An Interactive EEG Classification System for Seizure, Mental Illness, and Normal Brain Activity with Prescription Guidance
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
In this work, we introduce a deep learning and machine learning framework for identifying and categorizing neur ological disorders.We concentrate on drug recommendations, normal brain activity, mental disease, and seizures.We gathered several datasets from Kaggle and included further data, such as food recommendations and medicat ions.We produced a new dataset after combining these parameters.We created an intuitive user interface that allo ws users to enter a set of 178 EEG signal values.This research makes it possible to forecast neurological problem s in real time.Based on the detected ailment, the system creates a customized prescription plan or strategy for nut ritional and drug recommendations.After identifying the condition, the equipment automatically develops a comp letely individualized treatment planThe proposed system employs a comparative ensemble of classical and advanced machine learning algorithms, including Random Forest, XGBoost, SVM, Logistic Regression, KNN, GaussianNB, and Gradient Boosting, to identify the most accurate classifier based on model performance.The best model achieved 97% accuracy, outperforming the others in prediction and generalization.
Fields of Study & Subjects
EEG and Brain-Computer Interfaces
Artificial Intelligence in Healthcare
Emotion and Mood Recognition
Publication details
- Journal / source
- Advances in engineering research/Advances in Engineering Research
- Pages
- 308–318
- Publication date
- 31 March 2026
- Language
- EN
- Document type
- Book chapter