Wearable-based behaviour interpolation for semi-supervised human activity recognition

Abstract

While traditional feature engineering for Human Activity Recognition (HAR) involves a trial-anderror process, deep learning has emerged as a preferred method for high-level representations of sensor-based human activities. However, most deep learning-based HAR requires a large amount of labelled data and extracting HAR features from unlabelled data for effective deep learning training remains challenging. We, therefore, introduce a deep semi-supervised HAR approach, MixHAR, which concurrently uses labelled and unlabelled activities. Our MixHAR employs a linear interpolation mechanism to blend labelled and unlabelled activities while addressing both inter- and intra-activity variability. A unique challenge identified is the activityintrusion problem during mixing, for which we propose a mixing calibration mechanism to mitigate it in the feature embedding space. Additionally, we rigorously explored and evaluated the five conventional/popular deep semi-supervised technologies on HAR, acting as the benchmark of deep semi-supervised HAR. Our results demonstrate that MixHAR significantly improves performance, underscoring the potential of deep semi-supervised techniques in HAR.

References in corpus (4)

• Ensembles of Deep LSTM Learners for Activity Recognition using Wearables
• Multi-task Self-Supervised Learning for Human Activity Detection
• Machine learning approaches to understand the influence of urban environments on human's physiological response
• Human Activity Recognition with Low-Resolution Infrared Array Sensor Using Semi-supervised Cross-domain Neural Networks for Indoor Environment

Cited by in corpus (1)

• Machine Learning Techniques for Sensor-based Human Activity Recognition with Data Heterogeneity -- A Review