A DM-ELM based classifier for EEG brain signal classification for epileptic seizure detection

Area of Science:

• Neurology
• Biomedical Engineering
• Machine Learning

Background:

• Epilepsy is a widespread neurological disorder affecting millions globally.
• Timely seizure detection is critical for patient management and improving quality of life.
• Electroencephalogram (EEG) signal analysis offers a non-invasive method for seizure prediction.

Purpose of the Study:

• To develop and evaluate a novel classification technique for automated epilepsy identification from EEG signals.
• To enhance the accuracy and efficiency of seizure detection using advanced machine learning algorithms.
• To compare the performance of a new DM-ELM model against the standard ELM.

Main Methods:

• Utilized Discrete Wavelet Transform (DWT) for feature extraction from EEG signals.
• Implemented an Extreme Learning Machine (ELM) optimized with Moth Flame Optimization (MFO) algorithm, termed DM-ELM.
• Conducted experimental evaluations comparing DM-ELM with basic ELM for classification accuracy.

Main Results:

• The proposed DM-ELM technique demonstrated superior performance compared to the basic ELM model.
• Experimental results confirmed the effectiveness of DM-ELM in classifying EEG signals for epilepsy detection.
• DM-ELM achieved higher accuracy rates in identifying epileptic seizures from brain signals.

Conclusions:

• The DM-ELM classification technique presents a promising advancement for accurate and efficient epilepsy diagnosis.
• This novel approach holds potential for improving clinical seizure detection and patient outcomes.
• Further research may focus on addressing the time constraints observed with the DM-ELM model.