International Research Journal of Education and Technology

Signals from electroencephalography (EEG) carry the crucial data regarding the neural operations of the electrical brain. EEG analyses rhythmic and ongoing recordings of the brain impulses of nerve cells from the scalp's surface. One of the most important areas of neuroscience and neural engineering is EEG signal analysis because it is very helpful in dealing with the commercial applications as well. EEG research paired with machine learning reveals incredibly valuable information on the neurological processes that occur. The Lion Optimization Algorithm, a feature extraction technique that is suggested for efficiently extracting features from bio signals and for comprehending the crucial data it includes for assessing brain activities, was used in this study to assess the epilepsy risk level. The important features in terms of parameter components KNN with EM and Firefly with EM are extracted using the Lion Optimization Algorithm. The EEG needs to be classified in order to be more helpful and to be used in a variety of applications, eliminating the need for skilled personnel. As a result, the suggested dimensionality reduction is first used to perform the classification, and the results are compared to those of other conventional machine learning techniques. The flow of the proposed methodology is results show that the epileptic dataset both produce good classification when evaluated on a few common Bio signal datasets which is accuracy of 92.68% and 97.5%, respectively.

Keywords: EEG, LOA, KNN, Firefly and EM.