Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{174998,
        author = {neeraj damisetti and Chandra Mouli dasyam and Siva Ganesh Mailavrapu and Lakshmi Pavani Kusumanchi and Joshua Hamsa and Rajeshwari chintamneedi},
        title = {Continuous Stress Monitoring Using Attention-Based Deep Learning on Physiological Data},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {1278-1283},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=174998},
        abstract = {This paper presents an approach for detecting stress using electrocardiogram (ECG) signals by combining machine learning and deep learning techniques. By integrating XGBoost, long short-term Memory (LSTM), and transformer models, the system uncovers intricate patterns in heart activity to identify stress levels accurately. Designed for real-time analysis, this method processes ECG signals to detect stress responses efficiently. XGBoost provides reliable feature-based classification, whereas LSTM and transformer models specialize in capturing long-term dependencies in time-series data. By combining these strengths, the ensemble model enhances the prediction accuracy beyond what individual models can achieve. This research paves the way for smarter stress monitoring solutions, contributing to proactive mental health care and early intervention strategies.},
        keywords = {Stress detection, real-time stress detection, deep learning, ensemble learning, electrocardiography (ECG), hybrid model.},
        month = {April},
        }