An Evolving Cascade Neural Network Technique for Cleaning Sleep Electroencephalograms

Evolving Cascade Neural Networks (ECNNs) and a new training algorithm capable of selecting informative features are described. The ECNN initially learns with one input node and then evolves by adding new inputs as well as new hidden neurons. The resultant ECNN has a near minimal number of hidden neurons and inputs. The algorithm is successfully used for training ECNN to recognise artefacts in sleep electroencephalograms (EEGs) which were visually labelled by EEG-viewers. In our experiments, the ECNN outperforms the standard neural-network as well as evolutionary techniques.

[1]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[2]  Alberto Maria Segre,et al.  Programs for Machine Learning , 1994 .

[3]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[4]  Thomas G. Dietterich.  Machine-Learning Research Four Current Directions , 1997 .

[5]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[6]  Igor V. Tetko,et al.  Variable Selection in the Cascade-Correlation Learning Architecture , 2000 .

[7]  Dhananjay S. Phatak,et al.  Connectivity and performance tradeoffs in the cascade correlation learning architecture , 1994, IEEE Trans. Neural Networks.

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

[9]  Hitoshi Iba,et al.  Automated Discovery of Polynomials by Inductive Genetic Programming , 1999, PKDD.

[10]  Stephen J. Roberts,et al.  ARTEFACT DETECTION IN SLEEP EEG BY THE USE OF KALMAN FILTERING , 2007 .

[11]  Jihoon Yang,et al.  Feature Subset Selection Using a Genetic Algorithm , 1998, IEEE Intell. Syst..

[12]  Arno Siebes,et al.  Data Mining: the search for knowledge in databases. , 1994 .

[13]  F. Smieja.  Neural network constructive algorithms: Trading generalization for learning efficiency? , 1993 .

[14]  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.

[15]  L. Tarassenko,et al.  EEG analysis using self-organisation , 1991 .

[16]  F. Lemke,et al.  GMDH algorithms for complex systems modelling , 1998 .

[17]  Shumeet Baluja,et al.  Reducing Network Depth in the Cascade-Correlation Learning Architecture, , 1994 .