On machine learning classification of otoneurological data.

摘要: A dataset including cases of six otoneurological diseases was analysed using machine learning methods to investigate the classification problem these and compare effectiveness different for this data. Linear discriminant analysis best method next multilayer perceptron neural networks provided that data input into a network in form principal components. Nearest neighbour searching, k-means clustering Kohonen achieved almost as good results former, but decision trees slightly worse. Thus, fared well, Naive Bayes rule could not be used since some matrices were singular. Otoneurological subject given can reliably distinguished.