https://mw.hh.se/caisr/api.php?action=feedcontributions&feedformat=atom&user=Yuafan 2026-04-04T15:07:46Z User contributions MediaWiki 1.35.13 https://mw.hh.se/caisr/index.php?title=Vehicle_Operation_Classification&diff=3302 2016-10-26T10:01:05Z

<p>Yuafan: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Classify modes of operation of Volvo vehicles based on on-board data<br /> |Keywords=Data Mining, Machine Learning, Ubiquitous Knowledge Discovery<br /> |TimeFrame=Winter 2016 / Spring 2017<br /> |References=Time series classification<br /> <br /> Unsupervised and semi-supervised clustering<br /> <br /> ...<br /> |Prerequisites=Artificial Intelligence and Learning Systems courses<br /> |Supervisor=Sławomir Nowaczyk, Yuantao Fan<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> With 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 sensor data streaming from devices (on large scale), discover interesting patterns and knowledge.<br /> <br /> In the ReDi2Service project we have collected approximately 1TB of data from Volvo buses in normal operation. It is interesting to analyse this data from the usage point of view, and come up with good description and/or classification (possibly hierarchical or even an ontology) of vehicle operation. <br /> <br /> The data contains both GPS positions, as well as on-board signals such as vehicle speed or engine torque. The goal of the project is to provide a framework for organising the data in a way that will facilitate future access to interesting portions of this data according to multiple criteria.<br /> <br /> We are interested in both low-level information (for example, detecting workshop visits, splitting the data into trips from turning the engine on to turning it off, distinguishing between highway and in-city operation, or finding uphill and downhill driving) as well as in more abstract description (is the bus in regular line traffic or performing some other duty, automatically finding similarities and differences between missions, etc).<br /> <br /> More details to come...</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Representation_Learning_for_Deviation_Detection&diff=3286 2016-10-25T22:22:21Z

<p>Yuafan: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Optimise Echo State Networks for time series forecasting and reconstruction. Propose methods, e.g. objective functions, to train Echo State Networks for deviation detection<br /> |Keywords=Representation learning, Deviation detection, Echo State Network, Optimization, Differential evolution<br /> |TimeFrame=Winter 2016 / Spring 2017<br /> |References=[1] Bengio, Yoshua, Aaron Courville, and Pascal Vincent. &quot;Representation learning: A review and new perspectives.&quot; IEEE transactions on pattern analysis and machine intelligence 35.8 (2013): 1798-1828.<br /> <br /> [2] Jaeger, Herbert. Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the&quot; echo state network&quot; approach. GMD-Forschungszentrum Informationstechnik, 2002.<br /> <br /> [3] Jaeger, Herbert, et al. &quot;Optimization and applications of echo state networks with leaky-integrator neurons.&quot; Neural networks 20.3 (2007): 335-352.<br /> <br /> [4] Lukoševičius, Mantas. &quot;A practical guide to applying echo state networks.&quot; Neural networks: Tricks of the trade. Springer Berlin Heidelberg, 2012. 659-686.<br /> <br /> [5] Wang, Lin, Zhigang Wang, and Shan Liu. &quot;An effective multivariate time series classification approach using echo state network and adaptive differential evolution algorithm.&quot; Expert Systems with Applications 43 (2016): 237-249.<br /> |Prerequisites=Artificial Intelligence and Learning Systems courses; good knowledge of machine learning and neural networks; programming skills for implementing machine learning algorithms<br /> |Supervisor=Sławomir Nowaczyk, Yuantao Fan<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> Echo State Network (ESN) is a special class of recurrent neural networks that can be used for supervised learning, e.g. time series forecasting, pattern recognition and deviation detection. The main idea of ESN is to drive a large random, fixed neural network that induce input signal into each neurons. The nonlinear responses of all neurons are combined by a trainable linear combination to a desired output. The network captures temporal features of time series data. Compared to other recurrent neural networks, it can be trained much faster. ESN are characterized by a number of parameters (e.g. network architecture, spectral radius, type of neurons and input scaling etc.). In order to achieve desired performance, these parameters need to be optimized and, preferably, in an efficient way.<br /> <br /> There are many applications [0,1,2] ESN can be applied to. ESN can be used for general learning tasks, e.g. time series forecasting, or as representation of the data. In [3,4] ESN is employed to classify time series for fault detection. Similarly, in [6], air pressure signals are encoded into ESNs and anomalies are detected using an unsupervised deviation detection method, called Consensus Self-Organizing Models (COSMO) method. One key feature of COSMO method is the ability to capture and encode characteristics of the signals by using different representations. Generic representation that can be adapted to different type of signals and captures various characteristics is preferred for anomaly detection. Paper [6] demonstrated that ESNs are promising for this purpose. How to optimize the parameters of ESNs for deviation detection can be further investigated. <br /> <br /> <br /> Objectives:<br /> <br /> 1. Propose a framework to optimize Echo State Networks for forecasting and reconstructing time series.<br /> <br /> 2. Use ESNs as self-organizing data representation (can be trained without external supervision) for unsupervised deviation detection. Determine what are the criteria for ESNs to learn interesting characteristics of the time series for deviation detection. Note that, for example, minimizing the reconstruction error does not necessary to be the objective function when train ESNs, but rather how ESNs can be trained to generalize various properties that characterize the observed system.<br /> <br /> 3. Perform deviation detection (e.g. COSMO method) on both synthetic data and data from real world application based on Echo State Networks and other data representations. Compare and analyze the performance.<br /> <br /> <br /> <br /> References:<br /> <br /> [1] Li, Decai, Min Han, and Jun Wang. &quot;Chaotic time series prediction based on a novel robust echo state network.&quot; IEEE Transactions on Neural Networks and Learning Systems 23.5 (2012): 787-799.<br /> <br /> [2] Krause13, André Frank, et al. &quot;Evolutionary Optimization of Echo State Networks: multiple motor pattern learning.&quot; (2010).<br /> <br /> [3] Marco Rigamonti et al., &quot;Echo State Network for the Remaining Useful Life Prediction of a Turbofan Engine.&quot; Third European Conference of the Prognostics and Health Management Society 2016, Bilbao, Spain, 5-8 July, 2016. PHM Society, 2016.<br /> <br /> [4] Chen, Huanhuan, Peter Tiňo, and Xin Yao. &quot;Cognitive fault diagnosis in Tennessee Eastman Process using learning in the model space.&quot; Computers &amp; Chemical Engineering 67 (2014): 33-42.<br /> <br /> [5] Quevedo, Joseba, et al. &quot;Combining learning in model space fault diagnosis with data validation/reconstruction: Application to the Barcelona water network.&quot; Engineering Applications of Artificial Intelligence 30 (2014): 18-29.<br /> <br /> [6] Fan, Yuantao, et al. &quot;Predicting Air Compressor Failures with Echo State Networks.&quot; Third European Conference of the Prognostics and Health Management Society 2016, Bilbao, Spain, 5-8 July, 2016. PHM Society, 2016.</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Representation_Learning_for_Deviation_Detection&diff=3285 2016-10-25T22:22:03Z

<p>Yuafan: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Optimise Echo State Networks for time series forecasting and reconstruction. Propose methods, e.g. objective functions, to train Echo State Networks for deviation detection<br /> |Keywords=Representation learning, Deviation detection, Echo State Network, Optimization, Differential evolution<br /> |TimeFrame=Winter 2016 / Spring 2017<br /> |References=[1] Bengio, Yoshua, Aaron Courville, and Pascal Vincent. &quot;Representation learning: A review and new perspectives.&quot; IEEE transactions on pattern analysis and machine intelligence 35.8 (2013): 1798-1828.<br /> <br /> [2] Jaeger, Herbert. Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the&quot; echo state network&quot; approach. GMD-Forschungszentrum Informationstechnik, 2002.<br /> <br /> [3] Jaeger, Herbert, et al. &quot;Optimization and applications of echo state networks with leaky-integrator neurons.&quot; Neural networks 20.3 (2007): 335-352.<br /> <br /> [4] Lukoševičius, Mantas. &quot;A practical guide to applying echo state networks.&quot; Neural networks: Tricks of the trade. Springer Berlin Heidelberg, 2012. 659-686.<br /> <br /> [5] Wang, Lin, Zhigang Wang, and Shan Liu. &quot;An effective multivariate time series classification approach using echo state network and adaptive differential evolution algorithm.&quot; Expert Systems with Applications 43 (2016): 237-249.<br /> |Prerequisites=Artificial Intelligence and Learning Systems courses; good knowledge of machine learning and neural networks; programming skills for implementing machine learning algorithms<br /> |Supervisor=Sławomir Nowaczyk, Yuantao Fan<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> Echo State Network (ESN) is a special class of recurrent neural networks that can be used for supervised learning, e.g. time series forecasting, pattern recognition and deviation detection. The main idea of ESN is to drive a large random, fixed neural network that induce input signal into each neurons. The nonlinear responses of all neurons are combined by a trainable linear combination to a desired output. The network captures temporal features of time series data. Compared to other recurrent neural networks, it can be trained much faster. ESN are characterized by a number of parameters (e.g. network architecture, spectral radius, type of neurons and input scaling etc.). In order to achieve desired performance, these parameters need to be optimized and, preferably, in an efficient way.<br /> <br /> <br /> There are many applications [0,1,2] ESN can be applied to. ESN can be used for general learning tasks, e.g. time series forecasting, or as representation of the data. In [3,4] ESN is employed to classify time series for fault detection. Similarly, in [6], air pressure signals are encoded into ESNs and anomalies are detected using an unsupervised deviation detection method, called Consensus Self-Organizing Models (COSMO) method. One key feature of COSMO method is the ability to capture and encode characteristics of the signals by using different representations. Generic representation that can be adapted to different type of signals and captures various characteristics is preferred for anomaly detection. Paper [6] demonstrated that ESNs are promising for this purpose. How to optimize the parameters of ESNs for deviation detection can be further investigated. <br /> <br /> <br /> Objectives:<br /> <br /> 1. Propose a framework to optimize Echo State Networks for forecasting and reconstructing time series.<br /> <br /> 2. Use ESNs as self-organizing data representation (can be trained without external supervision) for unsupervised deviation detection. Determine what are the criteria for ESNs to learn interesting characteristics of the time series for deviation detection. Note that, for example, minimizing the reconstruction error does not necessary to be the objective function when train ESNs, but rather how ESNs can be trained to generalize various properties that characterize the observed system.<br /> <br /> 3. Perform deviation detection (e.g. COSMO method) on both synthetic data and data from real world application based on Echo State Networks and other data representations. Compare and analyze the performance.<br /> <br /> <br /> <br /> References:<br /> <br /> [1] Li, Decai, Min Han, and Jun Wang. &quot;Chaotic time series prediction based on a novel robust echo state network.&quot; IEEE Transactions on Neural Networks and Learning Systems 23.5 (2012): 787-799.<br /> <br /> [2] Krause13, André Frank, et al. &quot;Evolutionary Optimization of Echo State Networks: multiple motor pattern learning.&quot; (2010).<br /> <br /> [3] Marco Rigamonti et al., &quot;Echo State Network for the Remaining Useful Life Prediction of a Turbofan Engine.&quot; Third European Conference of the Prognostics and Health Management Society 2016, Bilbao, Spain, 5-8 July, 2016. PHM Society, 2016.<br /> <br /> [4] Chen, Huanhuan, Peter Tiňo, and Xin Yao. &quot;Cognitive fault diagnosis in Tennessee Eastman Process using learning in the model space.&quot; Computers &amp; Chemical Engineering 67 (2014): 33-42.<br /> <br /> [5] Quevedo, Joseba, et al. &quot;Combining learning in model space fault diagnosis with data validation/reconstruction: Application to the Barcelona water network.&quot; Engineering Applications of Artificial Intelligence 30 (2014): 18-29.<br /> <br /> [6] Fan, Yuantao, et al. &quot;Predicting Air Compressor Failures with Echo State Networks.&quot; Third European Conference of the Prognostics and Health Management Society 2016, Bilbao, Spain, 5-8 July, 2016. PHM Society, 2016.</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Representation_Learning_for_Deviation_Detection&diff=3284 2016-10-25T22:21:32Z

<p>Yuafan: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Optimise Echo State Networks for time series forecasting and reconstruction. Propose methods, e.g. objective functions, to train Echo State Networks for deviation detection<br /> |Keywords=Representation learning, Deviation detection, Echo State Network, Optimization, Differential evolution<br /> |TimeFrame=Winter 2016 / Spring 2017<br /> |References=[1] Bengio, Yoshua, Aaron Courville, and Pascal Vincent. &quot;Representation learning: A review and new perspectives.&quot; IEEE transactions on pattern analysis and machine intelligence 35.8 (2013): 1798-1828.<br /> <br /> [2] Jaeger, Herbert. Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the&quot; echo state network&quot; approach. GMD-Forschungszentrum Informationstechnik, 2002.<br /> <br /> [3] Jaeger, Herbert, et al. &quot;Optimization and applications of echo state networks with leaky-integrator neurons.&quot; Neural networks 20.3 (2007): 335-352.<br /> <br /> [4] Lukoševičius, Mantas. &quot;A practical guide to applying echo state networks.&quot; Neural networks: Tricks of the trade. Springer Berlin Heidelberg, 2012. 659-686.<br /> <br /> [5] Wang, Lin, Zhigang Wang, and Shan Liu. &quot;An effective multivariate time series classification approach using echo state network and adaptive differential evolution algorithm.&quot; Expert Systems with Applications 43 (2016): 237-249.<br /> |Prerequisites=Artificial Intelligence and Learning Systems courses; good knowledge of machine learning and neural networks; programming skills for implementing machine learning algorithms<br /> |Supervisor=Sławomir Nowaczyk, Yuantao Fan<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> Echo State Network (ESN) is a special class of recurrent neural networks that can be used for supervised learning, e.g. time series forecasting, pattern recognition and deviation detection. The main idea of ESN is to drive a large random, fixed neural network that induce input signal into each neurons. The nonlinear responses of all neurons are combined by a trainable linear combination to a desired output. The network captures temporal features of time series data. Compared to other recurrent neural networks, it can be trained much faster. ESN are characterized by a number of parameters (e.g. network architecture, spectral radius, type of neurons and input scaling etc.). In order to achieve desired performance, these parameters need to be optimized and, preferably, in an efficient way.<br /> <br /> There are many applications [0,1,2] ESN can be applied to. ESN can be used for general learning tasks, e.g. time series forecasting, or as representation of the data. In [3,4] ESN is employed to classify time series for fault detection. Similarly, in [6], air pressure signals are encoded into ESNs and anomalies are detected using an unsupervised deviation detection method, called Consensus Self-Organizing Models (COSMO) method. One key feature of COSMO method is the ability to capture and encode characteristics of the signals by using different representations. Generic representation that can be adapted to different type of signals and captures various characteristics is preferred for anomaly detection. Paper [6] demonstrated that ESNs are promising for this purpose. How to optimize the parameters of ESNs for deviation detection can be further investigated. <br /> <br /> Objectives:<br /> 1. Propose a framework to optimize Echo State Networks for forecasting and reconstructing time series.<br /> 2. Use ESNs as self-organizing data representation (can be trained without external supervision) for unsupervised deviation detection. Determine what are the criteria for ESNs to learn interesting characteristics of the time series for deviation detection. Note that, for example, minimizing the reconstruction error does not necessary to be the objective function when train ESNs, but rather how ESNs can be trained to generalize various properties that characterize the observed system.<br /> 3. Perform deviation detection (e.g. COSMO method) on both synthetic data and data from real world application based on Echo State Networks and other data representations. Compare and analyze the performance.<br /> <br /> <br /> <br /> References:<br /> <br /> [1] Li, Decai, Min Han, and Jun Wang. &quot;Chaotic time series prediction based on a novel robust echo state network.&quot; IEEE Transactions on Neural Networks and Learning Systems 23.5 (2012): 787-799.<br /> <br /> [2] Krause13, André Frank, et al. &quot;Evolutionary Optimization of Echo State Networks: multiple motor pattern learning.&quot; (2010).<br /> <br /> [3] Marco Rigamonti et al., &quot;Echo State Network for the Remaining Useful Life Prediction of a Turbofan Engine.&quot; Third European Conference of the Prognostics and Health Management Society 2016, Bilbao, Spain, 5-8 July, 2016. PHM Society, 2016.<br /> <br /> [4] Chen, Huanhuan, Peter Tiňo, and Xin Yao. &quot;Cognitive fault diagnosis in Tennessee Eastman Process using learning in the model space.&quot; Computers &amp; Chemical Engineering 67 (2014): 33-42.<br /> <br /> [5] Quevedo, Joseba, et al. &quot;Combining learning in model space fault diagnosis with data validation/reconstruction: Application to the Barcelona water network.&quot; Engineering Applications of Artificial Intelligence 30 (2014): 18-29.<br /> <br /> [6] Fan, Yuantao, et al. &quot;Predicting Air Compressor Failures with Echo State Networks.&quot; Third European Conference of the Prognostics and Health Management Society 2016, Bilbao, Spain, 5-8 July, 2016. PHM Society, 2016.</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Representation_Learning_for_Deviation_Detection&diff=3283 2016-10-25T22:21:05Z

<p>Yuafan: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Optimise Echo State Networks for time series forecasting and reconstruction. Propose methods, e.g. objective functions, to train Echo State Networks for deviation detection<br /> |Keywords=Representation learning, Deviation detection, Echo State Network, Optimization, Differential evolution<br /> |TimeFrame=Winter 2016 / Spring 2017<br /> |References=[1] Bengio, Yoshua, Aaron Courville, and Pascal Vincent. &quot;Representation learning: A review and new perspectives.&quot; IEEE transactions on pattern analysis and machine intelligence 35.8 (2013): 1798-1828.<br /> <br /> [2] Jaeger, Herbert. Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the&quot; echo state network&quot; approach. GMD-Forschungszentrum Informationstechnik, 2002.<br /> <br /> [3] Jaeger, Herbert, et al. &quot;Optimization and applications of echo state networks with leaky-integrator neurons.&quot; Neural networks 20.3 (2007): 335-352.<br /> <br /> [4] Lukoševičius, Mantas. &quot;A practical guide to applying echo state networks.&quot; Neural networks: Tricks of the trade. Springer Berlin Heidelberg, 2012. 659-686.<br /> <br /> [5] Wang, Lin, Zhigang Wang, and Shan Liu. &quot;An effective multivariate time series classification approach using echo state network and adaptive differential evolution algorithm.&quot; Expert Systems with Applications 43 (2016): 237-249.<br /> |Prerequisites=Artificial Intelligence and Learning Systems courses; good knowledge of machine learning and neural networks; programming skills for implementing machine learning algorithms<br /> |Supervisor=Sławomir Nowaczyk, Yuantao Fan<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> Echo State Network (ESN) is a special class of recurrent neural networks that can be used for supervised learning, e.g. time series forecasting, pattern recognition and deviation detection. The main idea of ESN is to drive a large random, fixed neural network that induce input signal into each neurons. The nonlinear responses of all neurons are combined by a trainable linear combination to a desired output. The network captures temporal features of time series data. Compared to other recurrent neural networks, it can be trained much faster. ESN are characterized by a number of parameters (e.g. network architecture, spectral radius, type of neurons and input scaling etc.). In order to achieve desired performance, these parameters need to be optimized and, preferably, in an efficient way.<br /> <br /> There are many applications [0,1,2] ESN can be applied to. ESN can be used for general learning tasks, e.g. time series forecasting, or as representation of the data. In [3,4] ESN is employed to classify time series for fault detection. Similarly, in [6], air pressure signals are encoded into ESNs and anomalies are detected using an unsupervised deviation detection method, called Consensus Self-Organizing Models (COSMO) method. One key feature of COSMO method is the ability to capture and encode characteristics of the signals by using different representations. Generic representation that can be adapted to different type of signals and captures various characteristics is preferred for anomaly detection. Paper [6] demonstrated that ESNs are promising for this purpose. How to optimize the parameters of ESNs for deviation detection can be further investigated. <br /> <br /> Objectives:<br /> 1. Propose a framework to optimize Echo State Networks for forecasting and reconstructing time series.<br /> 2. Use ESNs as self-organizing data representation (can be trained without external supervision) for unsupervised deviation detection. Determine what are the criteria for ESNs to learn interesting characteristics of the time series for deviation detection. Note that, for example, minimizing the reconstruction error does not necessary to be the objective function when train ESNs, but rather how ESNs can be trained to generalize various properties that characterize the observed system.<br /> 3. Perform deviation detection (e.g. COSMO method) on both synthetic data and data from real world application based on Echo State Networks and other data representations. Compare and analyze the performance.<br /> <br /> References:<br /> <br /> [1] Li, Decai, Min Han, and Jun Wang. &quot;Chaotic time series prediction based on a novel robust echo state network.&quot; IEEE Transactions on Neural Networks and Learning Systems 23.5 (2012): 787-799.<br /> <br /> [2] Krause13, André Frank, et al. &quot;Evolutionary Optimization of Echo State Networks: multiple motor pattern learning.&quot; (2010).<br /> <br /> [3] Marco Rigamonti et al., &quot;Echo State Network for the Remaining Useful Life Prediction of a Turbofan Engine.&quot; Third European Conference of the Prognostics and Health Management Society 2016, Bilbao, Spain, 5-8 July, 2016. PHM Society, 2016.<br /> <br /> [4] Chen, Huanhuan, Peter Tiňo, and Xin Yao. &quot;Cognitive fault diagnosis in Tennessee Eastman Process using learning in the model space.&quot; Computers &amp; Chemical Engineering 67 (2014): 33-42.<br /> <br /> [5] Quevedo, Joseba, et al. &quot;Combining learning in model space fault diagnosis with data validation/reconstruction: Application to the Barcelona water network.&quot; Engineering Applications of Artificial Intelligence 30 (2014): 18-29.<br /> <br /> [6] Fan, Yuantao, et al. &quot;Predicting Air Compressor Failures with Echo State Networks.&quot; Third European Conference of the Prognostics and Health Management Society 2016, Bilbao, Spain, 5-8 July, 2016. PHM Society, 2016.</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Representation_Learning_for_Deviation_Detection&diff=3282 2016-10-25T22:20:26Z

<p>Yuafan: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Optimise Echo State Networks for time series forecasting and reconstruction. Propose methods, e.g. objective functions, to train Echo State Networks for deviation detection<br /> |Keywords=Representation learning, Deviation detection, Echo State Network, Optimization, Differential evolution<br /> |TimeFrame=Winter 2016 / Spring 2017<br /> |References=[1] Bengio, Yoshua, Aaron Courville, and Pascal Vincent. &quot;Representation learning: A review and new perspectives.&quot; IEEE transactions on pattern analysis and machine intelligence 35.8 (2013): 1798-1828.<br /> <br /> [2] Jaeger, Herbert. Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the&quot; echo state network&quot; approach. GMD-Forschungszentrum Informationstechnik, 2002.<br /> <br /> [3] Jaeger, Herbert, et al. &quot;Optimization and applications of echo state networks with leaky-integrator neurons.&quot; Neural networks 20.3 (2007): 335-352.<br /> <br /> [4] Lukoševičius, Mantas. &quot;A practical guide to applying echo state networks.&quot; Neural networks: Tricks of the trade. Springer Berlin Heidelberg, 2012. 659-686.<br /> <br /> [5] Wang, Lin, Zhigang Wang, and Shan Liu. &quot;An effective multivariate time series classification approach using echo state network and adaptive differential evolution algorithm.&quot; Expert Systems with Applications 43 (2016): 237-249.<br /> |Prerequisites=Artificial Intelligence and Learning Systems courses; good knowledge of machine learning and neural networks; programming skills for implementing machine learning algorithms<br /> |Supervisor=Sławomir Nowaczyk, Yuantao Fan<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> Echo State Network (ESN) is a special class of recurrent neural networks that can be used for supervised learning, e.g. time series forecasting, pattern recognition and deviation detection. The main idea of ESN is to drive a large random, fixed neural network that induce input signal into each neurons. The nonlinear responses of all neurons are combined by a trainable linear combination to a desired output. The network captures temporal features of time series data. Compared to other recurrent neural networks, it can be trained much faster. ESN are characterized by a number of parameters (e.g. network architecture, spectral radius, type of neurons and input scaling etc.). In order to achieve desired performance, these parameters need to be optimized and, preferably, in an efficient way.<br /> <br /> There are many applications [0,1,2] ESN can be applied to. ESN can be used for general learning tasks, e.g. time series forecasting, or as representation of the data. In [3,4] ESN is employed to classify time series for fault detection. Similarly, in [6], air pressure signals are encoded into ESNs and anomalies are detected using an unsupervised deviation detection method, called Consensus Self-Organizing Models (COSMO) method. One key feature of COSMO method is the ability to capture and encode characteristics of the signals by using different representations. Generic representation that can be adapted to different type of signals and captures various characteristics is preferred for anomaly detection. Paper [6] demonstrated that ESNs are promising for this purpose. How to optimize the parameters of ESNs for deviation detection can be further investigated. <br /> <br /> Objectives:<br /> 1. Propose a framework to optimize Echo State Networks for forecasting and reconstructing time series.<br /> 2. Use ESNs as self-organizing data representation (can be trained without external supervision) for unsupervised deviation detection. Determine what are the criteria for ESNs to learn interesting characteristics of the time series for deviation detection. Note that, for example, minimizing the reconstruction error does not necessary to be the objective function when train ESNs, but rather how ESNs can be trained to generalize various properties that characterize the observed system.<br /> 3. Perform deviation detection (e.g. COSMO method) on both synthetic data and data from real world application based on Echo State Networks and other data representations. Compare and analyze the performance.<br /> <br /> References:<br /> <br /> [1] Li, Decai, Min Han, and Jun Wang. &quot;Chaotic time series prediction based on a novel robust echo state network.&quot; IEEE Transactions on Neural Networks and Learning Systems 23.5 (2012): 787-799.<br /> [2] Krause13, André Frank, et al. &quot;Evolutionary Optimization of Echo State Networks: multiple motor pattern learning.&quot; (2010).<br /> [3] Marco Rigamonti et al., &quot;Echo State Network for the Remaining Useful Life Prediction of a Turbofan Engine.&quot; Third European Conference of the Prognostics and Health Management Society 2016, Bilbao, Spain, 5-8 July, 2016. PHM Society, 2016.<br /> [4] Chen, Huanhuan, Peter Tiňo, and Xin Yao. &quot;Cognitive fault diagnosis in Tennessee Eastman Process using learning in the model space.&quot; Computers &amp; Chemical Engineering 67 (2014): 33-42.<br /> [5] Quevedo, Joseba, et al. &quot;Combining learning in model space fault diagnosis with data validation/reconstruction: Application to the Barcelona water network.&quot; Engineering Applications of Artificial Intelligence 30 (2014): 18-29.<br /> [6] Fan, Yuantao, et al. &quot;Predicting Air Compressor Failures with Echo State Networks.&quot; Third European Conference of the Prognostics and Health Management Society 2016, Bilbao, Spain, 5-8 July, 2016. PHM Society, 2016.</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Representation_Learning_for_Deviation_Detection&diff=3281 2016-10-25T22:19:11Z

<p>Yuafan: Created page with &quot;{{StudentProjectTemplate |Summary=Optimise Echo State Networks for time series forecasting and reconstruction. Propose methods, e.g. objective functions, to train Echo State N...&quot;</p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Optimise Echo State Networks for time series forecasting and reconstruction. Propose methods, e.g. objective functions, to train Echo State Networks for deviation detection<br /> |Keywords=Representation learning, Deviation detection, Echo State Network, Optimization, Differential evolution<br /> |TimeFrame=Winter 2016 / Spring 2017<br /> |References=[1] Bengio, Yoshua, Aaron Courville, and Pascal Vincent. &quot;Representation learning: A review and new perspectives.&quot; IEEE transactions on pattern analysis and machine intelligence 35.8 (2013): 1798-1828.<br /> <br /> [2] Jaeger, Herbert. Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the&quot; echo state network&quot; approach. GMD-Forschungszentrum Informationstechnik, 2002.<br /> <br /> [3] Jaeger, Herbert, et al. &quot;Optimization and applications of echo state networks with leaky-integrator neurons.&quot; Neural networks 20.3 (2007): 335-352.<br /> <br /> [4] Lukoševičius, Mantas. &quot;A practical guide to applying echo state networks.&quot; Neural networks: Tricks of the trade. Springer Berlin Heidelberg, 2012. 659-686.<br /> <br /> [5] Wang, Lin, Zhigang Wang, and Shan Liu. &quot;An effective multivariate time series classification approach using echo state network and adaptive differential evolution algorithm.&quot; Expert Systems with Applications 43 (2016): 237-249.<br /> |Prerequisites=Artificial Intelligence and Learning Systems courses; good knowledge of machine learning and neural networks; programming skills for implementing machine learning algorithms<br /> |Supervisor=Sławomir Nowaczyk, Yuantao Fan<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> Echo State Network (ESN) is a special class of recurrent neural networks that can be used for supervised learning, e.g. time series forecasting, pattern recognition and deviation detection. The main idea of ESN is to drive a large random, fixed neural network that induce input signal into each neurons. The nonlinear responses of all neurons are combined by a trainable linear combination to a desired output. The network captures temporal features of time series data. Compared to other recurrent neural networks, it can be trained much faster. ESN are characterized by a number of parameters (e.g. network architecture, spectral radius, type of neurons and input scaling etc.). In order to achieve desired performance, these parameters need to be optimized and, preferably, in an efficient way.<br /> <br /> There are many applications [0,1,2] ESN can be applied to. ESN can be used for general learning tasks, e.g. time series forecasting, or as representation of the data. In [3,4] ESN is employed to classify time series for fault detection. Similarly, in [6], air pressure signals are encoded into ESNs and anomalies are detected using an unsupervised deviation detection method, called Consensus Self-Organizing Models (COSMO) method. One key feature of COSMO method is the ability to capture and encode characteristics of the signals by using different representations. Generic representation that can be adapted to different type of signals and captures various characteristics is preferred for anomaly detection. Paper [6] demonstrated that ESNs are promising for this purpose. How to optimize the parameters of ESNs for deviation detection can be further investigated. <br /> <br /> Objectives:<br /> 1. Propose a framework to optimize Echo State Networks for forecasting and reconstructing time series.<br /> 2. Use ESNs as self-organizing data representation (can be trained without external supervision) for unsupervised deviation detection. Determine what are the criteria for ESNs to learn interesting characteristics of the time series for deviation detection. Note that, for example, minimizing the reconstruction error does not necessary to be the objective function when train ESNs, but rather how ESNs can be trained to generalize various properties that characterize the observed system.<br /> 3. Perform deviation detection (e.g. COSMO method) on both synthetic data and data from real world application based on Echo State Networks and other data representations. Compare and analyze the performance.</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Vehicle_Operation_Classification&diff=3280 2016-10-25T20:17:08Z

<p>Yuafan: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Classify modes of operation of Volvo vehicles based on on-board data<br /> |Keywords=Data Mining, Machine Learning, Ubiquitous Knowledge Discovery<br /> |TimeFrame=Winter 2016 / Spring 2017<br /> |References=Time series classification<br /> <br /> Unsupervised and semi-supervised clustering<br /> <br /> ...<br /> |Prerequisites=Cooperating Intelligent Systems and Learning Systems courses<br /> |Supervisor=Sławomir Nowaczyk, Yuantao Fan<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> <br /> With 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 sensor data streaming from devices (on large scale), discover interesting patterns and knowledge.<br /> <br /> In the ReDi2Service project we have collected approximately 1TB of data from Volvo buses in normal operation. It is interesting to analyse this data from the usage point of view, and come up with good description and/or classification (possibly hierarchical or even an ontology) of vehicle operation. <br /> <br /> The data contains both GPS positions, as well as on-board signals such as vehicle speed or engine torque. The goal of the project is to provide a framework for organising the data in a way that will facilitate future access to interesting portions of this data according to multiple criteria.<br /> <br /> We are interested in both low-level information (for example, detecting workshop visits, splitting the data into trips from turning the engine on to turning it off, distinguishing between highway and in-city operation, or finding uphill and downhill driving) as well as in more abstract description (is the bus in regular line traffic or performing some other duty, automatically finding similarities and differences between missions, etc).<br /> <br /> More details to come...</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Vehicle_Operation_Classification&diff=3279 2016-10-25T20:16:04Z

<p>Yuafan: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Classify modes of operation of Volvo vehicles based on on-board data<br /> |Keywords=Data Mining<br /> |TimeFrame=Winter 2016 / Spring 2017<br /> |References=Time series classification<br /> <br /> Unsupervised and semi-supervised clustering<br /> <br /> ...<br /> |Prerequisites=Cooperating Intelligent Systems and Learning Systems courses<br /> |Supervisor=Sławomir Nowaczyk, Yuantao Fan<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> <br /> With 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 sensor data streaming from devices (on large scale), discover interesting patterns and knowledge.<br /> <br /> In the ReDi2Service project we have collected approximately 500GB of data from Volvo buses in normal operation. It is interesting to analyse this data from the usage point of view, and come up with good description and/or classification (possibly hierarchical or even an ontology) of vehicle operation. <br /> <br /> The data contains both GPS positions, as well as on-board signals such as vehicle speed or engine torque. The goal of the project is to provide a framework for organising the data in a way that will facilitate future access to interesting portions of this data according to multiple criteria.<br /> <br /> We are interested in both low-level information (for example, detecting workshop visits, splitting the data into trips from turning the engine on to turning it off, distinguishing between highway and in-city operation, or finding uphill and downhill driving) as well as in more abstract description (is the bus in regular line traffic or performing some other duty, automatically finding similarities and differences between missions, etc).<br /> <br /> More details to come...</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Vehicle_Operation_Classification&diff=3278 2016-10-25T19:29:58Z

<p>Yuafan: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Classify modes of operation of Volvo vehicles based on on-board data<br /> |Keywords=Data Mining<br /> |TimeFrame=Spring 2016<br /> |References=Time series classification<br /> <br /> Unsupervised and semi-supervised clustering<br /> <br /> ...<br /> |Prerequisites=Cooperating Intelligent Systems and Learning Systems courses<br /> |Supervisor=Sławomir Nowaczyk, Yuantao Fan<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> <br /> With 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 sensor data streaming from devices (on large scale), discover interesting patterns and knowledge.<br /> <br /> In the ReDi2Service project we have collected approximately 500GB of data from Volvo buses in normal operation. It is interesting to analyse this data from the usage point of view, and come up with good description and/or classification (possibly hierarchical or even an ontology) of vehicle operation. <br /> <br /> The data contains both GPS positions, as well as on-board signals such as vehicle speed or engine torque. The goal of the project is to provide a framework for organising the data in a way that will facilitate future access to interesting portions of this data according to multiple criteria.<br /> <br /> We are interested in both low-level information (for example, detecting workshop visits, splitting the data into trips from turning the engine on to turning it off, distinguishing between highway and in-city operation, or finding uphill and downhill driving) as well as in more abstract description (is the bus in regular line traffic or performing some other duty, automatically finding similarities and differences between missions, etc).<br /> <br /> More details to come...</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Vehicle_Operation_Classification&diff=3277 2016-10-25T19:28:45Z

<p>Yuafan: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Classify modes of operation of Volvo vehicles based on on-board data<br /> |Keywords=Data Mining<br /> |TimeFrame=Spring 2016<br /> |References=Time series classification<br /> <br /> Unsupervised and semi-supervised clustering<br /> <br /> ...<br /> |Prerequisites=Cooperating Intelligent Systems and Learning Systems courses<br /> |Supervisor=Sławomir Nowaczyk, Yuantao Fan<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> <br /> With 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 sensor data streaming from devices (on a large scale), discover interesting patterns and knowledge.<br /> <br /> In the ReDi2Service project we have collected approximately 500GB of data from Volvo buses in normal operation. It is interesting to analyse this data from the usage point of view, and come up with good description and/or classification (possibly hierarchical or even an ontology) of vehicle operation. <br /> <br /> The data contains both GPS positions, as well as on-board signals such as vehicle speed or engine torque. The goal of the project is to provide a framework for organising the data in a way that will facilitate future access to interesting portions of this data according to multiple criteria.<br /> <br /> We are interested in both low-level information (for example, detecting workshop visits, splitting the data into trips from turning the engine on to turning it off, distinguishing between highway and in-city operation, or finding uphill and downhill driving) as well as in more abstract description (is the bus in regular line traffic or performing some other duty, automatically finding similarities and differences between missions, etc).<br /> <br /> More details to come...</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Vehicle_Operation_Classification&diff=3272 2016-10-25T15:48:38Z

<p>Yuafan: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=Classify modes of operation of Volvo vehicles based on on-board data<br /> |Keywords=Data Mining<br /> |TimeFrame=Spring 2016<br /> |References=Time series classification<br /> <br /> Unsupervised and semi-supervised clustering<br /> <br /> ...<br /> |Prerequisites=Cooperating Intelligent Systems and Learning Systems courses<br /> |Supervisor=Sławomir Nowaczyk, Yuantao Fan<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> In the ReDi2Service project we have collected approximately 500GB of data from Volvo buses in normal operation. It is interesting to analyse this data from the usage point of view, and come up with good description and/or classification (possibly hierarchical or even an ontology) of vehicle operation. <br /> <br /> The data contains both GPS positions, as well as on-board signals such as vehicle speed or engine torque. The goal of the project is to provide a framework for organising the data in a way that will facilitate future access to interesting portions of this data according to multiple criteria.<br /> <br /> We are interested in both low-level information (for example, detecting workshop visits, splitting the data into trips from turning the engine on to turning it off, distinguishing between highway and in-city operation, or finding uphill and downhill driving) as well as in more abstract description (is the bus in regular line traffic or performing some other duty, automatically finding similarities and differences between missions, etc).<br /> <br /> More details to come...</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Yuantao_Fan&diff=2256 2015-09-14T09:17:12Z

<p>Yuafan: </p> <hr /> <div>{{Person<br /> |Family Name=Fan<br /> |Given Name=Yuantao<br /> |Title=M.Sc.<br /> |Position=PhD. Candidate<br /> |Email=yuantao.fan@hh.se<br /> |Image=Yuantao_Fan_img2.jpg<br /> |Office=E513<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignProjects}}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Vehicle Diagnostics<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<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>

Yuafan https://mw.hh.se/caisr/index.php?title=RaspberryPiVolvoLogger&diff=1997 2015-01-22T14:36:36Z

<p>Yuafan: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=RaspberryPi-based solution for logging CAN data on Volvo trucks<br /> |Programme=Embedded and Intelligent Systems, 120 ECTS<br /> |Keywords=GNU/Linux, CAN interface, Data Mining, Knowledge Representation<br /> |TimeFrame=Spring 2015<br /> |References=http://www.raspberrypi.org/<br /> <br /> http://lnxpps.de/rpie/<br /> <br /> http://islab.hh.se/mediawiki/index.php/ReDi2Service<br /> <br /> http://www.youtube.com/watch?v=KJ5hMkWPEGY<br /> |Prerequisites=Basic Linux knowledge, programming competence, possibly electronics experience,<br /> Cooperating Intelligent Systems or equivalent basic Artificial Intelligence course<br /> |Supervisor=Slawomir Nowaczyk, Yuantao Fan<br /> |Examiner=Antanas Verikas<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> In the ReDi2Service project we are working together with Volvo Technology in Göteborg on collecting on-board data from a fleet of buses and comparing individual vehicles against rest of the group to detect faults and component wear. In that project we are using a specialized hardware and software solution, but we are interested in exploring possibilities of using products such as Raspberry Pi http://www.raspberrypi.org/ in order to lower the costs and increase the flexibility. <br /> <br /> The purpose of the project is to implement a flexible data logging system and use it to log data transmitted through the CAN interface. Supervised and unsupervised techniques will be used to compress the data, to investigate the relations between the sensors and to identify deviations from normal operation. The system will consist of three separate components. A service for data collection, a process performing analysis on the data and a User Interface. <br /> All the data will be stored in PostgreSQL DBMS and the data aggregation and compression models will be performed within the database. The system will be implemented for GNU/Linux. The hardware will be based on Raspberry Pi, but with no dependencies from it.<br /> <br /> The service will collect the data from the CAN interface and according to some rules store them in the database. The rules will include models for the expected values of the sensors, sensors to monitor, compression methods and sensor limits. If a reading from the CAN does not agree with the model the service transmits an alert to the interface or to the network and keeps a record of the deviation. <br /> <br /> The data analysis component will be a process with input from the SQL database and output to the configuration files of the service. The origin and nature of the data will not be taken into account on this part, to keep this tool reusable in other domains. Supervised and unsupervised learning will be used to generate data compression models, to find relations between different sensors, to find visualizations that could depict the variation of the operation of the vehicle and finally to create predictive models and rules about the values of the sensors. The generated rules of compression or prediction will then be used from the service to log only deviations from the model. For the purposes of model creation and data reduction, the techniques that will be tested include Principal component analysis (instance data), neural Autoencoder(instance data), histograms(time series data) and Discrete Fourier Transform (time series data). For the clustering of the modes of operation the algorithms that will be tested include k-means, hierarchical cluster analysis and OPTICS.<br /> <br /> The Graphical User Interface will allow customization of the conditions under which the data should be logged, setting rules that will trigger an alert, monitor real time data from the sensors and provide visualizations to the user, constructed either from the data analysis process, or defined by the user. The user feedback on an alert could be possibly used to improve the rules that define normal operation.</div>

Yuafan https://mw.hh.se/caisr/index.php?title=RaspberryPiVolvoLogger&diff=1996 2015-01-22T14:36:23Z

<p>Yuafan: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=RaspberryPi-based solution for logging CAN data on Volvo trucks<br /> |Programme=Embedded and Intelligent Systems, 120 ECTS<br /> |Keywords=GNU/Linux, CAN interface, Data Mining, Knowledge Representation<br /> |TimeFrame=Spring 2015<br /> |References=http://www.raspberrypi.org/<br /> <br /> http://lnxpps.de/rpie/<br /> <br /> http://islab.hh.se/mediawiki/index.php/ReDi2Service<br /> <br /> http://www.youtube.com/watch?v=KJ5hMkWPEGY<br /> |Prerequisites=Basic Linux knowledge, programming competence, possibly electronics experience,<br /> Cooperating Intelligent Systems or equivalent basic Artificial Intelligence course<br /> |Supervisor=Slawomir Nowaczyk, Yuantao Fan,<br /> |Examiner=Antanas Verikas<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> In the ReDi2Service project we are working together with Volvo Technology in Göteborg on collecting on-board data from a fleet of buses and comparing individual vehicles against rest of the group to detect faults and component wear. In that project we are using a specialized hardware and software solution, but we are interested in exploring possibilities of using products such as Raspberry Pi http://www.raspberrypi.org/ in order to lower the costs and increase the flexibility. <br /> <br /> The purpose of the project is to implement a flexible data logging system and use it to log data transmitted through the CAN interface. Supervised and unsupervised techniques will be used to compress the data, to investigate the relations between the sensors and to identify deviations from normal operation. The system will consist of three separate components. A service for data collection, a process performing analysis on the data and a User Interface. <br /> All the data will be stored in PostgreSQL DBMS and the data aggregation and compression models will be performed within the database. The system will be implemented for GNU/Linux. The hardware will be based on Raspberry Pi, but with no dependencies from it.<br /> <br /> The service will collect the data from the CAN interface and according to some rules store them in the database. The rules will include models for the expected values of the sensors, sensors to monitor, compression methods and sensor limits. If a reading from the CAN does not agree with the model the service transmits an alert to the interface or to the network and keeps a record of the deviation. <br /> <br /> The data analysis component will be a process with input from the SQL database and output to the configuration files of the service. The origin and nature of the data will not be taken into account on this part, to keep this tool reusable in other domains. Supervised and unsupervised learning will be used to generate data compression models, to find relations between different sensors, to find visualizations that could depict the variation of the operation of the vehicle and finally to create predictive models and rules about the values of the sensors. The generated rules of compression or prediction will then be used from the service to log only deviations from the model. For the purposes of model creation and data reduction, the techniques that will be tested include Principal component analysis (instance data), neural Autoencoder(instance data), histograms(time series data) and Discrete Fourier Transform (time series data). For the clustering of the modes of operation the algorithms that will be tested include k-means, hierarchical cluster analysis and OPTICS.<br /> <br /> The Graphical User Interface will allow customization of the conditions under which the data should be logged, setting rules that will trigger an alert, monitor real time data from the sensors and provide visualizations to the user, constructed either from the data analysis process, or defined by the user. The user feedback on an alert could be possibly used to improve the rules that define normal operation.</div>

Yuafan https://mw.hh.se/caisr/index.php?title=RaspberryPiVolvoLogger&diff=1995 2015-01-22T14:25:06Z

<p>Yuafan: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=RaspberryPi-based solution for logging CAN data on Volvo trucks<br /> |Programme=Embedded and Intelligent Systems, 120 ECTS<br /> |Keywords=GNU/Linux, CAN interface, Data Mining, Knowledge Representation<br /> |TimeFrame=Spring 2015<br /> |References=http://www.raspberrypi.org/<br /> <br /> http://lnxpps.de/rpie/<br /> <br /> http://islab.hh.se/mediawiki/index.php/ReDi2Service<br /> <br /> http://www.youtube.com/watch?v=KJ5hMkWPEGY<br /> |Prerequisites=Basic Linux knowledge, programming competence, possibly electronics experience,<br /> Cooperating Intelligent Systems or equivalent basic Artificial Intelligence course<br /> |Supervisor=Slawomir Nowaczyk, Rune Prytz, Yuantao Fan,<br /> |Examiner=Antanas Verikas<br /> |Level=Master<br /> |Status=Open<br /> }}<br /> In the ReDi2Service project we are working together with Volvo Technology in Göteborg on collecting on-board data from a fleet of buses and comparing individual vehicles against rest of the group to detect faults and component wear. In that project we are using a specialized hardware and software solution, but we are interested in exploring possibilities of using products such as Raspberry Pi http://www.raspberrypi.org/ in order to lower the costs and increase the flexibility. <br /> <br /> The purpose of the project is to implement a flexible data logging system and use it to log data transmitted through the CAN interface. Supervised and unsupervised techniques will be used to compress the data, to investigate the relations between the sensors and to identify deviations from normal operation. The system will consist of three separate components. A service for data collection, a process performing analysis on the data and a User Interface. <br /> All the data will be stored in PostgreSQL DBMS and the data aggregation and compression models will be performed within the database. The system will be implemented for GNU/Linux. The hardware will be based on Raspberry Pi, but with no dependencies from it.<br /> <br /> The service will collect the data from the CAN interface and according to some rules store them in the database. The rules will include models for the expected values of the sensors, sensors to monitor, compression methods and sensor limits. If a reading from the CAN does not agree with the model the service transmits an alert to the interface or to the network and keeps a record of the deviation. <br /> <br /> The data analysis component will be a process with input from the SQL database and output to the configuration files of the service. The origin and nature of the data will not be taken into account on this part, to keep this tool reusable in other domains. Supervised and unsupervised learning will be used to generate data compression models, to find relations between different sensors, to find visualizations that could depict the variation of the operation of the vehicle and finally to create predictive models and rules about the values of the sensors. The generated rules of compression or prediction will then be used from the service to log only deviations from the model. For the purposes of model creation and data reduction, the techniques that will be tested include Principal component analysis (instance data), neural Autoencoder(instance data), histograms(time series data) and Discrete Fourier Transform (time series data). For the clustering of the modes of operation the algorithms that will be tested include k-means, hierarchical cluster analysis and OPTICS.<br /> <br /> The Graphical User Interface will allow customization of the conditions under which the data should be logged, setting rules that will trigger an alert, monitor real time data from the sensors and provide visualizations to the user, constructed either from the data analysis process, or defined by the user. The user feedback on an alert could be possibly used to improve the rules that define normal operation.</div>

Yuafan https://mw.hh.se/caisr/index.php?title=RaspberryPiVolvoLogger&diff=1994 2015-01-22T14:21:13Z

<p>Yuafan: </p> <hr /> <div>{{StudentProjectTemplate<br /> |Summary=RaspberryPi-based solution for logging CAN data on Volvo trucks<br /> |Keywords=GNU/Linux, CAN interface, Data Mining, Knowledge Representation<br /> |TimeFrame=Spring 2015<br /> |References=http://www.raspberrypi.org/<br /> <br /> http://lnxpps.de/rpie/<br /> <br /> http://islab.hh.se/mediawiki/index.php/ReDi2Service<br /> <br /> http://www.youtube.com/watch?v=KJ5hMkWPEGY<br /> |Prerequisites=Basic Linux knowledge, programming competence, possibly electronics experience,<br /> Cooperating Intelligent Systems or equivalent basic Artificial Intelligence course<br /> |Supervisor=Slawomir Nowaczyk, Rune Prytz, Yuantao Fan, <br /> |Level=Master<br /> |Status=Open<br /> }}<br /> In the ReDi2Service project we are working together with Volvo Technology in Göteborg on collecting on-board data from a fleet of buses and comparing individual vehicles against rest of the group to detect faults and component wear. In that project we are using a specialized hardware and software solution, but we are interested in exploring possibilities of using products such as Raspberry Pi http://www.raspberrypi.org/ in order to lower the costs and increase the flexibility. <br /> <br /> The purpose of the project is to implement a flexible data logging system and use it to log data transmitted through the CAN interface. Supervised and unsupervised techniques will be used to compress the data, to investigate the relations between the sensors and to identify deviations from normal operation. The system will consist of three separate components. A service for data collection, a process performing analysis on the data and a User Interface. <br /> All the data will be stored in PostgreSQL DBMS and the data aggregation and compression models will be performed within the database. The system will be implemented for GNU/Linux. The hardware will be based on Raspberry Pi, but with no dependencies from it.<br /> <br /> The service will collect the data from the CAN interface and according to some rules store them in the database. The rules will include models for the expected values of the sensors, sensors to monitor, compression methods and sensor limits. If a reading from the CAN does not agree with the model the service transmits an alert to the interface or to the network and keeps a record of the deviation. <br /> <br /> The data analysis component will be a process with input from the SQL database and output to the configuration files of the service. The origin and nature of the data will not be taken into account on this part, to keep this tool reusable in other domains. Supervised and unsupervised learning will be used to generate data compression models, to find relations between different sensors, to find visualizations that could depict the variation of the operation of the vehicle and finally to create predictive models and rules about the values of the sensors. The generated rules of compression or prediction will then be used from the service to log only deviations from the model. For the purposes of model creation and data reduction, the techniques that will be tested include Principal component analysis (instance data), neural Autoencoder(instance data), histograms(time series data) and Discrete Fourier Transform (time series data). For the clustering of the modes of operation the algorithms that will be tested include k-means, hierarchical cluster analysis and OPTICS.<br /> <br /> The Graphical User Interface will allow customization of the conditions under which the data should be logged, setting rules that will trigger an alert, monitor real time data from the sensors and provide visualizations to the user, constructed either from the data analysis process, or defined by the user. The user feedback on an alert could be possibly used to improve the rules that define normal operation.</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Yuantao_Fan&diff=1787 2014-10-13T05:57:51Z

<p>Yuafan: </p> <hr /> <div>{{Person<br /> |Family Name=Fan<br /> |Given Name=Yuantao<br /> |Title=M.Sc.<br /> |Position=PhD. Candidate<br /> |Image=Head-unknown.jpg<br /> |Email=yuantao.fan@hh.se<br /> |Office=E513<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignProjects}}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Vehicle Diagnostics<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> <br /> [[Category:staff]]</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Yuantao_Fan&diff=1786 2014-10-06T04:00:04Z

<p>Yuafan: </p> <hr /> <div>{{Person<br /> |Family Name=Fan<br /> |Given Name=Yuantao<br /> |Title=M.Sc.<br /> |Position=PhD. Candidate<br /> |Email=yuantao.fan@hh.se<br /> |Office=E513<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignProjects}}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Vehicle Diagnostics<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> <br /> [[Category:staff]]</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Yuantao_Fan&diff=1785 2014-10-04T09:59:36Z

<p>Yuafan: </p> <hr /> <div>{{Person<br /> |Family Name=Fan<br /> |Given Name=Yuantao<br /> |Title=M.Sc.<br /> |Position=PhD. Candidate<br /> |Email=yuantao.fan@hh.se<br /> |Image=Yuantao_Fan_img.jpg<br /> |Office=E513<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignProjects}}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Vehicle Diagnostics<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> <br /> [[Category:staff]]</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Yuantao_Fan&diff=1784 2014-10-04T09:58:08Z

<p>Yuafan: </p> <hr /> <div>{{Person<br /> |Family Name=Fan<br /> |Given Name=Yuantao<br /> |Title=M.Sc.<br /> |Position=PhD. Candidate<br /> |Email=yuantao.fan@hh.se<br /> |Image=Yuantao Fan img.jpg<br /> |Office=E513<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignProjects}}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Vehicle Diagnostics<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> <br /> [[Category:staff]]</div>

Yuafan https://mw.hh.se/caisr/index.php?title=File:Yuantao_Fan_img.jpg&diff=1783 2014-10-04T09:56:35Z

<p>Yuafan: Yuafan uploaded a new version of &amp;quot;File:Yuantao Fan img.jpg&amp;quot;</p> <hr /> <div></div>

Yuafan https://mw.hh.se/caisr/index.php?title=Yuantao_Fan&diff=1782 2014-10-04T09:52:46Z

<p>Yuafan: </p> <hr /> <div>{{Person<br /> |Family Name=Fan<br /> |Given Name=Yuantao<br /> |Title=M.Sc.<br /> |Position=PhD. Candidate<br /> |Email=yuantao.fan@hh.se<br /> |Image=Yuantao_Fan_img.jpg<br /> |Office=E513<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignProjects}}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Vehicle Diagnostics<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> <br /> [[Category:staff]]</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Yuantao_Fan&diff=1781 2014-10-04T09:51:47Z

<p>Yuafan: </p> <hr /> <div>{{Person<br /> |Family Name=Fan<br /> |Given Name=Yuantao<br /> |Title=M.Sc.<br /> |Position=PhD. Candidate<br /> |Email=yuantao.fan@hh.se<br /> |Image=|Yuantao_Fan_img.jpg<br /> |Office=E513<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignProjects}}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Vehicle Diagnostics<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> <br /> [[Category:staff]]</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Yuantao_Fan&diff=1780 2014-10-04T09:50:34Z

<p>Yuafan: </p> <hr /> <div>{{Person<br /> |Family Name=Fan<br /> |Given Name=Yuantao<br /> |Title=M.Sc.<br /> |Position=PhD. Candidate<br /> |Email=yuantao.fan@hh.se<br /> |Image=Yuantao_Fan_Img.jpg<br /> |Office=E513<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignProjects}}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Vehicle Diagnostics<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> <br /> [[Category:staff]]</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Yuantao_Fan&diff=1779 2014-10-04T09:50:10Z

<p>Yuafan: </p> <hr /> <div>{{Person<br /> |Family Name=Fan<br /> |Given Name=Yuantao<br /> |Title=M.Sc.<br /> |Position=PhD. Candidate<br /> |Email=yuantao.fan@hh.se<br /> |Image=Yuantao_Fan_img.jpg<br /> |Office=E513<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignProjects}}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Vehicle Diagnostics<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> <br /> [[Category:staff]]</div>

Yuafan https://mw.hh.se/caisr/index.php?title=File:Yuantao_Fan_img.jpg&diff=1778 2014-10-04T09:49:00Z

<p>Yuafan: </p> <hr /> <div></div>

Yuafan https://mw.hh.se/caisr/index.php?title=File:In4UptimeInfo.pdf&diff=1615 2014-05-16T13:28:33Z

<p>Yuafan: </p> <hr /> <div></div>

Yuafan https://mw.hh.se/caisr/index.php?title=In4Uptime&diff=1614 2014-05-16T13:27:51Z

<p>Yuafan: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title= In4Uptime<br /> |ContactInformation=Sławomir Nowaczyk<br /> |ShortDescription= Vehicle diagnostics and predictive maintenance<br /> |Description=The goal of the project is to keep commercial vehicles in good operational condition, both from a financial and safety point of view. Haulers and transporters require OEMs to provide vehicles having close to 100% uptime. That means no stops, unless planned, as well as guarantees on optimal performance of all components ensuring acceptable levels of CO2 emission and fuel consumption. Utilizing data that comes from sources with different origin, such as on-board, off-board, structured, unstructured, private and public, and by combining information and finding common patterns will allow us to better adapt the service contracts and maintenance plans to the needs of individual customers and individual vehicles. Volvo Technology will coordinate the project and is overall responsible. The other partners of the project are: Volvo Information Technology, Högskolan i Halmstad, Svenska Innovationsinstitutet and Recorded Future.<br /> |LogotypeFile=Procedure.png<br /> |ProjectResponsible=Sławomir Nowaczyk<br /> |ProjectDetailsPDF=In4UptimeInfo.pdf<br /> |FundingMSEK=11<br /> |ProjectStart=2014/02<br /> |ProjectEnd=2016/01<br /> |ApplicationArea=Intelligent Vehicles<br /> |Image=Head-unknown.jpg<br /> |Lctitle=No<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=Volvo Group - Trucks Technology - Advanced Technology and Research<br /> }}<br /> __NOTOC__ <br /> {{ShowResearchProject}}<br /> &lt;!-- {{ShowProjectPublications}} --&gt;<br /> <br /> [[File:In4Uptime.png|center|thumb|caption|&quot;In4Uptime&quot;]]</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Yuantao_Fan&diff=1613 2014-05-16T13:06:30Z

<p>Yuafan: </p> <hr /> <div>{{Person<br /> |Family Name=Fan<br /> |Given Name=Yuantao<br /> |Title=M.Sc.<br /> |Position=PhD. Candidate<br /> |Email=yuantao.fan@hh.se<br /> |Image=Head-unknown.jpg<br /> |Office=E513<br /> |Subject=Learning Systems<br /> }}<br /> {{AssignProjects}}<br /> {{AssignProjects<br /> |project=In4Uptime<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Vehicle Diagnostics<br /> }}<br /> {{AssignSubjectAreas<br /> |SubjectArea=Data Mining<br /> }}<br /> {{AssignApplicationAreas<br /> |ApplicationArea=Intelligent Vehicles<br /> }}<br /> &lt;!--Remove or add comments --&gt;<br /> __NOTOC__<br /> {{ShowPerson}}<br /> {{InsertSubjAreas}}<br /> {{InsertProjects}}<br /> <br /> [[Category:staff]]</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Arne_N%C3%A5bo&diff=1612 2014-05-16T13:03:39Z

<p>Yuafan: Created page with &quot;{{Person |Family Name=Nåbo |Given Name=Arne |Affiliation=VTI }} {{AssignProjects |project=VICTIg }} Category:academic &lt;!--Remove or add comments --&gt; &lt;!-- __NOTOC__ --&gt; ...&quot;</p> <hr /> <div>{{Person<br /> |Family Name=Nåbo<br /> |Given Name=Arne<br /> |Affiliation=VTI<br /> }}<br /> {{AssignProjects<br /> |project=VICTIg<br /> }}<br /> [[Category:academic]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> {{InsertProjects}}<br /> &lt;!-- {{PublicationsList}} --&gt;</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Jonas_Jansson&diff=1611 2014-05-16T13:02:20Z

<p>Yuafan: </p> <hr /> <div>{{Person<br /> |Family Name=Jansson<br /> |Given Name=Jonas<br /> |Affiliation=VTI<br /> }}<br /> {{AssignProjects<br /> |project=VICTIg<br /> }}<br /> [[Category:academic]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> {{InsertProjects}}<br /> &lt;!-- {{PublicationsList}} --&gt;</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Jonas_Jansson&diff=1610 2014-05-16T13:01:45Z

<p>Yuafan: </p> <hr /> <div>{{Person<br /> |Family Name=Jansson<br /> |Given Name=Jonas<br /> |Affiliation=Viktoria Institutet<br /> }}<br /> {{AssignProjects<br /> |project=VICTIg<br /> }}<br /> [[Category:academic]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> {{InsertProjects}}<br /> &lt;!-- {{PublicationsList}} --&gt;</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Jonas_Jansson&diff=1609 2014-05-16T13:00:53Z

<p>Yuafan: Created page with &quot;{{Person |Family Name=Jansson |Given Name=Jonas |Affiliation=Viktoria Institutet }} {{AssignProjects |project=VICTIg }} Category:Staff &lt;!--Remove or add comments --&gt; &lt;!-...&quot;</p> <hr /> <div>{{Person<br /> |Family Name=Jansson<br /> |Given Name=Jonas<br /> |Affiliation=Viktoria Institutet<br /> }}<br /> {{AssignProjects<br /> |project=VICTIg<br /> }}<br /> [[Category:Staff]]<br /> &lt;!--Remove or add comments --&gt;<br /> &lt;!-- __NOTOC__ --&gt;<br /> {{ShowPerson}}<br /> {{InsertProjects}}<br /> &lt;!-- {{PublicationsList}} --&gt;</div>

Yuafan https://mw.hh.se/caisr/index.php?title=In4Uptime&diff=1588 2014-05-15T08:37:20Z

<p>Yuafan: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title= In4Uptime<br /> |ContactInformation=Sławomir Nowaczyk<br /> |ShortDescription= Vehicle diagnostics and predictive maintenance<br /> |Description=The goal of the project is to keep commercial vehicles in good operational condition, both from a financial and safety point of view. Haulers and transporters require OEMs to provide vehicles having close to 100% uptime. That means no stops, unless planned, as well as guarantees on optimal performance of all components ensuring acceptable levels of CO2 emission and fuel consumption. Utilizing data that comes from sources with different origin, such as on-board, off-board, structured, unstructured, private and public, and by combining information and finding common patterns will allow us to better adapt the service contracts and maintenance plans to the needs of individual customers and individual vehicles. Volvo Technology will coordinate the project and is overall responsible. The other partners of the project are: Volvo Information Technology, Högskolan i Halmstad, Svenska Innovationsinstitutet and Recorded Future.<br /> |LogotypeFile=Procedure.png<br /> |ProjectResponsible=Sławomir Nowaczyk<br /> |ProjectDetailsPDF=CAISR Poster 2013 AIMS.pdf<br /> |FundingMSEK=11<br /> |ProjectStart=2014/02<br /> |ProjectEnd=2016/01<br /> |ApplicationArea=Intelligent Vehicles<br /> |Image=Head-unknown.jpg<br /> |Lctitle=No<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=Volvo Group - Trucks Technology - Advanced Technology and Research<br /> }}<br /> __NOTOC__ <br /> {{ShowResearchProject}}<br /> &lt;!-- {{ShowProjectPublications}} --&gt;<br /> <br /> [[File:In4Uptime.png|center|thumb|caption|&quot;In4Uptime&quot;]]</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Intelligent_Vehicles&diff=1582 2014-05-14T17:06:39Z

<p>Yuafan: </p> <hr /> <div>{{Infobox<br /> |title = Intelligent Vehicles Group<br /> |header1 = Research in Intelligent Vehicles<br /> |header2 = [[CAISR]]<br /> |header3 = <br /> |header4 = &#039;&#039;&#039;Contact:&#039;&#039;&#039; [[Roland Philippsen]]<br /> }}<br /> <br /> == Funding and Partners ==<br /> {| class=&quot;wikitable&quot;<br /> |-<br /> ! Funding Agencies !! Academic &amp; Research Institutions !! Industrial Partners<br /> |-<br /> | European Commission (CORDIS - Seventh Framework Programme) || Örebro University || Autoliv<br /> |-<br /> | KK-stiftelsen || University of Skövde || Volvo Group Trucks Technology<br /> |-<br /> | Vinnova || SP Technical Research Institute of Sweden || Toyota Material Handling Europe AB<br /> |-<br /> | || Chalmers University of Technology || Optronic Partner dp AB<br /> |-<br /> | || VTI (the Swedish National Road and Transport Research Institute) || Kollmorgen Särö AB<br /> |-<br /> | || TNO || Volvo Car Corporation<br /> |-<br /> | || Institut de Robòtica i Informàtica Industrial || <br /> |}<br /> <br /> == People ==<br /> {{#ask: [[Category:Staff]] [[ApplicationArea::Intelligent Vehicles]]<br /> | ?firstName | ?lastName<br /> | format=ul<br /> }}<br /> <br /> * Jawad Masood<br /> <br /> == Projects ==<br /> <br /> {{#ask: [[Category:ResearchProject]] [[ApplicationArea::Intelligent Vehicles]] [[ProjectEnd::≥{{CURRENTYEAR}}/{{CURRENTMONTH}}/{{CURRENTDAY}}]]<br /> | ?ContactInformation<br /> | ?ShortDescription<br /> }}<br /> <br /> === [[AIMS]] (Automatic Inventory and Mapping of Stock) ===<br /> [[File:Aims semantic.png|thumb|caption|&quot;AIMS&quot;]]<br /> An intelligent warehouse environment that autonomously builds a map of articles in a warehouse and relates article identity from the warehouse database with the article’s position (metric) and visual appearance in the warehouse.<br /> * Intelligent warehouse: identity, location, and appearance of articles<br /> ** recognition and clustering<br /> ** 3D perception<br /> ** localization, mapping and map maintenance<br /> <br /> === [[Cargo ANTs]] ===<br /> [[File:Cargo-ANTS.png|thumb|caption|&quot;Cargo ANTs&quot;]]<br /> * automated cargo handling ITS<br /> * AGVs at trucks in ports and terminals<br /> * multi-vehicle path planning and adaptation<br /> <br /> === [[fuelFEET]] (Fuel FOT Energy Efficient Transport) ===<br /> [[File:FuelFEET.png|thumb|caption|&quot;fuelFEET&quot;]]<br /> Explore factors affecting fuel consumption.<br /> * Fuel FOT Energy Efficient Transport<br /> * which fuel consumption factors can be influenced by the driver or fleet owner?<br /> <br /> === [[InnoMerge]] ===<br /> [[File:InnoMerge.png|thumb|caption|&quot;InnoMerge&quot;]]<br /> * transfer to and from emerging markets<br /> * uptime &amp; safety<br /> * diagnostics, maintenance, monitoring<br /> <br /> === [[FFI NG-TEST]] (Next Generation Test) ===<br /> [[File:NGtest-logo-800x322.jpg|thumb|caption|&quot;NG Test&quot;]]<br /> Next Generation Test Methods for Active Safety Functions. &quot;NG TEST&quot; aims to move parts of the verification and validation of active safety functions from the proving ground to a complete or partly virtual environment.<br /> validated virtual testing of next-generation ADAS:<br /> * CPS modeling, executable math for requirement specification.<br /> * real-time positioning, rapid accurate positioning on test tracks.<br /> <br /> === [[VICTIg]] (Vehicle ICT Innovation Methodology) ===<br /> [[File: VICTIg.jpg|thumb|caption|&quot;VICTIg&quot;]]<br /> * Software intense ICT functions testing<br /> * Test software function of vehicle cooperative, automated and assisted vehicle driving.<br /> * Develop different level of driving simulation <br /> <br /> === [[ReDi2Service]] ===<br /> [[File:R2S.png|thumb|caption|&quot;ReDi2Service&quot;]]<br /> Algorithms for self-monitoring vehicles, capable of discovering and describing their own operation, as well as detecting deviations from the norm. Data mining across many data streams available on-board a modern truck or bus. Comparing discovered relations across the whole fleet. Faults and component wear can be discovered early and continuously monitored.<br /> * Remote Diagnostic Tools and Services<br /> * self-monitor operation and deviations<br /> * data mining: on-board, maintenance logs, driver comments, engineering expertise<br /> <br /> === [[V-Charge]] ===<br /> [[File:V-Charge.png|thumb|caption|&quot;V-Charge&quot;]]<br /> Autonomous navigation in parking structures using consumer car sensor.<br /> Halmstad University is involved in V-Charge indirectly by supervising PhD student.<br /> External [http://www.v-charge.eu/ link] to V-Charge webpage.<br /> <br /> === [[In4Uptime]] ===<br /> [[File:In4Uptime.png|thumb|caption|&quot;In4Uptime&quot;]]<br /> * Vehicle diagnostics and predictive maintenance<br /> * on-board data stream mining<br /> * Data analysis with special focus on developing Component Degradation Models.</div>

Yuafan https://mw.hh.se/caisr/index.php?title=VICTIg&diff=1581 2014-05-14T17:05:08Z

<p>Yuafan: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title=VICTIg<br /> |ContactInformation=Tony Larsson<br /> |ShortDescription=Vehicle ICT Innovation Methodology<br /> |Description=VICTIg is a collaboration project between VTI (Swedish National Road and Transport Research Institute) and Halmstad University, it aims to discover better method for development and test of software functions for cooperative, automated and assisted vehicle driving. The main research question is how to efficiently test such safety critical functions with sufficient coverage. The method could applied on different level of simulation e.g. driving simulator from VTI, Hardware-in-the-loop simulation, etc.<br /> |LogotypeFile=Procedure.png<br /> |ProjectResponsible=Tony Larsson<br /> |FundingMSEK=6<br /> |ProjectStart=2013/11/01<br /> |ProjectEnd=2016/03/31<br /> |ApplicationArea=Intelligent Vehicles<br /> |Lctitle=No<br /> }}<br /> <br /> {{AssignProjPartner<br /> |projectpartner=SAFER<br /> }}<br /> <br /> {{AssignProjPartner<br /> |projectpartner=VTI<br /> }}<br /> <br /> __NOTOC__ <br /> {{ShowResearchProject}}<br /> {{ShowProjectPublications}}<br /> <br /> [[File:VICTIg.jpg|center|thumb|caption|&quot;VICTIg&quot;]]</div>

Yuafan https://mw.hh.se/caisr/index.php?title=Intelligent_Vehicles&diff=1580 2014-05-14T17:02:40Z

<p>Yuafan: </p> <hr /> <div>{{Infobox<br /> |title = Intelligent Vehicles Group<br /> |header1 = Research in Intelligent Vehicles<br /> |header2 = [[CAISR]]<br /> |header3 = <br /> |header4 = &#039;&#039;&#039;Contact:&#039;&#039;&#039; [[Roland Philippsen]]<br /> }}<br /> <br /> == Funding and Partners ==<br /> {| class=&quot;wikitable&quot;<br /> |-<br /> ! Funding Agencies !! Academic &amp; Research Institutions !! Industrial Partners<br /> |-<br /> | European Commission (CORDIS - Seventh Framework Programme) || Örebro University || Autoliv<br /> |-<br /> | KK-stiftelsen || University of Skövde || Volvo Group Trucks Technology<br /> |-<br /> | Vinnova || SP Technical Research Institute of Sweden || Toyota Material Handling Europe AB<br /> |-<br /> | || Chalmers University of Technology || Optronic Partner dp AB<br /> |-<br /> | || VTI (the Swedish National Road and Transport Research Institute) || Kollmorgen Särö AB<br /> |-<br /> | || TNO || Volvo Car Corporation<br /> |-<br /> | || Institut de Robòtica i Informàtica Industrial || <br /> |}<br /> <br /> == People ==<br /> {{#ask: [[Category:Staff]] [[ApplicationArea::Intelligent Vehicles]]<br /> | ?firstName | ?lastName<br /> | format=ul<br /> }}<br /> <br /> * Jawad Masood<br /> <br /> == Projects ==<br /> <br /> {{#ask: [[Category:ResearchProject]] [[ApplicationArea::Intelligent Vehicles]] [[ProjectEnd::≥{{CURRENTYEAR}}/{{CURRENTMONTH}}/{{CURRENTDAY}}]]<br /> | ?ContactInformation<br /> | ?ShortDescription<br /> }}<br /> <br /> === [[AIMS]] (Automatic Inventory and Mapping of Stock) ===<br /> [[File:Aims semantic.png|thumb|caption|&quot;AIMS&quot;]]<br /> An intelligent warehouse environment that autonomously builds a map of articles in a warehouse and relates article identity from the warehouse database with the article’s position (metric) and visual appearance in the warehouse.<br /> * Intelligent warehouse: identity, location, and appearance of articles<br /> ** recognition and clustering<br /> ** 3D perception<br /> ** localization, mapping and map maintenance<br /> <br /> === [[Cargo ANTs]] ===<br /> [[File:Cargo-ANTS.png|thumb|caption|&quot;Cargo ANTs&quot;]]<br /> * automated cargo handling ITS<br /> * AGVs at trucks in ports and terminals<br /> * multi-vehicle path planning and adaptation<br /> <br /> === [[fuelFEET]] (Fuel FOT Energy Efficient Transport) ===<br /> [[File:FuelFEET.png|thumb|caption|&quot;fuelFEET&quot;]]<br /> Explore factors affecting fuel consumption.<br /> * Fuel FOT Energy Efficient Transport<br /> * which fuel consumption factors can be influenced by the driver or fleet owner?<br /> <br /> === [[InnoMerge]] ===<br /> [[File:InnoMerge.png|thumb|caption|&quot;InnoMerge&quot;]]<br /> * transfer to and from emerging markets<br /> * uptime &amp; safety<br /> * diagnostics, maintenance, monitoring<br /> <br /> === [[FFI NG-TEST]] (Next Generation Test) ===<br /> [[File:NGtest-logo-800x322.jpg|thumb|caption|&quot;NG Test&quot;]]<br /> Next Generation Test Methods for Active Safety Functions. &quot;NG TEST&quot; aims to move parts of the verification and validation of active safety functions from the proving ground to a complete or partly virtual environment.<br /> validated virtual testing of next-generation ADAS:<br /> * CPS modeling, executable math for requirement specification.<br /> * real-time positioning, rapid accurate positioning on test tracks.<br /> <br /> === [[VICTIg]] (Vehicle ICT Innovation Methodology) ===<br /> [[File: VICTIg .jpg|thumb|caption|&quot;VICTIg&quot;]]<br /> * Reduce accident risks beyond current ADAS capabilities<br /> * Combine the growing type and amount of available sensor data<br /> * we consult on motion generation (joint IV 2013 paper)<br /> <br /> === [[ReDi2Service]] ===<br /> [[File:R2S.png|thumb|caption|&quot;ReDi2Service&quot;]]<br /> Algorithms for self-monitoring vehicles, capable of discovering and describing their own operation, as well as detecting deviations from the norm. Data mining across many data streams available on-board a modern truck or bus. Comparing discovered relations across the whole fleet. Faults and component wear can be discovered early and continuously monitored.<br /> * Remote Diagnostic Tools and Services<br /> * self-monitor operation and deviations<br /> * data mining: on-board, maintenance logs, driver comments, engineering expertise<br /> <br /> === [[V-Charge]] ===<br /> [[File:V-Charge.png|thumb|caption|&quot;V-Charge&quot;]]<br /> Autonomous navigation in parking structures using consumer car sensor.<br /> Halmstad University is involved in V-Charge indirectly by supervising PhD student.<br /> External [http://www.v-charge.eu/ link] to V-Charge webpage.<br /> <br /> === [[In4Uptime]] ===<br /> [[File:In4Uptime.png|thumb|caption|&quot;In4Uptime&quot;]]<br /> * Vehicle diagnostics and predictive maintenance<br /> * on-board data stream mining<br /> * Data analysis with special focus on developing Component Degradation Models.</div>

Yuafan https://mw.hh.se/caisr/index.php?title=In4Uptime&diff=1579 2014-05-14T16:57:41Z

<p>Yuafan: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title= In4Uptime<br /> |ContactInformation=Sławomir Nowaczyk<br /> |ShortDescription= Transportation Efficiency<br /> |Description=The goal of the project is to keep commercial vehicles in good operational condition, both from a financial and safety point of view. Haulers and transporters require OEMs to provide vehicles having close to 100% uptime. That means no stops, unless planned, as well as guarantees on optimal performance of all components ensuring acceptable levels of CO2 emission and fuel consumption. Utilizing data that comes from sources with different origin, such as on-board, off-board, structured, unstructured, private and public, and by combining information and finding common patterns will allow us to better adapt the service contracts and maintenance plans to the needs of individual customers and individual vehicles. Volvo Technology will coordinate the project and is overall responsible. The other partners of the project are: Volvo Information Technology, Högskolan i Halmstad, Svenska Innovationsinstitutet and Recorded Future.<br /> |LogotypeFile=Procedure.png<br /> |ProjectResponsible=Sławomir Nowaczyk<br /> |ProjectDetailsPDF=CAISR Poster 2013 AIMS.pdf<br /> |FundingMSEK=11<br /> |ProjectStart=2014/02<br /> |ProjectEnd=2016/01<br /> |ApplicationArea=Intelligent Vehicles<br /> |Image=Head-unknown.jpg<br /> |Lctitle=No<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=Volvo Group - Trucks Technology - Advanced Technology and Research<br /> }}<br /> __NOTOC__ <br /> {{ShowResearchProject}}<br /> &lt;!-- {{ShowProjectPublications}} --&gt;<br /> <br /> [[File:In4Uptime.png|center|thumb|caption|&quot;In4Uptime&quot;]]</div>

Yuafan https://mw.hh.se/caisr/index.php?title=VICTIg&diff=1578 2014-05-14T16:56:13Z

<p>Yuafan: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title=VICTIg<br /> |ContactInformation=Tony Larsson<br /> |ShortDescription=Vehicle ICT Innovation Methodology<br /> |Description=VICTIg is a collaboration project between VTI (Swedish National Road and Transport Research Institute) and Halmstad University, the project aims at methods for efficient development and test of the software intense ICT functions enabling modern active safety functions for automated and assisted vehicles using on-board sensors and information exchange via wireless communication enabling cooperative system solutions. The project will develop methods and integrate different tools to address the complex task at hand when developing and testing interacting cooperative vehicle functions. Several state of the art tools such as VTIs advanced driving simulators, models of the road environment and the human driver interface as well as models of sensor data and communication disturbances will be used in the project.<br /> |LogotypeFile=Procedure.png<br /> |ProjectResponsible=Tony Larsson<br /> |FundingMSEK=6<br /> |ProjectStart=2013/11/01<br /> |ProjectEnd=2016/03/31<br /> |ApplicationArea=Intelligent Vehicles<br /> |Lctitle=No<br /> }}<br /> <br /> {{AssignProjPartner<br /> |projectpartner=SAFER<br /> }}<br /> <br /> {{AssignProjPartner<br /> |projectpartner=VTI<br /> }}<br /> <br /> __NOTOC__ <br /> {{ShowResearchProject}}<br /> {{ShowProjectPublications}}<br /> <br /> [[File:VICTIg.jpg|center|thumb|caption|&quot;VICTIg&quot;]]</div>

Yuafan https://mw.hh.se/caisr/index.php?title=VICTIg&diff=1577 2014-05-14T16:55:11Z

<p>Yuafan: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title=VICTIg<br /> |ContactInformation=Tony Larsson<br /> |ShortDescription=Vehicle ICT Innovation Methodology<br /> |Description=VICTIg is a collaboration project between VTI (Swedish National Road and Transport Research Institute) and Halmstad University, the project aims at methods for efficient development and test of the software intense ICT functions enabling modern active safety functions for automated and assisted vehicles using on-board sensors and information exchange via wireless communication enabling cooperative system solutions. The project will develop methods and integrate different tools to address the complex task at hand when developing and testing interacting cooperative vehicle functions. Several state of the art tools such as VTIs advanced driving simulators, models of the road environment and the human driver interface as well as models of sensor data and communication disturbances will be used in the project.<br /> <br /> |LogotypeFile=Procedure.png<br /> |ProjectResponsible=Tony Larsson<br /> |FundingMSEK=5?<br /> |ProjectStart=2013/11/01<br /> |ProjectEnd=2016/03/31<br /> |ApplicationArea=Intelligent Vehicles<br /> |Lctitle=No<br /> }}<br /> <br /> {{AssignProjPartner<br /> |projectpartner=SAFER<br /> }}<br /> <br /> {{AssignProjPartner<br /> |projectpartner=VTI<br /> }}<br /> <br /> <br /> __NOTOC__ <br /> {{ShowResearchProject}}<br /> {{ShowProjectPublications}}<br /> <br /> [[File:VICTIg.jpg|center|thumb|caption|&quot;VICTIg&quot;]]</div>

Yuafan https://mw.hh.se/caisr/index.php?title=VICTIg&diff=1576 2014-05-14T16:54:37Z

<p>Yuafan: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title=VICTIg<br /> |ContactInformation=Tony Larsson<br /> |ShortDescription=Vehicle ICT Innovation Methodology<br /> |Description=VICTIg is a collaboration project between VTI (Swedish National Road and Transport Research Institute) and Halmstad University, the project aims at methods for efficient development and test of the software intense ICT functions enabling modern active safety functions for automated and assisted vehicles using on-board sensors and information exchange via wireless communication enabling cooperative system solutions. The project will develop methods and integrate different tools to address the complex task at hand when developing and testing interacting cooperative vehicle functions. Several state of the art tools such as VTIs advanced driving simulators, models of the road environment and the human driver interface as well as models of sensor data and communication disturbances will be used in the project.<br /> <br /> |LogotypeFile=Procedure.png<br /> |ProjectResponsible=Tony Larsson<br /> |FundingMSEK=5?<br /> |ProjectStart=2013/11/01<br /> |ProjectEnd=2016/03/31<br /> |ApplicationArea=Intelligent Vehicles<br /> |Lctitle=No<br /> }}<br /> <br /> {{AssignProjPartner<br /> |projectpartner=SAFER<br /> }}<br /> <br /> {{AssignProjPartner<br /> |projectpartner=VTI<br /> }}<br /> <br /> <br /> [[File:VICTIg.jpg|center|thumb|caption|&quot;VICTIg&quot;]]<br /> <br /> <br /> __NOTOC__ <br /> {{ShowResearchProject}}<br /> {{ShowProjectPublications}}</div>

Yuafan https://mw.hh.se/caisr/index.php?title=In4Uptime&diff=1575 2014-05-14T16:54:28Z

<p>Yuafan: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title= In4Uptime<br /> |ContactInformation=Sławomir Nowaczyk<br /> |ShortDescription= In For Uptime<br /> |Description=The goal of the project is to keep commercial vehicles in good operational condition, both from a financial and safety point of view. Haulers and transporters require OEMs to provide vehicles having close to 100% uptime. That means no stops, unless planned, as well as guarantees on optimal performance of all components ensuring acceptable levels of CO2 emission and fuel consumption. Utilizing data that comes from sources with different origin, such as on-board, off-board, structured, unstructured, private and public, and by combining information and finding common patterns will allow us to better adapt the service contracts and maintenance plans to the needs of individual customers and individual vehicles. Volvo Technology will coordinate the project and is overall responsible. The other partners of the project are: Volvo Information Technology, Högskolan i Halmstad, Svenska Innovationsinstitutet and Recorded Future.<br /> |LogotypeFile=Procedure.png<br /> |ProjectResponsible=Sławomir Nowaczyk<br /> |ProjectDetailsPDF=CAISR Poster 2013 AIMS.pdf<br /> |FundingMSEK=11<br /> |ProjectStart=2014/02<br /> |ProjectEnd=2016/01<br /> |ApplicationArea=Intelligent Vehicles<br /> |Image=Head-unknown.jpg<br /> |Lctitle=No<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=Volvo Group - Trucks Technology - Advanced Technology and Research<br /> }}<br /> __NOTOC__ <br /> {{ShowResearchProject}}<br /> &lt;!-- {{ShowProjectPublications}} --&gt;<br /> <br /> [[File:In4Uptime.png|center|thumb|caption|&quot;In4Uptime&quot;]]</div>

Yuafan https://mw.hh.se/caisr/index.php?title=In4Uptime&diff=1574 2014-05-14T16:54:04Z

<p>Yuafan: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title= In4Uptime<br /> |ContactInformation=Sławomir Nowaczyk<br /> |ShortDescription= In For Uptime<br /> |Description=The goal of the project is to keep commercial vehicles in good operational condition, both from a financial and safety point of view. Haulers and transporters require OEMs to provide vehicles having close to 100% uptime. That means no stops, unless planned, as well as guarantees on optimal performance of all components ensuring acceptable levels of CO2 emission and fuel consumption. Utilizing data that comes from sources with different origin, such as on-board, off-board, structured, unstructured, private and public, and by combining information and finding common patterns will allow us to better adapt the service contracts and maintenance plans to the needs of individual customers and individual vehicles. Volvo Technology will coordinate the project and is overall responsible. The other partners of the project are: Volvo Information Technology, Högskolan i Halmstad, Svenska Innovationsinstitutet and Recorded Future.<br /> |LogotypeFile=Procedure.png<br /> |ProjectResponsible=Sławomir Nowaczyk<br /> |ProjectDetailsPDF=CAISR Poster 2013 AIMS.pdf<br /> |FundingMSEK=11<br /> |ProjectStart=2014/02<br /> |ProjectEnd=2016/01<br /> |ApplicationArea=Intelligent Vehicles<br /> |Image=Head-unknown.jpg<br /> |Lctitle=No<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=Volvo Group - Trucks Technology - Advanced Technology and Research<br /> }}<br /> __NOTOC__ <br /> {{ShowResearchProject}}<br /> &lt;!-- {{ShowProjectPublications}} --&gt;<br /> <br /> [[File:VICTIg.jpg|center|thumb|caption|&quot;VICTIg&quot;]]</div>

Yuafan https://mw.hh.se/caisr/index.php?title=File:VICTIg.jpg&diff=1573 2014-05-14T16:53:42Z

<p>Yuafan: </p> <hr /> <div></div>

Yuafan https://mw.hh.se/caisr/index.php?title=In4Uptime&diff=1572 2014-05-14T16:52:29Z

<p>Yuafan: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title= In4Uptime<br /> |ContactInformation=Sławomir Nowaczyk<br /> |ShortDescription= In For Uptime<br /> |Description=The goal of the project is to keep commercial vehicles in good operational condition, both from a financial and safety point of view. Haulers and transporters require OEMs to provide vehicles having close to 100% uptime. That means no stops, unless planned, as well as guarantees on optimal performance of all components ensuring acceptable levels of CO2 emission and fuel consumption. Utilizing data that comes from sources with different origin, such as on-board, off-board, structured, unstructured, private and public, and by combining information and finding common patterns will allow us to better adapt the service contracts and maintenance plans to the needs of individual customers and individual vehicles. Volvo Technology will coordinate the project and is overall responsible. The other partners of the project are: Volvo Information Technology, Högskolan i Halmstad, Svenska Innovationsinstitutet and Recorded Future.<br /> |LogotypeFile=Procedure.png<br /> |ProjectResponsible=Sławomir Nowaczyk<br /> |ProjectDetailsPDF=CAISR Poster 2013 AIMS.pdf<br /> |FundingMSEK=11<br /> |ProjectStart=2014/02<br /> |ProjectEnd=2016/01<br /> |ApplicationArea=Intelligent Vehicles<br /> |Image=Head-unknown.jpg<br /> |Lctitle=No<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=Volvo Group - Trucks Technology - Advanced Technology and Research<br /> }}<br /> __NOTOC__ <br /> {{ShowResearchProject}}<br /> &lt;!-- {{ShowProjectPublications}} --&gt;<br /> <br /> [[File:In4Uptime.png|center|thumb|caption|&quot;In4Uptime&quot;]]</div>

Yuafan https://mw.hh.se/caisr/index.php?title=In4Uptime&diff=1571 2014-05-14T16:51:11Z

<p>Yuafan: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title= In4Uptime<br /> |ContactInformation=Sławomir Nowaczyk<br /> |ShortDescription= In For Uptime<br /> |Description=The goal of the project is to keep commercial vehicles in good operational condition, both from a financial and safety point of view. Haulers and transporters require OEMs to provide vehicles having close to 100% uptime. That means no stops, unless planned, as well as guarantees on optimal performance of all components ensuring acceptable levels of CO2 emission and fuel consumption. Utilizing data that comes from sources with different origin, such as on-board, off-board, structured, unstructured, private and public, and by combining information and finding common patterns will allow us to better adapt the service contracts and maintenance plans to the needs of individual customers and individual vehicles. Volvo Technology will coordinate the project and is overall responsible. The other partners of the project are: Volvo Information Technology, Högskolan i Halmstad, Svenska Innovationsinstitutet and Recorded Future.<br /> |LogotypeFile=Procedure.png<br /> |ProjectResponsible=Sławomir Nowaczyk<br /> |FundingMSEK=11<br /> |ProjectStart=2014/02<br /> |ProjectEnd=2016/01<br /> |ApplicationArea=Intelligent Vehicles<br /> |Image=Head-unknown.jpg<br /> |Lctitle=No<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=Volvo Group - Trucks Technology - Advanced Technology and Research<br /> }}<br /> __NOTOC__ <br /> {{ShowResearchProject}}<br /> &lt;!-- {{ShowProjectPublications}} --&gt;<br /> <br /> [[File:In4Uptime.png|center|thumb|caption|&quot;In4Uptime&quot;]]</div>

Yuafan https://mw.hh.se/caisr/index.php?title=File:In4Uptime.png&diff=1570 2014-05-14T16:50:19Z

<p>Yuafan: </p> <hr /> <div></div>

Yuafan https://mw.hh.se/caisr/index.php?title=VICTIg&diff=1569 2014-05-14T16:49:34Z

<p>Yuafan: </p> <hr /> <div>{{ResearchProjInfo<br /> |Title=VICTIg<br /> |ContactInformation=Tony Larsson<br /> |ShortDescription=Vehicle ICT Innovation Methodology<br /> |Description=VICTIg is a collaboration project between VTI (Swedish National Road and Transport Research Institute) and Halmstad University, the project aims at methods for efficient development and test of the software intense ICT functions enabling modern active safety functions for automated and assisted vehicles using on-board sensors and information exchange via wireless communication enabling cooperative system solutions. The project will develop methods and integrate different tools to address the complex task at hand when developing and testing interacting cooperative vehicle functions. Several state of the art tools such as VTIs advanced driving simulators, models of the road environment and the human driver interface as well as models of sensor data and communication disturbances will be used in the project.<br /> <br /> |LogotypeFile=Procedure.png<br /> |ProjectResponsible=Tony Larsson<br /> |FundingMSEK=5?<br /> |ProjectStart=2013/11/01<br /> |ProjectEnd=2016/03/31<br /> |ApplicationArea=Intelligent Vehicles<br /> |Lctitle=No<br /> }}<br /> <br /> {{AssignProjPartner<br /> |projectpartner=SAFER<br /> }}<br /> <br /> {{AssignProjPartner<br /> |projectpartner=VTI<br /> }}<br /> <br /> <br /> [[File:VICTIg.png|thumb|caption|&quot;VICTIg&quot;]]<br /> <br /> <br /> <br /> __NOTOC__ <br /> {{ShowResearchProject}}<br /> {{ShowProjectPublications}}</div>

Yuafan https://mw.hh.se/caisr/index.php?title=In4Uptime&diff=1568 2014-05-14T16:44:45Z

<p>Yuafan: Created page with &quot;{{ResearchProjInfo |Title= In4Uptime |ContactInformation=Sławomir Nowaczyk |ShortDescription= In For Uptime |Description=Analysis of factors influencing fuel consumption is a...&quot;</p> <hr /> <div>{{ResearchProjInfo<br /> |Title= In4Uptime<br /> |ContactInformation=Sławomir Nowaczyk<br /> |ShortDescription= In For Uptime<br /> |Description=Analysis of factors influencing fuel consumption is a very important task both for automotive industry. There is a lot of knowledge already available concerning this topic, but it is poorly organized and often more anecdotal than rigorously verified. Nowadays, however, enough rich datasets from actual vehicle usage are available and a data-mining based approach can be used to not only validate earlier hypotheses, but also to potentially discover unexpected influencing factors.<br /> |LogotypeFile=Procedure.png<br /> |ProjectResponsible=Sławomir Nowaczyk<br /> |FundingMSEK=11<br /> |ProjectStart=2014/02<br /> |ProjectEnd=2016/01<br /> |ApplicationArea=Intelligent Vehicles<br /> |Image=Head-unknown.jpg<br /> |Lctitle=No<br /> }}<br /> {{AssignProjPartner<br /> |projectpartner=Volvo Group - Trucks Technology - Advanced Technology and Research<br /> }}<br /> __NOTOC__ <br /> {{ShowResearchProject}}<br /> &lt;!-- {{ShowProjectPublications}} --&gt;<br /> <br /> [[File:FuelFEET.png|center|thumb|caption|&quot;fuelFEET&quot;]]</div>

Yuafan