An Algorithm for On-Sensor Agnostic Detection of Changes in Human Activity for Ultra-Low-Power Applications

TL;DR

This paper introduces a lightweight, on-sensor change-detection algorithm for human activity recognition that significantly reduces energy consumption by activating the full HAR network only when activity changes are detected.

Contribution

It presents a non-parametric, calibration-free change-detection gate that operates efficiently on low-power devices without prior activity class definitions.

Findings

Reduces computational load by over 67% in realistic settings.

Achieves 98% sensitivity and 75% specificity on UCA-EHAR dataset.

Demonstrates robustness across multiple device types and datasets.

Abstract

Wearable devices running Human Activity Recognition(HAR) on Inertial Measurement Units~(IMUs) waste energy by performing continuous classification for each window, even during long periods of unchanged activity. We address this with a lightweight change-detection gate: a non-parametric algorithm based on dynamic template matching that runs continuously at only approximately 16kFLOPs per step, requires no offline training, and does not need prior definition of target activity classes. The gate invokes the full HAR network only when it detects an activity change, reducing the computational load by over 67% in realistic monitoring settings. The algorithm is evaluated on smart glasses, smartwatch, and smartphone data, requiring only a brief device-specific calibration phase. The gate achieves 98% sensitivity on UCA-EHAR, ensuring no genuine activity transition is missed, while 75% specificity keeps unnecessary HAR invocations low. Results on WISDM are 97% sensitivity and 76% specificity, demonstrating robustness and flexibility to various settings.