Genetic Algorithm-Based Machine Learning Approach for Epileptic Seizure Identification and Classification
K. Thanuja, Shoba M, Kirankumari Patil- General Engineering
Background:
Epileptic Seizure (ES) is a neural disorder that generates an uncontrolled brain signal impulse. The disorder is seen in young children and adults with a positive medical history.
Method:
In this paper, a novel approach to epileptic seizure detection and prediction is proposed and evaluated. The seizure is retrained from Electroencephalography (EEG) high-dimension datasets. The EEG datasets further segment features of interdependent EEG into a matrix. This matrix is linked to providing a validation occurrence of similar feature events with a minimum redundancy maximum relevance (MRMR) approach for ES feature optimization.
Result & Discussion:
The uncertainty-based genetic algorithm for parametric evaluation and validation (GAPEr) is used for predictive analysis and decision support via a dedicated neural networking model. The sizer detection and prediction are supported and validated via a series of interactions from trained datasets.
Conclusion:
The proposed setup has achieved higher accuracy and dependency in decision support of Epileptic Seizure identification and classification based on predictive evaluation.