Human Activity Recognition from the Acceleration Data of a Wearable Device. Which Features Are More Relevant by Activities?

Proceedings

Irvine, Naomi¹  Espinilla, Macarena²  Medina, Javier³  Donnelly, Mark⁴  Salguero, Alberto⁵ 

[1]Author to whom correspondence should be addressed.

[2]Department of Computer Science, University of Jaen, 23071 Jaén, Spain

[3]Department of Computer Science. University of Cadiz, 11001 Cádiz, Spain

[4]Presented at the 12th International Conference on Ubiquitous Computing and Ambient Intelligence (UCAmI 2018), Punta Cana, Dominican Republic, 4–7 December 2018

[5]School of Computing, Ulster University. County Antrim BT37 0QB, UK

关键词: activity recognition;    wearable devices;    acceleration;    feature selection;    classification;   

DOI  :  10.3390/proceedings2191242

学科分类：社会科学、人文和艺术（综合）

来源: mdpi

【 摘 要 】

Data driven approaches for human activity recognition learn from pre-existent large-scale datasets to generate a classification algorithm that can recognize target activities. Typically, several activities are represented within such datasets, characterized by multiple features that are computed from sensor devices. Often, some features are found to be more relevant to particular activities, which can lead to the classification algorithm providing less accuracy in detecting the activity where such features are not so relevant. This work presents an experimentation for human activity recognition with features derived from the acceleration data of a wearable device. Specifically, this work analyzes which features are most relevant for each activity and furthermore investigates which classifier provides the best accuracy with those features. The results obtained indicate that the best classifier is the k-nearest neighbor and furthermore, confirms that there do exist redundant features that generally introduce noise into the classification, leading to decreased accuracy.

【 授权许可】

CC BY