This paper provides a review of machine learning-based approaches to electroencephalogram (EEG) data classification. Machine learning algorithms are used to classify EEG in a variety of health applications. Mainly, they aggregate and categorize patient signals based on the learning and development of specified characteristics and measures. Thirty-two reputable research papers are provided in this work with an emphasis on the developed and executed techniques, applied dataset, achieved results, and applicable assessment. For each of the included publications, critical analysis and statement are provided, as well as an overall analysis for all of the studies in comparison with each other. Evidently, SVM, CNN, KNN, multi-classifier, and more other classification approaches are analyzed and investigated. All the classification approaches have shown a promise achievement within EEG classification process. Multi-classifier approaches have outperformed all other models in terms of persistence and performance with an average accuracy of 98.8%.
CITATION STYLE
Al-hamzawi, A. A., Al-Shammary, D., & Hammadi, A. H. (2022). A Survey on Healthcare EEG Classification-Based ML Methods. In Lecture Notes on Data Engineering and Communications Technologies (Vol. 126, pp. 923–936). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-19-2069-1_64
Mendeley helps you to discover research relevant for your work.