Research Area:  Machine Learning
Epilepsy is a well-known neurological disorder which affects moreover 2% of the World-s population. Irregular excessive neuronal activities to the human brain cause epileptic seizures onset. Electroencephalograph (EEG) signals are mostly examined for the detection of epileptic seizure onsets. But an EEG signal consists of a huge amount of complicated information and it is very difficult to analyze it manually. Over the decades, a lot of research has been focused on the development of automated epilepsy diagnosis systems. These systems are dependent on sophisticated feature captureization and classification techniques. The paper aims to present a generalized review and performance comparison of the work reported over a decade in the area of automated epilepsy diagnosis systems that will help future researchers lead a better direction.
Keywords:  
Author(s) Name:  Satyender, Sanjeev Kumar Dhull & Krishna Kant Singh
Journal name:  
Conferrence name:  Advances in Communication and Computational Technology
Publisher name:  Springer
DOI:  10.1007/978-981-15-5341-7_110
Volume Information:  
Paper Link:   https://link.springer.com/chapter/10.1007/978-981-15-5341-7_110