TMP19: A Novel Ternary Motif Pattern-Based ADHD Detection Model Using EEG Signals.

Area of Science:

• Neuroscience
• Biomedical Engineering
• Signal Processing

Background:

• Attention Deficit Hyperactivity Disorder (ADHD) is a prevalent global neurodevelopmental condition.
• Electroencephalography (EEG) signals are crucial for understanding brain activity but are often noisy.
• Accurate classification of ADHD using EEG is essential for diagnosis and treatment.

Purpose of the Study:

• To develop and validate a novel hand-modeled EEG classification model for differentiating ADHD from healthy individuals.
• To incorporate advanced signal processing techniques for robust feature extraction from noisy EEG data.
• To evaluate the model's classification performance using rigorous cross-validation methods.

Main Methods:

• A new model, TMP19, was developed, mimicking deep learning principles.
• Tunable Q Wavelet Transform (TQWT) was used for wavelet subband generation.
• Ternary Motif Pattern (TMP) and statistical features were extracted from raw EEG and wavelet bands.
• Neighborhood Component Analysis (NCA) performed feature selection, and k-Nearest Neighbors (kNN) classified the features.
• Iterative Hard Majority Voting (IHMV) enhanced classification robustness across 14 EEG channels.

Main Results:

• The TMP19 model achieved a 95.57% classification accuracy with 10-fold cross-validation.
• Leave-One-Subject-Out (LOSO) cross-validation yielded a classification accuracy of 77.93%.
• The proposed method demonstrated effectiveness in classifying noisy EEG signals for ADHD detection.

Conclusions:

• The TMP19 model, integrating TQWT, TMP, NCA, and kNN, provides a promising approach for ADHD classification from EEG.
• The hand-modeled approach offers an alternative to purely data-driven deep learning methods for EEG analysis.
• The model's performance highlights the potential of advanced signal processing for neurodevelopmental disorder identification.