An Information Gain-Based Model and an Attention-Based RNN for Wearable Human Activity Recognition

Leyuan Liu; Jian He; Keyan Ren; Jonathan Lungu; Yibin Hou; Ruihai Dong

doi:10.3390/e23121635

An Information Gain-Based Model and an Attention-Based RNN for Wearable Human Activity Recognition

Entropy (Basel). 2021 Dec 6;23(12):1635. doi: 10.3390/e23121635.

Authors

Leyuan Liu¹, Jian He^{1

2}, Keyan Ren^{1

2}, Jonathan Lungu¹, Yibin Hou^{1

2}, Ruihai Dong³

Affiliations

¹ Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.
² Beijing Engineering Research Center for IOT Software and Systems, Beijing University of Technology, Beijing 100124, China.
³ School of Computer Science, University College Dublin, D04 V1W8 Dublin 4, Ireland.

Abstract

Wearable sensor-based HAR (human activity recognition) is a popular human activity perception method. However, due to the lack of a unified human activity model, the number and positions of sensors in the existing wearable HAR systems are not the same, which affects the promotion and application. In this paper, an information gain-based human activity model is established, and an attention-based recurrent neural network (namely Attention-RNN) for human activity recognition is designed. Besides, the attention-RNN, which combines bidirectional long short-term memory (BiLSTM) with attention mechanism, was tested on the UCI opportunity challenge dataset. Experiments prove that the proposed human activity model provides guidance for the deployment location of sensors and provides a basis for the selection of the number of sensors, which can reduce the number of sensors used to achieve the same classification effect. In addition, experiments show that the proposed Attention-RNN achieves F1 scores of 0.898 and 0.911 in the ML (Modes of Locomotion) task and GR (Gesture Recognition) task, respectively.

Keywords: Attention-RNN; attention mechanism; human activity recognition; information gain.