An Autonomous Agent for Learning Spatiotemporal Models of Human Daily Activities

• Main Authors: Gao, Shan, Tan, Ah-Hwee
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2016
• Subjects: Activity pattern; spatiotemporal features; Fusion ART
• Online Access: https://hdl.handle.net/10356/81332; http://hdl.handle.net/10220/40734; http://www.ifaamas.org/proceedings.html
• Institution: Nanyang Technological University

Activities of Daily Living (ADLs) refer to activities performed by individuals on a daily basis. As ADLs are indicatives of a person's habits, lifestyle, and well being, learning the knowledge of people's ADL routine has great values in the healthcare and consumer domains. In this paper, we propose an autonomous agent, named Agent for Spatia-Temporal Activity Pattern Modeling (ASTAPM), being able to learn spatial and temporal patterns of human ADLs. ASTAPM utilises a self-organizing neural network model named Spatiotemporal - Adaptive Resonance Theory (ST-ART). ST-ART is capable of integrating multimodal contextual information, involving the time and space, wherein the ADL are performed. Empirical experiments have been conducted to assess the performance of ASTAPM in terms of accuracy and generalization.