ADHD Detection Using Artificial Neural Network

Attention deficit hyperactivity disorder (ADHD) is one of the most prevalent mental diseases in children. The symptoms include difficulty in focusing, hyperactivity, and reckless behaviour. In this work, we explore a publicly available EEG database for ADHD. The EEG signals are pre-processed using band-pass filtering, segmentation and normalization. Thereafter, the frames are decomposed into sub-bands using Fourier decomposition technique. The sub-bands are then used to extract features like energy, kurtosis and mean absolute deviation. These features are fed to a simple Artificial neural network (ANN) for Classification into ADHD and non-ADHD cases. The proposed work achieves an accuracy of 97.08%.