ABSTRACT
The extremely complex nature of the electroencephalogram (EEG), and the subtle, nonquantified methods of pattern recognition used by human interpreters have made EEG analysis resistant to automation. Attempts at pattern recognition using multivariate classification procedures have not produced generalizable results due to the inadequate degree and quality of feature extraction prior to classification.
A real time, on-line EEG analysis strategy is described which incorporates feature extracting algorithms derived from models of human EEG interpretation. A system based upon this strategy has been implemented on a dedicated minicomputer. It includes: 1) spectral analysis using the Fast Fourier Transform (FFT) to produce continuous estimates of power and coherence; 2) parallel time domain analysis to detect the occurrence of sharp transient events of possible clinical significance; 3) continuous isometric display of spectral and transient functions; 4) spectral and time domain algorithms for the rejection of noncortical and instrumental artifact; 5) heuristics to isolate patterns and events of potential clinical significance; 6) interactive alteration of analysis and display parameters to facilitate manipulation of data from various experimental paradigms; 7) on-line feedback to alter, when necessary, artifact rejection, transient detection and feature extraction decision thresholds.
- Gibbs, F. A. and Gibbs, E. L. Atlas of Electroencephalography, 3 volumes, Addison Wesley, Reading, Mass., 1964.Google Scholar
- Hill, D. and Parr, D. (Eds). Electroencephalography. MacMillan, New York, 1963.Google Scholar
- Kooi, K. A. Fundamentals of Electroencephalography. Harper&Row, New York, 1971.Google Scholar
- Cox, J. R., Nolle, F. M. and Arthur, R. M. Digital analysis of the electroencephalogram, the blood pressure wave, and the electrocardiogram. IEEE Proceed. 60, 10 (1972), 1137--1164.Google ScholarCross Ref
- Katzan, Harry Jr. Operating Systems, Van Nostrand Reinhold Co., New York, 1973. Google ScholarDigital Library
- Jenkins, G. M. and Watts, D. G. Spectral Analysis and its Applications. Holden Day, San Francisco, 1968.Google Scholar
- Bendat, J. and Piersol, A. G. The Measurement and Analysis of Random Data. John Wiley, New York, 1966.Google Scholar
- Otnes, R. K. and Enochson, L. Digital Time Series Analysis. John Wiley, New York, 1972. Google ScholarDigital Library
- Walter, D. O. Spectral analysis for electroencephalograms: mathematical determination of neurophysiological relationships from records of limited duration. Exp. Neurol. 8 (1963), 155.Google ScholarCross Ref
- Walter, D. O., Rhodes, J. M., Brown, B. S. and Adey, W. R. Comprehensive spectral analysis of human EEG generators in posterior cerebral regions. Electroenceph. clin. Neurophysiol., 20 (1966), 224--237.Google Scholar
- Dumermuth, G. and Fluhler, H. Some modern aspects in numerical analysis of multichannel electroencephalographic data. Med. Biol. Eng. 5 (1967), 319.Google ScholarCross Ref
- Gevins, A. S. and Yeager, C. L. EEG spectral analysis in real time. DECUS Proceed., Spring (1972), 71--80.Google Scholar
- Gevins, A. S. and Yeager, C. L. An interactive, developmental approach to real time EEG analysis. In N. Burch (ed.) Behavior and Brain Electrical Activity. Plenum Press, New York. In press.Google Scholar
- Bickford, R. G., Fleming, N. I. and Billinger, T. W. Compression of EEG data by isometric power spectral plots. Electroenceph. clin. Neurophysiol. 31 (1971), 632.Google Scholar
- Buckley, J. K., Saltzberg, B. and Heath, R. G. Decision criteria and detection circuitry for multiple channel EEG correlation. IEEE Region 3 Convention Record 26, 3 (1968), 1--4.Google Scholar
- Carrie, J. R. G. A technique for analyzing transient EEG abnormalities. Electroenceph. clin. Neurophysiol. 32 (1972), 199--201.Google Scholar
- Goldberg, P., Samson-Dollfus, D. and Cremy, F. An approach to automatic pattern recognition of the electroencephalogram: background rhythm and paroxysmal elements. Meth. Inform. Med. 13, 3 (1973), 155--163.Google Scholar
- Hill, A. G. and Townsend, H. R. A. The automatic estimation of epileptic spike activity. Bio-Med Comput. 4 (1973), 149--156.Google Scholar
- Smith, J. R. Automatic analysis and detection of EEG spikes. IEEE Tr. Bio-Med. Eng. 21, 1 (1974), 1--5.Google ScholarCross Ref
- Girton, D. G. and Kamiya, J. A simple on-line technique for removing eye movement artifacts from the EEG. Electroenceph. clin. Neurophysiol. 34 (1973), 212--216.Google Scholar
- Andrews, H. C. Introduction to Mathematical Techniques in Pattern Recognition. John Wiley, New York, 1972.Google Scholar
- Meisel, W. S. Computer-Oriented Approaches to Pattern Recognition. Academic Press, New York, 1972.Google Scholar
- Heuristic real time feature extraction of the electroencephalogram (EEG)
Recommendations
Channel optimization and nonlinear feature extraction for Electroencephalogram signals classification
In present work, a methodology for automatic vigilance level detection of human brain using nonlinear features of Electroencephalogram (EEG) signals is presented. Vigilance level detection methodology consists of three steps, EEG channels selection, ...
Detecting epileptic seizures using electroencephalogram: a novel frequency domain feature extraction technique for seizure classification using fast ANFIS
ICACCI '12: Proceedings of the International Conference on Advances in Computing, Communications and InformaticsEpileptic seizures usually results in a mixture of temporal alterations in perception and behavior. Epilepsy is considered to be one of the highly frequent neurological disorders. A considerable manner for detecting and examining epileptic seizure ...
Unsupervised feature extraction with autoencoders for EEG based multiclass motor imagery BCI
Highlights- Proposed a novel feature extraction method for EEG signal classification.
- The ...
AbstractDecoding of motor imagery (MI) from Electroencephalogram (EEG) is an important component of BCI system that helps motor-disabled people interact with the outside world via external devices. One of the main issues associated with the ...
Comments