Grasshopper optimization algorithm-based approach for the optimization of ensemble classifier and feature selection...

Area of Science:

• Neurology
• Biomedical Engineering
• Machine Learning

Background:

• Epilepsy is a common neurological disorder diagnosed using electroencephalogram (EEG) recordings.
• Current EEG analysis for epilepsy diagnosis is time-consuming and prone to errors.
• There is a need for automated and accurate methods for epileptic seizure detection.

Purpose of the Study:

• To propose a novel methodology for the classification of epileptic seizures from EEG signals.
• To enhance the accuracy and efficiency of epilepsy diagnosis through advanced signal processing and machine learning.
• To develop an ensemble classifier that outperforms individual machine learning models.

Main Methods:

• EEG signals were decomposed into intrinsic mode functions (IMFs) using empirical mode decomposition (EMD).
• Non-linear and spike-based features were extracted from each IMF and fused.
• The Grasshopper Optimization Algorithm (GOA) was used to optimize parameters and select significant features for five machine learning algorithms (k-NN, ELM, RF, SVM, ANN).
• An ensemble classifier was created by combining the optimized individual classifiers.

Main Results:

• The ensemble classifier demonstrated superior performance in epileptic seizure classification compared to individual classifiers.
• Feature selection and parameter optimization using GOA significantly improved classification accuracy.
• The proposed methodology showed competitive results when compared to existing state-of-the-art techniques.

Conclusions:

• The developed ensemble classification methodology offers a promising approach for accurate and efficient epileptic seizure detection.
• Combining multiple optimized machine learning models enhances diagnostic capabilities for epilepsy.
• This work contributes to the advancement of automated EEG analysis for neurological disorders.