Real-time sensor observation segmentation for complex activity recognition within smart environments

Activity Recognition (AR) is at the heart of any types of assistive living systems. One of the key challenges faced in AR is segmentation of the sensor events when inhabitant performs simple or composite activities of daily living (ADLs). In addition, each inhabitant may follow a particular ritual or a tradition in performing different ADLs and their patterns may change overtime. Many recent studies apply methods to segment and recognise generic ADLs performed in a composite manner. However, little has been explored in semantically distinguishing individual sensor events and directly passing it to the relevant ongoing/new atomic activities. This paper proposes to use the ontological model to capture generic knowledge of ADLs and methods which also takes inhabitant-specific preferences into considerations when segmenting sensor events. The system implementation was developed, deployed and evaluated against 84 use case scenarios. The result suggests that all sensor events were adequately segmented with 98% accuracy and the average classification time of 3971ms and 62183ms for single and composite ADL scenarios were recorded, respectively.

[1]  Heiner Stuckenschmidt,et al.  Towards Activity Recognition Using Probabilistic Description Logics , 2012, AAAI 2012.

[2]  Chris D. Nugent,et al.  An Ontology-Based Hybrid Approach to Activity Modeling for Smart Homes , 2014, IEEE Transactions on Human-Machine Systems.

[3]  Senem Velipasalar,et al.  A Survey on Activity Detection and Classification Using Wearable Sensors , 2017, IEEE Sensors Journal.

[4]  Albert Zündorf,et al.  Scaling Parallel Rule-Based Reasoning , 2014, ESWC.

[5]  Alexander Schirrer,et al.  Overview and Motivation , 2015 .

[6]  Liming Chen,et al.  Combining ontological and temporal formalisms for composite activity modelling and recognition in smart homes , 2014, Future Gener. Comput. Syst..

[7]  Yunchuan Sun,et al.  ERAR: An Event-Driven Approach for Real-Time Activity Recognition , 2015, 2015 International Conference on Identification, Information, and Knowledge in the Internet of Things (IIKI).

[8]  Georgios Meditskos,et al.  MetaQ: A knowledge-driven framework for context-aware activity recognition combining SPARQL and OWL 2 activity patterns , 2016, Pervasive Mob. Comput..

[9]  Mohammad Reza Keyvanpour,et al.  SOnAr: Smart Ontology activity recognition framework to fulfill semantic web in smart homes , 2016, 2016 Second International Conference on Web Research (ICWR).

[10]  Maria E. Niessen,et al.  Monitoring Activities of Daily Living in Smart Homes: Understanding human behavior , 2016, IEEE Signal Processing Magazine.

[11]  Chris D. Nugent,et al.  From Activity Recognition to Intention Recognition for Assisted Living Within Smart Homes , 2017, IEEE Transactions on Human-Machine Systems.

[12]  Jeff Z. Pan,et al.  A Combined Approach to Incremental Reasoning for EL Ontologies , 2016, RR.

[13]  Steffen Staab,et al.  Incremental Maintenance of Materialized Ontologies , 2003, OTM.

[14]  Chris D. Nugent,et al.  A systematic approach to adaptive activity modeling and discovery in smart homes , 2011, 2011 4th International Conference on Biomedical Engineering and Informatics (BMEI).

[15]  Chris D. Nugent,et al.  Ontological user modelling and semantic rule-based reasoning for personalisation of Help-On-Demand services in pervasive environments , 2014, Future Gener. Comput. Syst..

[16]  Rabih Bashroush,et al.  Activities of daily life recognition using process representation modelling to support intention analysis , 2015, Int. J. Pervasive Comput. Commun..

[17]  Sunitha Abburu,et al.  A Survey on Ontology Reasoners and Comparison , 2012 .

[18]  Jin Guo,et al.  Ambient Intelligence Based Context-Aware Assistive System to Improve Independence for People with Autism Spectrum Disorder , 2016, 2016 49th Hawaii International Conference on System Sciences (HICSS).

[19]  Chris D. Nugent,et al.  A Knowledge-Driven Approach to Activity Recognition in Smart Homes , 2012, IEEE Transactions on Knowledge and Data Engineering.

[20]  Gregory M. P. O'Hare,et al.  Dynamic sensor event segmentation for real-time activity recognition in a smart home context , 2014, Personal and Ubiquitous Computing.

[21]  Nicolette de Keizer,et al.  Comparison of reasoners for large ontologies in the OWL 2 EL profile , 2011, Semantic Web.

[22]  Roy Sterritt,et al.  Dynamic Sensor Data Segmentation for Real- time Activity Recognition , 2011 .

[23]  Rosario Culmone,et al.  Human Activity Recognition using a Semantic Ontology-Based Framework , 2015 .

[24]  Claudio Bettini,et al.  OWL 2 modeling and reasoning with complex human activities , 2011, Pervasive Mob. Comput..

[25]  Liming Chen,et al.  Dynamic sensor data segmentation for real-time knowledge-driven activity recognition , 2014, Pervasive Mob. Comput..

[26]  Liming Chen,et al.  A Hybrid Ontological and Temporal Approach for Composite Activity Modelling , 2012, 2012 IEEE 11th International Conference on Trust, Security and Privacy in Computing and Communications.

[27]  Chris D. Nugent,et al.  Ontology-based Activity Recognition Framework and Services , 2013, IIWAS '13.

[28]  Nicolette de Keizer,et al.  A Survey on Ontology Reasoners and Comparison , 2016 .

[29]  Cristiano Premebida,et al.  Probabilistic human daily activity recognition towards robot-assisted living , 2015, 2015 24th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN).

[30]  Bernardo Cuenca Grau,et al.  History Matters: Incremental Ontology Reasoning Using Modules , 2007, ISWC/ASWC.

[31]  Liming Chen,et al.  Towards a Mobile Assistive System Using Service-Oriented Architecture , 2016, 2016 IEEE Symposium on Service-Oriented System Engineering (SOSE).

[32]  Liming Chen,et al.  Towards a Service-Oriented Architecture for a Mobile Assistive System with Real-time Environmental Sensing , 2016 .