# Stress Classification from ECG Signals Using Vision Transformer

arXiv: https://arxiv.org/abs/2603.26721 · HTML: https://mlsanity.com/paper/2603.26721/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 38 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations](https://mlsanity.com/paper/2106.01548/) (2021)
- [Self-supervised ECG Representation Learning for Emotion Recognition](https://mlsanity.com/paper/2002.03898/) (2020)
- [Delving Deep into the Generalization of Vision Transformers under Distribution Shifts](https://mlsanity.com/paper/2106.07617/) (2021)
- [A Transformer Architecture for Stress Detection from ECG](https://mlsanity.com/paper/2108.09737/) (2021)
- [Transformer-Based Self-Supervised Learning for Emotion Recognition](https://mlsanity.com/paper/2204.05103/) (2022)
- [A Survey on Physiological Signal Based Emotion Recognition](https://mlsanity.com/paper/2205.10466/) (2022)
- [DeepBreath: Deep Learning of Breathing Patterns for Automatic Stress Recognition using Low-Cost Thermal Imaging in Unconstrained Settings](https://mlsanity.com/paper/1708.06026/) (2017)
- [StressNAS: Affect State and Stress Detection Using Neural Architecture Search](https://mlsanity.com/paper/2108.12502/) (2021)
- [Multi-level Stress Assessment Using Multi-domain Fusion of ECG Signal](https://mlsanity.com/paper/2008.05503/) (2020)
- [Multi-level Stress Assessment from ECG in a Virtual Reality Environment using Multimodal Fusion](https://mlsanity.com/paper/2107.04566/) (2021)

## Built on by (most cited first, 1 of 1)

- [Artifact Annotations Partially Substitute for Per-User Calibration: SAFE-EDA and a Normalization-Controlled Evaluation of Wrist-EDA Affect Recognition](https://mlsanity.com/paper/2610.01692/) (2026)

## Abstract (arXiv)

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.