CACE: Exploiting Behavioral Interactions for Improved Activity Recognition in Multi-Inhabitant Smart Homes

Author/Creator ORCID

Date

2016-08-11

Department

Program

Citation of Original Publication

M. A. U. Alam, N. Roy, A. Misra and J. Taylor, "CACE: Exploiting Behavioral Interactions for Improved Activity Recognition in Multi-inhabitant Smart Homes," 2016 IEEE 36th International Conference on Distributed Computing Systems (ICDCS), Nara, 2016, pp. 539-548

Rights

This item may be protected under Title 17 of the U.S. Copyright Law. It is made available by UMBC for non-commercial research and education. For permission to publish or reproduce, please contact the author.

Abstract

We propose CACE (Constraints And Correlations mining Engine) which investigates the challenges of improving the recognition of complex daily activities in multi-inhabitant smart homes, by better exploiting the spatiotemporal relationships across the activities of different individuals. We first propose and develop a loosely-coupled Hierarchical Dynamic Bayesian Network (HDBN), which both (a) captures the hierarchical inference of complex (macro-activity) contexts from lower-layer microactivity context (postural and improved oral gestural context), and (b) embeds the various types of behavioral correlations and constraints (at both micro-and macro-activity contexts) across the individuals. While this model is rich in terms of accuracy, it is computationally prohibitive, due to the explosive increase in the number of jointly-defined states. To tackle this challenge, we employ data mining to learn behaviorally-driven context correlations in the form of association rules, we then use such rules to prune the state space dramatically. To evaluate our framework, we build a customized smart home system and collected naturalistic multi-inhabitant smart home activities data. The system performance is illustrated with results from real-time system deployment experiences in a smart home environment reveals a radical (max 16 fold) reduction in the computational overhead compared to traditional hybrid classification approaches, as well as an improved activity recognition accuracy of max 95%.