A seizure is an uncontrolled electrical disturbance in the brain that causes changes in behavior, movements or feelings, and in the levels of consciousness. The occurrence of recurrent seizure in patient indicates the presence of epilepsy, which directly affects central nervous system. The detection of Epilepsy is performed based on the Electroencephalogram (EEG) signals, which helps in recognizing the mental state of the patient suffering from the brain disorders. Since the manual detection and monitoring of electrographic seizures in continuous EEG is very time-consuming and requires a trained expert, so attempting to develop an automatic seizure detection is challenging task Various researches have been studied on Epilepsy disease using machine learning and big data concepts. Several features, classifiers, and data transformation have been used to classify seizures based on EEG signals that recognize the mental state of the patient. The features used from feature extraction, data transformation and decomposition techniques are summarized with a comparative study with respect to the performance metrics. The present research gives an overview of the seizure detection from the EEG signals and also provide challenges during seizure determination. A comparison is made among the state-of-art techniques and the algorithms that are involved in the Epilepsy seizure determination. The comparative analysis for the Epilepsy seizure determination was evaluated by means of accuracy, precision, sensitivity, and specificity. At last, an efficient emprical mode decomposition (EMD) algorithm is used for seizure detection to overcome the limitations faced in existing research and clearly explained in this research.
EEG Signals in Epilepsy Seizure Detection: An Empirical Study
2020-11-05
123488 byte
Conference paper
Electronic Resource
English
Seizure Detection in Focal Epilepsy Patients Using High Frequency EEG Signal
British Library Online Contents | 2018
|Epileptic Seizure Prediction Method Based on Empirical Mode Decomposition and Kolmogorov Complexity
British Library Online Contents | 2007
|