Activity Recognition Using Complex Network Analysis

• Published in: IEEE journal of biomedical and health informatics Vol. 22; no. 4; pp. 989 - 1000
• Main Authors: Jalloul, Nahed, Poree, Fabienne, Viardot, Geoffrey, L' Hostis, Phillipe, Carrault, Guy
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.07.2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); Institute of Electrical and Electronics Engineers
• Subjects: Accelerometers; Activity classification; Activity recognition; Bioengineering; Biomedical measurement; body sensor network; Classification; complex network analysis; Complex networks; Correlation; Data processing; Engineering Sciences; Life Sciences; Modules; Monitoring; Monitoring systems; Neck; Network analysis; Protocols; Sensors; Signal and Image processing; Thigh; wearable sensors; wearable sensors; activity classification; complex network analysis; body sensor network
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2017.2762404

In this paper, we perform complex network analysis on a connectivity dataset retrieved from a monitoring system in order to classify simple daily activities. The monitoring system is composed of a set of wearable sensing modules positioned on the subject's body and the connectivity data consists of the correlation between each pair of modules. A number of network measures are then computed followed by the application of statistical significance and feature selection methods. These methods were implemented for the purpose of reducing the total number of modules in the monitoring system required to provide accurate activity classification. The obtained results show that an overall accuracy of 84.6% for activity classification is achieved, using a random forest classifier, and when considering a monitoring system composed of only two modules positioned at the neck and thigh of the subject's body.