference publications ==<br /> {{#ask: [[Category:Publication]] [[PublicationType::Conference Paper]] <br /> | ?Year<br /> | ?Author<br /> | ?Title<br /> | ?HostPublication<br /> | ?Conference<br /> | ?diva<br /> | limit=100<br /> | sort=Year,Author<br /> | order=descending,ascending<br /> | format=template<br /> | named args=yes<br /> | template=TestPubOutput<br /> }}<br /> <br /> == Intelligent systems lab Licentiate and PhD Theses ==<br /> {{#ask: [[Category:Publication]] [[PublicationType::Licentiate Thesis]] OR [[PublicationType::PhD Thesis]] <br /> | ?Year<br /> | ?Author<br /> | ?Title<br /> | ?HostPublication<br /> | ?Conference<br /> | ?diva<br /> | limit=100<br /> | sort=Year,Author<br /> | order=descending,ascending<br /> | format=template<br /> | named args=yes<br /> | template=TestPubOutput<br /> }}<br /> <br /> == Intelligent systems lab edited conference proceedings ==<br /> {{#ask: [[Category:Publication]] [[PublicationType::Conference Proceedings]] <br /> | ?Year<br /> | ?Author<br /> | ?Title<br /> | ?HostPublication<br /> | ?Conference<br /> | ?diva<br /> | limit=100<br /> | sort=Year,Author<br /> | order=descending,ascending<br /> | format=template<br /> | named args=yes<br /> | template=TestPubOutput<br /> }}<br /> <br /> == Intelligent systems lab book chapters ==<br /> {{#ask: [[Category:Publication]] [[PublicationType::Book Chapter]] <br /> | ?Year<br /> | ?Author<br /> | ?Title<br /> | ?HostPublication<br /> | ?Conference<br /> | ?diva<br /> | limit=100<br /> | sort=Year,Author<br /> | order=descending,ascending<br /> | format=template<br /> | named args=yes<br /> | template=TestPubOutput<br /> }}<br /> <br /> == Intelligent systems lab reports ==<br /> {{#ask: [[Category:Publication]] [[PublicationType::Report]] <br /> | ?Year<br /> | ?Author<br /> | ?Title<br /> | ?HostPublication<br /> | ?Conference<br /> | ?diva<br /> | limit=10<br /> | sort=Year,Author<br /> | order=descending,ascending<br /> | format=template<br /> | named args=yes<br /> | template=TestPubOutput<br /> }}<br /> <br /> &lt;div class=&quot;hidden_not_loggedin&quot;&gt;<br /> == Intelligent systems lab publications (Other) ==<br /> {{#ask: [[Category:Publication]] [[PublicationType::!Conference Paper]] [[PublicationType::!Journal Paper]] [[PublicationType::!PhD Thesis]] [[PublicationType::!Licentiate Thesis]] [[PublicationType::!Conference Proceedings]]<br /> | ?Year<br /> | ?Author<br /> | ?Title<br /> | ?HostPublication<br /> | ?diva<br /> | limit=100<br /> | sort=Year,Author<br /> | order=descending,ascending<br /> | format=template<br /> | named args=yes<br /> | template=TestPubOutput<br /> }}<br /> <br /> == Student Theses ==<br /> &#039;&#039;under construction&#039;&#039;<br /> &lt;/div&gt;</div> Mohbou https://mw.hh.se/caisr/index.php?title=Consensus_clustering_for_categorizing_orthogonal_vehicle_operations&diff=3802 Consensus clustering for categorizing orthogonal vehicle operations 2017-12-01T16:41:03Z <p>Mohbou: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Discovering multiple clustering solutions, compare them, and find out if there is a single best (consensus) clustering, or multiple consistent clustering solutions.<br /> |Keywords=Data Mining, Machine Learning, Clustering, Unsupervised learning, knowledge discovery<br /> |References=- Some slides: https://www.siam.org/meetings/sdm11/clustering.pdf<br /> <br /> - Muller, E., Gunnemann, S., Farber, I., &amp; Seidl, T. (2012, April). Discovering multiple clustering solutions: Grouping objects in different views of the data. In Data Engineering (ICDE), 2012 IEEE 28th International Conference on (pp. 1207-1210). IEEE.<br /> <br /> - Hu, J., &amp; Pei, J. (2017). Subspace multi-clustering: a review. Knowledge and Information Systems, 1-28.<br /> <br /> - Yang, S., &amp; Zhang, L. (2017). Non-redundant multiple clustering by nonnegative matrix factorization. Machine Learning, 106(5), 695-712.<br /> <br /> - Dang, X. H., &amp; Bailey, J. (2015). A framework to uncover multiple alternative clusterings. Machine Learning, 98(1-2), 7-30.<br /> <br /> - Gionis, A., Mannila, H., &amp; Tsaparas, P. (2007). Clustering aggregation. ACM Transactions on Knowledge Discovery from Data (TKDD), 1(1), 4.<br /> <br /> - Qi, Z., &amp; Davidson, I. (2009, June). A principled and flexible framework for finding alternative clusterings. In Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 717-726). ACM.<br /> <br /> - Muller, E., Gunnemann, S., Farber, I., &amp; Seidl, T. (2012). Discovering multiple clustering solutions: Grouping objects in different views of the data. In IEEE 28th International Conference on Data Engineering (ICDE), (pp. 1207-1210).<br /> <br /> - Cui, Y., Fern, X. Z., &amp; Dy, J. G. (2007). Non-redundant multi-view clustering via orthogonalization. In IEEE International Conference on Data Mining (ICDM), (pp. 133-142).<br /> <br /> - Strehl, A., &amp; Ghosh, J. (2002). Cluster ensembles---a knowledge reuse framework for combining multiple partitions. Journal of machine learning research, pp. 583-617.<br /> |Prerequisites=Data mining course.<br /> |Supervisor=Mohamed-Rafik Bouguelia, Sławomir Nowaczyk<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> With the rapid development and growth of interconnected devices, more physical systems are integrated with computer-based systems, e.g. sensors and actuators can be sensed and controlled remotely across the network. It is enticing to analyze on-board sensor data streaming from devices (e.g. vehicle speed, engine torque etc.), in order to discover interesting patterns and knowledge. We have collected such data from Volvo buses in normal operation. It is interesting to analyze this data from the usage point of view, in order to discover and categorize various vehicle operations in an unsupervised way (using clustering).<br /> <br /> Clustering is the task of grouping data in such a way that objects in the same group (i.e. cluster) are more similar to each other than to those in other groups (i.e. other clusters). Typical clustering algorithms output a single clustering (i.e. grouping) of the data. However, in real world applications (such as vehicle operation analysis), data can be interpreted in many different ways, leading to different groupings that are reasonable and interesting from different perspectives.<br /> <br /> The goal of the thesis is to propose a method that allows to discover multiple clustering solutions, compare them, and find out if there is a single best (consensus) clustering, or multiple consistent clustering solutions. In the latter case, each data object would be grouped in multiple clusters, representing different perspectives on the data. (i.e. orthogonal, or independent clusterings).<br /> <br /> Clustering solutions that differ in a significant but consistent way can be obtained by constructing different views of the data, for example:<br /> - Using different combinations of feature may reveal different structures of the data.<br /> - Using different similarity/distance measures.<br /> - Various data sources (different sources of the same data).<br /> - Varying the hyperparameters of the clustering algorithm.<br /> - Combining various clustering algorithms, etc.<br /> <br /> While the main application focuses on grouping vehicle operations, the proposed method could be general and applicable for any data with such orthogonal clusters.<br /> <br /> References: check the of references above.<br /> <br /> Contact:<br /> <br /> - Mohamed-Rafik Bouguelia ( mohbou@hh.se )<br /> <br /> - Slawomir Nowaczyk ( slawomir.nowaczyk@hh.se )</div> Mohbou https://mw.hh.se/caisr/index.php?title=Consensus_clustering_for_categorizing_orthogonal_vehicle_operations&diff=3781 Consensus clustering for categorizing orthogonal vehicle operations 2017-11-17T13:13:14Z <p>Mohbou: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Discovering multiple clustering solutions, compare them, and find out if there is a single best (consensus) clustering, or multiple consistent clustering solutions.<br /> |Keywords=Data Mining, Machine Learning, Clustering, Unsupervised learning, knowledge discovery<br /> |References=- Some slides: https://www.siam.org/meetings/sdm11/clustering.pdf<br /> <br /> - Muller, E., Gunnemann, S., Farber, I., &amp; Seidl, T. (2012, April). Discovering multiple clustering solutions: Grouping objects in different views of the data. In Data Engineering (ICDE), 2012 IEEE 28th International Conference on (pp. 1207-1210). IEEE.<br /> <br /> - Hu, J., &amp; Pei, J. (2017). Subspace multi-clustering: a review. Knowledge and Information Systems, 1-28.<br /> <br /> - Yang, S., &amp; Zhang, L. (2017). Non-redundant multiple clustering by nonnegative matrix factorization. Machine Learning, 106(5), 695-712.<br /> <br /> - Dang, X. H., &amp; Bailey, J. (2015). A framework to uncover multiple alternative clusterings. Machine Learning, 98(1-2), 7-30.<br /> <br /> - Gionis, A., Mannila, H., &amp; Tsaparas, P. (2007). Clustering aggregation. ACM Transactions on Knowledge Discovery from Data (TKDD), 1(1), 4.<br /> <br /> - Qi, Z., &amp; Davidson, I. (2009, June). A principled and flexible framework for finding alternative clusterings. In Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 717-726). ACM.<br /> <br /> - Muller, E., Gunnemann, S., Farber, I., &amp; Seidl, T. (2012). Discovering multiple clustering solutions: Grouping objects in different views of the data. In IEEE 28th International Conference on Data Engineering (ICDE), (pp. 1207-1210).<br /> <br /> - Cui, Y., Fern, X. Z., &amp; Dy, J. G. (2007). Non-redundant multi-view clustering via orthogonalization. In IEEE International Conference on Data Mining (ICDM), (pp. 133-142).<br /> <br /> - Strehl, A., &amp; Ghosh, J. (2002). Cluster ensembles---a knowledge reuse framework for combining multiple partitions. Journal of machine learning research, pp. 583-617.<br /> |Prerequisites=Data mining course.<br /> |Supervisor=Mohamed-Rafik Bouguelia, Sławomir Nowaczyk<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> With the rapid development and growth of interconnected devices, more physical systems are integrated with computer-based systems, e.g. sensors and actuators can be sensed and controlled remotely across the network. It is enticing to analyze on-board sensor data streaming from devices (e.g. vehicle speed, engine torque etc.), in order to discover interesting patterns and knowledge. We have collected such data from Volvo buses in normal operation. It is interesting to analyze this data from the usage point of view, in order to discover and categorize various vehicle operations in an unsupervised way (using clustering).<br /> <br /> Clustering is the task of grouping data in such a way that objects in the same group (i.e. cluster) are more similar to each other than to those in other groups (i.e. other clusters). Typical clustering algorithms output a single clustering (i.e. grouping) of the data. However, in real world applications (such as vehicle operation analysis), data can be interpreted in many different ways, leading to different groupings that are reasonable and interesting from different perspectives.<br /> <br /> The goal of the thesis is to propose a method that allows to discover multiple clustering solutions, compare them, and find out if there is a single best (consensus) clustering, or multiple consistent clustering solutions. In the latter case, each data object would be grouped in multiple clusters, representing different perspectives on the data. (i.e. orthogonal clusters).<br /> <br /> Clustering solutions that differ in a significant but consistent way can be obtained by constructing different views of the data, for example:<br /> - Using different combinations of feature may reveal different structures of the data.<br /> - Using different similarity/distance measures.<br /> - Various data sources (different sources of the same data).<br /> - Varying the hyperparameters of the clustering algorithm.<br /> - Combining various clustering algorithms, etc.<br /> <br /> While the main application focuses on grouping vehicle operations, the proposed method could be general and applicable for any data with such orthogonal clusters.<br /> <br /> References: check the of references above.<br /> <br /> Contact:<br /> <br /> - Mohamed-Rafik Bouguelia ( mohbou@hh.se )<br /> <br /> - Slawomir Nowaczyk ( slawomir.nowaczyk@hh.se )</div> Mohbou https://mw.hh.se/caisr/index.php?title=BIDAF&diff=3665 BIDAF 2017-10-19T14:39:25Z <p>Mohbou: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title=BIDAF<br /> |ContactInformation=Slawomir Nowaczyk<br /> |ShortDescription=Big Data Analytics Framework for smart society<br /> |Description=BIDAF is a five-year research project financed by the KK-stiftelsen. The project is carried out by researchers at Halmstad University, SICS Swedish ICT AB, and University of Skövde, Sweden. The overall aim of the BIDAF project is to significantly further the research within massive data analysis, by means of machine learning, in response to the increasing demand of retrieving value from data in all of society. This will be done by creating a strong distributed research environment for big data analytics.<br /> |LogotypeFile=Bidaf.png<br /> |ProjectResponsible=Slawomir Nowaczyk<br /> |ProjectStart=2014/11/01<br /> |ProjectEnd=2019/10/31<br /> |Lctitle=No<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=SICS<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=University of Skövde<br /> }}<br /> __NOTOC__<br /> {{ShowResearchProject}}<br /> The BIDAF project addresses challenges on several levels:<br /> &lt;ul&gt;<br /> &lt;li&gt;Platforms to store and process the data.&lt;/li&gt;<br /> &lt;li&gt;Machine learning algorithms to analyze the data.&lt;/li&gt;<br /> &lt;li&gt;High level tools to access the results.&lt;/li&gt;<br /> &lt;/ul&gt;<br /> <br /> All of these challenges must be addressed together, in order to enable end users to successfully perform analysis of massive data: (i) the hardware and platform level with the capacity to collect, store, and process the necessary volumes of data in real time, (ii) machine learning algorithms to model and analyse the collected data, and (iii) high level tools and functionality to access the results and to allow exploring and visualizing both the data and the models.<br /> <br /> &lt;h3&gt;Challenge 1. To develop a computation platform suitable for machine learning of massive streaming and distributed data.&lt;/h3&gt;<br /> <br /> One of the important characteristics of Big Data is that it is often streaming or at least constantly updated. It typically originates from a large number of distributed sources, and is, like most real world data, inherently noisy, vague or uncertain. At the same time, due to sheer size, a scalable framework for efficient processing is needed to adequately take advantage of it. However, today’s Big Data platforms are not well adapted to the specific needs of machine learning algorithms:<br /> <br /> &lt;ul&gt;<br /> &lt;li&gt;Current platforms lack functionality suitable for analysing real-time, streaming and distributed data.&lt;/li&gt;<br /> &lt;li&gt;Machine learning requires storing and updating an internal model of the data. Current platforms lack suitable support for stateful computing.&lt;/li&gt;<br /> &lt;li&gt;The advanced processing in machine learning requires a more flexible computational structure than provided within the map-reduce paradigm of big data platforms, for example, iteration.&lt;/li&gt;<br /> &lt;/ul&gt;<br /> <br /> &lt;h3&gt;Challenge 2. To develop machine learning algorithms suitable for handling both the opportunities and challenges with massive, distributed, and streaming data produced in society.&lt;/h3&gt;<br /> <br /> A lot of recent research in machine learning, as a means to automatically sieve through large amounts<br /> of information, model it, and draw conclusions, are motivated by Big Data. Traditional machine learning<br /> algorithms are, however, not suitable for dealing with the opportunities nor the challenges that come with<br /> massive distributed and streaming data:<br /> <br /> &lt;ul&gt;<br /> &lt;li&gt;Many machine learning methods are designed for small training sets, trying to squeeze maximum out of them, usually by iterating over the examples many times. Then they use cross validation schemes to evaluate the methods on, again, limited amounts of data. With larger, especially streaming, data, there should be no need to iterate over the same examples for training and validation.&lt;/li&gt;<br /> &lt;li&gt;A large class of successful machine learning algorithms are sample based (e.g., kernel density estimators and support vector machines), meaning that the model increases in size as more data arrives. This can quickly become infeasible, and so there is a need for more compact models, ones that manage to catch the essence of the data, without out-of-control growth in size.&lt;/li&gt;<br /> &lt;li&gt;Most machine learning approaches assume a fixed training set, or possibly a batch-wise updated scenario, where training and usage can be separated. When new data arrives continuously, and the underlying reality changes constantly, the models need to gradually adapt. When the knowledge is to be used by many users, or by users with varying interests, a single model is not enough. There is a need for methods that can learn many models at the same time, each capturing different aspects of the data, and combine them in flexible ways to provide up-to-date, relevant knowledge.&lt;/li&gt;<br /> &lt;li&gt;Data coming from different sources and being of different types raises several uncertainty issues associated with it, such as the validity, precision, and bias of those sources. This again changes the analytics task in a qualitative way, and calls for principled methods to handle all those aspects throughout the full course of data processing. Machine learning algorithms needs to take this uncertainty into account when creating models, but also be capable of propagating it into their results.&lt;/li&gt;<br /> &lt;/ul&gt;<br /> <br /> &lt;h3&gt;Challenge 3. To provide analytics methodology and high-level interactive functionality, to make the value in massive data easier available to end-users.&lt;/h3&gt;<br /> <br /> Big Data Analytics is capable of highlighting interesting aspects and discovering things of which users are completely unaware: detecting deviations, anomalies and trends, analysing key values, relations and co-occurrences, as well as making predictions. A crucial aspect of Big Data Analytics is enabling end users to use machine learning solutions more efficiently. On the one hand, unrealistic expectations have to be addressed by clearer presentation of the models, their quality and applicability limitations. At the same time, the full capabilities of machine learning in the Big Data context need to be made available to those who can benefit from it the most. The solution is the combination of elevating the abstraction level of machine learning algorithms, increased interactivity, using better visualisation techniques, and engaging end users into the whole data analytics cycle.<br /> <br /> &lt;ul&gt;<br /> &lt;li&gt;Traditional software and hardware layers for big data analytics lack important services that the human cognitive system needs in processing complex information, and how to make machine learning meet the demands of big data analysts remains an open problem.&lt;/li&gt;<br /> &lt;li&gt;Despite extensive research on how interactive visualization can facilitate the understanding of machine learning algorithms, there is a lack of results indicating the effectiveness of the different visualization techniques in terms of how well they are perceived and understood by the users and how the visualization influences analytical reasoning.&lt;/li&gt;<br /> &lt;li&gt;Most state-of-the-art visual analytics (VA) tools and techniques do not properly accommodate big data. A major challenge is the capability of visual analysis methods to work incrementally and improving real-time analytical capability. How to handle streaming data and how to cooperate with approximate machine learning algorithms are open research questions.&lt;/li&gt;<br /> &lt;li&gt;By default ML algorithms today aim to offer users as much flexibility as possible, based on the assumption that those users are themselves experts in the field. There is a need to develop high level, abstract presentation layer on top of such implementations, one that will allow domain experts to use ML solutions efficiently.&lt;/li&gt;<br /> &lt;/ul&gt;<br /> {{ShowProjectPublications}}</div> Mohbou https://mw.hh.se/caisr/index.php?title=BIDAF&diff=3664 BIDAF 2017-10-19T14:36:18Z <p>Mohbou: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title=BIDAF<br /> |ContactInformation=Slawomir Nowaczyk<br /> |ShortDescription=Big Data Analytics Framework for smart society<br /> |Description=BIDAF is a five-year research project financed by the KK-stiftelsen. The project is carried out by researchers at Halmstad University, SICS Swedish ICT AB, and University of Skövde, Sweden. The overall aim of the BIDAF project is to significantly further the research within massive data analysis, by means of machine learning, in response to the increasing demand of retrieving value from data in all of society. This will be done by creating a strong distributed research environment for big data analytics.<br /> |LogotypeFile=Bidaf.png<br /> |ProjectResponsible=Slawomir Nowaczyk<br /> |ProjectStart=2014/11/01<br /> |ProjectEnd=2019/10/31<br /> |Lctitle=No<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=SICS<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=University of Skövde<br /> }}<br /> __NOTOC__<br /> {{ShowResearchProject}}<br /> The BIDAF project addresses challenges on several levels:<br /> &lt;ul&gt;<br /> &lt;li&gt;Platforms to store and process the data.&lt;/li&gt;<br /> &lt;li&gt;Machine learning algorithms to analyze the data.&lt;/li&gt;<br /> &lt;li&gt;High level tools to access the results.&lt;/li&gt;<br /> &lt;/ul&gt;<br /> <br /> All of these challenges must be addressed together, in order to enable end users to successfully perform analysis of massive data: (i) the hardware and platform level with the capacity to collect, store, and process the necessary volumes of data in real time, (ii) machine learning algorithms to model and analyse the collected data, and (iii) high level tools and functionality to access the results and to allow exploring and visualizing both the data and the models.<br /> <br /> &lt;h3&gt;Challenge 1. To develop a computation platform suitable for machine learning of massive streaming and distributed data.&lt;/h3&gt;<br /> <br /> One of the important characteristics of Big Data is that it is often streaming or at least constantly updated. It typically originates from a large number of distributed sources, and is, like most real world data, inherently noisy, vague or uncertain. At the same time, due to sheer size, a scalable framework for efficient processing is needed to adequately take advantage of it. However, today’s Big Data platforms are not well adapted to the specific needs of machine learning algorithms:<br /> <br /> &lt;ul&gt;<br /> &lt;li&gt;Current platforms lack functionality suitable for analysing real-time, streaming and distributed data.&lt;/li&gt;<br /> &lt;li&gt;Machine learning requires storing and updating an internal model of the data. Current platforms lack suitable support for stateful computing.&lt;/li&gt;<br /> &lt;li&gt;The advanced processing in machine learning requires a more flexible computational structure than provided within the map-reduce paradigm of big data platforms, for example, iteration.&lt;/li&gt;<br /> &lt;/ul&gt;<br /> <br /> &lt;h3&gt;Challenge 2. To develop machine learning algorithms suitable for handling both the opportunities and challenges with massive, distributed, and streaming data produced in society.&lt;/h3&gt;<br /> <br /> A lot of recent research in machine learning, as a means to automatically sieve through large amounts<br /> of information, model it, and draw conclusions, are motivated by Big Data. Traditional machine learning<br /> algorithms are, however, not suitable for dealing with the opportunities nor the challenges that come with<br /> massive, distributed and, streaming data:<br /> <br /> &lt;ul&gt;<br /> &lt;li&gt;Many machine learning methods are designed for small training sets, trying to squeeze maximum out of them, usually by iterating over the examples many times. Then they use cross validation schemes to evaluate the methods on, again, limited amounts of data. With larger, especially streaming, data, there should be no need to iterate over the same examples for training and validation.&lt;/li&gt;<br /> &lt;li&gt;A large class of successful machine learning algorithms are sample based (e.g., kernel density estimators and support vector machines), meaning that the model increases in size as more data arrives. This can quickly become infeasible, and so there is a need for more compact models, ones that manage to catch the essence of the data, without out-of-control growth in size.&lt;/li&gt;<br /> &lt;li&gt;Most machine learning approaches assume a fixed training set, or possibly a batch-wise updated scenario, where training and usage can be separated. When new data arrives continuously, and the underlying reality changes constantly, the models need to gradually adapt. When the knowledge is to be used by many users, or by users with varying interests, a single model is not enough. There is a need for methods that can learn many models at the same time, each capturing different aspects of the data, and combine them in flexible ways to provide up-to-date, relevant knowledge.&lt;/li&gt;<br /> &lt;li&gt;Data coming from different sources and being of different types raises several uncertainty issues associated with it, such as the validity, precision, and bias of those sources. This again changes the analytics task in a qualitative way, and calls for principled methods to handle all those aspects throughout the full course of data processing. Machine learning algorithms needs to take this uncertainty into account when creating models, but also be capable of propagating it into their results.&lt;/li&gt;<br /> &lt;/ul&gt;<br /> <br /> &lt;h3&gt;Challenge 3. To provide analytics methodology and high-level interactive functionality, to make the value in massive data easier available to end-users.&lt;/h3&gt;<br /> <br /> Big Data Analytics is capable of highlighting interesting aspects and discovering things of which users are completely unaware: detecting deviations, anomalies and trends, analysing key values, relations and co-occurrences, as well as making predictions. A crucial aspect of Big Data Analytics is enabling end users to use machine learning solutions more efficiently. On the one hand, unrealistic expectations have to be addressed by clearer presentation of the models, their quality and applicability limitations. At the same time, the full capabilities of machine learning in the Big Data context need to be made available to those who can benefit from it the most. The solution is the combination of elevating the abstraction level of machine learning algorithms, increased interactivity, using better visualisation techniques, and engaging end users into the whole data analytics cycle.<br /> <br /> &lt;ul&gt;<br /> &lt;li&gt;Traditional software and hardware layers for big data analytics lack important services that the human cognitive system needs in processing complex information, and how to make machine learning meet the demands of big data analysts remains an open problem.&lt;/li&gt;<br /> &lt;li&gt;Despite extensive research on how interactive visualization can facilitate the understanding of machine learning algorithms, there is a lack of results indicating the effectiveness of the different visualization techniques in terms of how well they are perceived and understood by the users and how the visualization influences analytical reasoning.&lt;/li&gt;<br /> &lt;li&gt;Most state-of-the-art visual analytics (VA) tools and techniques do not properly accommodate big data. A major challenge is the capability of visual analysis methods to work incrementally and improving real-time analytical capability. How to handle streaming data and how to cooperate with approximate machine learning algorithms are open research questions.&lt;/li&gt;<br /> &lt;li&gt;By default ML algorithms today aim to offer users as much flexibility as possible, based on the assumption that those users are themselves experts in the field. There is a need to develop high level, abstract presentation layer on top of such implementations, one that will allow domain experts to use ML solutions efficiently.&lt;/li&gt;<br /> &lt;/ul&gt;<br /> {{ShowProjectPublications}}</div> Mohbou https://mw.hh.se/caisr/index.php?title=BIDAF&diff=3663 BIDAF 2017-10-19T14:34:00Z <p>Mohbou: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title=BIDAF<br /> |ContactInformation=Slawomir Nowaczyk<br /> |ShortDescription=Big Data Analytics Framework for smart society<br /> |Description=BIDAF is a five-year research project financed by the KK-stiftelsen. The project is carried out by researchers at Halmstad University, SICS Swedish ICT AB, and University of Skövde, Sweden. The overall aim of the BIDAF project is to significantly further the research within massive data analysis, by means of machine learning, in response to the increasing demand of retrieving value from data in all of society. This will be done by creating a strong distributed research environment for big data analytics.<br /> |LogotypeFile=Bidaf.png<br /> |ProjectResponsible=Slawomir Nowaczyk<br /> |ProjectStart=2014/11/01<br /> |ProjectEnd=2019/10/31<br /> |Lctitle=No<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=SICS<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=University of Skövde<br /> }}<br /> __NOTOC__<br /> {{ShowResearchProject}}<br /> The BIDAF project addresses challenges on several levels:&lt;br /&gt;<br /> - Platforms to store and process the data&lt;br /&gt;<br /> - Machine learning algorithms to analyze the data&lt;br /&gt;<br /> - High level tools to access the results&lt;br /&gt;<br /> <br /> All of these challenges must be addressed together, in order to enable end users to successfully perform analysis of massive data: (i) the hardware and platform level with the capacity to collect, store, and process the necessary volumes of data in real time, (ii) machine learning algorithms to model and analyse the collected data, and (iii) high level tools and functionality to access the results and to allow exploring and visualizing both the data and the models.<br /> <br /> &lt;h3&gt;Challenge 1. To develop a computation platform suitable for machine learning of massive streaming and distributed data.&lt;/h3&gt;<br /> <br /> One of the important characteristics of Big Data is that it is often streaming or at least constantly updated. It typically originates from a large number of distributed sources, and is, like most real world data, inherently noisy, vague or uncertain. At the same time, due to sheer size, a scalable framework for efficient processing is needed to adequately take advantage of it. However, today’s Big Data platforms are not well adapted to the specific needs of machine learning algorithms:<br /> <br /> &lt;ul&gt;<br /> &lt;li&gt;Current platforms lack functionality suitable for analysing real-time, streaming and distributed data.&lt;/li&gt;<br /> &lt;li&gt;Machine learning requires storing and updating an internal model of the data. Current platforms lack suitable support for stateful computing.&lt;/li&gt;<br /> &lt;li&gt;The advanced processing in machine learning requires a more flexible computational structure than provided within the map-reduce paradigm of big data platforms, for example, iteration.&lt;/li&gt;<br /> &lt;/ul&gt;<br /> <br /> &lt;h3&gt;Challenge 2. To develop machine learning algorithms suitable for handling both the opportunities and challenges with massive, distributed, and streaming data produced in society.&lt;/h3&gt;<br /> <br /> A lot of recent research in machine learning, as a means to automatically sieve through large amounts<br /> of information, model it, and draw conclusions, are motivated by Big Data. Traditional machine learning<br /> algorithms are, however, not suitable for dealing with the opportunities nor the challenges that come with<br /> massive, distributed and, streaming data:<br /> <br /> - Many machine learning methods are designed for small training sets, trying to squeeze maximum out of them, usually by iterating over the examples many times. Then they use cross validation schemes to evaluate the methods on, again, limited amounts of data. With larger, especially streaming, data, there should be no need to iterate over the same examples for training and validation.<br /> - A large class of successful machine learning algorithms are sample based (e.g., kernel density estimators and support vector machines), meaning that the model increases in size as more data arrives. This can quickly become infeasible, and so there is a need for more compact models, ones that manage to catch the essence of the data, without out-of-control growth in size.<br /> - Most machine learning approaches assume a fixed training set, or possibly a batch-wise updated scenario, where training and usage can be separated. When new data arrives continuously, and the underlying reality changes constantly, the models need to gradually adapt. When the knowledge is to be used by many users, or by users with varying interests, a single model is not enough. There is a need for methods that can learn many models at the same time, each capturing different aspects of the data, and combine them in flexible ways to provide up-to-date, relevant knowledge.<br /> - Data coming from different sources and being of different types raises several uncertainty issues associated with it, such as the validity, precision, and bias of those sources. This again changes the analytics task in a qualitative way, and calls for principled methods to handle all those aspects throughout the full course of data processing. Machine learning algorithms needs to take this uncertainty into account when creating models, but also be capable of propagating it into their results.<br /> <br /> &lt;h3&gt;Challenge 3. To provide analytics methodology and high-level interactive functionality, to make the value in massive data easier available to end-users.&lt;/h3&gt;<br /> <br /> Big Data Analytics is capable of highlighting interesting aspects and discovering things of which users are completely unaware: detecting deviations, anomalies and trends, analysing key values, relations and co-occurrences, as well as making predictions. A crucial aspect of Big Data Analytics is enabling end users to use machine learning solutions more efficiently. On the one hand, unrealistic expectations have to be addressed by clearer presentation of the models, their quality and applicability limitations. At the same time, the full capabilities of machine learning in the Big Data context need to be made available to those who can benefit from it the most. The solution is the combination of elevating the abstraction level of machine learning algorithms, increased interactivity, using better visualisation techniques, and engaging end users into the whole data analytics cycle.<br /> <br /> - Traditional software and hardware layers for big data analytics lack important services that the human cognitive system needs in processing complex information, and how to make machine learning meet the demands of big data analysts remains an open problem.<br /> - Despite extensive research on how interactive visualization can facilitate the understanding of machine learning algorithms, there is a lack of results indicating the effectiveness of the different visualization techniques in terms of how well they are perceived and understood by the users and how the visualization influences analytical reasoning.<br /> - Most state-of-the-art visual analytics (VA) tools and techniques do not properly accommodate big data. A major challenge is the capability of visual analysis methods to work incrementally and improving real-time analytical capability. How to handle streaming data and how to cooperate with approximate machine learning algorithms are open research questions.<br /> - By default ML algorithms today aim to offer users as much flexibility as possible, based on the assumption that those users are themselves experts in the field. There is a need to develop high level, abstract presentation layer on top of such implementations, one that will allow domain experts to use ML solutions efficiently.<br /> <br /> {{ShowProjectPublications}}</div> Mohbou https://mw.hh.se/caisr/index.php?title=BIDAF&diff=3662 BIDAF 2017-10-19T14:32:21Z <p>Mohbou: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title=BIDAF<br /> |ContactInformation=Slawomir Nowaczyk<br /> |ShortDescription=Big Data Analytics Framework<br /> |Description=BIDAF is a five-year research project financed by the KK-stiftelsen. The project is carried out by researchers at Halmstad University, SICS Swedish ICT AB, and University of Skövde, Sweden. The overall aim of the BIDAF project is to significantly further the research within massive data analysis, by means of machine learning, in response to the increasing demand of retrieving value from data in all of society. This will be done by creating a strong distributed research environment for big data analytics.<br /> |LogotypeFile=Bidaf.png<br /> |ProjectResponsible=Slawomir Nowaczyk<br /> |ProjectStart=2014/11/01<br /> |ProjectEnd=2019/10/31<br /> |Lctitle=No<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=SICS<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=University of Skövde<br /> }}<br /> __NOTOC__<br /> {{ShowResearchProject}}<br /> The BIDAF project addresses challenges on several levels:&lt;br /&gt;<br /> - Platforms to store and process the data&lt;br /&gt;<br /> - Machine learning algorithms to analyze the data&lt;br /&gt;<br /> - High level tools to access the results&lt;br /&gt;<br /> <br /> All of these challenges must be addressed together, in order to enable end users to successfully perform analysis of massive data: (i) the hardware and platform level with the capacity to collect, store, and process the necessary volumes of data in real time, (ii) machine learning algorithms to model and analyse the collected data, and (iii) high level tools and functionality to access the results and to allow exploring and visualizing both the data and the models.<br /> <br /> &lt;h3&gt;Challenge 1. To develop a computation platform suitable for machine learning of massive streaming and distributed data.&lt;/h3&gt;<br /> <br /> One of the important characteristics of Big Data is that it is often streaming or at least constantly updated. It typically originates from a large number of distributed sources, and is, like most real world data, inherently noisy, vague or uncertain. At the same time, due to sheer size, a scalable framework for efficient processing is needed to adequately take advantage of it. However, today’s Big Data platforms are not well adapted to the specific needs of machine learning algorithms:<br /> <br /> - Current platforms lack functionality suitable for analysing real-time, streaming and distributed data.<br /> - Machine learning requires storing and updating an internal model of the data. Current platforms lack suitable support for stateful computing.<br /> - The advanced processing in machine learning requires a more flexible computational structure than provided within the map-reduce paradigm of big data platforms, for example, iteration.<br /> <br /> &lt;h3&gt;Challenge 2. To develop machine learning algorithms suitable for handling both the opportunities and challenges with massive, distributed, and streaming data produced in society.&lt;/h3&gt;<br /> <br /> A lot of recent research in machine learning, as a means to automatically sieve through large amounts<br /> of information, model it, and draw conclusions, are motivated by Big Data. Traditional machine learning<br /> algorithms are, however, not suitable for dealing with the opportunities nor the challenges that come with<br /> massive, distributed and, streaming data:<br /> <br /> - Many machine learning methods are designed for small training sets, trying to squeeze maximum out of them, usually by iterating over the examples many times. Then they use cross validation schemes to evaluate the methods on, again, limited amounts of data. With larger, especially streaming, data, there should be no need to iterate over the same examples for training and validation.<br /> - A large class of successful machine learning algorithms are sample based (e.g., kernel density estimators and support vector machines), meaning that the model increases in size as more data arrives. This can quickly become infeasible, and so there is a need for more compact models, ones that manage to catch the essence of the data, without out-of-control growth in size.<br /> - Most machine learning approaches assume a fixed training set, or possibly a batch-wise updated scenario, where training and usage can be separated. When new data arrives continuously, and the underlying reality changes constantly, the models need to gradually adapt. When the knowledge is to be used by many users, or by users with varying interests, a single model is not enough. There is a need for methods that can learn many models at the same time, each capturing different aspects of the data, and combine them in flexible ways to provide up-to-date, relevant knowledge.<br /> - Data coming from different sources and being of different types raises several uncertainty issues associated with it, such as the validity, precision, and bias of those sources. This again changes the analytics task in a qualitative way, and calls for principled methods to handle all those aspects throughout the full course of data processing. Machine learning algorithms needs to take this uncertainty into account when creating models, but also be capable of propagating it into their results.<br /> <br /> &lt;h3&gt;Challenge 3. To provide analytics methodology and high-level interactive functionality, to make the value in massive data easier available to end-users.&lt;/h3&gt;<br /> <br /> Big Data Analytics is capable of highlighting interesting aspects and discovering things of which users are completely unaware: detecting deviations, anomalies and trends, analysing key values, relations and co-occurrences, as well as making predictions. A crucial aspect of Big Data Analytics is enabling end users to use machine learning solutions more efficiently. On the one hand, unrealistic expectations have to be addressed by clearer presentation of the models, their quality and applicability limitations. At the same time, the full capabilities of machine learning in the Big Data context need to be made available to those who can benefit from it the most. The solution is the combination of elevating the abstraction level of machine learning algorithms, increased interactivity, using better visualisation techniques, and engaging end users into the whole data analytics cycle.<br /> <br /> - Traditional software and hardware layers for big data analytics lack important services that the human cognitive system needs in processing complex information, and how to make machine learning meet the demands of big data analysts remains an open problem.<br /> - Despite extensive research on how interactive visualization can facilitate the understanding of machine learning algorithms, there is a lack of results indicating the effectiveness of the different visualization techniques in terms of how well they are perceived and understood by the users and how the visualization influences analytical reasoning.<br /> - Most state-of-the-art visual analytics (VA) tools and techniques do not properly accommodate big data. A major challenge is the capability of visual analysis methods to work incrementally and improving real-time analytical capability. How to handle streaming data and how to cooperate with approximate machine learning algorithms are open research questions.<br /> - By default ML algorithms today aim to offer users as much flexibility as possible, based on the assumption that those users are themselves experts in the field. There is a need to develop high level, abstract presentation layer on top of such implementations, one that will allow domain experts to use ML solutions efficiently.<br /> <br /> {{ShowProjectPublications}}</div> Mohbou https://mw.hh.se/caisr/index.php?title=BIDAF&diff=3661 BIDAF 2017-10-19T14:31:16Z <p>Mohbou: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title=BIDAF<br /> |ContactInformation=Slawomir Nowaczyk<br /> |ShortDescription=Big Data Analytics Framework<br /> |Description=KK-Synergy project<br /> |LogotypeFile=Bidaf.png<br /> |ProjectResponsible=Slawomir Nowaczyk<br /> |ProjectStart=2014/11/01<br /> |ProjectEnd=2019/10/31<br /> |Lctitle=No<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=SICS<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=University of Skövde<br /> }}<br /> __NOTOC__<br /> {{ShowResearchProject}}<br /> BIDAF is a five-year research project financed by the KK-stiftelsen. The project is carried out by researchers at Halmstad University, SICS Swedish ICT AB, and University of Skövde, Sweden. The overall aim of the BIDAF project is to significantly further the research within massive data analysis, by means of machine learning, in response to the increasing demand of retrieving value from data in all of society. This will be done by creating a strong distributed research environment for big data analytics.&lt;br /&gt;&lt;br /&gt;<br /> <br /> The project addresses challenges on several levels:&lt;br /&gt;<br /> - Platforms to store and process the data&lt;br /&gt;<br /> - Machine learning algorithms to analyze the data&lt;br /&gt;<br /> - High level tools to access the results&lt;br /&gt;<br /> <br /> All of these challenges must be addressed together, in order to enable end users to successfully perform analysis of massive data: (i) the hardware and platform level with the capacity to collect, store, and process the necessary volumes of data in real time, (ii) machine learning algorithms to model and analyse the collected data, and (iii) high level tools and functionality to access the results and to allow exploring and visualizing both the data and the models.<br /> <br /> &lt;h3&gt;Challenge 1. To develop a computation platform suitable for machine learning of massive streaming and distributed data.&lt;/h3&gt;<br /> <br /> One of the important characteristics of Big Data is that it is often streaming or at least constantly updated. It typically originates from a large number of distributed sources, and is, like most real world data, inherently noisy, vague or uncertain. At the same time, due to sheer size, a scalable framework for efficient processing is needed to adequately take advantage of it. However, today’s Big Data platforms are not well adapted to the specific needs of machine learning algorithms:<br /> <br /> - Current platforms lack functionality suitable for analysing real-time, streaming and distributed data.<br /> - Machine learning requires storing and updating an internal model of the data. Current platforms lack suitable support for stateful computing.<br /> - The advanced processing in machine learning requires a more flexible computational structure than provided within the map-reduce paradigm of big data platforms, for example, iteration.<br /> <br /> &lt;h3&gt;Challenge 2. To develop machine learning algorithms suitable for handling both the opportunities and challenges with massive, distributed, and streaming data produced in society.&lt;/h3&gt;<br /> <br /> A lot of recent research in machine learning, as a means to automatically sieve through large amounts<br /> of information, model it, and draw conclusions, are motivated by Big Data. Traditional machine learning<br /> algorithms are, however, not suitable for dealing with the opportunities nor the challenges that come with<br /> massive, distributed and, streaming data:<br /> <br /> - Many machine learning methods are designed for small training sets, trying to squeeze maximum out of them, usually by iterating over the examples many times. Then they use cross validation schemes to evaluate the methods on, again, limited amounts of data. With larger, especially streaming, data, there should be no need to iterate over the same examples for training and validation.<br /> - A large class of successful machine learning algorithms are sample based (e.g., kernel density estimators and support vector machines), meaning that the model increases in size as more data arrives. This can quickly become infeasible, and so there is a need for more compact models, ones that manage to catch the essence of the data, without out-of-control growth in size.<br /> - Most machine learning approaches assume a fixed training set, or possibly a batch-wise updated scenario, where training and usage can be separated. When new data arrives continuously, and the underlying reality changes constantly, the models need to gradually adapt. When the knowledge is to be used by many users, or by users with varying interests, a single model is not enough. There is a need for methods that can learn many models at the same time, each capturing different aspects of the data, and combine them in flexible ways to provide up-to-date, relevant knowledge.<br /> - Data coming from different sources and being of different types raises several uncertainty issues associated with it, such as the validity, precision, and bias of those sources. This again changes the analytics task in a qualitative way, and calls for principled methods to handle all those aspects throughout the full course of data processing. Machine learning algorithms needs to take this uncertainty into account when creating models, but also be capable of propagating it into their results.<br /> <br /> &lt;h3&gt;Challenge 3. To provide analytics methodology and high-level interactive functionality, to make the value in massive data easier available to end-users.&lt;/h3&gt;<br /> <br /> Big Data Analytics is capable of highlighting interesting aspects and discovering things of which users are completely unaware: detecting deviations, anomalies and trends, analysing key values, relations and co-occurrences, as well as making predictions. A crucial aspect of Big Data Analytics is enabling end users to use machine learning solutions more efficiently. On the one hand, unrealistic expectations have to be addressed by clearer presentation of the models, their quality and applicability limitations. At the same time, the full capabilities of machine learning in the Big Data context need to be made available to those who can benefit from it the most. The solution is the combination of elevating the abstraction level of machine learning algorithms, increased interactivity, using better visualisation techniques, and engaging end users into the whole data analytics cycle.<br /> <br /> - Traditional software and hardware layers for big data analytics lack important services that the human cognitive system needs in processing complex information, and how to make machine learning meet the demands of big data analysts remains an open problem.<br /> - Despite extensive research on how interactive visualization can facilitate the understanding of machine learning algorithms, there is a lack of results indicating the effectiveness of the different visualization techniques in terms of how well they are perceived and understood by the users and how the visualization influences analytical reasoning.<br /> - Most state-of-the-art visual analytics (VA) tools and techniques do not properly accommodate big data. A major challenge is the capability of visual analysis methods to work incrementally and improving real-time analytical capability. How to handle streaming data and how to cooperate with approximate machine learning algorithms are open research questions.<br /> - By default ML algorithms today aim to offer users as much flexibility as possible, based on the assumption that those users are themselves experts in the field. There is a need to develop high level, abstract presentation layer on top of such implementations, one that will allow domain experts to use ML solutions efficiently.<br /> <br /> {{ShowProjectPublications}}</div> Mohbou https://mw.hh.se/caisr/index.php?title=BIDAF&diff=3660 BIDAF 2017-10-19T14:28:54Z <p>Mohbou: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title=BIDAF<br /> |ContactInformation=Slawomir Nowaczyk<br /> |ShortDescription=Big Data Analytics Framework<br /> |Description=KK-Synergy project<br /> |LogotypeFile=Bidaf.png<br /> |ProjectResponsible=Slawomir Nowaczyk<br /> |ProjectStart=2014/11/01<br /> |ProjectEnd=2019/10/31<br /> |Lctitle=No<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=SICS<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=University of Skövde<br /> }}<br /> __NOTOC__<br /> {{ShowResearchProject}}<br /> BIDAF is a five-year research project financed by the KK-stiftelsen. The project is carried out by researchers at Halmstad University, SICS Swedish ICT AB, and University of Skövde, Sweden. The overall aim of the BIDAF project is to significantly further the research within massive data analysis, by means of machine learning, in response to the increasing demand of retrieving value from data in all of society. This will be done by creating a strong distributed research environment for big data analytics.&lt;br /&gt;&lt;br /&gt;<br /> <br /> The project addresses challenges on several levels:&lt;br /&gt;<br /> - Platforms to store and process the data&lt;br /&gt;<br /> - Machine learning algorithms to analyze the data&lt;br /&gt;<br /> - High level tools to access the results&lt;br /&gt;<br /> <br /> All of these challenges must be addressed together, in order to enable end users to successfully perform analysis of massive data: (i) the hardware and platform level with the capacity to collect, store, and process the necessary volumes of data in real time, (ii) machine learning algorithms to model and analyse the collected data, and (iii) high level tools and functionality to access the results and to allow exploring and visualizing both the data and the models.<br /> <br /> &lt;h2&gt;Challenge 1. To develop a computation platform suitable for machine learning of massive streaming and distributed data.&lt;/h2&gt;<br /> <br /> One of the important characteristics of Big Data is that it is often streaming or at least constantly updated. It typically originates from a large number of distributed sources, and is, like most real world data, inherently noisy, vague or uncertain. At the same time, due to sheer size, a scalable framework for efficient processing is needed to adequately take advantage of it. However, today’s Big Data platforms are not well adapted to the specific needs of machine learning algorithms:<br /> <br /> - Current platforms lack functionality suitable for analysing real-time, streaming and distributed data.<br /> - Machine learning requires storing and updating an internal model of the data. Current platforms lack suitable support for stateful computing.<br /> - The advanced processing in machine learning requires a more flexible computational structure than provided within the map-reduce paradigm of big data platforms, for example, iteration.<br /> <br /> <br /> {{ShowProjectPublications}}</div> Mohbou https://mw.hh.se/caisr/index.php?title=BIDAF&diff=3659 BIDAF 2017-10-19T14:25:52Z <p>Mohbou: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title=BIDAF<br /> |ContactInformation=Slawomir Nowaczyk<br /> |ShortDescription=Big Data Analytics Framework<br /> |Description=KK-Synergy project<br /> |LogotypeFile=Bidaf.png<br /> |ProjectResponsible=Slawomir Nowaczyk<br /> |ProjectStart=2014/11/01<br /> |ProjectEnd=2019/10/31<br /> |Lctitle=No<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=SICS<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=University of Skövde<br /> }}<br /> __NOTOC__<br /> {{ShowResearchProject}}<br /> BIDAF is a five-year research project financed by the KK-stiftelsen. The project is carried out by researchers at Halmstad University, SICS Swedish ICT AB, and University of Skövde, Sweden. The overall aim of the BIDAF project is to significantly further the research within massive data analysis, by means of machine learning, in response to the increasing demand of retrieving value from data in all of society. This will be done by creating a strong distributed research environment for big data analytics.<br /> There are challenges on several levels that must be addressed:<br /> - Platforms to store and process the data&lt;br /&gt;<br /> - Machine learning algorithms to analyze the data&lt;br /&gt;<br /> - High level tools to access the results&lt;br /&gt;<br /> <br /> <br /> {{ShowProjectPublications}}</div> Mohbou https://mw.hh.se/caisr/index.php?title=BIDAF&diff=3658 BIDAF 2017-10-19T14:25:02Z <p>Mohbou: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title=BIDAF<br /> |ContactInformation=Slawomir Nowaczyk<br /> |ShortDescription=Big Data Analytics Framework<br /> |Description=KK-Synergy project<br /> |LogotypeFile=Bidaf.png<br /> |ProjectResponsible=Slawomir Nowaczyk<br /> |ProjectStart=2014/11/01<br /> |ProjectEnd=2019/10/31<br /> |Lctitle=No<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=SICS<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=University of Skövde<br /> }}<br /> __NOTOC__<br /> {{ShowResearchProject}}<br /> BIDAF is a five-year research project financed by the KK-stiftelsen. The project is carried out by researchers at Halmstad University, SICS Swedish ICT AB, and University of Skövde, Sweden. The overall aim of the BIDAF project is to significantly further the research within massive data analysis, by means of machine learning, in response to the increasing demand of retrieving value from data in all of society. This will be done by creating a strong distributed research environment for big data analytics.<br /> There are challenges on several levels that must be addressed:<br /> - Platforms to store and process the data<br /> - Machine learning algorithms to analyze the data<br /> - High level tools to access the results<br /> <br /> <br /> {{ShowProjectPublications}}</div> Mohbou https://mw.hh.se/caisr/index.php?title=File:Bidaf.png&diff=3657 File:Bidaf.png 2017-10-19T14:21:23Z <p>Mohbou: </p> <hr /> <div></div> Mohbou https://mw.hh.se/caisr/index.php?title=BIDAF&diff=3656 BIDAF 2017-10-19T14:15:09Z <p>Mohbou: Created page with &quot;{{ResearchProjInfo |Title=BIDAF |ContactInformation=Slawomir Nowaczyk |ShortDescription=Big Data Analytics Framework |Description=KK-Synergy project |LogotypeFile= |ProjectRes...&quot;</p> <hr /> <div>{{ResearchProjInfo<br /> |Title=BIDAF<br /> |ContactInformation=Slawomir Nowaczyk<br /> |ShortDescription=Big Data Analytics Framework<br /> |Description=KK-Synergy project<br /> |LogotypeFile=<br /> |ProjectResponsible=<br /> |ProjectStart=2014/11/01<br /> |ProjectEnd=2019/10/31<br /> |ApplicationArea=<br /> |Lctitle=No<br /> }}<br /> __NOTOC__<br /> {{ShowResearchProject}}<br /> TODO<br /> <br /> {{ShowProjectPublications}}</div> Mohbou https://mw.hh.se/caisr/index.php?title=Mohamed-Rafik_Bouguelia&diff=3655 Mohamed-Rafik Bouguelia 2017-10-19T14:08:20Z <p>Mohbou: </p> <hr /> <div>{{Person<br /> |Family Name=Bouguelia<br /> |Given Name=Mohamed-Rafik<br /> |Title=PhD<br /> |Phone=+4635167589<br /> |Cell Phone=+46728368919<br /> |Position=Researcher<br /> |Email=mohbou@hh.se<br /> |Image=Rafiko.jpg<br /> |Office=F509<br /> }}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignProjects<br /> |project=SeMI<br /> }}<br /> {{AssignProjects<br /> |project=BIDAF<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Machine Learning<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> [[Category:Staff]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> <br /> ==&#039;&#039;&#039;Research Projects&#039;&#039;&#039;==<br /> {{InsertProjects}}<br /> <br /> ==&#039;&#039;&#039;Publications&#039;&#039;&#039;==<br /> See my Google Scholar publication list [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= by clicking here]<br /> <br /> &#039;&#039;&#039;The following is an automatically retrieved incomplete list of publications. [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= Please click here for a more complete list.]&#039;&#039;&#039;<br /> <br /> {{PublicationsList}}<br /> <br /> [[Category:staff]]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Mohamed-Rafik_Bouguelia&diff=3654 Mohamed-Rafik Bouguelia 2017-10-19T13:59:43Z <p>Mohbou: </p> <hr /> <div>{{Person<br /> |Family Name=Bouguelia<br /> |Given Name=Mohamed-Rafik<br /> |Title=PhD<br /> |Phone=+4635167589<br /> |Cell Phone=+46728368919<br /> |Position=Researcher<br /> |Email=mohbou@hh.se<br /> |Image=Rafiko.jpg<br /> |Office=F509<br /> }}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignProjects<br /> |project=SeMI<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Machine Learning<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> [[Category:Staff]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> <br /> ==&#039;&#039;&#039;Research Projects&#039;&#039;&#039;==<br /> {{InsertProjects}}<br /> <br /> ==&#039;&#039;&#039;Publications&#039;&#039;&#039;==<br /> See my Google Scholar publication list [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= by clicking here]<br /> <br /> &#039;&#039;&#039;The following is an automatically retrieved incomplete list of publications. [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= Please click here for a more complete list.]&#039;&#039;&#039;<br /> <br /> {{PublicationsList}}<br /> <br /> [[Category:staff]]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Mohamed-Rafik_Bouguelia&diff=3653 Mohamed-Rafik Bouguelia 2017-10-19T13:53:54Z <p>Mohbou: </p> <hr /> <div>{{Person<br /> |Family Name=Bouguelia<br /> |Given Name=Mohamed-Rafik<br /> |Title=PhD<br /> |Phone=+4635167589<br /> |Cell Phone=+46728368919<br /> |Position=Researcher<br /> |Email=mohbou@hh.se<br /> |Image=Rafiko.jpg<br /> |Office=F509<br /> }}<br /> {{AssignProjects<br /> |project=BIDAF A Big Data Analytics Framework for a Smart Society<br /> }}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignProjects<br /> |project=SeMI<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Machine Learning<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> [[Category:Staff]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> <br /> ==&#039;&#039;&#039;Research Projects&#039;&#039;&#039;==<br /> {{InsertProjects}}<br /> <br /> ==&#039;&#039;&#039;Publications&#039;&#039;&#039;==<br /> See my Google Scholar publication list [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= by clicking here]<br /> <br /> &#039;&#039;&#039;The following is an automatically retrieved incomplete list of publications. [https://scholar.google.com/citations?user=YXM_FmgAAAAJ&amp;hl= Please click here for a more complete list.]&#039;&#039;&#039;<br /> <br /> {{PublicationsList}}<br /> <br /> [[Category:staff]]</div> Mohbou https://mw.hh.se/caisr/index.php?title=Publications:Unsupervised_classification_of_slip_events_for_planetary_exploration_rovers&diff=3652 Publications:Unsupervised classification of slip events for planetary exploration rovers 2017-10-19T13:49:51Z <p>Mohbou: </p> <hr /> <div>&lt;div style=&#039;display: none&#039;&gt;<br /> == Do not edit this section ==<br /> &lt;/div&gt;<br /> {{PublicationSetupTemplate|Author=Mohamed-Rafik Bouguelia, Ramon Gonzalez, Karl Iagnemma, Stefan Byttner<br /> |PID=1147910<br /> |Name=Bouguelia, Mohamed-Rafik (mohbou) (0000-0002-2859-6155) (Högskolan i Halmstad (2804), Akademin för informationsteknologi (16904), Halmstad Embedded and Intelligent Systems Research (EIS) (3938), CAISR Centrum för tillämpade intelligenta system (IS-lab) (13650));Gonzalez, Ramon (Massachusetts Institute of Technology);Iagnemma, Karl (Massachusetts Institute of Technology);Byttner, Stefan (Högskolan i Halmstad (2804), Akademin för informationsteknologi (16904), Halmstad Embedded and Intelligent Systems Research (EIS) (3938), CAISR Centrum för tillämpade intelligenta system (IS-lab) (13650))<br /> |Title=Unsupervised classification of slip events for planetary exploration rovers<br /> |PublicationType=Journal Paper<br /> |ContentType=Refereegranskat<br /> |Language=eng<br /> |Journal=Journal of terramechanics<br /> |JournalISSN=0022-4898<br /> |Status=published<br /> |Volume=73C<br /> |Issue=<br /> |HostPublication=<br /> |Conference=<br /> |StartPage=95<br /> |EndPage=106<br /> |Year=2017<br /> |Edition=<br /> |Pages=<br /> |City=<br /> |Publisher=Elsevier<br /> |Series=<br /> |SeriesISSN=<br /> |ISBN=<br /> |Urls=http://www.sciencedirect.com/science/article/pii/S0022489817300435<br /> |ISRN=<br /> |DOI=http://dx.doi.org/10.1016/j.jterra.2017.09.001<br /> |ISI=<br /> |PMID=<br /> |ScopusId=<br /> |NBN=urn:nbn:se:hh:diva-35169<br /> |LocalId=<br /> |ArchiveNumber=<br /> |Keywords=Unsupervised learning;Clustering;Data-driven modeling;Slip;MSL rover;LATUV rover<br /> |Categories=Datavetenskap (datalogi) (10201)<br /> |ResearchSubjects=<br /> |Projects=<br /> |Notes=<br /> |Abstract=&lt;p&gt;This paper introduces an unsupervised method for the classification of discrete rovers’ slip events based on proprioceptive signals. In particular, the method is able to automatically discover and track various degrees of slip (i.e. low slip, moderate slip, high slip). The proposed method is based on aggregating the data over time, since high level concepts, such as high and low slip, are concepts that are dependent on longer time perspectives. Different features and subsets of the data have been identified leading to a proper clustering, interpreting those clusters as initial models of the prospective concepts. Bayesian tracking has been used in order to continuously improve the parameters of these models, based on the new data. Two real datasets are used to validate the proposed approach in comparison to other known unsupervised and supervised machine learning methods. The first dataset is collected by a single-wheel testbed available at MIT. The second dataset was collected by means of a planetary exploration rover in real off-road conditions. Experiments prove that the proposed method is more accurate (up to 86% of accuracy vs. 80% for K-means) in discovering various levels of slip while being fully unsupervised (no need for hand-labeled data for training).&lt;/p&gt;<br /> |Opponents=<br /> |Supervisors=<br /> |Examiners=<br /> |Patent=<br /> |ThesisLevel=<br /> |Credits=<br /> |Programme=<br /> |Subject=<br /> |Uppsok=<br /> |DefencePlace=<br /> |DefenceLanguage=<br /> |DefenceDate=<br /> |CreatedDate=2017-10-09<br /> |PublicationDate=2017-10-09<br /> |LastUpdated=2017-10-09<br /> |diva=http://hh.diva-portal.org/smash/record.jsf?searchId=1&amp;pid=diva2:1147910}}<br /> &lt;div style=&#039;display: none&#039;&gt;<br /> <br /> == Keep all hand-made modifications below ==<br /> &lt;/div&gt;{{PublicationDisplayTemplate}}</div> Mohbou https://mw.hh.se/caisr/index.php?title=Publications:Unsupervised_classification_of_slip_events_for_planetary_exploration_rovers&diff=3651 Publications:Unsupervised classification of slip events for planetary exploration rovers 2017-10-19T13:49:21Z <p>Mohbou: </p> <hr /> <div>&lt;div style=&#039;display: none&#039;&gt;<br /> == Do not edit this section ==<br /> &lt;/div&gt;<br /> {{PublicationSetupTemplate|Author=Mohamed-Rafik Bouguelia and Ramon Gonzalez and Karl Iagnemma and Stefan Byttner<br /> |PID=1147910<br /> |Name=Bouguelia, Mohamed-Rafik (mohbou) (0000-0002-2859-6155) (Högskolan i Halmstad (2804), Akademin för informationsteknologi (16904), Halmstad Embedded and Intelligent Systems Research (EIS) (3938), CAISR Centrum för tillämpade intelligenta system (IS-lab) (13650));Gonzalez, Ramon (Massachusetts Institute of Technology);Iagnemma, Karl (Massachusetts Institute of Technology);Byttner, Stefan (Högskolan i Halmstad (2804), Akademin för informationsteknologi (16904), Halmstad Embedded and Intelligent Systems Research (EIS) (3938), CAISR Centrum för tillämpade intelligenta system (IS-lab) (13650))<br /> |Title=Unsupervised classification of slip events for planetary exploration rovers<br /> |PublicationType=Journal Paper<br /> |ContentType=Refereegranskat<br /> |Language=eng<br /> |Journal=Journal of terramechanics<br /> |JournalISSN=0022-4898<br /> |Status=published<br /> |Volume=73C<br /> |Issue=<br /> |HostPublication=<br /> |Conference=<br /> |StartPage=95<br /> |EndPage=106<br /> |Year=2017<br /> |Edition=<br /> |Pages=<br /> |City=<br /> |Publisher=Elsevier<br /> |Series=<br /> |SeriesISSN=<br /> |ISBN=<br /> |Urls=http://www.sciencedirect.com/science/article/pii/S0022489817300435<br /> |ISRN=<br /> |DOI=http://dx.doi.org/10.1016/j.jterra.2017.09.001<br /> |ISI=<br /> |PMID=<br /> |ScopusId=<br /> |NBN=urn:nbn:se:hh:diva-35169<br /> |LocalId=<br /> |ArchiveNumber=<br /> |Keywords=Unsupervised learning;Clustering;Data-driven modeling;Slip;MSL rover;LATUV rover<br /> |Categories=Datavetenskap (datalogi) (10201)<br /> |ResearchSubjects=<br /> |Projects=<br /> |Notes=<br /> |Abstract=&lt;p&gt;This paper introduces an unsupervised method for the classification of discrete rovers’ slip events based on proprioceptive signals. In particular, the method is able to automatically discover and track various degrees of slip (i.e. low slip, moderate slip, high slip). The proposed method is based on aggregating the data over time, since high level concepts, such as high and low slip, are concepts that are dependent on longer time perspectives. Different features and subsets of the data have been identified leading to a proper clustering, interpreting those clusters as initial models of the prospective concepts. Bayesian tracking has been used in order to continuously improve the parameters of these models, based on the new data. Two real datasets are used to validate the proposed approach in comparison to other known unsupervised and supervised machine learning methods. The first dataset is collected by a single-wheel testbed available at MIT. The second dataset was collected by means of a planetary exploration rover in real off-road conditions. Experiments prove that the proposed method is more accurate (up to 86% of accuracy vs. 80% for K-means) in discovering various levels of slip while being fully unsupervised (no need for hand-labeled data for training).&lt;/p&gt;<br /> |Opponents=<br /> |Supervisors=<br /> |Examiners=<br /> |Patent=<br /> |ThesisLevel=<br /> |Credits=<br /> |Programme=<br /> |Subject=<br /> |Uppsok=<br /> |DefencePlace=<br /> |DefenceLanguage=<br /> |DefenceDate=<br /> |CreatedDate=2017-10-09<br /> |PublicationDate=2017-10-09<br /> |LastUpdated=2017-10-09<br /> |diva=http://hh.diva-portal.org/smash/record.jsf?searchId=1&amp;pid=diva2:1147910}}<br /> &lt;div style=&#039;display: none&#039;&gt;<br /> <br /> == Keep all hand-made modifications below ==<br /> &lt;/div&gt;{{PublicationDisplayTemplate}}</div> Mohbou