Paperdoi:10.48550/arxiv.2604.26078
PPG-based affect recognition with long-range deep models: a measurement-driven comparison of CNN, Transformer and Mamba architectures
arXiv 2604.26078 (2026-04-28)
TL;DR
Compares CNN, CNN-LSTM, Transformer and Mamba for arousal, valence and relaxation classification from wrist PPG under subject-independent 5-fold CV with identical pipelines. Transformer and Mamba match but do not consistently beat the CNN; CNN is best overall with the smallest model; Transformers balance F1 better for arousal and relaxation. Dataset not named in the abstract; no numbers in the abstract.
- Form factor: wrist
Abstract
Photoplethysmography (PPG) is increasingly used in wearable affective computing due to its low cost and ease of integration into consumer devices. Recent advances in deep learning have introduced long-range sequence models, such as Transformers, and state-space models, like Mamba, which have demonstrated strong performance on natural language and general time-series tasks. However, it remains unclear whether these architectures offer tangible benefits over widely used Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTMs) for PPG-based affect recognition, given that datasets are typically small and noisy. This work presents a measurement-driven comparison of four deep learning architectures, CNN, CNN-LSTM hybrid, Transformers, and Mamba, for classifying arousal, valence, and relaxation states from wrist-based PPG signals. All models are evaluated under a subject-independent 5-fold cross-validation protocol using identical preprocessing, segmentation, and training pipelines. Our results show that the Transformer and Mamba models achieve performance comparable to that of a CNN baseline, but do not consistently outperform it across all tasks. CNNs remain the most effective overall, providing the highest accuracy with the smallest model size, whereas Transformers have a better balance of F1 scores for Arousal and Relaxation. The study provides the first evaluation of Transformer and Mamba models for PPG-based affect recognition, offering practical guidance on model selection for wearable affective monitoring systems.
Verbatim from DataCite (opens in a new tab) · Licence: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
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
Alghoul, K., Al Osman, H., & Saddik, A. E. (2026). PPG-based affect recognition with long-range deep models: a measurement-driven comparison of CNN, Transformer and Mamba architectures. arXiv 2604.26078. https://doi.org/10.48550/arxiv.2604.26078
Alghoul, Karim, Hussein Al Osman, and Abdulmotaleb El Saddik. 2026. "PPG-based affect recognition with long-range deep models: a measurement-driven comparison of CNN, Transformer and Mamba architectures." arXiv 2604.26078. https://doi.org/10.48550/arxiv.2604.26078.
Alghoul, K., Al Osman, H. and Saddik, A. E. (2026) 'PPG-based affect recognition with long-range deep models: a measurement-driven comparison of CNN, Transformer and Mamba architectures', arXiv 2604.26078. doi: 10.48550/arxiv.2604.26078.
Alghoul, Karim, et al. "PPG-based affect recognition with long-range deep models: a measurement-driven comparison of CNN, Transformer and Mamba architectures." arXiv 2604.26078, 2026. https://doi.org/10.48550/arxiv.2604.26078.
K. Alghoul, H. Al Osman, and A. E. Saddik, "PPG-based affect recognition with long-range deep models: a measurement-driven comparison of CNN, Transformer and Mamba architectures," arXiv 2604.26078, 2026, doi: 10.48550/arxiv.2604.26078.
@misc{alghoul2026ppgbased,
title = {{PPG-based affect recognition with long-range deep models: a measurement-driven comparison of CNN, Transformer and Mamba architectures}},
author = {Alghoul, Karim and Al Osman, Hussein and Saddik, Abdulmotaleb El},
year = {2026},
howpublished = {arXiv 2604.26078},
doi = {10.48550/arxiv.2604.26078}
}Added to the ChatPPG research hub
