Paperdoi:10.1109/icce70609.2026.11658479
Lightweight PPG-Based Drowsiness Detection: A Multi-Domain Feature Ablation and Computational Analysis
IEEE ICCE 2026 (2026-07-01)
TL;DR
Random Forest drowsiness detector on PPG features from four domains (time, frequency, wavelet, nonlinear), ablating 15 combinations. Best F1 0.601 (time + wavelet + nonlinear); full 4-domain recall 0.775. Nonlinear feature extraction costs 245.2 ms, ~500× the model inference (0.5 ms, 0.3 MB).
- Form factor: unspecified
Abstract
Photoplethysmography (PPG) is an effective noninvasive approach to detect drowsiness and cognitive impairment. Given its compatibility with wearable and edge devices, this method is increasingly adopted in environments requiring continuous monitoring, such as driving and high-intensity workloads. However, existing studies lack a systematic evaluation of individual feature domain contributions and do not adequately address the feasibility of deployment on resource-constrained hardware. This study proposes a multi-domain feature extraction pipeline comprising four domains (time, frequency, wavelet, and nonlinear), coupled with a Random Forest classifier for drowsiness detection. A comprehensive ablation study on 15 feature combinations is conducted to analyze the trade-off between classification performance and computational cost. Experimental results indicate that the 3-domain combination (time, wavelet, and nonlinear) achieves the highest F1-score (0.601), while the full 4-domain configuration yields a higher recall rate (0.775), making it more suitable for safety-critical applications. In particular, computational cost analysis indicates that the feature extraction phase constitutes the primary computational bottleneck of the system. Specifically, extracting nonlinear features alone consumes 245.2 ms, approximately 500 times more than the model’s inference time (0.5 ms with a memory footprint of 0.3 MB). These findings highlight the critical role of feature domain selection in practical deployment. Consequently, this study provides an empirical foundation for designing reliable and resource-optimized drowsiness detection systems on edge hardware platforms.
Verbatim from Semantic Scholar (opens in a new tab) · Abstract via Semantic Scholar; © the authors/publisher
Results on ChatPPG leaderboards
All leaderboardsNo results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.
Tasks & signals
Tasks
Signals
Keywords
How it works
Cite this paper
Tu, V. T., Hoang, T. M., & Huy, N. D. (2026). Lightweight PPG-Based Drowsiness Detection: A Multi-Domain Feature Ablation and Computational Analysis. IEEE ICCE 2026. https://doi.org/10.1109/icce70609.2026.11658479
Tu, Vu Trinh, Thang Manh Hoang, and Nguyen Duy Huy. 2026. "Lightweight PPG-Based Drowsiness Detection: A Multi-Domain Feature Ablation and Computational Analysis." IEEE ICCE 2026. https://doi.org/10.1109/icce70609.2026.11658479.
Tu, V. T., Hoang, T. M. and Huy, N. D. (2026) 'Lightweight PPG-Based Drowsiness Detection: A Multi-Domain Feature Ablation and Computational Analysis', IEEE ICCE 2026. doi: 10.1109/icce70609.2026.11658479.
Tu, Vu Trinh, et al. "Lightweight PPG-Based Drowsiness Detection: A Multi-Domain Feature Ablation and Computational Analysis." IEEE ICCE 2026, 2026. https://doi.org/10.1109/icce70609.2026.11658479.
V. T. Tu, T. M. Hoang, and N. D. Huy, "Lightweight PPG-Based Drowsiness Detection: A Multi-Domain Feature Ablation and Computational Analysis," IEEE ICCE 2026, 2026, doi: 10.1109/icce70609.2026.11658479.
@article{tu2026lightweight,
title = {{Lightweight PPG-Based Drowsiness Detection: A Multi-Domain Feature Ablation and Computational Analysis}},
author = {Tu, Vu Trinh and Hoang, Thang Manh and Huy, Nguyen Duy},
year = {2026},
journal = {IEEE ICCE 2026},
doi = {10.1109/icce70609.2026.11658479}
}Added to the ChatPPG research hub