Abstract
Classification of non-averaged task-related EEG responses with different types of classifier, including self-organising feature map and learning vector quantiser, K-mean, back-propagation and a combination of the last two, is reported. EEG data are collected from approximately one second periods prior to movement of the right or left index finger. A cue stimulus indicating which hand to use is employed. Feature vectors are formed by concatenating spatial information from different EEG electrodes and temporal information from different time incidents during the planning of hand movement. Power values of the most reactive frequencies within the extended alpha-band (5–16 Hz) are used as features. The features are derived from an autoregressive model fitted to the EEG signals. The performance of the classifiers and their ability to learn and generalise is tested with 200 arbitrarily selected event-related EEG data from a normal subject. Classification accuracies as high as 85–90% are achieved with the methods described here. A comparison of the classifiers is made.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Ahalt, S. C., Krishnamurthy, A. K., Gevins, A. S., Bressler, S. L., Morgan, N. H., Cutillo, B. A., White, R. M., Greer, D. S., andIlles, J. (1990): ‘Competitive learning algorithms for vector quantisations’,Neural Networks 3, pp. 277–299
Andreasson, I. J. (1970): ‘Computer program package for the analysis of a stationary process. Technical Report 27, Royal Institute of Technology, Stockholm
Foley, D. H. (1972): ‘Considerations of sample and feature size’,IEEE Trans.,IT-18, (15), pp. 618–626
Gevins, A. S., andMorgan, N. H. (1986): ‘Classifier-directed signal processing in brain research’,IEEE Trans.,BME-33, (12), pp. 1054–1068
Gevins, A. S., Bressler, N. H., Ahalt, S. C., Krishamurthy, A. K., Chen, P., andMelton, D. E. (1989): ‘Event-related covariances during a bimanual visuomotor task. Methods and analysis of stimulus- and response-locked data’,Electroenceph. & Clin. Neurophysiol.,74, pp. 58–75
Hartigan, J. A. (1975): ‘Clustering algorithms’ (J. Wiley & Sons)
Hiraiwa, A., andShimohara, K. (1990): ‘EEG topography recognition by neural network’,IEEE Eng. Med. & Biol. Mag.,9, (3), pp. 39–42
Hjorth, B. (1975): ‘An on-line transformation of EEG scalp potentials into orthogonal source derivation’,Electroenceph. & Clin. Neurophysiol.,39, pp. 526–530
Ibrahim, M. K. (1987): ‘On-line splitting in the optimum tapered burg algorithm’,IEEE Trans.,ASSP-35, (10), pp. 1476–1479
Jansen, B. H., Hasman, A., Lenten, R., andVisser, S. L. (1979): ‘Usefulness of autoregressive models to classify EEG-segments,’Biomedizinische Technik,24, pp. 216–223
Kangas, J. A., Kohonen, T. K., andLaaksonen, J. T. (1990): ‘Variants of self-organising maps,’IEEE Trans.,NN-1, (1), pp. 93–99
Kohonen, T. K. (1982): ‘Self-organised formation of topologically correct feature maps’,Biol. Cybern.,43, pp. 59–69
Kohonen, T. K. (1988): ‘The ‘neural’ phonetic typewriter,’IEEE Comput., March, pp 11–22
Kohonen, T. K. (1990a): ‘The self-organising map’,Proc. IEEE,78, (9), pp. 1464–1480
Kohonen, T. K. (1990b): ‘Statistical pattern recognition revisited’,in Eckmiller, R. (Ed.): ‘Advanced neural computers’ (Elsevier Science Publishers)
Lippman, R. (1987): ‘An introduction to computing with neural nets’,IEEE ASSP Mag.,4, (2), pp. 4–22
Marple, A. L. Jr. (1987): ‘Digital spectral analysis with applications’ (Prentice Hall)
McDermott, E., andKatagiri, S. (1991): ‘LVQ-based shift tolerant phoneme recognition’,IEEE Trans.,SP-39, (6), pp. 1398–1411
Pao, Y.-H. (1989): ‘Adaptive pattern recognition and neural networks’ (Addison-Wesley)
Peltoranta, M., andPfurtscheller, G. (1993): ‘Neural network based classification of event-related Berger waves’in Rother, M., andZwiener, U. (Eds.): Quantitative EEG analysis-clinical utility and new methods’ (Universitätsverlag GmbH, Jena), pp. 92–98
Pfurtscheller, G., andAranibar, A. (1977): ‘Event-related cortical desynchronization detected by power measurements of scalp EEG’,Electroenceph. & Clin. Neurophysiol.,2, pp. 817–826
Pfurtscheller, G., andBerghold, A. (1989): ‘Patterns of cortical activation during planning of voluntary movement’,Electroenceph. & Clin. Neurophysiol.,72, pp. 250–258
Pfurtscheller, G., Flotzinger, D., Mohl, W., andPeltoranta, M. (1992): ‘Prediction of the side of hand movement from single-trial multi-channel EEG data using neural networks’,Electroenceph. & Clin. Neurophysiol.,82, pp. 313–315
Pfurtscheller, G. (1992): ‘Event-related synchronisation (ERS): An electrophysiological correlate of cortical areas at rest’,Ibid.,83, pp. 62–69
Pukkila, T., andKrisnaiah, P. (1988): ‘On the use of auto-regressive order determination criteria in multivariate white noise tests’,IEEE Trans.,ASSP-36, (9), pp. 1396–1403
Ritter, H. (1991): ‘Asymptotic level density for a class of vector quantization provess’,IEEE Trans.,NN-2, (1), pp 173–175
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Peltoranta, M., Pfurtscheller, G. Neural network based classification of non-averaged event-related EEG responses. Med. Biol. Eng. Comput. 32, 189–196 (1994). https://doi.org/10.1007/BF02518917
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF02518917