Efficient Approach for Epileptic Seizure Classification and Detection based on Genetic Algorithm with CNN-RNN Classifier

One of the most physically and psychologically damaging neurological conditions that affect people of all ages is an epileptic seizure. The abnormality should be recognized early so that the proper treatment is timely. It is possible only with advanced signal processing techniques to distinguish and predict epileptic patterns in which substantial effort is invested. Therefore, efficient seizure detection and classification methods are proposed for machine learning and deep learning algorithms. The proposed method uses deep and machine-learning algorithms for seizure detection and classification. The objective is to analyze the performance and efficiency of deep and machine learning classifiers by comparing the various classifiers. This proposed work uses 11,500 EEG data samples from the UCI machine learning repository. To suggest an Improved Fitness Function Genetic Algorithm (IGA) technique for optimal feature selection to improve the detection rate and CNN-RNN algorithm used as the classifier. The analysis proved that the hybrid CNNRNN(LSTM with GRU) classifier with GA-based feGAbased-lection provides better densification accuracy results of 98% when compared with all other classifiers.