Epileptic Seizure Classification and Feature Optimization Technique Using Grey Wolf Algorithm on Dynamic Datasets

Epileptic seizure (ES) is caused due to the unpredictable and imbalanced discharge of electric signals causing a muscle ruptures. The instance is critical if unattended medically. In the proposed paper, a feature optimization and classification technique is discussed. The technique is based on the dynamic feature set extraction and producing cluster based on categorization labels. The technique is structured on grey-wolf optimization algorithm in identifying the highlighted feature–attribute co-relationship. The technique has processed attribute inter-connectivity coordinates in creating a virtual mapping and labeling of cluster-heads to provide seizure severity. The technique has successfully adopted multi-dimensional datasets for improved performance and calibration under inter-dependent attribute-feature mapping. The technique has achieved 96.76% accuracy on trained datasets with 98.76% sensitivity and 97.86% in precision on epileptic seizure classification for decision-making.