CLAD-Net: Continual Activity Recognition in Multi-Sensor Wearable Systems Article Swipe

MAKE IMPACT

Reza Rahimi Azghan , Gautham Krishna Gudur , Mohit Malu , Edison Thomaz , Giulia Pedrielli , Pavan Turaga , Hassan Ghasemzadeh · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2509.23077

The rise of deep learning has greatly advanced human behavior monitoring using wearable sensors, particularly human activity recognition (HAR). While deep models have been widely studied, most assume stationary data distributions - an assumption often violated in real-world scenarios. For example, sensor data from one subject may differ significantly from another, leading to distribution shifts. In continual learning, this shift is framed as a sequence of tasks, each corresponding to a new subject. Such settings suffer from catastrophic forgetting, where prior knowledge deteriorates as new tasks are learned. This challenge is compounded by the scarcity and inconsistency of labeled data in human studies. To address these issues, we propose CLAD-Net (Continual Learning with Attention and Distillation), a framework enabling wearable-sensor models to be updated continuously without sacrificing performance on past tasks. CLAD-Net integrates a self-supervised transformer, acting as long-term memory, with a supervised Convolutional Neural Network (CNN) trained via knowledge distillation for activity classification. The transformer captures global activity patterns through cross-attention across body-mounted sensors, learning generalizable representations without labels. Meanwhile, the CNN leverages knowledge distillation to retain prior knowledge during subject-wise fine-tuning. On PAMAP2, CLAD-Net achieves 91.36 percent final accuracy with only 8.78 percent forgetting, surpassing memory-based and regularization-based baselines such as Experience Replay and Elastic Weight Consolidation. In semi-supervised settings with only 10-20 percent labeled data, CLAD-Net still delivers strong performance, demonstrating robustness to label scarcity. Ablation studies further validate each module's contribution.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2509.23077

PDF

https://arxiv.org/pdf/2509.23077

OA Status

green

OpenAlex ID

https://openalex.org/W4415332020

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4415332020

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2509.23077

Digital Object Identifier

Title

CLAD-Net: Continual Activity Recognition in Multi-Sensor Wearable Systems

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-09-27

Full publication date if available

Authors

Reza Rahimi Azghan, Gautham Krishna Gudur, Mohit Malu, Edison Thomaz, Giulia Pedrielli, Pavan Turaga, Hassan Ghasemzadeh

List of authors in order

Landing page

https://arxiv.org/abs/2509.23077

Publisher landing page

PDF URL

https://arxiv.org/pdf/2509.23077

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2509.23077

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload