On Using Temporal Features to Create More Accurate Human-Activity Classifiers

Through advances in sensing technology, a huge amount of data is available to context-aware applications. A major challenge is extracting features of this data that correlate to high-level human activities. Time, while being semantically rich and an essentially free source of information, has not received sufficient attention for this task. In this paper, we examine the potential for taking temporal features--inherent in human activities--into account when classifying them. Preliminary experiments using the PlaceLab dataset show that absolute time and temporal relationships between activities can improve the accuracy of activity classifiers.

[1]  Roy H. Campbell,et al.  MiddleWhere: A Middleware for Location Awareness in Ubiquitous Computing Applications , 2004, Middleware.

[2]  Henry A. Kautz,et al.  Improving the recognition of interleaved activities , 2008, UbiComp.

[3]  Judy Kay,et al.  Location Conflict Resolution with an Ontology , 2009, Pervasive.

[4]  Massimo Piccardi,et al.  Hidden Markov Models with Kernel Density Estimation of Emission Probabilities and their Use in Activity Recognition , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Sungyoung Lee,et al.  A Reconfigurable HMM for Activity Recognition , 2008, 2008 10th International Conference on Advanced Communication Technology.

[6]  Jennifer Healey,et al.  A Long-Term Evaluation of Sensing Modalities for Activity Recognition , 2007, UbiComp.

[7]  Simon A. Dobson,et al.  Ontology-based models in pervasive computing systems , 2007, The Knowledge Engineering Review.

[8]  Bernt Schiele,et al.  Discovery of activity patterns using topic models , 2008 .

[9]  John Krumm,et al.  UbiComp 2007: Ubiquitous Computing, 9th International Conference, UbiComp 2007, Innsbruck, Austria, September 16-19, 2007, Proceedings , 2007, UbiComp.

[10]  Harry Chen,et al.  SOUPA: standard ontology for ubiquitous and pervasive applications , 2004, The First Annual International Conference on Mobile and Ubiquitous Systems: Networking and Services, 2004. MOBIQUITOUS 2004..

[11]  Philippe Golle,et al.  On using existing time-use study data for ubiquitous computing applications , 2008, UbiComp.

[12]  Richard C. H. Connor,et al.  Architectural Support for Global Smart Spaces , 2003, Mobile Data Management.

[13]  Simon A. Dobson,et al.  Representing and Manipulating Situation Hierarchies using Situation Lattices , 2008, Rev. d'Intelligence Artif..

[14]  Uwe Hansmann,et al.  Pervasive Computing , 2003 .

[15]  Harry Chen,et al.  An ontology for context-aware pervasive computing environments , 2003, The Knowledge Engineering Review.

[16]  Juan Ye,et al.  Gathering Datasets for Activity Identification , 2009 .

[17]  James F. Allen,et al.  Actions and Events in Interval Temporal Logic , 1994 .

[18]  Andreas Krause,et al.  Context-aware mobile computing: learning context- dependent personal preferences from a wearable sensor array , 2006, IEEE Transactions on Mobile Computing.

[19]  Simon A. Dobson,et al.  Using situation lattices in sensor analysis , 2009, 2009 IEEE International Conference on Pervasive Computing and Communications.