Tracking and behavior augmented activity recognition for multiple inhabitants

• Main Authors: UL ALAM, Mohammad Arif, ROY, Nirmalya, MISRA, Archan
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: Multiple inhabitants; multi-modal sensing; scalable activity recognition; tracking; Numerical Analysis and Scientific Computing; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/6907
• Institution: Singapore Management University

We develop CACE (Constraints And Correlations mining Engine), a framework that significantly improves the recognition accuracy of complex daily activities in multi-inhabitant smarthomes. CACE views the implicit relationships between the activities of multiple people as an asset, and exploits such constraints and correlations in a hierarchical fashion, taking advantage of both person-specific sensor data (generated by wearable devices) and person-independent ambient sensor data (generated by ambient sensors). To effectively utilize such couplings, CACE first uses a multi-target particle filtering approach over ambient sensors captured movement data, to identify the number of distinct users and infer individual-specific movement trajectories. We then utilize a Hierarchical Dynamic Bayesian Network (HDBN)-based model for activity recognition. This model utilizes the inter-and-intra individual correlations and constraints, at both micro-activity and macro-activity levels, to recognize individual activities accurately. These constraints are learnt automatically using data-mining techniques, and help to dramatically reduce the computational complexity of HDBN-based inferencing. Empirical studies using a real-world testbed of five multi-inhabitant smarthomes shows that CACE is able to achieve an activity recognition accuracy of approximate to 95%, with a 16-fold reduction in computational overhead compared to traditional hybrid classification approaches.