Enhancing affordable EEG to act as a quantitative EEG for inattention treatment using MATLAB

Lack of attention is a chronic behavior in attention deficit hyperactivity disorder (ADHD), autism spectrum disorder (ASD), and other disorders that harm academic and social performance. ADHD is a disorder whose typical symptoms include inattention, hyperactivity, and impulsivity. They have a major impact on the affected person’s function and development. The electroencephalogram (EEG) device is a diagnostic tool, whereas the quantitative EEG (QEEG) device is a diagnostic and therapeutic tool for most mental disorders. QEEG applies the neurofeedback method in treatment. Neurofeedback is a technique for training brain functions and is an alternative to the traditional oral treatment of inattention disorders due to its numerous side effects. The proposed software can upgrade most EEG devices in hospitals and clinics into QEEGs capable of neurofeedback. The upgrading tools and stages are introduced in this study. The cost of upgrading an EEG device is 25 times less than the purchase price of a QEEG device. The EEG device (Open BCI) has been upgraded with MATLAB to function as a QEEG system, integrating a variety of feature extraction methods for inattention detection such as fractal dimension (FD), wavelet transform (WT), multi-resolution techniques (MR), and empirical mode decomposition (EMD) which signified a notable progress in the field. Furthermore, the implemented software is easily customizable to include any forthcoming superior techniques that may arise. Earlier research distinguished the differences between states of relaxation and concentration using a simple fixed threshold. In this paper, short training has been utilized to calculate adaptive thresholds to optimize individual effects. Different thresholding techniques were employed with the EMD_Dt technique to distinguish between focused and unfocused epochs. The adaptive threshold method results have been more accurate reaching the benchmark of 99.82%, as opposed to the fixed threshold method, which reaches an accuracy of 97.73%. The findings were assessed through a pilot study involving 3483 epochs collected across 24 sessions from male and female children aged between 5 and 16. The proposed QEEG software was evaluated to be Specific, Measurable, Achievable, Realistic, and Timed (SMART) with an effect size of 0.85528336, which is significant.