Context-aware mutual learning for semi-supervised human activity recognition using wearable sensors

With the increasing popularity of wearable sensors, deep-learning-based human activity recognition (HAR) has attracted great interest from both academic and industrial fields in recent years. Nevertheless, the performance of deep HAR methods highly depends on the quality and quantity of annotations that are not so prone to obtain in HAR. This practical concern raises broad research of semi-supervised HAR. Despite the brilliant achievements, there remain three important issues to be settled: aggravation of overfitting, deviation of distribution and ignorance of contextual information. This paper proposes a novel context-aware mutual learning method for semi-supervised HAR. Firstly, a semi-supervised mutual learning framework is introduced to alleviate the overfitting of single network. In this framework, the main and auxiliary networks are collaboratively trained with supervised information from each other. Secondly, the distribution-preserving loss, which minimizes the distance between the class distribution of predictions and that of labeled data, is proposed to hinder the deviation of the distribution. Finally, the contextual information from the neighbor sequences is adopted through a context-aware aggregation module. This module extracts richer information from a broader range of sequences. Our method is validated on four characteristic published human activity recognition datasets: UCI, WISDM, PAMAP2 and mHealth. The experimental result shows that the proposed method achieves superior performance compared with four typical methods in semi-supervised HAR.

Automated summary

This paper proposes a novel context-aware mutual learning method for semi-supervised human activity recognition. It introduces a semi-supervised mutual learning framework to alleviate the overfitting problem and proposes a distribution-preserving loss to hinder distribution deviation. It also adopts contextual information through a context-aware aggregation module. Experimental results show that the proposed method outperforms four typical methods in semi-supervised human activity recognition.