Abstract Epilepsy is a serious, persistent neurological disorder that may be detected via brain signals generated by brain neurons. The abnormalities in the brain that cause epileptic seizures can have a negative impact on a patient's health. It appears all of sudden and shows no symptoms, that further increases the death rate of people. Nearly 1% of people worldwide experience epileptic seizures. Over the years, a number of techniques have been researched, put forth, and created. For the purpose of signal transmission and internal organ communication, neurons are closely coupled to one another. Electrocorticography (ECoG) and electroencephalography (EEG) media are typically accustomed to discover these brain impulses. These signals generate a large amount of data and are complicated, noisy, non-linear, and non-stationary. These restrictions on automated interictal spike and epileptic seizure identification, a crucial tool for closely reviewing and analyzing the EEG data, are recommended. These limitations draw our attention to a study of automated methods that may classify signals into epileptic and nonepileptic categories for neurologists. This paper presents a review on the primary difficulties that are observed during the implementation of epilepsy prediction algorithms, the paper also provides various feature selection and classification techniques.
Alan : Mühendislik
Dergi Türü : Uluslararası
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|