Energy-efficient recognition of human activity in body sensor networks via compressed classification | Zendy

Ling Xiao | Zendy; Renfa Li | Zendy; Juan Luo | Zendy; Zhu Xiao | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Energy-efficient recognition of human activity in body sensor networks via compressed classification

Author(s) -

Ling Xiao,

Renfa Li,

Juan Luo,

Zhu Xiao

Publication year - 2016

Publication title -

international journal of distributed sensor networks

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.324

H-Index - 53

eISSN - 1550-1477

pISSN - 1550-1329

DOI - 10.1177/1550147716679668

Subject(s) - computer science , compressed sensing , random projection , wireless sensor network , sparse approximation , energy (signal processing) , projection (relational algebra) , wearable computer , energy consumption , artificial intelligence , pattern recognition (psychology) , sensor node , representation (politics) , node (physics) , activity recognition , wireless , key distribution in wireless sensor networks , embedded system , algorithm , wireless network , computer network , telecommunications , statistics , mathematics , ecology , structural engineering , politics , political science , law , biology , engineering

Energy efficiency is an important challenge to broad deployment of wireless body sensor networks for long-term physical movement monitoring. Inspired by theories of sparse representation and compressed sensing, the power-aware compressive classification approach SRC-DRP (sparse representation–based classification with distributed random projection) for activity recognition is proposed, which integrates data compressing and classification. Random projection as a data compression tool is individually implemented on each sensor node to reduce the amount of data for transmission. Compressive classification can be applied directly on the compressed samples received from all nodes. This method was validated on the Wearable Action Recognition Dataset and implemented on embedded nodes for offline and online experiments. It is shown that our method reduces energy consumption by approximately 20% while maintaining an activity recognition accuracy of 88% at a compression ratio of 0.5.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research