ConvSNN: an energy-efficient hybrid convolutional-spiking neural network for wrist-worn stress and affective state recognition

Continuous stress monitoring on wrist-worn devices matters for real-time affective computing, digital health, and personalized well-being, yet it remains difficult because a wearable model must operate with few sensors, little compute, and a tight energy budget. Chest-mounted systems can draw on high signal-to-noise signals such as ECG, EMG, and respiration, but a wrist device captures only blood-volume pulse, electrodermal activity, skin temperature, and accelerometry, which makes accurate and efficient stress recognition harder. This study presents ConvSNN, a hybrid convolutional–spiking neural network for multimodal affective recognition from wrist-worn physiological signals.

ConvSNN pairs a compact four-stage 1D convolutional backbone with a time-to-first-spike (TTFS) classification head that reads aggregated rate-coded and time-coded spike statistics to keep predictions stable. It also adds a spiking confidence gate for uncertainty-aware window acceptance and a temperature-scaling step for probability calibration. We evaluate ConvSNN on the WESAD benchmark using only the six wrist channels of the Empatica E4 wearable (blood-volume pulse, electrodermal activity, skin temperature, and three-axis accelerometry).

Under random 85/15 split evaluation it reaches a mean accuracy of 98.07% with a macro-F1 of 0.977 across five random seeds. Under strict leave-one-subject-out (LOSO) cross-validation, ConvSNN reaches a mean accuracy of 94.0% with a macro-F1 of 0.932 over five seeds, which confirms strong subject-independent generalization and amounts to a 4.1-percentage-point drop from the random-split protocol. Temperature scaling lowers the expected calibration error from 0.149 to 0.017 with no change in accuracy, and the spiking confidence gate opens a 5.9-percentage-point accuracy gap between accepted and rejected windows, which supports principled abstention on low-confidence inputs.

Based on operation-count emulation, ConvSNN has an estimated per-inference energy of 48.31 \(\mu\)J at 5.70 ms latency, which points to low-power real-time use on smartwatch-class devices once it is validated on embedded hardware. Taken together, these results show that hybrid convolutional–spiking models can strike an effective balance among recognition performance, subject-independent robustness, calibrated confidence estimation, and energy-efficient deployment for continuous wrist-worn affective monitoring. The authors acknowledge the use of AI-based language-assistance tools, including the latest versions of Grammarly and Writefull for Overleaf, solely to refine the language and grammar of the manuscript (spelling, wording, and readability).

Department of Electrical and Computer Engineering, George Mason University, Fairfax, 22030, VA, USA College of Engineering and IT, University of Dubai, Dubai, UAE Software Engineering Department, Faculty of Informatics, Kaunas University of Technology, Kaunas, 51423, Lithuania Correspondence to Muhammad Zaheer Sajid. The authors declare no competing interests. The WESAD dataset used in this study is publicly available and was collected by its original providers under their respective ethics approvals.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material.