Journal of ISMAC
IRO Journals
Volume 8 — Issue 1 — March 2026

Brainwave Monitoring and Stress Alert System with AI Smart Therapy

https://doi.org/10.36548/jismac.2026.1.002
Pages: 15-39
PDF
Babylatha M.
Department of Information Technology, Paavai Engineering College, Namakkal, Tamil Nadu, India
Manoj Kumar S.
Department of Information Technology, Paavai Engineering College, Namakkal, Tamil Nadu, India
Ganapathy R.
Department of Information Technology, Paavai Engineering College, Namakkal, Tamil Nadu, India
Giribalan G.
Department of Information Technology, Paavai Engineering College, Namakkal, Tamil Nadu, India
PDF

How to Cite

M., Babylatha, Manoj Kumar S., Ganapathy R., and Giribalan G. 2026. “Brainwave Monitoring and Stress Alert System With AI Smart Therapy”. Journal of ISMAC 8 (1): 15-39. https://doi.org/10.36548/jismac.2026.1.002.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

— EEG
— Stress Detection
— Anxiety Monitoring
— IoT
— ESP32
— Smart Therapy
— MLP
— CNN
— HRV
— Real-time Alert System
Published: 09-03-2026

Abstract

Anxiety and metal stress is the critical health challenges particularly for people with mental disabilities and unable to communicate effectively. The standard healthcare-based evaluations are inconsistent and failed to detect the early stress. This proposed work uses a wearable EEG-based monitoring system integrates Artificial Intelligence (AI) and Internet of Things (IoT) technologies to classify five mental states: normal, low stress, medium stress, high stress and anxiety. The EEG signals are collected from the wearable headband, preprocessed using band-pass and notch filtering which converted into physiological and statistical features such as mean, standard deviation, peak amplitude, entropy, heart rate and RR variance. Multilayer Perceptron (MLP) and Convolutional Neural Network (CNN) are the two models evaluated for classification performance. MLP used to implement low interference latency and stable performance on lightweight hardware in real-time. The classified mental states are transmitted to the healthcare people through cloud dashboard. When the critical states are detected, triggering the local SOS buzzer using ESP32. Additionally, the smart therapy is activated automatically to provide treatments. The experimental evaluation demonstrates the stress classification accuracy above 85% with real-time alert latency approximately 2-3s supports continuous monitoring and proactive method.

References

  1. Hafeez, Muhammad Adeel, and Sadia Shakil. "EEG-based stress identification and classification using deep learning." Multimedia Tools and Applications 83, no. 14 (2024): 42703-42719.
  2. de la Torre Díez, Isabel, Susel Góngora Alonso, Sofiane Hamrioui, Eduardo Motta Cruz, Lola Morón Nozaleda, and Manuel A. Franco. "IoT-based services and applications for mental health in the literature." Journal of medical systems 43, no. 1 (2019): 11.
  3. Saeidi, Maham, Waldemar Karwowski, Farzad V. Farahani, Krzysztof Fiok, Redha Taiar, Peter A. Hancock, and Awad Al-Juaid. "Neural decoding of EEG signals with machine learning: a systematic review." Brain sciences 11, no. 11 (2021): 1525.
  4. Al-Shargie, Fares, Yara Badr, Usman Tariq, Fabio Babiloni, Fadwa Al-Mughairbi, and Hasan Al-Nashash. "Classification of mental stress levels using EEG connectivity and convolutional neural networks." In 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp. 1-5. IEEE, 2023.
  5. Peng, Peizhen, Yang Song, Lu Yang, and Haikun Wei. "Seizure prediction in EEG signals using STFT and domain adaptation." Frontiers in Neuroscience 15 (2022): 825434.
  6. Sudhakar, J. Goldwyn, and Konguvel Elango. "A comprehensive review of eeg-based seizure detection techniques." IEEE Access (2025).
  7. Batista, Joana, Mauro F. Pinto, Mariana Tavares, Fábio Lopes, Ana Oliveira, and César Teixeira. "EEG epilepsy seizure prediction: the post-processing stage as a chronology." Scientific Reports 14, no. 1 (2024): 407.
  8. Yang, Hongliu, Jens Mueller, Matthias Eberlein, Sotirios Kalousios, Georg Leonhardt, Jonas Duun-Henriksen, Troels Kjaer, and Ronald Tetzlaff. "Seizure forecasting with ultra long-term EEG signals." Clinical Neurophysiology 167 (2024): 211-220.
  9. Hag, Ala, Fares Al-Shargie, Dini Handayani, and Houshyar Asadi. "Mental Stress Classification based on Selected EEG Channels using Correlation Coefficient of Hjorth Parameters." (2023).
  10. Kim, Hun-gyeom, Solwoong Song, Baek Hwan Cho, and Dong Pyo Jang. "Deep learning-based stress detection for daily life use using single-channel EEG and GSR in a virtual reality interview paradigm." PLoS One 19, no. 7 (2024): e0305864.
  11. Premchand, Brian, Liyuan Liang, Kok Soon Phua, Zhuo Zhang, Chuanchu Wang, Ling Guo, Jennifer Ang, Juliana Koh, Xueyi Yong, and Kai Keng Ang. "Wearable EEG-based brain–computer interface for stress monitoring." NeuroSci 5, no. 4 (2024): 407-428.
  12. Tzevelekakis, Konstantinos, Zinovia Stefanidi, and George Margetis. "Real-time stress level feedback from raw ecg signals for personalised, context-aware applications using lightweight convolutional neural network architectures." Sensors 21, no. 23 (2021): 7802.
  13. Grouiller, Frédéric, Laurent Vercueil, Alexandre Krainik, Christoph Segebarth, Philippe Kahane, and Olivier David. "A comparative study of different artefact removal algorithms for EEG signals acquired during functional MRI." Neuroimage 38, no. 1 (2007): 124-137.
  14. Sathiya, A., D. Angel, M. Iswarya, R. Poonkodi, and Kandavalli Michael Angelo. "IoT enabled healthcare framework using edge AI and advanced wearable sensors for real time health monitoring." In 2025 International Conference on Multi-Agent Systems for Collaborative Intelligence (ICMSCI), pp. 384-392. IEEE, 2025.
  15. Paris, Iqbal Luqman Bin Mohd, Mohamed Hadi Habaebi, and Alhareth Mohammed Zyoud. "Implementation of SSL/TLS security with MQTT protocol in IoT environment." Wireless Personal Communications 132, no. 1 (2023): 163-182.
  16. Zhang, Xinyang, Haimin Zhang, and Min Xu. "Multimodal Classification Algorithms for Emotional Stress Analysis with an ECG-Centered Framework: A Comprehensive Review." AI 7, no. 2 (2026): 63.
  17. Alharthi, Abdullah, Ahmed Alqurashi, Turki Alharbi, Mohammed Alammar, Nasser Aldosari, Houssem Bouchekara, Yusuf Shaaban, Mohammad Shoaib Shahriar, and Abdulrahman Al Ayidh. "Explainable AI for sensor signal interpretation to revolutionize human health monitoring: a review." IEEE Access (2025).
  18. Alfian, Ganjar, Muhammad Syafrudin, Muhammad Fazal Ijaz, M. Alex Syaekhoni, Norma Latif Fitriyani, and Jongtae Rhee. "A personalized healthcare monitoring system for diabetic patients by utilizing BLE-based sensors and real-time data processing." Sensors 18, no. 7 (2018): 2183.
  19. Sadad, Tariq, Mejdl Safran, Inayat Khan, Sultan Alfarhood, Razaullah Khan, and Imran Ashraf. "Efficient classification of ECG images using a lightweight CNN with attention module and IoT." Sensors 23, no. 18 (2023): 7697.
  20. Chi, Ethan Andrew, Gordon Chi, Cheuk To Tsui, Yan Jiang, Karolin Jarr, Chiraag V. Kulkarni, Michael Zhang et al. "Development and validation of an artificial intelligence system to optimize clinician review of patient records." JAMA network open 4, no. 7 (2021): e2117391.