Today, the primary topic of discussion in the signal processing domain is the analysis of non-stationary and nonlinear signal data. The use of biomedical equipment generates enormous amounts of physiological data that can be analyzed and used for clinical diagnosis. Manual inference of specific decisions from such signals is laborious due to artifacts and the time-series nature of the data, particularly for electroencephalography (EEG) signals. As a result, it is critical to employ appropriate methods for signal analysis. The purpose of this survey is to gain an understanding of the various techniques used to process EEG signal data in epileptic seizure detection frameworks. A variety of classification and regression frameworks based on machine learning have been reviewed. This systematic review will adhere to the PRISMA guidelines. This survey uncovered several significant findings.