Supervised Machine Learning and Deep Learning Techniques for Epileptic Seizure Recognition Using EEG Signals—A Systematic Literature Review

Abstract

Electroencephalography (EEG) is a complicated, non-stationary signal that requires extensive preprocessing and feature extraction approaches to be accurately analyzed. In recent times, Deep learning (DL) has shown great promise in exploiting the characteristics of EEG signals as it can learn relevant features from raw data autonomously. Although studies involving DL have become more common in the last two years, the topic of whether DL truly delivers advantages over conventional Machine learning (ML) methodologies remains unsettled. This study aims to present a detailed overview of the main challenges in the field of seizure detection, prediction, and classification utilizing EEG data, and the approaches taken to solve them using ML and DL methods. A systematic review was conducted surveying peer-reviewed publications published between 2017 and 16 July 2022 using two scientific databases (Web of Science and Scopus) totaling 6822 references after discarding duplicate publications. Whereas 2262 articles were screened based on the title, abstract, and keywords, only 214 were eligible for full-text assessment. A total of 91 papers have been included in this survey after meeting the eligible inclusion and exclusion criteria. The most significant findings from the review are summarized, and several important concepts involving ML and DL for seizure detection, prediction, and classification are discussed in further depth. This review aims to learn more about the different approaches for identifying different types and stages of epileptic seizures, which may then be employed to enhance the lives of epileptic patients in the future, as well as aid experts in the field.

Machine Learning Model to Detect Seizures Using EEG Signals

“…It is then expected to give accurate outcome when same type of test data is fed in it. [3], [15], [17], [19]Many researchers have started using Machine Learning methods to solve their problems faster and also because lowcost processing and memory are at our disposal. Because of the availability of Machine Learning approaches, it is now feasible to study and analyze huge datasets to reveal the patterns and trends which might not be visible to the naked eye.…”

“…In contrast to how [3] Machine Learning utilizes the raw data, Deep Learning uses a network which learn by discovering intricate structures in the data they experience. Deep Learning uses several non-activation units which are distributed over multiple layers.…”

Prediction of Cognitive Load from Electroencephalography Signals Using Long Short-Term Memory Network

“…EEG is the flow of electricity generated by signal transmission between brain nerves, and EEG analysis analyzes the frequency change in the EEG. Because EEGs exhibit different frequency wavelengths depending on mental activity, the degree of cognitive load can be measured by EEG analysis [ 9 , 10 ]. However, the generation of brainwaves is greatly affected by physical exercise and by differences in individual cognitive abilities.…”

A New Hybrid Approach Based on Time Frequency Images and Deep Learning Methods for Diagnosis of Migraine Disease and Investigation of Stimulus Effect

“…In addition, when the appropriate number of data is used in studies with EEG signals, DL models can perform better than ML [12]. For this reason, EEG-based DL studies are promising and increasing in number [13]. EEG signal-and DL model-based studies are of interest in the diagnosis of neurological diseases.…”