Transition-Aware Human Activity Recognition Using Smartphones

详细信息    查看全文

• 作者：Jorge-L. Reyes-Ortiz^a ; ^b ; ^{jorge.reyes.ortiz@smartlab.ws" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Luca Oneto^c ; ^{Luca.Oneto@unige.it" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Albert Samà ; ^b ; ^{albert.sama@upc.edu" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Xavier Parra^b ; ^{xavier.parra@upc.edu" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Davide Anguita^a ; ^{Davide.Anguita@unige.it" class="auth_mail" title="E-mail the corresponding author}Author Vitae
• 关键词：Activity Recognition ; Smartphones ; Transitions ; Support Vector Machines ; Machine learning
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：1 January 2016
• 年：2016
• 卷：171
• 期：Complete
• 页码：754-767
• 全文大小：1272 K

文摘

This work presents the Transition-Aware Human Activity Recognition (TAHAR) system architecture for the recognition of physical activities using smartphones. It targets real-time classification with a collection of inertial sensors while addressing issues regarding the occurrence of transitions between activities and unknown activities to the learning algorithm. We propose two implementations of the architecture which differ in their prediction technique as they deal with transitions either by directly learning them or by considering them as unknown activities. This is accomplished by combining the probabilistic output of consecutive activity predictions of a Support Vector Machine (SVM) with a heuristic filtering approach. The architecture is validated over three case studies that involve data from people performing a broad spectrum of activities (up to 33), while carrying smartphones or wearable sensors. Results show that TAHAR outperforms state-of-the-art baseline works and reveal the main advantages of the architecture.