Home > Research > Publications & Outputs > Inferring contexts from human activities in sma...
View graph of relations

Inferring contexts from human activities in smart spaces

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Publication date2016
Host publication29th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2016
EditorsZdravko Markov, Ingrid Russell
Place of PublicationPalo Alto
Number of pages6
ISBN (print)9781577357568
<mark>Original language</mark>English


Modeling and simulation of human activities is becoming a hot research area for validating activity recognition algorithms used to generate useful synthetic datasets for assistive environments and other smart spaces. Context-driven simulation, an emerging approach that utilizes abstract structures of state spaces (contexts), can enhance the scalability and realism of simulations. However, the context-driven approach is demanding of users' efforts in specifying not only activity models, but also the corresponding contexts and contextual transitions associated with these activities. In this paper, we propose a method to reduce users' efforts in configuring simulation by using &-means clustering and principal component analysis approaches to automate the derivation of contexts from a given set of activities. We validate our approach by comparing the actual sequenced activities with the derived sequenced activities. Copyright © 2016, Association for the Advancement of Artificial Intelligence (www.aaai.org). All right reserved.