Discriminating Mental States Using EEG Represented by Power Spectral Density

Artificial neural networks were trained to classify segments of 12 channel EEG data into one of five classes corresponding to five cognitive tasks performed by one subject. Three-layer feedforward neural networks were trained using a validation set to control over-fitting. Independent Component Analysis (ICA) was used to segregate obvious artifactual EEG components from other sources, and a frequency-band representation was used to represent the sources computed by ICA. The most notable result is an 85% accuracy rate on differentiation between two tasks, using a segment of EEG 1/20th of a second long.

[1]  E. A. Stolz,et al.  Multivariate Autoregressive Models for Classification of Spontaneous Electroencephalogram During Mental Tasks1 , 1998 .

[2]  Z. Keirn,et al.  A new mode of communication between man and his surroundings , 1990, IEEE Transactions on Biomedical Engineering.

[3]  Ferdinand Hergert,et al.  Improving model selection by nonconvergent methods , 1993, Neural Networks.

[4]  Andrzej Cichocki,et al.  A New Learning Algorithm for Blind Signal Separation , 1995, NIPS.

[5]  J. Wolpaw,et al.  Multichannel EEG-based brain-computer communication. , 1994, Electroencephalography and clinical neurophysiology.

[6]  J. Fermaglich.  Electric Fields of the Brain: The Neurophysics of EEG , 1982 .

[7]  Gert Pfurtscheller,et al.  Prompt recognition of brain states by their EEG signals , 1997 .

[8]  Scott C. Douglas,et al.  Blind Signal Separation and Blind Deconvolution , 2018, Handbook of Neural Network Signal Processing.

[9]  G. Pfurtscheller,et al.  Differentiation between finger, toe and tongue movement in man based on 40 Hz EEG. , 1994, Electroencephalography and clinical neurophysiology.

[10]  Terrence J. Sejnowski,et al.  An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.

[11]  G Pfurtscheller,et al.  Selection of electrode positions for an EEG-based Brain Computer Interface (BCI). Auswahl von Elektrodenpositionen für ein auf EEG-Ableitungen basierendes Brain Computer Interface (BCI) , 1994, Biomedizinische Technik. Biomedical engineering.

[12]  Charles W. Anderson,et al.  EEG signal classification with different signal representations , 1995, Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing.

[13]  Charles W. Anderson,et al.  Determining Mental State from EEG Signals Using Parallel Implementations of Neural Networks , 1995, Sci. Program..

[14]  G. Pfurtscheller,et al.  Visualization of sensorimotor areas involved in preparation for hand movement based on classification of μ and central β rhythms in single EEG trials in man , 1994, Neuroscience Letters.

[15]  S. Tseng,et al.  Evaluation of parametric methods in EEG signal analysis. , 1995, Medical engineering & physics.

[16]  Gert Pfurtscheller,et al.  Brain-computer interface: a new communication device for handicapped persons , 1993 .

[17]  T. Fernández,et al.  EEG activation patterns during the performance of tasks involving different components of mental calculation. , 1995, Electroencephalography and clinical neurophysiology.