IDMatchHAR: Semi-Supervised Learning for Sensor-Based Human Activity Recognition Using Pretraining

Abstract

In sensor-based human activity recognition (HAR), the annotation cost for sensor data is higher compared to data, such as images. One can use semisupervised learning (semi-SL) to reduce annotation costs. This method lever-ages unlabeled datasets by assigning pseudolabels. How- ever, these methods have the issue of confirmation bias, where performance degrades due to incorrect pseudolabels. Some approaches have attempted to solve this problem by performing multistage pretraining with labeled and unlabeled data, but these methods require significant computational resources. We propose a framework called IDMatchHAR, which performs semi-SL with a single-stage pretraining process on small-scale datasets. We use instance discrimination (ID) during pretraining to learn robust feature representations applied to the subsequent semi-SL task. We verify the effectiveness of the proposed framework using various convolutional neural networks (CNNs), such as VGG and residual network (ResNet), as well as Transformers, on HASC, WISDM, and Pamap2. Our proposed framework significantly reduces the computational cost of pretraining while demonstrating performance comparable to or exceeding that of existing semi-SL methods.