Mining multi-channel EEG for its information content: an ANN-based method for a brain-computer interface

We have studied 56-channel electroencephalograms (EEG) from three subjects who planned and performed three kinds of movements, left and right index finger, and right foot movement. Using autoregressive modeling of EEG time series and artificial neural nets (ANN), we have developed a classifier that can tell which movement is performed from a segment of the EEG signal from a single trial. The classifier's rate of recognition of EEGs not seen before was 92-99% on the basis of a 1s segment per trial. The recognition rate provides a pragmatic measure of the information content of the EEG signal. This high recognition rate makes the classifier suitable for a so-called 'Brain-Computer Interface', a system that allows one to control a computer, or another device, with ones brain waves. Our classifier Laplace filters the EEG spatially, but makes use of its entire frequency range, and automatically locates regions of relevant activity on the skull.

[1]  L. K. Hansen,et al.  Adaptive regularization , 1994, Proceedings of IEEE Workshop on Neural Networks for Signal Processing.

[2]  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.

[3]  Vittorio Pizzella,et al.  Neuromagnetic study of movement-related changes in rhythmic brain activity , 1996, Brain Research.

[4]  Pieter R. Roelfsema,et al.  Binding and Response Selection in the Temporal Domain - a New Paradigm for Neurobiological Research , 1997 .

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

[6]  L. Deecke,et al.  Neuromagnetic fields accompanying unilateral and bilateral voluntary movements: topography and analysis of cortical sources. , 1991, Electroencephalography and clinical neurophysiology.

[7]  E. Donchin,et al.  EEG-based communication: prospects and problems. , 1996, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

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

[9]  G. Pfurtscheller,et al.  Event-related synchronization of mu rhythm in the EEG over the cortical hand area in man , 1994, Neuroscience Letters.

[10]  J. W. Kuhlman,et al.  Functional topography of the human mu rhythm. , 1978, Electroencephalography and clinical neurophysiology.

[11]  Niels Birbaumer.  Selbstregulation langsamer Hirnpotentiale , 1998 .

[12]  Conrad V. Kufta,et al.  Event-related desynchronization and movement-related cortical potentials on the ECoG and EEG. , 1994, Electroencephalography and clinical neurophysiology.

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

[14]  Donald G. Childers,et al.  Modern Spectrum Analysis , 1978 .

[15]  E B Stear,et al.  A new approach to prosthetic control: EEG motor signal tracking with an adaptively designed phase-locked loop. , 1971, IEEE transactions on bio-medical engineering.

[16]  G. Pfurtscheller,et al.  Event-related cortical desynchronization detected by power measurements of scalp EEG. , 1977, Electroencephalography and clinical neurophysiology.

[17]  J. Rohrbaugh,et al.  Improving spatial and temporal resolution in evoked EEG responses using surface Laplacians. , 1993, Electroencephalography and clinical neurophysiology.