Continual learning in inertial measurement unit-based human activity recognition with user-centric class-incremental learning scenario

• Published in: Expert systems with applications Vol. 280; p. 127469
• Main Authors: Kanoga, Suguru, Tsukiji, Yuya, Karakida, Ryo
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 25.06.2025
• Subjects: Class-incremental learning; Continual learning; Human activity recognition; Inertial measurement unit; Neural network; Neural network; Inertial measurement unit; Human activity recognition; Continual learning; Class-incremental learning
• ISSN: 0957-4174
• DOI: 10.1016/j.eswa.2025.127469

The development of neural networks and wearable sensing technologies has increased the focus on modules for human activity recognition (HAR) using inertial measurement units (IMUs). Updating a pre-trained network has the potential to enhance user-centric interfaces. However, updating the network parameters with new class data can lead to catastrophic forgetting. Continual learning (CL) methods have been proposed to address this issue. The amount of new class data from the user (target subject) is considerably small compared to the amount of existing class data from the pre-measured subjects that are used for pre-training the network. The efficiency of CL methods in IMU-based HAR with user-centric class-incremental learning (Class-IL) scenarios is unclear. Thus, we compared 12 CL methods employing the regularization, architectural, and replay approaches. The evaluation was performed using five well-known IMU-based HAR datasets. Among the three approaches, the replay-based methods effectively prevented forgetting in IMU-based HAR, even with a small amount of data, by providing several samples per class. Moreover, in some cases, hybrid regularization and replay methods performed better than replay-based methods. The findings of this study highlight the challenging nature of suppressing forgetting in the Class-IL scenario, particularly when incrementally incorporating a limited amount of new class data from a target subject. Our future work will focus on the development of a hybrid method for IMU-based HAR with online user-centric Class-IL scenarios. •Comparative analysis of 12 continual learning methods for IMU-based HAR.•Replay-based methods, ER and BIR, outperform regularization in Class-IL scenarios.•Addressing catastrophic forgetting when updating pre-trained models with new user data.•Hybrid methods, like FROMP and BIR-SI, rival pure replay-based approaches in Class-IL.•Results guide future hybrid continual learning methods for user-centric IMU-based HAR.