Abstract
Convolutional Neural Network and Power Spectrum Density Features for Detection and Prediction of Epilepsy
Author(s): G. Alizadeha*, T. Yousefi Rezaiia and S. MeshginiaEpilepsy is a neurological disorder that affects the lives of more than 60 million people worldwide. Timely diagnosis of the onset of epileptic attacks will significantly help people suffering from epileptic seizures. At present, the use of a seizure detection device has not been reported. A neurologist analyzes the brain signal in diagnosis and treatment centers, often associated with human error. In recent years, researchers have done a lot of research to design and build an automatic system for diagnosing and estimating the occurrence of epilepsy. This study proposed a new method based on brain signals and the Convolutional Neural Network (CNN). In this research, Power Spectrum Density (PSD) is used to create features. Several tests were conducted, and the accuracy of the proposed algorithm was 96.9%. The proposed method is more accurate, cheap, simple, and practical than the previous methods. After entering the field of operation, it can be used as a doctor's assistant and as a warning system for the patient.