• Mr. Praneeth V R
• Ms. Aruna M
• Mr. Adeeb Salim
• Mr. Lakshmanan V

This paper presents a novel approach to the early detection of epilepsy by integrating sensor derived data from biosensors equipped. The vital parameters recorded by the biosensors are heart rate, oxygen saturation level, muscle contractions and flex, etc. Leveraging the K-Nearest Neighbors (KNN) machine learning algorithm, this system analyses the multidimensional sensor data to identify patterns indicative of pre-ictal states. Data pre-processing includes filtering and normalization, followed by feature extraction to highlight relevant aspects of the user’s physical state during various activities. The KNN model is trained on labelled datasets, striking a balance between seizure and non-seizure instances. Real-time monitoring ensures timely identification, with a user-friendly interface providing intuitive visualization and interaction. The system’s performance is evaluated using metrics such as accuracy, precision, recall, and F1 score, with cross validation techniques to ensure robustness. Collaboration with healthcare professionals validates the system’s accuracy, while ethical considerations prioritize user privacy and data security. This research contributes to advancing early epilepsy detection systems, offering potential benefits for both medical practitioners and individuals at risk of epileptic seizures.

"Early detection of epileptic disorder using machine learning.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 3, page no.k221-k226, March-2024, Available :http://www.jetir.org/papers/JETIR2403A28.pdf

"Early detection of epileptic disorder using machine learning.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 3, page no. ppk221-k226, March-2024, Available at : http://www.jetir.org/papers/JETIR2403A28.pdf