Identifying Mental Tasks from Spontaneous EEG: Signal Representation and Spatial Analysis

Feedforward neural networks are trained to classify half-second segments of six-channel, EEG data into one of five classes corresponding to five mental tasks performed by one subject. Two and three-layer neural networks are trained on a 128-processor SIMD computer using 10-fold cross-validation and early stopping to limit over-fitting. Four representations of the EEG signals, based on autoregressive (AR) models and Fourier Transforms, are compared. Using the AR representation and averaging over consecutive segments, an average of 72% of the test segments are correctly classified; for some test sets 100% are correctly classified. Cluster arm, is of the resulting hidden-unit weight vectors suggests which electrodes and representation components are the most relevant to the classification problem.

[1]  A. C. Sanderson,et al.  Hierarchical modeling of EEG signals , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  T. Yunck,et al.  Comparison of decision rules for automatic EEG classification , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  M. Osaka,et al.  Peak alpha frequency of EEG during a mental task: task difficulty and hemispheric differences. , 1984, Psychophysiology.

[4]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[5]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[6]  Antoine Rémond,et al.  Methods of Analysis of Brain Electrical and Magnetic Signals , 1987 .

[7]  Steven Kay,et al.  Modern Spectral Estimation: Theory and Application , 1988 .

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

[9]  Bart Kosko,et al.  Neural networks for signal processing , 1992 .

[10]  T. Inouye,et al.  Localization of activated areas and directional EEG patterns during mental arithmetic. , 1993, Electroencephalography and clinical neurophysiology.

[11]  Ah Chung Tsoi,et al.  Classification of Electroencephalogram Using Artificial Neural Networks , 1993, NIPS.

[12]  Charles W. Anderson,et al.  Discriminating mental tasks using EEG represented by AR models , 1995, Proceedings of 17th International Conference of the Engineering in Medicine and Biology Society.

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

[14]  Tzyy-Ping Jung,et al.  Using Feedforward Neural Networks to Monitor Alertness from Changes in EEG Correlation and Coherence , 1995, NIPS.

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

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

[17]  Satoru Goto,et al.  On-line spectral estimation of nonstationary time series based on AR model parameter estimation and order selection with a forgetting factor , 1995, IEEE Trans. Signal Process..

[18]  R. Benjamin Knapp,et al.  Controlling computers with neural signals. , 1996 .

[19]  Charles W. Anderson,et al.  Effects of Variations in Neural Network Topology and Output Averaging on the Discrimination of Mental Tasks from Spontaneous Electroencephalogram , 1997 .

[20]  C.W. Anderson,et al.  Multivariate autoregressive models for classification of spontaneous electroencephalographic signals during mental tasks , 1998, IEEE Transactions on Biomedical Engineering.

[21]  H. Jasper,et al.  The ten-twenty electrode system of the International Federation. The International Federation of Clinical Neurophysiology. , 1999, Electroencephalography and clinical neurophysiology. Supplement.