Real-Time Mental Arithmetic Task Recognition From EEG Signals

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 21; no. 2; pp. 225 - 232
• Main Authors: Wang, Qiang, Sourina, Olga
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.03.2013; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Adult; Algorithms; Attention Deficit Hyperactivity Disorder; Biofeedback, Psychology - methods; Biofeedback, Psychology - physiology; Brain - physiology; Brain Mapping - methods; Brain modeling; Brain state; Cognition - physiology; Computer Systems; Electroencephalography; electroencephalography (EEG); Electroencephalography - methods; Feature extraction; Female; fractal dimension; Fractals; Humans; Male; Mathematics; mental arithmetic task; Neurofeedback; Pattern Recognition, Automated - methods; Principal component analysis; Studies; Young Adult
• ISSN: 1534-4320; 1558-0210; 1558-0210
• DOI: 10.1109/TNSRE.2012.2236576

Electroencephalography (EEG)-based monitoring the state of the user's brain functioning and giving her/him the visual/audio/tactile feedback is called neurofeedback technique, and it could allow the user to train the corresponding brain functions. It could provide an alternative way of treatment for some psychological disorders such as attention deficit hyperactivity disorder (ADHD), where concentration function deficit exists, autism spectrum disorder (ASD), or dyscalculia where the difficulty in learning and comprehending the arithmetic exists. In this paper, a novel method for multifractal analysis of EEG signals named generalized Higuchi fractal dimension spectrum (GHFDS) was proposed and applied in mental arithmetic task recognition from EEG signals. Other features such as power spectrum density (PSD), autoregressive model (AR), and statistical features were analyzed as well. The usage of the proposed fractal dimension spectrum of EEG signal in combination with other features improved the mental arithmetic task recognition accuracy in both multi-channel and one-channel subject-dependent algorithms up to 97.87% and 84.15% correspondingly. Based on the channel ranking, four channels were chosen which gave the accuracy up to 97.11%. Reliable real-time neurofeedback system could be implemented based on the algorithms proposed in this paper.