Modeling interaction in multi-resident activities

详细信息    查看全文

• 作者：Asma Benmansour^aAuthor Vitae ; Abdelhamid Bouchachia^b ; ^{abouchachia@bournemouth.ac.uk}Author Vitae ; Mohammed Feham^aAuthor Vitae
• 关键词：Activity recognition ; Multiple residents ; Cooperative and parallel activities ; Graphical models
• 刊名：Neurocomputing
• 出版年：2017
• 出版时间：22 March 2017
• 年：2017
• 卷：230
• 期：Complete
• 页码：133-142
• 全文大小：431 K
• 卷排序：230

文摘

In this paper we investigate the problem of modeling multi-resident activities. Specifically, we explore different approaches based on Hidden Markov Models (HMMs) to deal with parallel activities and cooperative activities. We propose an HMM-based method, called CL-HMM, where activity labels as well as observation labels of different residents are combined to generate the corresponding sequence of activities as well as the corresponding sequence of observations on which a conventional HMM is applied. We also propose a Linked HMM (LHMM) in which activities of all residents are linked at each time step. We compare these two models to baseline models which are Coupled HMM (CHMM) and Parallel HMM (PHMM). The experimental results show that the proposed models outperform CHMM and PHMM when tested on parallel and cooperative activities.