An explainable multimodal deep learning approach for stress detection in emotion-aware systems

Read full text Summarise with VIRAT
Authors: Sai H. Prajwal, Sofia Singh, Deepti P. Theng
Cited by: 0
References: 18

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

We propose a continuous stress-detection pipeline that integrates wavelet-based heart-rate-variability (HRV) features with behavioural signals in a staged ensemble. The method computes time-resolved HRV spectral indices (VLF/LF/HF) using wavelet decomposition and incorporates them with behavioural descriptors before training a Random-Forest-based ensemble on the fused feature set. Post-hoc SHAP analysis yields both dataset-level importance rankings and instance-level attributions, enabling clinicians and end users to interpret the rationale underlying each prediction. Evaluated on the WESAD dataset ( N =15; ECG sampled at 700 Hz; session duration ≈35–40 min), the system achieved 83.0% accuracy on a held-out test split. SHAP consistently highlighted LF and HF approximate power as dominant predictors, while the wavelet plots revealed short-term spectral fluctuations aligned with well-known stress episodes, reinforcing the physiological validity of the reported findings.

Fields of Study & Subjects

Emotion and Mood Recognition Heart Rate Variability and Autonomic Control ECG Monitoring and Analysis

Publication details

Journal / source
Discover Applied Sciences
Volume
8
Issue
5
Publication date
21 March 2026
Language
EN