Hybridization of Sparrow Search Algorithm and Sine Cosine Algorithm for Epileptic Seizure Detection

An imbalance in electrical signal flow among neurons causes epilepsy, a complex brain disease that affects other parts of the body and results in seizures. Researchers and neurologists have put their efforts into devising powerful electroencephalogram devices to address the importance of health issues. In this context, machine learning algorithms are used to accurately detect the presence of a seizure signal. This experiment uses the hybridization of two meta-heuristic optimization algorithms: the sparrow search algorithm and the sine cosine algorithm. To conduct the research, this experiment uses the publicly available CHB-MIT EEG dataset, and for feature extraction, it uses the discrete wavelet transform (DWT). ANOVA We use feature selection to identify similar groups. This study uses three classifiers: support vector machines (SVM), Adaptive Neuro Fuzzy Inference System (ANFIS), and Extreme Learning ANFIS (ELANFIS). We got 99.8% accuracy, 98.35% sensitivity, 99.02% specificity, 98% positive predictive value, and 1 for area-under-curve for SSA-SCA-DWT-ELANFIS. This shows that it works better than SSA-SCA-DWT-SVM, SSA-SCA-DWT-ANFIS, and other methods that are already out there. In the future, we can integrate this study with the Internet of Things (IoT).