Optimal time window for temporal segmentation of sensor streams in multi-activity recognition

Multi-activity recognition in the urban environment is a challenging task. This is largely attributed to the influence of urban dynamics, the variety of the label sets, and the heterogeneous nature of sensor data that arrive irregularly and at different rates. One of the first tasks in multi-activity recognition is temporal segmentation. A common temporal segmentation method is the sliding window approach with a fixed window size, which is widely used for single activity recognition. In order to recognise multiple activities from heterogeneous sensor streams, we propose a new time windowing technique that can optimally extract segments with multiple activity labels. The mixture of activity labels causes the impurity in the corresponding temporal segment. Hence, larger window size imposes higher impurity in temporal segments while increasing class separability. In addition, the combination of labels from multiple activity label sets (i.e. number of unique multi-activity) may decrease as impurity increases. Naturally, these factors will affect the performance of classification task. In our proposed technique, the optimal window size is found by gaining the balance between minimising impurity and maximising class separability in temporal segments. As a result, it accelerates the learning process for recognising multiple activities (such as higher level and atomic human activities under different environment contexts) in comparison to laborious tasks of sensitivity analysis. The evaluation was validated by experiments on a real-world dataset for recognising multiple human activities in a smart environment.

[1]  Jesse Read,et al.  Labeling sensing data for mobility modeling , 2016, Inf. Syst..

[2]  Venu Govindaraju,et al.  Parallel Feature Selection Inspired by Group Testing , 2014, NIPS.

[3]  Robert I. Damper,et al.  A fast separability-based feature-selection method for high-dimensional remotely sensed image classification , 2008, Pattern Recognit..

[4]  Heikki Mannila,et al.  Time series segmentation for context recognition in mobile devices , 2001, Proceedings 2001 IEEE International Conference on Data Mining.

[5]  Diane J. Cook,et al.  Activity recognition on streaming sensor data , 2014, Pervasive Mob. Comput..

[6]  Gregory D. Abowd,et al.  The Aware Home: A Living Laboratory for Ubiquitous Computing Research , 1999, CoBuild.

[7]  Cecilia Mascolo,et al.  EmotionSense: a mobile phones based adaptive platform for experimental social psychology research , 2010, UbiComp.

[8]  Ben Kröse,et al.  Care: context awareness in residences for elderly , 2008 .

[9]  Hjp Harry Timmermans,et al.  Transportation mode recognition using GPS and accelerometer data , 2013 .

[10]  Jorge Cancela,et al.  A mobile monitoring tool for the automatic activity recognition and its application for Parkinson’s disease rehabilitation , 2015 .

[11]  Jesse Hoey,et al.  Sensor-Based Activity Recognition , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[12]  Jian Lu,et al.  Sensor-Based Human Activity Recognition in a Multi-user Scenario , 2009, AmI.

[13]  Paul Lukowicz,et al.  Activity and emotion recognition to support early diagnosis of psychiatric diseases , 2008, 2008 Second International Conference on Pervasive Computing Technologies for Healthcare.

[14]  Di Liu,et al.  Feature selection for fusion of speaker verification via Maximum Kullback-Leibler distance , 2010, IEEE 10th INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS.

[15]  Francisco C. Pereira,et al.  Activity Recognition for a Smartphone Based Travel Survey Based on Cross-User History Data , 2014, 2014 22nd International Conference on Pattern Recognition.

[16]  J.K. Aggarwal,et al.  Human activity analysis , 2011, ACM Comput. Surv..

[17]  Jianhua Lin,et al.  Divergence measures based on the Shannon entropy , 1991, IEEE Trans. Inf. Theory.

[18]  Michael Beigl,et al.  Activity recognition for creatures of habit , 2014, Pers. Ubiquitous Comput..

[19]  Ching Y. Suen,et al.  Analysis of Class Separation and Combination of Class-Dependent Features for Handwriting Recognition , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Ricardo Chavarriaga,et al.  Benchmarking classification techniques using the Opportunity human activity dataset , 2011, 2011 IEEE International Conference on Systems, Man, and Cybernetics.

[21]  Sasu Tarkoma,et al.  Accelerometer-based transportation mode detection on smartphones , 2013, SenSys '13.

[22]  Huaiyu Zhu On Information and Sufficiency , 1997 .

[23]  Weihua Sheng,et al.  Human daily activity recognition in robot-assisted living using multi-sensor fusion , 2009, 2009 IEEE International Conference on Robotics and Automation.

[24]  Diane J. Cook,et al.  MavHome: an agent-based smart home , 2003, Proceedings of the First IEEE International Conference on Pervasive Computing and Communications, 2003. (PerCom 2003)..

[25]  Tatsuo Nakajima,et al.  Feature Selection and Activity Recognition from Wearable Sensors , 2006, UCS.

[26]  Damith Chinthana Ranasinghe,et al.  Evaluation of Wearable Sensor Tag Data Segmentation Approaches for Real Time Activity Classification in Elderly , 2013, MobiQuitous.

[27]  Kent Larson,et al.  Using a Live-In Laboratory for Ubiquitous Computing Research , 2006, Pervasive.

[28]  Yvan Saeys,et al.  Java-ML: A Machine Learning Library , 2009, J. Mach. Learn. Res..

[29]  Rama Chellappa,et al.  Machine Recognition of Human Activities: A Survey , 2008, IEEE Transactions on Circuits and Systems for Video Technology.

[30]  Yishi Zhang,et al.  Divergence-based feature selection for separate classes , 2013, Neurocomputing.

[31]  Karl Aberer,et al.  An adaptive approach for online segmentation of multi-dimensional mobile data , 2012, MobiDE '12.

[32]  Claudio Bettini,et al.  COSAR: hybrid reasoning for context-aware activity recognition , 2011, Personal and Ubiquitous Computing.

[33]  Étienne Belin,et al.  On the value of the Kullback–Leibler divergence for cost-effective spectral imaging of plants by optimal selection of wavebands , 2016, Machine Vision and Applications.

[34]  Albert-László Barabási,et al.  Understanding individual human mobility patterns , 2008, Nature.

[35]  Hanghang Tong,et al.  Activity recognition with smartphone sensors , 2014 .

[36]  Fan Ye,et al.  Mobile crowdsensing: current state and future challenges , 2011, IEEE Communications Magazine.

[37]  Grigorios Tsoumakas,et al.  Multi-Label Classification: An Overview , 2007, Int. J. Data Warehous. Min..

[38]  Jesús Favela,et al.  Activity Recognition for the Smart Hospital , 2008, IEEE Intelligent Systems.

[39]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.