https://mw.hh.se/caisr/api.php?action=feedcontributions&feedformat=atom&user=Ececal 2026-04-04T06:53:33Z User contributions MediaWiki 1.35.13 https://mw.hh.se/caisr/index.php?title=Be_The_Change:_Video_Analysis_for_Environmental_Sustainability&diff=5131 2022-10-03T09:18:22Z

<p>Ececal: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Analysis of online climate change video contents and identification of video features rendering a video ‘effective’ using machine learning techniques<br /> |Keywords=video analysis, deep learning, representation learning, climate change<br /> |TimeFrame=Fall 2022<br /> |Supervisor=Ece Calikus, Sławomir Nowaczyk,<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> Climate change is the greatest global threat facing the world in the 21st century, according to organizations such as the UN &amp; WHO. In the fight against climate change, one of the key goals is awareness-raising about the environmental challenges &amp; actions that can be taken to mitigate them. Education is key to addressing climate change (Meyer, 2015). Commission calls for env. sustainability to be at the core of EU education &amp; training systems. Despite the problem&#039;s urgency, there is a lack of educational programs on climate change in the context of formal education. In Europe, in particular, there is a lack of innovative and engaging learning environments to foster scientific literacy. Our project aims to develop an Interactive Educational Programme (IEP) on climate change, which transforms both challenges into advantages. By harnessing social media video education on climate change, we aim to perform automated &amp; structured analytics on both the contents &amp; users’ reactions in order to identify the elements that make a video on climate change appealing and engaging. <br /> <br /> This project specifically focuses on two goals: (a) analyzing online video features and identification of video features rendering a video ‘effective’ using machine learning techniques and (b) analyzing video chat content and identification of commentary characteristics of ‘effective’ videos.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Be_The_Change:_Online_Video_Selection_for_Climate_Change_Education&diff=5130 2022-10-03T09:17:44Z

<p>Ececal: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Creating a video selection algorithm to identify the most effective videos by extracting educational, learning, and behavior change activities from online video content.<br /> |Keywords=video analysis, deep learning, representation learning, climate change<br /> |TimeFrame=Fall 2022<br /> |Supervisor=Ece Calikus, Prayag Tiwari, Sławomir Nowaczyk<br /> |Level=Master<br /> }}<br /> Climate change is the greatest global threat facing the world in the 21st century, according to organizations such as the UN &amp; WHO. In the fight against climate change, one of the key goals is awareness-raising about the environmental challenges &amp; actions that can be taken to mitigate them. Education is key to addressing climate change (Meyer, 2015). Commission calls for env. sustainability to be at the core of EU education &amp; training systems. Despite the problem&#039;s urgency, there is a lack of educational programs on climate change in the context of formal education. In Europe, in particular, there is a lack of innovative and engaging learning environments to foster scientific literacy. Our project aims to develop an Interactive Educational Programme (IEP) on climate change, which transforms both challenges into advantages. By harnessing social media video education on climate change, we aim to perform automated &amp; structured analytics on both the contents &amp; users’ reactions in order to identify the elements that make a video on climate change appealing and engaging.<br /> <br /> This project specifically focuses on creating a video selection algorithm to identify the most effective videos by extracting educational, learning, and behavior change activities from online video content.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Be_The_Change:_Video_Analysis_for_Environmental_Sustainability&diff=5129 2022-10-03T09:12:33Z

<p>Ececal: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Analysis of online climate change video contents and identification of video features rendering a video ‘effective’ using machine learning techniques<br /> |Keywords=video analysis, deep learning, representation learning, climate change<br /> |TimeFrame=Fall 2022<br /> |Supervisor=Ece Calikus, Prayag Tiwari, Sławomir Nowaczyk,<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> Climate change is the greatest global threat facing the world in the 21st century, according to organizations such as the UN &amp; WHO. In the fight against climate change, one of the key goals is awareness-raising about the environmental challenges &amp; actions that can be taken to mitigate them. Education is key to addressing climate change (Meyer, 2015). Commission calls for env. sustainability to be at the core of EU education &amp; training systems. Despite the problem&#039;s urgency, there is a lack of educational programs on climate change in the context of formal education. In Europe, in particular, there is a lack of innovative and engaging learning environments to foster scientific literacy. Our project aims to develop an Interactive Educational Programme (IEP) on climate change, which transforms both challenges into advantages. By harnessing social media video education on climate change, we aim to perform automated &amp; structured analytics on both the contents &amp; users’ reactions in order to identify the elements that make a video on climate change appealing and engaging. <br /> <br /> This project specifically focuses on two goals: (a) analyzing online video features and identification of video features rendering a video ‘effective’ using machine learning techniques and (b) analyzing video chat content and identification of commentary characteristics of ‘effective’ videos.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Fair_representation_learning_of_electronic_health_records&diff=5126 2022-10-03T09:01:50Z

<p>Ececal: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Fair representation learning of electronic health records<br /> |Keywords=fair machine learning, bias, fairness<br /> |TimeFrame=Fall 2022<br /> |References=Dullerud, N., Roth, K., Hamidieh, K., Papernot, N. and Ghassemi, M., 2022. Is fairness only metric deep? evaluating and addressing subgroup gaps in deep metric learning. arXiv preprint arXiv:2203.12748.<br /> <br /> Reddy, C., Sharma, D., Mehri, S., Romero-Soriano, A., Shabanian, S. and Honari, S., 2021, June. Benchmarking bias mitigation algorithms in representation learning through fairness metrics. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1).<br /> <br /> Yuan, Y., Xun, G., Suo, Q., Jia, K. and Zhang, A., 2019. Wave2vec: Deep representation learning for clinical temporal data. Neurocomputing, 324, pp.31-42.<br /> |Supervisor=Ali Amirahmadi, Ece Calikus, Kobra Etminani<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> Deep representation learning methods have shown promising performance in different domains, including NLP, image analysis, and healthcare modeling. In healthcare, researchers focus on mitigating data sparsity and high dimensionality and modeling the complex short and long-term dependencies in electric health records (EHR by different representation learning methods. These models are used as feature extractors for few-shot learning and various other downstream tasks. Ensuring fairness in machine learning is extremely important to achieve health equity across different groups in society. Different approaches and frameworks address bias and fairness issues, such as anti-classification, parity, and calibration.<br /> <br /> The ultimate goal of this project is to analyze the effect of different EHR representation learning methods on fairness and look for representations that are agnostic to the patients’ sensitive attributes or have low subgroup gaps in downstream tasks.<br /> <br /> Potential datasets:<br /> https://mimic.mit.edu/docs/about/<br /> https://docs.nightingalescience.org/</div>

Ececal https://mw.hh.se/caisr/index.php?title=Human-in-the-loop_Discovery_of_Interpretable_Concepts_in_Deep_Learning_Models&diff=5124 2022-10-03T09:00:38Z

<p>Ececal: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Interactive discovery of disentangled and interpretable concepts in Deep Learning Models<br /> |Keywords=disentangled learning, representation learning, human-in-the-loop, explainable AI<br /> |TimeFrame=Fall 2022<br /> |Supervisor=Ece Calikus,<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> Learning interpretable representations of data that expose semantic meaning has numerous benefits for artificial intelligence, including de-noising, imputing missing values, reducing bias, and interpretable latent spaces for better insight into the application domain. However, most deep learning methods cannot guarantee that lower dimensional latent representations are semantically meaningful to humans as a concept. Disentangled representation learning is an unsupervised learning technique that breaks down, or disentangles, each feature into narrowly defined variables and encodes them as separate dimensions. The goal is to mimic the quick intuition process of a human, using both “high” and “low” dimension reasoning. A representation is considered a disentangled representation if a change in one dimension corresponds to a change in one factor of variation while being relatively invariant to changes in other factors. For example, a disentangled representation would represent gender, hair color, age, and similar features of a face image as separate dimensions of the latent embedding. However, not every disentangled feature is useful for the certain downstream task. Features such as the border shape, the color, or the size of a skin lesion are useful to detect skin cancer, while the same features are not equally useful for other tasks.<br /> <br /> In this project, we propose an interactive framework to integrate human knowledge in the visual concept extraction process and use the identified concepts to improve the prediction performance of the downstream task. We will also investigate whether some features are meaningful and transferable across different tasks and domains.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Be_The_Change:_Online_Video_Selection_for_Climate_Change_Education&diff=5118 2022-10-03T08:49:15Z

<p>Ececal: Created page with &quot;{{StudentProjectTemplate |Summary=Creating a video selection algorithm to identify the most effective videos by extracting educational, learning, and behavior change activitie...&quot;</p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Creating a video selection algorithm to identify the most effective videos by extracting educational, learning, and behavior change activities from online video content. <br /> |Keywords=video analysis, deep learning, representation learning, climate change<br /> |TimeFrame=Fall 2022<br /> |Supervisor=Ece Calikus, Prayag Tiwari, Sławomir Nowaczyk <br /> }}<br /> Climate change is the greatest global threat facing the world in the 21st century, according to organizations such as the UN &amp; WHO. In the fight against climate change, one of the key goals is awareness-raising about the environmental challenges &amp; actions that can be taken to mitigate them. Education is key to addressing climate change (Meyer, 2015). Commission calls for env. sustainability to be at the core of EU education &amp; training systems. Despite the problem&#039;s urgency, there is a lack of educational programs on climate change in the context of formal education. In Europe, in particular, there is a lack of innovative and engaging learning environments to foster scientific literacy. Our project aims to develop an Interactive Educational Programme (IEP) on climate change, which transforms both challenges into advantages. By harnessing social media video education on climate change, we aim to perform automated &amp; structured analytics on both the contents &amp; users’ reactions in order to identify the elements that make a video on climate change appealing and engaging.<br /> <br /> This project specifically focuses on creating a video selection algorithm to identify the most effective videos by extracting educational, learning, and behavior change activities from online video content.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Be_The_Change:_Video_Analysis_for_Environmental_Sustainability&diff=5114 2022-10-03T08:39:27Z

<p>Ececal: Created page with &quot;{{StudentProjectTemplate |Summary=AnaAnalysis of online climate change video contents and identification of video features rendering a video ‘effective’ using machine lear...&quot;</p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=AnaAnalysis of online climate change video contents and identification of video features rendering a video ‘effective’ using machine learning techniques<br /> |Keywords=video analysis, deep learning, representation learning, climate change<br /> |TimeFrame=Fall 2022<br /> |Supervisor=Ece Calikus, Prayag Tiwari, Sławomir Nowaczyk, <br /> }}<br /> Climate change is the greatest global threat facing the world in the 21st century, according to organizations such as the UN &amp; WHO. In the fight against climate change, one of the key goals is awareness-raising about the environmental challenges &amp; actions that can be taken to mitigate them. Education is key to addressing climate change (Meyer, 2015). Commission calls for env. sustainability to be at the core of EU education &amp; training systems. Despite the problem&#039;s urgency, there is a lack of educational programs on climate change in the context of formal education. In Europe, in particular, there is a lack of innovative and engaging learning environments to foster scientific literacy. Our project aims to develop an Interactive Educational Programme (IEP) on climate change, which transforms both challenges into advantages. By harnessing social media video education on climate change, we aim to perform automated &amp; structured analytics on both the contents &amp; users’ reactions in order to identify the elements that make a video on climate change appealing and engaging. <br /> <br /> This project specifically focuses on two goals: (a) analyzing online video features and identification of video features rendering a video ‘effective’ using machine learning techniques and (b) analyzing video chat content and identification of commentary characteristics of ‘effective’ videos.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Fair_representation_learning_of_electronic_health_records&diff=5110 2022-10-03T08:26:10Z

<p>Ececal: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Fair representation learning of electronic health records<br /> |Keywords=fair machine learning, bias, fairness<br /> |TimeFrame=Fall 2022<br /> |References=Dullerud, N., Roth, K., Hamidieh, K., Papernot, N. and Ghassemi, M., 2022. Is fairness only metric deep? evaluating and addressing subgroup gaps in deep metric learning. arXiv preprint arXiv:2203.12748.<br /> <br /> Reddy, C., Sharma, D., Mehri, S., Romero-Soriano, A., Shabanian, S. and Honari, S., 2021, June. Benchmarking bias mitigation algorithms in representation learning through fairness metrics. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1).<br /> <br /> Yuan, Y., Xun, G., Suo, Q., Jia, K. and Zhang, A., 2019. Wave2vec: Deep representation learning for clinical temporal data. Neurocomputing, 324, pp.31-42.<br /> |Supervisor=Ali Amirahmadi, Ece Calikus, Kobra Etminani<br /> }}<br /> Deep representation learning methods have shown promising performance in different domains, including NLP, image analysis, and healthcare modeling. In healthcare, researchers focus on mitigating data sparsity and high dimensionality and modeling the complex short and long-term dependencies in electric health records (EHR by different representation learning methods. These models are used as feature extractors for few-shot learning and various other downstream tasks. Ensuring fairness in machine learning is extremely important to achieve health equity across different groups in society. Different approaches and frameworks address bias and fairness issues, such as anti-classification, parity, and calibration.<br /> <br /> The ultimate goal of this project is to analyze the effect of different EHR representation learning methods on fairness and look for representations that are agnostic to the patients’ sensitive attributes or have low subgroup gaps in downstream tasks.<br /> <br /> Potential datasets:<br /> https://mimic.mit.edu/docs/about/<br /> https://docs.nightingalescience.org/</div>

Ececal https://mw.hh.se/caisr/index.php?title=Fair_representation_learning_of_electronic_health_records&diff=5109 2022-10-03T08:24:11Z

<p>Ececal: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Fair representation learning of electronic health records<br /> |Keywords=fair machine learning, bias, fairness<br /> |TimeFrame=Fall 2022<br /> |References=Reddy, C., Sharma, D., Mehri, S., Romero-Soriano, A., Shabanian, S. and Honari, S., 2021, June. Benchmarking bias mitigation algorithms in representation learning through fairness metrics. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1).<br /> <br /> Yuan, Y., Xun, G., Suo, Q., Jia, K. and Zhang, A., 2019. Wave2vec: Deep representation learning for clinical temporal data. Neurocomputing, 324, pp.31-42.<br /> |Supervisor=Ali Amirahmadi, Ece Calikus, Kobra Etminani<br /> }}<br /> Deep representation learning methods have shown promising performance in different domains, including NLP, image analysis, and healthcare modeling. In healthcare, researchers focus on mitigating data sparsity and high dimensionality and modeling the complex short and long-term dependencies in electric health records (EHR by different representation learning methods. These models are used as feature extractors for few-shot learning and various other downstream tasks. Ensuring fairness in machine learning is extremely important to achieve health equity across different groups in society. Different approaches and frameworks address bias and fairness issues, such as anti-classification, parity, and calibration.<br /> <br /> The ultimate goal of this project is to analyze the effect of different EHR representation learning methods on fairness and look for representations that are agnostic to the patients’ sensitive attributes or have low subgroup gaps in downstream tasks.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Fair_representation_learning_of_electronic_health_records&diff=5108 2022-10-03T08:22:30Z

<p>Ececal: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Fair representation learning of electronic health records<br /> |Keywords=fair machine learning, bias, fairness<br /> |TimeFrame=Fall 2022<br /> |Supervisor=Ali Amirahmadi, Ece Calikus, Kobra Etminani<br /> }}<br /> Deep representation learning methods have shown promising performance in different domains, including NLP, image analysis, and healthcare modeling. In healthcare, researchers focus on mitigating data sparsity and high dimensionality and modeling the complex short and long-term dependencies in electric health records (EHR by different representation learning methods. These models are used as feature extractors for few-shot learning and various other downstream tasks. Ensuring fairness in machine learning is extremely important to achieve health equity across different groups in society. Different approaches and frameworks address bias and fairness issues, such as anti-classification, parity, and calibration.<br /> <br /> The ultimate goal of this project is to analyze the effect of different EHR representation learning methods on fairness and look for representations that are agnostic to the patients’ sensitive attributes or have low subgroup gaps in downstream tasks.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Fair_representation_learning_of_electronic_health_records&diff=5107 2022-10-03T08:15:27Z

<p>Ececal: Created page with &quot;{{StudentProjectTemplate |Summary= Fair representation learning of electronic health records |Keywords=fair machine learning, bias, fairness |Supervisor=Ali Amirahmadi, Ece Ca...&quot;</p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary= Fair representation learning of electronic health records<br /> |Keywords=fair machine learning, bias, fairness<br /> |Supervisor=Ali Amirahmadi, Ece Calikus, Kobra Etminani<br /> }}<br /> Deep representation learning methods have shown promising performance in different domains, including NLP, image analysis, and healthcare modeling. In healthcare, researchers focus on mitigating data sparsity and high dimensionality and modeling the complex short and long-term dependencies in electric health records (EHR by different representation learning methods. These models are used as feature extractors for few-shot learning and various other downstream tasks. Ensuring fairness in machine learning is extremely important to achieve health equity across different groups in society. Different approaches and frameworks address bias and fairness issues, such as anti-classification, parity, and calibration.<br /> <br /> The ultimate goal of this project is to analyze the effect of different EHR representation learning methods on fairness and look for representations that are agnostic to the patients’ sensitive attributes or have low subgroup gaps in downstream tasks.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Human-in-the-loop_Discovery_of_Interpretable_Concepts_in_Deep_Learning_Models&diff=5072 2022-09-20T14:08:03Z

<p>Ececal: Created page with &quot;{{StudentProjectTemplate |Summary=Interactive discovery of disentangled and interpretable concepts in Deep Learning Models |Keywords=disentangled learning, representation lea...&quot;</p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Interactive discovery of disentangled and interpretable concepts in Deep Learning Models <br /> |Keywords=disentangled learning, representation learning, human-in-the-loop, explainable AI<br /> |TimeFrame=Fall 2022<br /> |Supervisor=Ece Calikus, <br /> }}<br /> Learning interpretable representations of data that expose semantic meaning has numerous benefits for artificial intelligence, including de-noising, imputing missing values, reducing bias, and interpretable latent spaces for better insight into the application domain. However, most deep learning methods cannot guarantee that lower dimensional latent representations are semantically meaningful to humans as a concept. Disentangled representation learning is an unsupervised learning technique that breaks down, or disentangles, each feature into narrowly defined variables and encodes them as separate dimensions. The goal is to mimic the quick intuition process of a human, using both “high” and “low” dimension reasoning. A representation is considered a disentangled representation if a change in one dimension corresponds to a change in one factor of variation while being relatively invariant to changes in other factors. For example, a disentangled representation would represent gender, hair color, age, and similar features of a face image as separate dimensions of the latent embedding. However, not every disentangled feature is useful for the certain downstream task. Features such as the border shape, the color, or the size of a skin lesion are useful to detect skin cancer, while the same features are not equally useful for other tasks.<br /> <br /> In this project, we propose an interactive framework to integrate human knowledge in the visual concept extraction process and use the identified concepts to improve the prediction performance of the downstream task. We will also investigate whether some features are meaningful and transferable across different tasks and domains.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Fair_Conformal_Prediction&diff=5071 2022-09-20T13:03:49Z

<p>Ececal: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Our goal is to design algorithms using conformal prediction framework that make fair predictions across various groups based on e.g., age, sex, income.<br /> |Keywords=fair machine learning, bias, fairness<br /> |TimeFrame=Fall 2022<br /> |References=https://ojs.aaai.org/index.php/AAAI/article/view/21459<br /> |Supervisor=Ece Calikus,<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> The goal of fairness in machine learning is to design algorithms that make fair predictions across various demographic groups. Conformal prediction [1] is a technique devised to assess the uncertainty of predictions produced by a machine learning model. In particular, given an input, conformal prediction estimates a prediction interval in regression problems and a set of classes in classification problems. Both the prediction interval and sets are guaranteed to cover the true value with high probability. <br /> <br /> Our goal is to use this approach to assess prediction uncertainty among different subpopulations (i.e., bias) with sensitive attributes (e.g., race, sex, income, age, etc.) and extend this approach to provide equal coverage among different subgroupsPotential applications for this project involve healthcare, education, and the environment.<br /> <br /> [1] Shafer, G. and Vovk, V., 2008. A Tutorial on Conformal Prediction. Journal of Machine Learning Research, 9(3).</div>

Ececal https://mw.hh.se/caisr/index.php?title=Fair_Conformal_Prediction&diff=5070 2022-09-20T12:41:43Z

<p>Ececal: Our goal is to design algorithms using conformal prediction framework that make fair predictions across various groups based on e.g., age, sex, income.</p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Our goal is to design algorithms using conformal prediction framework that make fair predictions across various groups based on e.g., age, sex, income.<br /> |Keywords=fair machine learning, bias, fairness<br /> |TimeFrame=Fall 2022<br /> |References=https://ojs.aaai.org/index.php/AAAI/article/view/21459<br /> |Supervisor=Ece Calikus, <br /> |Level=Master<br /> |Status=Open<br /> }}<br /> The goal of fairness in machine learning is to design algorithms that make fair predictions across various demographic groups. Conformal prediction is a technique devised to assess the uncertainty of predictions produced by a machine learning model. In particular, given an input, conformal prediction estimates a prediction interval in regression problems and a set of classes in classification problems. Both the prediction interval and sets are guaranteed to cover the true value with high probability. <br /> <br /> Our goal is to use this approach to assess prediction uncertainty among different subpopulations (i.e., bias) with sensitive attributes (e.g., race, sex, income, age, etc.) and extend this approach to provide equal coverage among different subgroupsPotential applications for this project involve healthcare, education, and the environment.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Peer_Group_Discovery_in_District_Heating_Substations_and_Heat_Pumps_for_Self-Monitoring&diff=3573 2017-09-27T21:04:44Z

<p>Ececal: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Finding suitable peer groups to represent district heating and heat pump customers<br /> |References=Y. Kim and S. Sohn, &quot;Stock fraud detection using peer group analysis&quot;, Expert Systems with Applications, vol. 39, no. 10, pp. 8986-8992, 2012.<br /> <br /> D. Weston, D. Hand, N. Adams, C. Whitrow and P. Juszczak, &quot;Plastic card fraud detection using peer group analysis&quot;, Advances in Data Analysis and Classification, vol. 2, no. 1, pp. 45-62, 2008.<br /> <br /> D. Weston, N. Adams, Y. Kim and D. Hand, &quot;Fault Mining Using Peer Group Analysis&quot;, Challenges at the Interface of Data Analysis, Computer Science, and Optimization, pp. 453-461, 2012.<br /> |Prerequisites=Artificial Intelligence and Learning Systems courses; good knowledge of data mining; programming skills for implementing machine learning algorithms<br /> |Supervisor=Ece Calikus, Sławomir Nowaczyk,<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> Peer group analysis is an unsupervised method for monitoring behaviour over time. The objective of this method is to characterize the expected pattern of behaviour around the target object by monitoring the behaviour of similar objects, and then to detect any differences between the expected pattern and the target. Peer group analysis can basically be divided into two stages: <br /> <br /> (1) building peer groups,<br /> (2) detecting anomalous behaviour in the constructed peer groups. <br /> <br /> In this project, the aim is to study methods to identify and build appropriate peer groups and evaluating peer group membership of the samples in district heating and heat pumps datasets. <br /> <br /> Building suitable peer groups for different heat pump and district heating customers is a very challenging task. There are different types of customers which show varying behaviours changing over time. In most of the cases, they are not easily separable into well-defined clusters. Moreover, it is important to discover groups considering more than just &quot;similar&quot; customers based on their overall behaviour. For example; grouping the most commonly occurring patterns in daily energy consumption, grouping buildings according to their sensitivity to outside temperature etc. <br /> <br /> Objectives:<br /> <br /> - Finding good features to represent data<br /> <br /> - Applying different unsupervised clustering methods and similarity measures<br /> <br /> - Interpreting the clustering results in order to define peer groups <br /> <br /> - Evaluation strategy to measure the purity of peer groups using different metrics such as silhouette coefficient, entropy, homogeneity etc. <br /> <br /> - Evaluation strategy to measure how correctly samples are clustered into their peer groups. <br /> <br /> We have collaboration with 3 companies within this project i.e. HEM, Öresundskraft and EasyServ.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Peer_Group_Discovery_in_District_Heating_Substations_and_Heat_Pumps_for_Self-Monitoring&diff=3572 2017-09-27T21:04:10Z

<p>Ececal: Created page with &quot;{{StudentProjectTemplate |Summary=Finding suitable peer groups to represent district heating and heat pump customers |References=Y. Kim and S. Sohn, &quot;Stock fraud detection usi...&quot;</p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Finding suitable peer groups to represent district heating and heat pump customers<br /> |References=Y. Kim and S. Sohn, &quot;Stock fraud detection using peer group analysis&quot;, Expert Systems with Applications, vol. 39, no. 10, pp. 8986-8992, 2012.<br /> <br /> D. Weston, D. Hand, N. Adams, C. Whitrow and P. Juszczak, &quot;Plastic card fraud detection using peer group analysis&quot;, Advances in Data Analysis and Classification, vol. 2, no. 1, pp. 45-62, 2008.<br /> <br /> D. Weston, N. Adams, Y. Kim and D. Hand, &quot;Fault Mining Using Peer Group Analysis&quot;, Challenges at the Interface of Data Analysis, Computer Science, and Optimization, pp. 453-461, 2012.<br /> |Prerequisites=Artificial Intelligence and Learning Systems courses; good knowledge of data mining; programming skills for implementing machine learning algorithms<br /> <br /> |Supervisor=Ece Calikus, Sławomir Nowaczyk, <br /> |Level=Master<br /> |Status=Open<br /> }}<br /> Peer group analysis is an unsupervised method for monitoring behaviour over time. The objective of this method is to characterize the expected pattern of behaviour around the target object by monitoring the behaviour of similar objects, and then to detect any differences between the expected pattern and the target. Peer group analysis can basically be divided into two stages: <br /> <br /> (1) building peer groups,<br /> (2) detecting anomalous behaviour in the constructed peer groups. <br /> <br /> In this project, the aim is to study methods to identify and build appropriate peer groups and evaluating peer group membership of the samples in district heating and heat pumps datasets. <br /> <br /> Building suitable peer groups for different heat pump and district heating customers is a very challenging task. There are different types of customers which show varying behaviours changing over time. In most of the cases, they are not easily separable into well-defined clusters. Moreover, it is important to discover groups considering more than just &quot;similar&quot; customers based on their overall behaviour. For example; grouping the most commonly occurring patterns in daily energy consumption, grouping buildings according to their sensitivity to outside temperature etc. <br /> <br /> Objectives:<br /> <br /> - Finding good features to represent data<br /> - Applying different unsupervised clustering methods and similarity measures<br /> - Interpreting the clustering results in order to define peer groups <br /> - Evaluation strategy to measure the purity of peer groups using different metrics such as silhouette coefficient, entropy, homogeneity etc. <br /> - Evaluation strategy to measure how correctly samples are clustered into their peer groups. <br /> <br /> We have collaboration with 3 companies within this project i.e. HEM, Öresundskraft and EasyServ.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Anomaly_ranking_of_District_Heating_Substations&diff=3565 2017-09-27T20:51:17Z

<p>Ececal: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Implementing anomaly ranking algorithm to monitor district heating substations.<br /> |Keywords=anomaly detection, self monitoring, data mining, learnin-to-rank<br /> |References=M. Goldstein and S. Uchida, &quot;A Comparative Evaluation of Unsupervised Anomaly Detection Algorithms for Multivariate Data&quot;, PLOS ONE, vol. 11, no. 4, p. e0152173, 2016.<br /> <br /> P. Arjunan, H. Khadilkar, T. Ganu, Z. Charbiwala, A. Singh and P. Singh, &quot;Multi-User Energy Consumption Monitoring and Anomaly Detection with Partial Context Information&quot;, Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments - BuildSys &#039;15, 2015.<br /> <br /> D. Araya, K. Grolinger, H. ElYamany, M. Capretz and G. Bitsuamlak, &quot;An ensemble learning framework for anomaly detection in building energy consumption&quot;, Energy and Buildings, vol. 144, pp. 191-206, 2017.<br /> <br /> S. Rayana and L. Akoglu, &quot;Less is More&quot;, ACM Transactions on Knowledge Discovery from Data, vol. 10, no. 4, pp. 1-33, 2016.<br /> <br /> Huang, Huaming, &quot;Rank Based Anomaly Detection Algorithms&quot; (2013). Electrical Engineering and Computer Science - Dissertations.Paper 331.<br /> |Prerequisites=Artificial Intelligence and Learning Systems courses; good knowledge of data mining; programming skills for implementing machine learning algorithms<br /> |Supervisor=Ece Calikus, Sławomir Nowaczyk<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> District heating system is a common way to distribute heat through underground pipelines for residential and commercial requirements. Faults are common in district energy systems due to the high number of substations and instrumentation components. Also, the standard energy-metering instrumentation is designed for low cost and billing, not for automated fault detection. Large variations in building dynamics, building subsystems, human behaviour and the environment make the system complex to model and analyse. <br /> <br /> Anomaly detection refers to the process of detecting abnormal events that do not conform to expected patterns. However, it is hard to differentiate actual faults from the changes in energy consumption due to seasonal variations and changes in personal profiles such as holidays etc. <br /> <br /> In practice, multiple anomaly detection tools are used to continuously raise alarms for different application domains. These alarms include both true positives and false alarms. Operators act on these alarms for diagnosis and deeper root cause<br /> analysis and take appropriate maintenance actions to mitigate the anomalous behaviours. Given the scale and scope of the district heating substations, the operators can be overwhelmed with the large number of alarms at any given instant. It is therefore necessary to prioritize and rank these alarms by their severity. In this project, we aim to propose a novel anomaly ranking algorithm in order to monitor district heating substations.<br /> <br /> Ensemble methods are meta-algorithms that combine several machine learning techniques into one predictive model in order to improve prediction. Ensemble learning for anomaly detection aims to combine results from different detectors with varying outputs to achieve better anomaly detection performance. It generally follows following steps:<br /> <br /> • Model Creation: This is the individual methodology or algorithm which is used to create the corresponding component of the ensemble. <br /> <br /> • Normalization: Different methods may create outlier scores which are on very different scales. In some cases,<br /> the scores may be in ascending order, whereas in others, they may be in descending order. In such cases, normalization is important in being able to combine the scores meaningfully, so that the outlier scores from different components are roughly comparable.<br /> <br /> • Model Combination: This refers to the final combination function, which is used in order to create the outlier score.<br /> <br /> <br /> Objectives:<br /> <br /> -Applying and comparing state-of-the-art unsupervised anomaly detection methods<br /> <br /> -Implementing novel ensemble method by combining multiple detectors<br /> <br /> -Implementing novel anomaly ranking schema in order to aggregate results from different detectors <br /> <br /> -Testing anomaly-ranking framework on district heating and heat pump datasets. <br /> <br /> We have collaboration with 2 companies within this project i.e. HEM and Öresundskraft.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Anomaly_ranking_of_District_Heating_Substations&diff=3562 2017-09-27T20:50:19Z

<p>Ececal: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Anomaly ranking algorithm in order to monitor district heating substations.<br /> |Keywords=anomaly detection, self monitoring, data mining, learnin-to-rank<br /> |References=M. Goldstein and S. Uchida, &quot;A Comparative Evaluation of Unsupervised Anomaly Detection Algorithms for Multivariate Data&quot;, PLOS ONE, vol. 11, no. 4, p. e0152173, 2016.<br /> <br /> P. Arjunan, H. Khadilkar, T. Ganu, Z. Charbiwala, A. Singh and P. Singh, &quot;Multi-User Energy Consumption Monitoring and Anomaly Detection with Partial Context Information&quot;, Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments - BuildSys &#039;15, 2015.<br /> <br /> D. Araya, K. Grolinger, H. ElYamany, M. Capretz and G. Bitsuamlak, &quot;An ensemble learning framework for anomaly detection in building energy consumption&quot;, Energy and Buildings, vol. 144, pp. 191-206, 2017.<br /> <br /> S. Rayana and L. Akoglu, &quot;Less is More&quot;, ACM Transactions on Knowledge Discovery from Data, vol. 10, no. 4, pp. 1-33, 2016.<br /> <br /> Huang, Huaming, &quot;Rank Based Anomaly Detection Algorithms&quot; (2013). Electrical Engineering and Computer Science - Dissertations.Paper 331.<br /> |Prerequisites=Artificial Intelligence and Learning Systems courses; good knowledge of data mining; programming skills for implementing machine learning algorithms<br /> |Supervisor=Ece Calikus, Sławomir Nowaczyk<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> District heating system is a common way to distribute heat through underground pipelines for residential and commercial requirements. Faults are common in district energy systems due to the high number of substations and instrumentation components. Also, the standard energy-metering instrumentation is designed for low cost and billing, not for automated fault detection. Large variations in building dynamics, building subsystems, human behaviour and the environment make the system complex to model and analyse. <br /> <br /> Anomaly detection refers to the process of detecting abnormal events that do not conform to expected patterns. However, it is hard to differentiate actual faults from the changes in energy consumption due to seasonal variations and changes in personal profiles such as holidays etc. <br /> <br /> In practice, multiple anomaly detection tools are used to continuously raise alarms for different application domains. These alarms include both true positives and false alarms. Operators act on these alarms for diagnosis and deeper root cause<br /> analysis and take appropriate maintenance actions to mitigate the anomalous behaviours. Given the scale and scope of the district heating substations, the operators can be overwhelmed with the large number of alarms at any given instant. It is therefore necessary to prioritize and rank these alarms by their severity. In this project, we aim to propose a novel anomaly ranking algorithm in order to monitor district heating substations.<br /> <br /> Ensemble methods are meta-algorithms that combine several machine learning techniques into one predictive model in order to improve prediction. Ensemble learning for anomaly detection aims to combine results from different detectors with varying outputs to achieve better anomaly detection performance. It generally follows following steps:<br /> <br /> • Model Creation: This is the individual methodology or algorithm which is used to create the corresponding component of the ensemble. <br /> <br /> • Normalization: Different methods may create outlier scores which are on very different scales. In some cases,<br /> the scores may be in ascending order, whereas in others, they may be in descending order. In such cases, normalization is important in being able to combine the scores meaningfully, so that the outlier scores from different components are roughly comparable.<br /> <br /> • Model Combination: This refers to the final combination function, which is used in order to create the outlier score.<br /> <br /> <br /> Objectives:<br /> <br /> -Applying and comparing state-of-the-art unsupervised anomaly detection methods<br /> <br /> -Implementing novel ensemble method by combining multiple detectors<br /> <br /> -Implementing novel anomaly ranking schema in order to aggregate results from different detectors <br /> <br /> -Testing anomaly-ranking framework on district heating and heat pump datasets. <br /> <br /> We have collaboration with 2 companies within this project i.e. HEM and Öresundskraft.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Thermal_Profiling_of_Residential_Energy_Consumption_for_Heat_Pump_and_District_Heating_Customers&diff=3559 2017-09-27T20:48:52Z

<p>Ececal: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Finding interesting patterns of heat pump and district heating customers in order to identify meaningful thermal profiles<br /> |Keywords=interesting pattern discovery, energy optimization, data mining, machine learning<br /> |References=H. Gadd and S. Werner, &quot;Heat load patterns in district heating substations&quot;, Applied Energy, vol. 108, pp. 176-183, 2013.<br /> <br /> A. Albert and R. Rajagopal, &quot;Thermal Profiling of Residential Energy Use&quot;, IEEE Transactions on Power Systems, vol. 30, no. 2, pp. 602-611, 2015.<br /> <br /> A. Albert and R. Rajagopal, &quot;Building dynamic thermal profiles of energy consumption for individuals and neighborhoods&quot;, 2013 IEEE International Conference on Big Data, 2013.<br /> |Prerequisites=Artificial Intelligence and Learning Systems courses; good knowledge of data mining; programming skills for implementing machine learning algorithms<br /> |Supervisor=Ece Calikus, Sławomir Nowaczyk,<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> Nowadays large volumes of energy data are continuously collected through a variety of smart meters from different environments. Such data have a great potential to influence the overall energy balance of our communities by identifying thermal behaviour and optimizing building energy consumption and by enhancing people’s awareness of energy wasting. Modelling thermal behaviours of households, buildings and substations are key elements to estimate heat demand and identify normal-abnormal energy consumption. Gadd and Werner (2013) have conducted such study by manually analyzing district heating customers in different categories. They identified four different profiles as a result:<br /> <br /> -Continuous operation control by profiling continuous activity of different type of buildings <br /> <br /> -Night setback control by profiling night by profiling when the set point for the indoor temperature is lowered during the night <br /> <br /> -Time clock operation control 5 days a week by profiling daytime and weekdays use of buildings <br /> <br /> -Time clock operation control 7 days a week by profiling daytime and 7 days a week use of buildings.<br /> <br /> However, it is extremely costly to extract such patterns from various customers by manually. In this project, we aim to automatically find interesting behavioural patterns of heat pump and district heating customers in order to identify meaningful thermal occupancy or building profiles by applying data mining and machine learning approaches.<br /> <br /> Objectives: <br /> <br /> - Data exploration: Analyzing and visualizing data collected from smart meter readings of district heating and heat pump customers <br /> <br /> - Thermal profiling: Modelling different thermal profiles based on spatial behaviours (Helsinborg customers, Halmstad customers etc.), temporal behaviours (holidays, seasons etc. ), building categories, billing amounts, etc. <br /> <br /> - Evaluation: Finding evaluation strategy to measure interestingness of those profiles. Estimating usefulness of those profiles in other machine learning tasks like anomaly detection or energy demand forecasting of the customers.<br /> <br /> We have collaboration with 3 companies in energy domain within this project i.e. HEM, Öresundskraft and EasyServ which give an opportunity to work on solving real-world problems.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Anomaly_ranking_of_District_Heating_Substations&diff=3543 2017-09-27T16:27:42Z

<p>Ececal: In this project, we aim to propose a novel anomaly ranking algorithm in order to monitor district heating substations.</p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=In this project, we aim to propose a novel anomaly ranking algorithm in order to monitor district heating substations.<br /> |Keywords=anomaly detection, self monitoring, data mining, learnin-to-rank<br /> |References=M. Goldstein and S. Uchida, &quot;A Comparative Evaluation of Unsupervised Anomaly Detection Algorithms for Multivariate Data&quot;, PLOS ONE, vol. 11, no. 4, p. e0152173, 2016.<br /> <br /> P. Arjunan, H. Khadilkar, T. Ganu, Z. Charbiwala, A. Singh and P. Singh, &quot;Multi-User Energy Consumption Monitoring and Anomaly Detection with Partial Context Information&quot;, Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments - BuildSys &#039;15, 2015.<br /> <br /> D. Araya, K. Grolinger, H. ElYamany, M. Capretz and G. Bitsuamlak, &quot;An ensemble learning framework for anomaly detection in building energy consumption&quot;, Energy and Buildings, vol. 144, pp. 191-206, 2017.<br /> <br /> S. Rayana and L. Akoglu, &quot;Less is More&quot;, ACM Transactions on Knowledge Discovery from Data, vol. 10, no. 4, pp. 1-33, 2016.<br /> <br /> Huang, Huaming, &quot;Rank Based Anomaly Detection Algorithms&quot; (2013). Electrical Engineering and Computer Science - Dissertations.Paper 331.<br /> |Prerequisites=Artificial Intelligence and Learning Systems courses; good knowledge of data mining; programming skills for implementing machine learning algorithms<br /> |Supervisor=Ece Calikus, Sławomir Nowaczyk<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> District heating system is a common way to distribute heat through underground pipelines for residential and commercial requirements. Faults are common in district energy systems due to the high number of substations and instrumentation components. Also, the standard energy-metering instrumentation is designed for low cost and billing, not for automated fault detection. Large variations in building dynamics, building subsystems, human behaviour and the environment make the system complex to model and analyse. <br /> <br /> Anomaly detection refers to the process of detecting abnormal events that do not conform to expected patterns. However, it is hard to differentiate actual faults from the changes in energy consumption due to seasonal variations and changes in personal profiles such as holidays etc. <br /> <br /> In practice, multiple anomaly detection tools are used to continuously raise alarms for different application domains. These alarms include both true positives and false alarms. Operators act on these alarms for diagnosis and deeper root cause<br /> analysis and take appropriate maintenance actions to mitigate the anomalous behaviours. Given the scale and scope of the district heating substations, the operators can be overwhelmed with the large number of alarms at any given instant. It is therefore necessary to prioritize and rank these alarms by their severity. In this project, we aim to propose a novel anomaly ranking algorithm in order to monitor district heating substations.<br /> <br /> Ensemble methods are meta-algorithms that combine several machine learning techniques into one predictive model in order to improve prediction. Ensemble learning for anomaly detection aims to combine results from different detectors with varying outputs to achieve better anomaly detection performance. It generally follows following steps:<br /> <br /> • Model Creation: This is the individual methodology or algorithm which is used to create the corresponding component of the ensemble. <br /> <br /> • Normalization: Different methods may create outlier scores which are on very different scales. In some cases,<br /> the scores may be in ascending order, whereas in others, they may be in descending order. In such cases, normalization is important in being able to combine the scores meaningfully, so that the outlier scores from different components are roughly comparable.<br /> <br /> • Model Combination: This refers to the final combination function, which is used in order to create the outlier score.<br /> <br /> <br /> Objectives:<br /> <br /> -Applying and comparing state-of-the-art unsupervised anomaly detection methods<br /> <br /> -Implementing novel ensemble method by combining multiple detectors<br /> <br /> -Implementing novel anomaly ranking schema in order to aggregate results from different detectors <br /> <br /> -Testing anomaly-ranking framework on district heating and heat pump datasets. <br /> <br /> We have collaboration with 2 companies within this project i.e. HEM and Öresundskraft.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Anomaly_ranking_of_District_Heating_Substations&diff=3542 2017-09-27T16:25:52Z

<p>Ececal: In this project, we aim to propose a novel anomaly ranking algorithm in order to monitor district heating substations.</p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=In this project, we aim to propose a novel anomaly ranking algorithm in order to monitor district heating substations.<br /> |References=M. Goldstein and S. Uchida, &quot;A Comparative Evaluation of Unsupervised Anomaly Detection Algorithms for Multivariate Data&quot;, PLOS ONE, vol. 11, no. 4, p. e0152173, 2016.<br /> <br /> P. Arjunan, H. Khadilkar, T. Ganu, Z. Charbiwala, A. Singh and P. Singh, &quot;Multi-User Energy Consumption Monitoring and Anomaly Detection with Partial Context Information&quot;, Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments - BuildSys &#039;15, 2015.<br /> <br /> D. Araya, K. Grolinger, H. ElYamany, M. Capretz and G. Bitsuamlak, &quot;An ensemble learning framework for anomaly detection in building energy consumption&quot;, Energy and Buildings, vol. 144, pp. 191-206, 2017.<br /> <br /> S. Rayana and L. Akoglu, &quot;Less is More&quot;, ACM Transactions on Knowledge Discovery from Data, vol. 10, no. 4, pp. 1-33, 2016.<br /> <br /> Huang, Huaming, &quot;Rank Based Anomaly Detection Algorithms&quot; (2013). Electrical Engineering and Computer Science - Dissertations.Paper 331.<br /> |Prerequisites=Artificial Intelligence and Learning Systems courses; good knowledge of data mining; programming skills for implementing machine learning algorithms<br /> |Supervisor=Ec<br /> }}<br /> District heating system is a common way to distribute heat through underground pipelines for residential and commercial requirements. Faults are common in district energy systems due to the high number of substations and instrumentation components. Also, the standard energy-metering instrumentation is designed for low cost and billing, not for automated fault detection. Large variations in building dynamics, building subsystems, human behaviour and the environment make the system complex to model and analyse. <br /> <br /> Anomaly detection refers to the process of detecting abnormal events that do not conform to expected patterns. However, it is hard to differentiate actual faults from the changes in energy consumption due to seasonal variations and changes in personal profiles such as holidays etc. <br /> <br /> In practice, multiple anomaly detection tools are used to continuously raise alarms for different application domains. These alarms include both true positives and false alarms. Operators act on these alarms for diagnosis and deeper root cause<br /> analysis and take appropriate maintenance actions to mitigate the anomalous behaviours. Given the scale and scope of the district heating substations, the operators can be overwhelmed with the large number of alarms at any given instant. It is therefore necessary to prioritize and rank these alarms by their severity. In this project, we aim to propose a novel anomaly ranking algorithm in order to monitor district heating substations.<br /> <br /> Ensemble methods are meta-algorithms that combine several machine learning techniques into one predictive model in order to improve prediction. Ensemble learning for anomaly detection aims to combine results from different detectors with varying outputs to achieve better anomaly detection performance. It generally follows following steps:<br /> <br /> • Model Creation: This is the individual methodology or algorithm which is used to create the corresponding component of the ensemble. <br /> <br /> • Normalization: Different methods may create outlier scores which are on very different scales. In some cases,<br /> the scores may be in ascending order, whereas in others, they may be in descending order. In such cases, normalization is important in being able to combine the scores meaningfully, so that the outlier scores from different components are roughly comparable.<br /> <br /> • Model Combination: This refers to the final combination function, which is used in order to create the outlier score.<br /> <br /> <br /> Objectives:<br /> <br /> -Applying and comparing state-of-the-art unsupervised anomaly detection methods<br /> <br /> -Implementing novel ensemble method by combining multiple detectors<br /> <br /> -Implementing novel anomaly ranking schema in order to aggregate results from different detectors <br /> <br /> -Testing anomaly-ranking framework on district heating and heat pump datasets. <br /> <br /> We have collaboration with 2 companies within this project i.e. HEM and Öresundskraft.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Thermal_Profiling_of_Residential_Energy_Consumption_for_Heat_Pump_and_District_Heating_Customers&diff=3534 2017-09-27T13:02:31Z

<p>Ececal: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=The aim of this project is to find interesting patterns of heat pump and district heating customers in order to identify meaningful thermal profiles <br /> |Keywords=interesting pattern discovery, energy optimization, data mining, machine learning<br /> |References=H. Gadd and S. Werner, &quot;Heat load patterns in district heating substations&quot;, Applied Energy, vol. 108, pp. 176-183, 2013.<br /> <br /> A. Albert and R. Rajagopal, &quot;Thermal Profiling of Residential Energy Use&quot;, IEEE Transactions on Power Systems, vol. 30, no. 2, pp. 602-611, 2015.<br /> <br /> A. Albert and R. Rajagopal, &quot;Building dynamic thermal profiles of energy consumption for individuals and neighborhoods&quot;, 2013 IEEE International Conference on Big Data, 2013.<br /> |Prerequisites=Artificial Intelligence and Learning Systems courses; good knowledge of data mining; programming skills for implementing machine learning algorithms<br /> |Supervisor=Ece Calikus, Sławomir Nowaczyk, <br /> |Level=Master<br /> |Status=Open<br /> }}<br /> Nowadays large volumes of energy data are continuously collected through a variety of smart meters from different environments. Such data have a great potential to influence the overall energy balance of our communities by identifying thermal behaviour and optimizing building energy consumption and by enhancing people’s awareness of energy wasting. Modelling thermal behaviours of households, buildings and substations are key elements to estimate heat demand and identify normal-abnormal energy consumption. Gadd and Werner (2013) have conducted such study by manually analyzing district heating customers in different categories. They identified four different profiles as a result:<br /> <br /> -Continuous operation control by profiling continuous activity of different type of buildings <br /> <br /> -Night setback control by profiling night by profiling when the set point for the indoor temperature is lowered during the night <br /> <br /> -Time clock operation control 5 days a week by profiling daytime and weekdays use of buildings <br /> <br /> -Time clock operation control 7 days a week by profiling daytime and 7 days a week use of buildings.<br /> <br /> However, it is extremely costly to extract such patterns from various customers by manually. In this project, we aim to automatically find interesting behavioural patterns of heat pump and district heating customers in order to identify meaningful thermal occupancy or building profiles by applying data mining and machine learning approaches.<br /> <br /> Objectives: <br /> <br /> - Data exploration: Analyzing and visualizing data collected from smart meter readings of district heating and heat pump customers <br /> <br /> - Thermal profiling: Modelling different thermal profiles based on spatial behaviours (Helsinborg customers, Halmstad customers etc.), temporal behaviours (holidays, seasons etc. ), building categories, billing amounts, etc. <br /> <br /> - Evaluation: Finding evaluation strategy to measure interestingness of those profiles. Estimating usefulness of those profiles in other machine learning tasks like anomaly detection or energy demand forecasting of the customers.<br /> <br /> We have collaboration with 3 companies in energy domain within this project i.e. HEM, Öresundskraft and EasyServ which give an opportunity to work on solving real-world problems.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Thermal_Profiling_of_Residential_Energy_Consumption_for_Heat_Pump_and_District_Heating_Customers&diff=3533 2017-09-27T13:01:55Z

<p>Ececal: The aim of this project is to find interesting patterns of heat pump and district heating customers in order to identify meaningful thermal profiles</p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=The aim of this project is to find interesting patterns of heat pump and district heating customers in order to identify meaningful thermal profiles <br /> |Keywords=interesting pattern discovery, energy optimization, data mining, machine learning<br /> |References=H. Gadd and S. Werner, &quot;Heat load patterns in district heating substations&quot;, Applied Energy, vol. 108, pp. 176-183, 2013.<br /> <br /> A. Albert and R. Rajagopal, &quot;Thermal Profiling of Residential Energy Use&quot;, IEEE Transactions on Power Systems, vol. 30, no. 2, pp. 602-611, 2015.<br /> <br /> A. Albert and R. Rajagopal, &quot;Building dynamic thermal profiles of energy consumption for individuals and neighborhoods&quot;, 2013 IEEE International Conference on Big Data, 2013.<br /> |Prerequisites=Artificial Intelligence and Learning Systems courses; good knowledge of data mining; programming skills for implementing machine learning algorithms<br /> |Supervisor=Ece Calikus, Sławomir Nowaczyk, <br /> |Level=Master<br /> |Status=Open<br /> }}<br /> Nowadays large volumes of energy data are continuously collected through a variety of smart meters from different environments. Such data have a great potential to influence the overall energy balance of our communities by identifying thermal behaviour and optimizing building energy consumption and by enhancing people’s awareness of energy wasting. Modelling thermal behaviours of households, buildings and substations are key elements to estimate heat demand and identify normal-abnormal energy consumption. Gadd and Werner (2013) have conducted such study by manually analyzing district heating customers in different categories. They identified four different profiles as a result:<br /> <br /> -Continuous operation control by profiling continuous activity of different type of buildings <br /> -Night setback control by profiling night by profiling when the set point for the indoor temperature is lowered during the night <br /> -Time clock operation control 5 days a week by profiling daytime and weekdays use of buildings <br /> -Time clock operation control 7 days a week by profiling daytime and 7 days a week use of buildings.<br /> <br /> However, it is extremely costly to extract such patterns from various customers by manually. In this project, we aim to automatically find interesting behavioural patterns of heat pump and district heating customers in order to identify meaningful thermal occupancy or building profiles by applying data mining and machine learning approaches.<br /> <br /> Objectives: <br /> - Data exploration: Analyzing and visializing data collected from smart meter readings of district heating and heat pump customers <br /> - Thermal profiling: Modelling different thermal profiles based on spatial behaviours (Helsinborg customers, Halmstad customers etc.), temporal behaviours (holidays, seasons etc. ), building categories, billing amounts, etc. <br /> - Evaluation: Finding evaluation strategy to measure interestingness of those profiles. Estimating usefulness of those profiles in other machine learning tasks like anomaly detection or energy demand forecasting of the customers.<br /> <br /> We have collaboration with 3 companies in energy domain within this project i.e. HEM, Öresundskraft and EasyServ which give an opportunity to work on solving real-world problems.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Smart_City_Monitoring_Using_Ontology-based_Machine_Learning&diff=3319 2016-10-26T11:02:14Z

<p>Ececal: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=The aim of this project is to create ontology-based supervised and unsupervised machine learning methods for self monitoring to improve reliability of complex environments in smart cities<br /> |Keywords=Data Mining, Knowledge Discovery<br /> |References= [1] Kassahun, Y., Perrone, R., De Momi, E., Berghöfer, E., Tassi, L., Canevini, M.P., Spreafico, R., Ferrigno, G. and Kirchner, F., 2014. Automatic classification of epilepsy types using ontology-based and genetics-based machine learning. Artificial intelligence in medicine, 61(2), pp.79-88.<br /> <br /> [2] Cheong, Y.G., Kim, Y.J., Yoo, S.Y., Lee, H., Lee, S., Chae, S.C. and Choi, H.J., 2011, January. An ontology-based reasoning approach towards energy-aware smart homes. In 2011 IEEE Consumer Communications and Networking Conference (CCNC) (pp. 850-854). IEEE.<br /> <br /> [3] Middleton, Stuart E., David C. De Roure, and Nigel R. Shadbolt. &quot;Capturing knowledge of user preferences: ontologies in recommender systems.&quot; Proceedings of the 1st international conference on Knowledge capture. ACM, 2001.<br /> <br /> [4] Rudin, C., Waltz, D., Anderson, R.N., Boulanger, A., Salleb-Aouissi, A., Chow, M., Dutta, H., Gross, P.N., Huang, B., Ierome, S. and Isaac, D.F., 2012. Machine learning for the New York City power grid. IEEE transactions on pattern analysis and machine intelligence, 34(2), pp.328-345.<br /> |Prerequisites=Good knowledge of machine learning and programming skills for implementing machine learning algorithms<br /> |Supervisor=Sławomir Nowaczyk, Ece Calikus,<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> Ontological modelling provides an insight of a specific knowledge domain and it is made of classes, relationships and instances. Ontologies made of hierarchies and properties between classes can be useful for data aggregation and clustering. Such ontologies provide domain knowledge and support the interpretation of relations identified in dataset through data mining processes, based on statistical techniques. Therefore, ontology-based machine learning approaches can directly incorporate human knowledge.<br /> <br /> In smart city field, ontologies can be used for sharing city knowledge in a reliable format so that it is understandable and can be processed by both humans and machines. The aim of this project is to create ontology-based supervised and unsupervised machine learning methods for self monitoring to improve reliability of complex environments in smart cities. Furthermore, we will use data obtained from various industrial partners such as Volvo AB, HMS, HEM, Alfa Laval etc. in order to combine different domain knowledges (smart vehicles, district heating, industrial networks and etc.) hierarchically for smart cities.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Smart_City_Monitoring_Using_Ontology-based_Machine_Learning&diff=3317 2016-10-26T11:00:16Z

<p>Ececal: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=The aim of this project is to create ontology-based supervised and unsupervised machine learning methods for self monitoring to improve reliability of complex environments in smart cities<br /> |Keywords=Data Mining, Knowledge Discovery<br /> |References=<br /> [1] Kassahun, Y., Perrone, R., De Momi, E., Berghöfer, E., Tassi, L., Canevini, M.P., Spreafico, R., Ferrigno, G. and Kirchner, F., 2014. Automatic classification of epilepsy types using ontology-based and genetics-based machine learning. Artificial intelligence in medicine, 61(2), pp.79-88.<br /> <br /> [2] Cheong, Y.G., Kim, Y.J., Yoo, S.Y., Lee, H., Lee, S., Chae, S.C. and Choi, H.J., 2011, January. An ontology-based reasoning approach towards energy-aware smart homes. In 2011 IEEE Consumer Communications and Networking Conference (CCNC) (pp. 850-854). IEEE.<br /> <br /> [3] Middleton, Stuart E., David C. De Roure, and Nigel R. Shadbolt. &quot;Capturing knowledge of user preferences: ontologies in recommender systems.&quot; Proceedings of the 1st international conference on Knowledge capture. ACM, 2001.<br /> <br /> [4] Rudin, C., Waltz, D., Anderson, R.N., Boulanger, A., Salleb-Aouissi, A., Chow, M., Dutta, H., Gross, P.N., Huang, B., Ierome, S. and Isaac, D.F., 2012. Machine learning for the New York City power grid. IEEE transactions on pattern analysis and machine intelligence, 34(2), pp.328-345.<br /> |Prerequisites=Good knowledge of machine learning and programming skills for implementing machine learning algorithms<br /> |Supervisor=Sławomir Nowaczyk, Ece Calikus,<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> Ontological modelling provides an insight of a specific knowledge domain and it is made of classes, relationships and instances. Ontologies made of hierarchies and properties between classes can be useful for data aggregation and clustering. Such ontologies provide domain knowledge and support the interpretation of relations identified in dataset through data mining processes, based on statistical techniques. Therefore, ontology-based machine learning approaches can directly incorporate human knowledge.<br /> <br /> In smart city field, ontologies can be used for sharing city knowledge in a reliable format so that it is understandable and can be processed by both humans and machines. The aim of this project is to create ontology-based supervised and unsupervised machine learning methods for self monitoring to improve reliability of complex environments in smart cities. Furthermore, we will use data obtained from various industrial partners such as Volvo AB, HMS, HEM, Alfa Laval etc. in order to combine different domain knowledges (smart vehicles, district heating, industrial networks and etc.) hierarchically for smart cities.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Smart_City_Monitoring_Using_Ontology-based_Machine_Learning&diff=3316 2016-10-26T10:59:16Z

<p>Ececal: Created page with &quot;{{StudentProjectTemplate |Summary=The aim of this project is to create ontology-based supervised and unsupervised machine learning methods for self monitoring to improve reli...&quot;</p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=The aim of this project is to create ontology-based supervised and unsupervised machine learning methods for self monitoring to improve reliability of complex environments in smart cities<br /> |Keywords=Data Mining, Knowledge Discovery<br /> |References=[1] Kassahun, Y., Perrone, R., De Momi, E., Berghöfer, E., Tassi, L., Canevini, M.P., Spreafico, R., Ferrigno, G. and Kirchner, F., 2014. Automatic classification of epilepsy types using ontology-based and genetics-based machine learning. Artificial intelligence in medicine, 61(2), pp.79-88.<br /> [2] Cheong, Y.G., Kim, Y.J., Yoo, S.Y., Lee, H., Lee, S., Chae, S.C. and Choi, H.J., 2011, January. An ontology-based reasoning approach towards energy-aware smart homes. In 2011 IEEE Consumer Communications and Networking Conference (CCNC) (pp. 850-854). IEEE.<br /> [3] Middleton, Stuart E., David C. De Roure, and Nigel R. Shadbolt. &quot;Capturing knowledge of user preferences: ontologies in recommender systems.&quot; Proceedings of the 1st international conference on Knowledge capture. ACM, 2001.<br /> [4] Rudin, C., Waltz, D., Anderson, R.N., Boulanger, A., Salleb-Aouissi, A., Chow, M., Dutta, H., Gross, P.N., Huang, B., Ierome, S. and Isaac, D.F., 2012. Machine learning for the New York City power grid. IEEE transactions on pattern analysis and machine intelligence, 34(2), pp.328-345.<br /> |Prerequisites=Good knowledge of machine learning and programming skills for implementing machine learning algorithms<br /> |Supervisor=Sławomir Nowaczyk, Ece Calikus, <br /> |Level=Master<br /> |Status=Open<br /> }}<br /> Ontological modelling provides an insight of a specific knowledge domain and it is made of classes, relationships and instances. Ontologies made of hierarchies and properties between classes can be useful for data aggregation and clustering. Such ontologies provide domain knowledge and support the interpretation of relations identified in dataset through data mining processes, based on statistical techniques. Therefore, ontology-based machine learning approaches can directly incorporate human knowledge.<br /> <br /> In smart city field, ontologies can be used for sharing city knowledge in a reliable format so that it is understandable and can be processed by both humans and machines. The aim of this project is to create ontology-based supervised and unsupervised machine learning methods for self monitoring to improve reliability of complex environments in smart cities. Furthermore, we will use data obtained from various industrial partners such as Volvo AB, HMS, HEM, Alfa Laval etc. in order to combine different domain knowledges (smart vehicles, district heating, industrial networks and etc.) hierarchically for smart cities.</div>

Ececal https://mw.hh.se/caisr/index.php?title=Ece_Calikus&diff=2701 2016-09-27T14:34:39Z

<p>Ececal: </p> <hr /> <div>{{StaffTemplate<br /> |head_image=Ece calikus.jpg<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignProjects<br /> |project=SeMI<br /> }}<br /> {{Person<br /> |Family Name=Calikus<br /> |Given Name=Ece<br /> |Title=M.Sc.<br /> |Phone=+46-72-977-36-40<br /> |Position=PhD. Candidate<br /> |Email=ece.calikus@hh.se<br /> |Image=Ece calikus.jpg<br /> |Office=E512<br /> |Subject=Learning Systems<br /> }}<br /> <br /> <br /> {{AssignApplicationAreas<br /> |ApplicationArea=Industrial Networks<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Heat Pumps<br /> }}<br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> {{PublicationsList}}<br /> [[Category:staff]]</div>

Ececal https://mw.hh.se/caisr/index.php?title=File:Ece_calikus.jpg&diff=2700 2016-09-27T14:34:22Z

<p>Ececal: </p> <hr /> <div></div>

Ececal https://mw.hh.se/caisr/index.php?title=Ece_Calikus&diff=2699 2016-09-27T14:25:05Z

<p>Ececal: </p> <hr /> <div>{{Person<br /> |Family Name=Calikus<br /> |Given Name=Ece<br /> |Title=M.Sc.<br /> |Phone=+46-72-977-36-40<br /> |Position=PhD. Candidate<br /> |Email=ece.calikus@hh.se<br /> |Image=Ece_large.jpg<br /> |Office=E512<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignProjects<br /> |project=SeMI<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Industrial Networks<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Heat Pumps<br /> }}<br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> {{PublicationsList}}<br /> [[Category:staff]]</div>

Ececal https://mw.hh.se/caisr/index.php?title=Ece_Calikus&diff=2698 2016-09-27T14:22:29Z

<p>Ececal: </p> <hr /> <div>{{Person<br /> |Family Name=Calikus<br /> |Given Name=Ece<br /> |Title=M.Sc.<br /> |Phone=+46-72-977-36-40<br /> |Position=PhD. Candidate<br /> |Email=ece.calikus@hh.se<br /> |Image=Ece_large.jpg<br /> |Office=E512<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Industrial Networks<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Heat Pumps<br /> }}<br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> {{PublicationsList}}<br /> [[Category:staff]]</div>

Ececal https://mw.hh.se/caisr/index.php?title=Ece_Calikus&diff=2697 2016-09-27T14:21:08Z

<p>Ececal: </p> <hr /> <div>{{Person<br /> |Family Name=Calikus<br /> |Given Name=Ece<br /> |Title=M.Sc.<br /> |Phone=+46-72-977-36-40<br /> |Position=PhD. Candidate<br /> |Email=ece.calikus@hh.se<br /> |Image=Ece_large.jpg<br /> |Office=E512<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Industrial Networks<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Heat Pumps<br /> }}<br /> [[Category:Staff]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> {{InsertProjects}}<br /> &lt;!-- {{PublicationsList}} --&gt;</div>

Ececal https://mw.hh.se/caisr/index.php?title=Ece_Calikus&diff=2696 2016-09-27T14:19:23Z

<p>Ececal: </p> <hr /> <div>{{Person<br /> |Family Name=Calikus<br /> |Given Name=Ece<br /> |Title=M.Sc.<br /> |Phone=+46-72-977-36-40<br /> |Position=PhD. Candidate<br /> |Email=ece.calikus@hh.se<br /> |Image=Ece_large.jpg<br /> |Office=E512<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Industrial Networks<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Heat Pumps<br /> }}<br /> {{StaffTemplate<br /> |head_image=Ece large.jpg<br /> |givenname=Ece<br /> |surname=Calikus<br /> |subject=Data Mining<br /> |ptitle=PhD. Candidate, M.Sc.<br /> |phonenr=+46-72-977-36-40<br /> |email=ece.calikus@hh.se<br /> |Image=Ece_large.jpg<br /> }}<br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> {{PublicationsList}}<br /> [[Category:staff]]</div>

Ececal https://mw.hh.se/caisr/index.php?title=Ece_Calikus&diff=2695 2016-09-27T14:18:59Z

<p>Ececal: </p> <hr /> <div>{{Person<br /> |Family Name=Calikus<br /> |Given Name=Ece<br /> |Title=M.Sc.<br /> |Phone=+46-72-977-36-40<br /> |Position=PhD. Candidate<br /> |Email=ece.calikus@hh.se<br /> |Image=Ece_large.jpg<br /> |Office=E512<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Industrial Networks<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Heat Pumps<br /> }}<br /> {{StaffTemplate<br /> |head_image=Ece large.jpg<br /> |givenname=Ece<br /> |surname=Calikus<br /> |subject=Data Mining<br /> |ptitle=PhD. Candidate, M.Sc.<br /> |phonenr=+46-72-977-36-40<br /> |email=ece.calikus@hh.se<br /> |Image=Ece_large.jpg<br /> }}<br /> <br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> {{PublicationsList}}<br /> [[Category:staff]]</div>

Ececal https://mw.hh.se/caisr/index.php?title=Ece_Calikus&diff=2694 2016-09-27T14:18:42Z

<p>Ececal: </p> <hr /> <div>{{Person<br /> |Family Name=Calikus<br /> |Given Name=Ece<br /> |Title=M.Sc.<br /> |Phone=+46-72-977-36-40<br /> |Position=PhD. Candidate<br /> |Email=ece.calikus@hh.se<br /> |Image=Ece_large.jpg<br /> |Office=E512<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Industrial Networks<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Heat Pumps<br /> }}<br /> {{StaffTemplate<br /> |head_image=Ece large.jpg<br /> |givenname=Ece<br /> |surname=Calikus<br /> |subject=Data Mining<br /> |ptitle=PhD. Candidate, M.Sc.<br /> |phonenr=+46-72-977-36-40<br /> |email=ece.calikus@hh.se<br /> |Image=Ece_large.jpg<br /> }}</div>

Ececal https://mw.hh.se/caisr/index.php?title=Ece_Calikus&diff=2693 2016-09-27T14:15:24Z

<p>Ececal: </p> <hr /> <div>{{Person<br /> |Family Name=Calikus<br /> |Given Name=Ece<br /> |Title=M.Sc.<br /> |Phone=+46-72-977-36-40<br /> |Position=PhD. Candidate<br /> |Email=ece.calikus@hh.se<br /> |Image=Ece_large.jpg<br /> |Office=E512<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Industrial Networks<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Heat Pumps<br /> }}<br /> {{StaffTemplate<br /> |head_image=Ece large.jpg<br /> |givenname=Ece<br /> |surname=Calikus<br /> |subject=Data Mining<br /> |ptitle=PhD. Candidate, M.Sc.<br /> |phonenr=+46-72-977-36-40<br /> |email=ece.calikus@hh.se<br /> |Image=Ece_large.jpg<br /> }}<br /> <br /> <br /> <br /> <br /> <br /> <br /> <br /> <br /> <br /> <br /> <br /> <br /> <br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> {{PublicationsList}}<br /> [[Category:staff]]</div>

Ececal https://mw.hh.se/caisr/index.php?title=Ece_Calikus&diff=2692 2016-09-27T14:14:15Z

<p>Ececal: </p> <hr /> <div>{{Person<br /> |Family Name=Ece<br /> |Given Name=Calikus<br /> |Title=M.Sc.<br /> |Phone=+46-72-977-36-40<br /> |Position=PhD. Candidate<br /> |Email=ece.calikus@hh.se<br /> |Image=Ece_large.jpg<br /> |Office=E512<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Industrial Networks<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Heat Pumps<br /> }}<br /> {{StaffTemplate<br /> |head_image=Ece large.jpg<br /> |givenname=Ece<br /> |surname=Calikus<br /> |subject=Data Mining<br /> |ptitle=PhD. Candidate, M.Sc.<br /> |phonenr=+46-72-977-36-40<br /> |email=ece.calikus@hh.se<br /> |Image=Ece_large.jpg<br /> }}<br /> <br /> <br /> <br /> <br /> <br /> <br /> <br /> <br /> <br /> <br /> <br /> <br /> <br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> {{PublicationsList}}<br /> [[Category:staff]]</div>

Ececal https://mw.hh.se/caisr/index.php?title=Ece_Calikus&diff=2691 2016-09-27T14:12:14Z

<p>Ececal: </p> <hr /> <div>{{StaffTemplate<br /> |head_image=Ece large.jpg<br /> |givenname=Ece<br /> |surname=Calikus<br /> |subject=Data Mining<br /> |ptitle=PhD. Candidate, M.Sc.<br /> |phonenr=+46-72-977-36-40<br /> |email=ece.calikus@hh.se<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{Person<br /> |Family Name=Ece<br /> |Given Name=Calikus<br /> |Title=M.Sc.<br /> |Phone=+46-72-977-36-40<br /> |Position=PhD. Candidate<br /> |Email=ece.calikus@hh.se<br /> |Office=E512<br /> |Subject=Learning Systems<br /> }}<br /> <br /> {{AssignApplicationAreas<br /> |ApplicationArea=Industrial Networks<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Heat Pumps<br /> }}<br /> <br /> <br /> <br /> <br /> <br /> <br /> <br /> <br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> {{PublicationsList}}<br /> [[Category:staff]]</div>

Ececal https://mw.hh.se/caisr/index.php?title=File:Ece_large.jpg&diff=2690 2016-09-27T14:12:03Z

<p>Ececal: </p> <hr /> <div></div>

Ececal https://mw.hh.se/caisr/index.php?title=Ece_Calikus&diff=2682 2016-09-22T09:20:17Z

<p>Ececal: </p> <hr /> <div>{{Person<br /> |Family Name=Ece<br /> |Given Name=Calikus<br /> |Title=M.Sc.<br /> |Phone=+46-72-977-36-40<br /> |Position=PhD. Candidate<br /> |Email=ece.calikus@hh.se<br /> |Office=E512<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Industrial Networks<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Heat Pumps<br /> }}<br /> {{StaffTemplate<br /> |head_image=S.jpg<br /> |givenname=Ece<br /> |surname=Calikus<br /> |subject=Data Mining<br /> |ptitle=PhD. Candidate, M.Sc.<br /> |phonenr=+46-72-977-36-40<br /> |email=ece.calikus@hh.se<br /> }}<br /> <br /> <br /> <br /> <br /> <br /> <br /> <br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> {{PublicationsList}}<br /> [[Category:staff]]</div>

Ececal https://mw.hh.se/caisr/index.php?title=Ece_Calikus&diff=2681 2016-09-22T09:19:41Z

<p>Ececal: </p> <hr /> <div>{{Person<br /> |Family Name=Ece<br /> |Given Name=Calikus<br /> |Title=M.Sc.<br /> |Phone=+46-72-977-36-40<br /> |Cell Phone=+46-72-977-36-40<br /> |Position=PhD. Candidate<br /> |Email=ece.calikus@hh.se<br /> |Office=E512<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Industrial Networks<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Heat Pumps<br /> }}<br /> {{StaffTemplate<br /> |head_image=S.jpg<br /> |givenname=Ece<br /> |surname=Calikus<br /> |subject=Data Mining<br /> |ptitle=PhD. Candidate, M.Sc.<br /> |phonenr=+46-72-977-36-40<br /> |email=ece.calikus@hh.se<br /> }}<br /> <br /> <br /> <br /> <br /> <br /> <br /> <br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> {{PublicationsList}}<br /> [[Category:staff]]</div>

Ececal https://mw.hh.se/caisr/index.php?title=Ece_Calikus&diff=2680 2016-09-22T09:17:15Z

<p>Ececal: </p> <hr /> <div>{{Person<br /> |Family Name=Ece<br /> |Given Name=Calikus<br /> |Title=M.Sc.<br /> |Cell Phone=+46-72-977-36-40<br /> |Position=PhD. Candidate<br /> |Email=ece.calikus@hh.se<br /> |Office=E513<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Industrial Networks<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Heat Pumps<br /> }}<br /> {{StaffTemplate<br /> |head_image=S.jpg<br /> |givenname=Ece<br /> |surname=Calikus<br /> |subject=Data Mining<br /> |ptitle=PhD. Candidate, M.Sc.<br /> |phonenr=+46-72-977-36-40<br /> |email=ece.calikus@hh.se<br /> }}<br /> <br /> <br /> <br /> <br /> <br /> <br /> <br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> {{PublicationsList}}<br /> [[Category:staff]]</div>

Ececal https://mw.hh.se/caisr/index.php?title=Ece_Calikus&diff=2679 2016-09-22T09:11:37Z

<p>Ececal: </p> <hr /> <div>{{StaffTemplate<br /> |head_image=S.jpg<br /> |givenname=Ece<br /> |surname=Calikus<br /> |subject=Data Mining<br /> |ptitle=PhD. Candidate, M.Sc.<br /> |phonenr=+46-72-977-36-40<br /> |email=ece.calikus@hh.se<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> {{Person<br /> |Family Name=Ece<br /> |Given Name=Calikus<br /> |Title=M.Sc.<br /> |Position=PhD. Candidate<br /> |Email=ece.calikus@hh.se<br /> |Office=E513<br /> |Subject=Learning Systems<br /> }}<br /> <br /> <br /> <br /> <br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> {{PublicationsList}}<br /> [[Category:staff]]</div>

Ececal https://mw.hh.se/caisr/index.php?title=Ece_Calikus&diff=2678 2016-09-22T09:06:52Z

<p>Ececal: </p> <hr /> <div>{{StaffTemplate<br /> |position=PhD. Candidate, M.Sc.<br /> |head_image=S.jpg<br /> |givenname=Ece<br /> |surname=Calikus<br /> |subject=Data Mining<br /> |ptitle=PhD. Candidate, M.Sc.<br /> |phonenr=+46-72-977-36-40<br /> |email=ece.calikus@hh.se<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> {{PublicationsList}}</div>

Ececal https://mw.hh.se/caisr/index.php?title=File:S.jpg&diff=2677 2016-09-22T09:06:06Z

<p>Ececal: </p> <hr /> <div></div>

Ececal https://mw.hh.se/caisr/index.php?title=Ece_Calikus&diff=2676 2016-09-22T08:56:32Z

<p>Ececal: Created page with &quot;{{StaffTemplate |position=PhD. Candidate, M.Sc. |givenname=Ece |surname=Calikus |subject=Data Mining |ptitle=PhD. Candidate, M.Sc. |phonenr=+46-72-977-36-40 |email=ece.calikus...&quot;</p> <hr /> <div>{{StaffTemplate<br /> |position=PhD. Candidate, M.Sc.<br /> |givenname=Ece<br /> |surname=Calikus<br /> |subject=Data Mining<br /> |ptitle=PhD. Candidate, M.Sc.<br /> |phonenr=+46-72-977-36-40<br /> |email=ece.calikus@hh.se<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Learning Systems<br /> }}<br /> <br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> {{PublicationsList}}</div>

Ececal https://mw.hh.se/caisr/index.php?title=File:No-avatar_female1.jpg&diff=2674 2016-09-22T08:45:52Z

<p>Ececal: </p> <hr /> <div></div>

Ececal