%0 Conference Proceedings
%T Ontology Model for Spatio-Temporal Contexts in Smart Home Environments
%+ Department of Computer Science, Amrita Vishwa Vidyapeetham, Bangalore, India
%A Shrinidhi, L.
%A Kadiresan, Nalinadevi
%A Parameswaran, Latha
%Z Part 1: Machine Learning (ML), Deep Learning (DL), Internet of Things (IoT)
%< avec comité de lecture
%( IFIP Advances in Information and Communication Technology
%B 4th International Conference on Computational Intelligence in Data Science (ICCIDS)
%C Chennai, India
%Y Vallidevi Krishnamurthy
%Y Suresh Jaganathan
%Y Kanchana Rajaram
%Y Saraswathi Shunmuganathan
%I Springer International Publishing
%3 Computational Intelligence in Data Science
%V AICT-611
%P 113-124
%8 2021-03-18
%D 2021
%R 10.1007/978-3-030-92600-7_11
%K Ontology model
%K Sensor optimization
%K Spatio-temporal context
%K Smart home
%Z Computer Science [cs]Conference papers
%X Smart home environment supports in simplifying the daily routines of the residents by learning the repetitive tasks and automating the activities. Sensors provide an unobtrusive way of collecting the state change in the environment, residents and the objects. The numbers of sensors are directly proportional to the cost and power consumptions. The sensor to activity mapping can be used for various task in smart home environment like the sensor optimization and sensor placement. Though the data-driven methods are proven to provide accurate results for recognizing activities, it does not provide context information for sensor to activity mapping. This paper deals with identifying sensors used in an activity, based on the spatial and temporal contexts. An ontology model is developed for representing the real-time smart home sensor data. A rule-based reasoner is developed using SWRL and SQWRL to infer spatial and temporal contexts. In SWRL rules, spatial context provides insight on where an activity happens. This becomes vital when more than one activity takes place at two different places. Thereby, the sensors responsible for monitoring an activity during the occurrence of concurrent events are derived. Similarly, with the help of temporal information, the path covered by the user when performing an activity is traced. The results from the developed expert system serve as input for sensor optimization task.
%G English
%Z TC 12
%2 https://inria.hal.science/hal-03772941/document
%2 https://inria.hal.science/hal-03772941/file/512058_1_En_11_Chapter.pdf
%L hal-03772941
%U https://inria.hal.science/hal-03772941
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-AICT
%~ IFIP-TC
%~ IFIP-TC12
%~ IFIP-ICCIDS
%~ IFIP-AICT-611