ORIGINAL RESEARCH article

Front. Comput. Neurosci.

Volume 19 - 2025 | doi: 10.3389/fncom.2025.1545425

This article is part of the Research TopicModern applications of EEG in neurological and cognitive researchView all 8 articles

iSeizdiag: Towards the Framework Development of Epileptic Seizure Detection for Healthcare

Provisionally accepted
Ashish SharmaAshish Sharma1Akshat SaxenaAkshat Saxena2Mradul AgrawalMradul Agrawal2Kunal KishorKunal Kishor2Deepti KaushikDeepti Kaushik3Prateek JainPrateek Jain4Arvind R YadavArvind R Yadav4Manob Jyoti SaikiaManob Jyoti Saikia5*
  • 1Manipal University Jaipur, Jaipur, Rajasthan, India
  • 2Indian Institute of Information Technology, Kota (IIIT Kota), Kota, Rajasthan, India
  • 3S.R Goyal Government Hospital Sethi Colony, Jaipur, India
  • 4Nirma University, Ahmedabad, Gujarat, India
  • 5University of Memphis, Memphis, United States

The final, formatted version of the article will be published soon.

Select one of your emails

You have multiple emails registered with Frontiers:

Notify me on publication

Please enter your email address:

If you already have an account, please login

You don't have a Frontiers account ? You can register here

The seizure episodes result from abnormal and excessive electrical discharges by a group of brain cells. EEG framework-based signal acquisition is the real-time module that records the electrical discharges produced by the brain cells. The electrical discharges are amplified and appear as a graph on electroencephalogram systems. Different neurological disorders are represented as different waves on EEG records. This paper involves the detection of Epilepsy which appears as rapid spiking on electroencephalogram signals, using feature extraction and machine learning techniques. Various models, such as the Support Vector Machine, K Nearest Neighbour, and random forest, have been trained, and accuracy has been analysed to predict the seizure. An average accuracy of 95% has been claimed using the optimized model for epileptic seizure detection during training and validation. During the analysis of multiple models, the 97% accuracy is claimed after testing. Some statistical parameters are calculated to justify the optimised framework. The proposed approach represents a satisfactory contribution in precise detection for smart healthcare.

Keywords: EEG signal, Temporospatial Mapping, Classification, Epileptic, SVM, RF, KNN disorders like Epilepsy, Schizophrenia

Received: 14 Dec 2024; Accepted: 25 Apr 2025.

Copyright: © 2025 Sharma, Saxena, Agrawal, Kishor, Kaushik, Jain, Yadav and Saikia. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Manob Jyoti Saikia, University of Memphis, Memphis, United States

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.

Supplementary Material