A comparison of neural network and Bayes recognition approaches in the evaluation of the brainstem trigeminal evoked potentials in multiple sclerosis
| Autor: | Andrei V. Chistyakov, Hugo Gutermana, Jean F. Soustiel, Youval Nehmadi, Moshe Feinsod |
|---|---|
| Rok vydání: | 1996 |
| Předmět: |
Self-organizing map
Multiple Sclerosis Computer science Computer Science::Neural and Evolutionary Computation Medicine (miscellaneous) Bayes classifier Machine learning computer.software_genre Trigeminal Nuclei Probabilistic neural network Bayes' theorem Evoked Potentials Auditory Brain Stem Humans Diagnosis Computer-Assisted Learning vector quantization Fourier Analysis Quantitative Biology::Neurons and Cognition Artificial neural network Time delay neural network business.industry Bayes Theorem Signal Processing Computer-Assisted Pattern recognition Perceptron Magnetic Resonance Imaging Electric Stimulation ComputingMethodologies_PATTERNRECOGNITION Neural Networks Computer Artificial intelligence business computer |
| Zdroj: | International Journal of Bio-Medical Computing. 43:203-213 |
| ISSN: | 0020-7101 |
| Popis: | This article describes the application of Multi-Layer Perceptron (MLP), Probabilistic Neural Network and Kohonen's Learning Vector Quantization to the problem of diagnosing Multiple Sclerosis. The classification information is obtained from brainstem trigeminal evoked potential. The performance of the neural networks based classifiers is compared with that of the human experts and the Bayes classifier. The ability of the MLP classifier to generalize is far better than that of the Bayes classifier. The efficiency of the neural network based classifiers in conjunction with several types of well-known evoked potential features, such as Fourier transform space, latency and temporal wave, is examined. Although a large clinical data base would be necessary, before this approach can be fully validated, the initial results are promising. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect