Key result
Depth-separable CNN using ECG signals achieves 99.9% accuracy in classifying stress states.
Why the study?
Accurate detection of stress is challenging due to its subjective nature.
Does a depth-separable convolutional neural network (DSCNN) model using continuous wavelet transform (CWT) on ECG signals accurately detect stress?
Does a depth-separable convolutional neural network (DSCNN) model using continuous wavelet transform (CWT) on ECG signals accurately detect stress?
A novel DSCNN model using continuous wavelet transform on ECG signals can highly accurately detect stress states without complex feature extraction.
Should not yet change clinical stress assessment; leaves open prospective validation in larger cohorts.
Stress is a natural response of the organism to challenging situations, but its accurate detection is challenging due to its subjective nature. This study proposes a model based on depth-separable convolutional neural networks (DSCNN) to analyze heart rate variability (HRV) and detect stress. Electrocardiogram (ECG) signals are pre-processed to remove noise and ensure data quality. The signals are then transformed into two-dimensional images using the continuous wavelet transform (CWT) to identify pattern recognition in the time–frequency domain. These representations are classified using the DSCNN model to determine the presence of stress. The methodology has been validated using the SWELL-KW dataset, achieving an accuracy of 99.9% by analyzing the variability in three states (neutral, time pressure, and interruptions) of the 25 samples in the experiment, scanning the acquired signal every 5 s for 45 min per state. The proposed approach is characterized by its ability to transform ECG signals into time–frequency representations by means of short duration sampling, achieving an accurate classification of stress states without the need for complex feature extraction processes. This model is an efficient and accurate tool for stress analysis from biomedical signals.
No takes yet. Share an insight, caveat, or question.
Mateo-Reyes et al. (2025) studied Stress (n=25). Depth-separable convolutional neural networks (DSCNN) with continuous wavelet transform (CWT) was evaluated on Accuracy of stress state classification. A depth-separable convolutional neural network model using continuous wavelet transform of ECG signals achieved 99.9% accuracy in classifying stress states.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: