Assurance-oriented activity recognition

Activity recognition (AR) research promises to enable a multitude of human-centric applications in smart environments. Nevertheless, application developers will require assurance mechanisms before they can confidently use and apply AR in real-world pervasive systems. In this work we propose an extension of an existing AR approach in which richer recognition semantics that address confidence and assurance are provided. Our approach differentiates between an activity and its effect and subsequently relies on verifying an activity by recognizing its effect. We present our approach along with a comparative experimental evaluation.

[1]  D. Altman,et al.  Statistics Notes: Diagnostic tests 1: sensitivity and specificity , 1994 .

[2]  Henry A. Kautz,et al.  Sensor-Based Understanding of Daily Life via Large-Scale Use of Common Sense , 2006, AAAI.

[3]  Gregory D. Abowd,et al.  Towards a Better Understanding of Context and Context-Awareness , 1999, HUC.

[4]  Larry L. Constantine,et al.  Human Activity Modeling: Toward A Pragmatic Integration of Activity Theory and Usage-Centered Design , 2009, Human-Centered Software Engineering.

[5]  Malik Ghallab,et al.  Situation Recognition: Representation and Algorithms , 1993, IJCAI.

[6]  Abdelsalam Helal,et al.  Revisiting Human Activity Frameworks , 2010, S-CUBE.

[7]  Sergio A. Alvarez,et al.  An exact analytical relation among recall , precision , and classification accuracy in information retrieval , 2002 .

[8]  Carl K. Chang,et al.  Situ: A Situation-Theoretic Approach to Context-Aware Service Evolution , 2009, IEEE Transactions on Services Computing.

[9]  Daniel J. Garland,et al.  Situation Awareness Analysis and Measurement , 2009 .

[10]  S. Broder,et al.  From the National Institutes of Health. , 1992, JAMA.

[11]  Diane J. Cook,et al.  Human Activity Recognition and Pattern Discovery , 2010, IEEE Pervasive Computing.

[12]  Stephen S. Yau,et al.  Development and runtime support for situation-aware application software in ubiquitous computing environments , 2004, Proceedings of the 28th Annual International Computer Software and Applications Conference, 2004. COMPSAC 2004..

[13]  N. F. Talyzina,et al.  The Problem of Activity in the Works of A. N. Leont'ev , 1983 .

[14]  Jean-Marc Nigro,et al.  IDRES: A rule-based system for driving situation recognition with uncertainty management , 2003, Inf. Fusion.

[15]  Minsoo Kim,et al.  A Formal Definition of Situation towards Situation-Aware Computing , 2009, WSKS.

[16]  Mica R. Endsley,et al.  Theoretical Underpinnings of Situation Awareness, A Critical Review , 2000 .

[17]  B. Nardi.  Context and consciousness: activity theory and human-computer interaction , 1995 .

[18]  Hanna M. Wallach,et al.  Conditional Random Fields: An Introduction , 2004 .

[19]  Amy Loutfi,et al.  Towards template-based situation recognition , 2009, Defense + Commercial Sensing.

[20]  Gwenn Englebienne,et al.  Accurate activity recognition in a home setting , 2008, UbiComp.

[21]  K. Kuutti.  Activity theory as a potential framework for human-computer interaction research , 1995 .