Entropy difference-based EEG channel selection technique for automated detection of ADHD.

Area of Science:

• Neuroscience
• Biomedical Engineering
• Machine Learning

Background:

• Attention Deficit Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental disorder in children.
• Accurate and early detection of ADHD is crucial for effective intervention and management.
• Existing ADHD detection methods often lack efficiency and require significant manual input.

Purpose of the Study:

• To develop an automated and highly accurate approach for ADHD detection using electroencephalogram (EEG) data.
• To introduce a novel entropy difference (EnD)-based channel selection method for identifying significant EEG channels.
• To evaluate the performance of the proposed method against existing techniques.

Main Methods:

• Utilized an entropy difference (EnD)-based approach for selecting the most significant EEG channels.
• Extracted features from selected channels using Discrete Wavelet Transform (DWT), Empirical Mode Decomposition (EMD), and Symmetrically-weighted Local Binary Pattern (SLBP).
• Employed k-nearest neighbor (k-NN), Ensemble classifier, and Support Vector Machine (SVM) for automated classification.

Main Results:

• The proposed EnD-based channel selection method achieved a highest accuracy of 99.29% on a public database.
• The EnD approach consistently outperformed traditional entropy-based channel selection methods.
• The developed automated ADHD detection system demonstrated superior performance compared to existing approaches.

Conclusions:

• The proposed automated ADHD detection system, utilizing EnD-based EEG channel selection, offers a highly accurate and efficient diagnostic tool.
• The EnD method effectively identifies crucial EEG channels, enhancing classification performance.
• This approach holds significant potential for improving the early diagnosis and management of ADHD in children.