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{191153,
        author = {Shreyas Sunil and Lakshmikanth Reddy and Nandha Kumar S and Nsenga Ngoie and Pavan Krishna K R},
        title = {Non-Invasive Intracranial Monitoring for Detection of Epilepsy Using EEG Signals},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {5618-5625},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=191153},
        abstract = {Epilepsy is a lifelong neurological disorder characterized by sudden and unpredictable surges of electrical activity in the brain, resulting in seizures that affect movement, awareness, and behavior. Although electroencephalography (EEG) plays a crucial role in epilepsy diagnosis, conventional EEG monitoring requires sophisticated clinical infrastructure, making long-term and continuous observation impractical for many patients. This work presents a compact, non-invasive, and portable system capable of detecting seizure-like patterns in real time using EEG signals. The proposed system employs lightweight preprocessing, eighteen interpretable EEG features with additional derived measures, and an embedded hybrid CNN–LSTM classifier deployed on a low-cost microcontroller. An IoT layer enables real-time alerts and remote visualization of physiological parameters. Experimental validation using the CHB-MIT Scalp EEG Dataset and supplementary dry-electrode recordings demonstrates that the proposed approach achieves high detection accuracy while remaining cost-effective and suitable for home-based and non-clinical monitoring applications.},
        keywords = {Epilepsy, EEG, Embedded Machine Learning, CNN–LSTM, IoT Monitoring, Biomedical Signal Processing},
        month = {January},
        }