Application of Neural Networks to Automated Brain Maturation Study
An application of Neural Networks (NN) to brain maturation prediction is presented. The problem consists of, given a pattern extracted from electroencephalographic (EEG) signals, state the degree of brain development (low or normal/high). To that end, a population of subjects with their EEG assessed by a neurologist is available. A Backpropagation (BP) neural network is used for this supervised classification task, and a comparison with standard statistical classifiers is made. The effect on performance of several preprocessing techniques such as Principal Components Analysis (PCA), normalization and scaling is investigated. It is found better performance in the NN approach, both in terms of efficiency and consistency.
KeywordsLinear Discriminant Analysis Training Group Direct Memory Access Quadratic Discriminant Analysis Brain Maturation
Unable to display preview. Download preview PDF.
- E.R. John et al., ‘Validity, Utility and Limitations of Neurometric Evaluations in Children’, in ‘Event-Related Potentials in Children’, A. Rothenberger (Ed.), Elsevier Biomedical Press, 1982.Google Scholar
- C. Chatfield, A.J. Collins, ‘Introduction to Multivariate Analysis’, Chapman and Hall, 1980.Google Scholar
- L. Moreno, J.L. Sánchez, L. Acosta, J.D. Pineiro, J.L. Ichaso, S. Mañas, ‘Multichannel Digital Processing for EEG Analysis’, Proc. IASTED Int. Symp. on Circuits and Systems, Zurich 1991.Google Scholar
- L. Moreno, J.L. Sánchez, S. Mañas, J. D. Piñeiro, L. Acosta, A. Hamilton, ‘Multivariate Analysis and Mapping of EEG’, 6th European Congress of Clinical Neurophysiology, Lisbon 1992.Google Scholar
- D.E. Rumelhart, J.L. McClelland and PDP Research Group, ‘Parallel Distributed Processing’, vol. 1. Cambridge, MA: MIT Press, 1988.Google Scholar
- S.S. Rao, ‘Optimization Theory and Applications’, 2nd. Edition, Wiley Eastern Limited, 1984.Google Scholar