Detection and Treatment of Epilepsy Disease using EEG Signals

Epilepsy Seizures is a neurological illness that causes repeated seizures and affects millions of people throughout the world. From the studies it has been detected that 70% peoples in the world suffer from epilepsy disease. The prognosis and medical care of epileptic seizure are critical for improving the quality of life of affected individual. Electroencephalography (EEG) is a valuable technique for diagnosing and managing epilepsy because it allows for real-time monitoring of brain electrical activity. Recent advancements in signal processing techniques, such as the Discrete Wavelet Transform (DWT), have shown significant promise in enhancing the diagnosis and treatment of epilepsy. This paper purposed an optimize Random Forest (RF) algorithm by using the DWT application in the analysis of EEG signals for the prognosis of epilepsy disease along with its treatment like medicines, therapies and other treatments methods to cure epilepsy disease. The suggested approach provides clinicians with a promising tool for early and precise identification of epileptic seizures, which is critical for making improvements in patient outcomes and quality of life. The simulation results show that the purposed optimize support vector machine algorithm gives better results with an accuracy of 98% along with the sensitivity, specificity and f1_score of 97%, 96% and 98% respectively.