Application of the Walsh transform towards seizure detection
Maria Tito, Malek Adjouadi, Mercedes Cabrerizo, Melvin Ayala, Ilker Yaylali, Armando B. Barreto, Naphtali David Rishe · 2007
Abstract:- Epilepsy is a neurological disorder, a physical condition, which causes sudden bursts of electrical energy in the brain. Electrical activity in the brain has been studied for years in an attempt to detect seizures. This paper processes raw intracranial electroencephalographic recordings in the time prior and during a seizure.This study focuses on the design of orthogonal operators based on the Walsh transform in order to detect the onset of epileptic seizures in EEG data. The merits of the algorithm are: (a) in elaborating a unique analysis scheme that scrutinizes EEG data through orthogonal operators designed to extract patterns that best characterize seizures in epileptogenic EEG data; and (b) in establishing mathematical derivations that provide not only quantitative measures through the designed operators, but also characterize and locate the event of a seizure. In this study, EEG recordings from different patients are processed. A set of parameters is extracted from non-overlapping scrolling windows of 1 sec duration. The objective was to detect the seizure applying the operators of the Walsh transform using these parameters.