A systematic mapping of feature extraction and feature selection methods of electroencephalogram signals for neurological diseases diagnostic assistance

Electroencephalogram (EEG) is a non-invasive tool used to monitor the electrical activities of the brain. EEG signal analysis has several applications in the medical field. It is widely used for clinical diagnostics and for advances in the Brain-Computer Interface (BCI) area. In recent years, several studies about the automatic execution of this analysis have been proposed, motivated by the fact that the visual inspection demands a long time from an expert, besides being subject to a misdiagnosis. In order to extract and select relevant information from recordings of brain electrical activity, many computerized analysis methods have been developed based on different approaches. Although some proposed methods have achieved good performance, many of them are not suitable for real-world application due to their high computational cost. Thus, there is opportunity in the area to identify and categorize techniques in order to support studies about the influence of these techniques on diagnostic performance and to propose the optimization of this task. In this context, this Systematic Mapping evaluates the 144 primary studies identified according to the criteria defined in the protocol. The purpose is to highlight which neurological disorders have been studied in recent years and which techniques for feature extraction and feature selection have been applied during signal analysis, individually or jointly, to provide specifically an automatic diagnosis of a neurological disorder using a classifier.