Learning Multi-class Neural-Network Models from Electroencephalograms

We describe a new algorithm for learning multi-class neural-network models from large-scale clinical electroencephalograms (EEGs). This algorithm trains hidden neurons separately to classify all the pairs of classes. To find best pairwise classifiers, our algorithm searches for input variables which are relevant to the classification problem. Despite patient variability and heavily overlapping classes, a 16-class model learnt from EEGs of 65 sleeping newborns correctly classified 80.8% of the training and 80.1% of the testing examples. Additionally, the neural-network model provides a probabilistic interpretation of decisions.

[1]  Carla E. Brodley,et al.  Multivariate decision trees , 2004, Machine Learning.

[2]  I. Kononenko,et al.  INDUCTION OF DECISION TREES USING RELIEFF , 1995 .

[3]  Krzysztof J. Cios,et al.  A machine learning method for generation of a neural network architecture: a continuous ID3 algorithm , 1992, IEEE Trans. Neural Networks.

[4]  Robert Tibshirani,et al.  Classification by Pairwise Coupling , 1997, NIPS.

[5]  Olaf Breidbach,et al.  ANALYSIS OF EEG DATA ROOM IN SUDDEN INFANT DEATH RISK PATIENTS , 1998 .

[6]  Stephen I. Gallant,et al.  Neural network learning and expert systems , 1993 .

[7]  Herbert Witte,et al.  Common Optimization of Adaptive Preprocessing Units and a Neural Network during the Learning Period. Application in EEG Pattern Recognition , 1997, Neural Networks.

[8]  Carla E. Brodley,et al.  Linear Machine Decision Trees , 1991 .

[9]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

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

[11]  Simon Kasif,et al.  A System for Induction of Oblique Decision Trees , 1994, J. Artif. Intell. Res..

[12]  J. Frenzel,et al.  Clinical relevance of age-dependent EEG signatures in the detection of neonates at high risk for apnea , 1999, Neuroscience Letters.

[13]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[14]  Marcus R. Frean,et al.  A "Thermal" Perceptron Learning Rule , 1992, Neural Computation.

[15]  J Wackermann,et al.  From the 'EEG age' to a rational scale of brain electric maturation. , 1998, Electroencephalography and clinical neurophysiology.