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{191875,
        author = {Manish Ladke and Aryan Mane and Rudrali Kalyane and Prapti Mahadik Patil and Rupali Jadhav},
        title = {CalmPulse: A Wearable Device and ML-Based Framework for Real-Time Panic Attack Detection and Intervention},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {9028-9032},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=191875},
        abstract = {symptoms like rapid heartbeat and shortness of breath. Detecting and managing these attacks quickly is very important, but existing methods often fail to give real-time help. This paper presents Calm Pulse; an affordable wearable device developed for real-time panic attack detection and intervention. It uses an ESP32 microcontroller and a HW-827 heart rate sensor to continuously record heart rate data. A Random Forest machine learning model, trained in Python and deployed through TensorFlow Lite, analyzes this data to detect panic attacks accurately. The results are shared with a Streamlit application, which provides users with real-time visuals and calming support like guided breathing and motivational messages. The system achieved around 90–95% accuracy in identifying panic conditions. Future improvements will include additional sensors, cloud analytics, and an AI chatbot for mental health support.},
        keywords = {Panic attack detection, wearable device, ESP32, heart rate sensor, machine learning, Random Forest, Internet of Things, Streamlit, biofeedback, mental health support.},
        month = {January},
        }