Key result
A contrastive self-supervised learning model based on the SimCLR framework improved stress detection accuracy from ECG data by 9% on the WESAD dataset and 3.7% on the RML dataset compared to SOTA models.
Why the study?
Most ECG-based stress assessment models rely on manually-annotated data, with limited research using self-supervised learning approaches and none utilizing contrastive self-supervised learning.
Does a contrastive self-supervised learning model improve stress detection accuracy from ECG data compared to state-of-the-art SSL models?
Does a contrastive self-supervised learning model improve stress detection accuracy from ECG data compared to state-of-the-art SSL models?
A contrastive self-supervised learning approach improves the accuracy of ECG-based stress detection compared to existing self-supervised models, potentially enhancing wearable health monitoring.
Answers are grounded in this paper and cite their sources.
May advance ECG-based stress monitoring tools; leaves open clinical validation before practice adoption.
In recent literature, ECG-based stress assessment has become popular due to its proven correlation to stress and increased accessibility of ECG data through commodity hardware. However, most ECG-based stress assessment models use supervised learning, relying on manually-annotated data. Limited research is done in the area of self-supervised learning (SSL) approaches that leverage unlabelled data and none that utilize contrastive SSL. However, with the dominance of contrastive SSL in domains such as computer vision, it is essential to see if the same excellence in performance can be obtained on an ECG-based stress assessment dataset. In this paper, we propose a contrastive SSL model for stress assessment using ECG signals based on the SimCLR framework. We test our model on two ECG-based stress assessment datasets. We show that our proposed solution results in a 9% improvement in accuracy on the WESAD dataset and 3.7% on the RML dataset when compared with SOTA ECG-based SSL models for stress assessment. The development of more accurate stress assessment models, particularly those that employ non-invasive data such as ECG for assessment, leads to developments in wearable technology and the creation of better health monitoring applications in areas such as stress management and relaxation therapy.
No takes yet. Share an insight, caveat, or question.
Rabbani et al. (2022) studied Stress. Contrastive self-supervised learning model based on SimCLR framework vs. State-of-the-art ECG-based SSL models was evaluated on Accuracy (9% improvement on WESAD and 3.7% on RML). A contrastive self-supervised learning model based on the SimCLR framework improved stress detection accuracy from ECG data by 9% on the WESAD dataset and 3.7% on the RML dataset compared to SOTA models.
Synapse has enriched 10 related papers. Consider them for comparative context: