Stress Classification from ECG Signals Using Vision Transformer

TL;DR

This paper introduces a vision transformer-based method for stress classification from ECG spectrograms, outperforming CNNs and previous methods in intersubject variability handling and accuracy.

Contribution

The study demonstrates the effectiveness of vision transformers on ECG-based stress assessment, addressing intersubject variability without handcrafted features.

Findings

Vision transformer outperforms CNN models in stress classification.

Achieved 71.01% and 76.7% accuracy on RML and WESAD datasets for three-class classification.

Achieved 88.3% accuracy for binary classification on WESAD.

Abstract

Vision Transformers have shown tremendous success in numerous computer vision applications; however, they have not been exploited for stress assessment using physiological signals such as Electrocardiogram (ECG). In order to get the maximum benefit from the vision transformer for multilevel stress assessment, in this paper, we transform the raw ECG data into 2D spectrograms using short time Fourier transform (STFT). These spectrograms are divided into patches for feeding to the transformer encoder. We also perform experiments with 1D CNN and ResNet-18 (CNN model). We perform leave-onesubject-out cross validation (LOSOCV) experiments on WESAD and Ryerson Multimedia Lab (RML) dataset. One of the biggest challenges of LOSOCV based experiments is to tackle the problem of intersubject variability. In this research, we address the issue of intersubject variability and show our success using 2D spectrograms and the attention mechanism of transformer. Experiments show that vision transformer handles the effect of intersubject variability much better than CNN-based models and beats all previous state-of-the-art methods by a considerable margin. Moreover, our method is end-to-end, does not require handcrafted features, and can learn robust representations. The proposed method achieved 71.01% and 76.7% accuracies with RML dataset and WESAD dataset respectively for three class classification and 88.3% for binary classification on WESAD.