The Combination of Fuzzy Min–Max Neural Network and Semi-supervised Learning in Solving Liver Disease Diagnosis Support Problem
Autor: | Thi Ngan Tran, Dinh Minh Vu, Ba Dung Le, Manh Tuan Tran |
---|---|
Rok vydání: | 2018 |
Předmět: |
Multidisciplinary
Artificial neural network Computer science business.industry 010102 general mathematics Pattern recognition Sample (statistics) Semi-supervised learning 01 natural sciences Fuzzy logic ComputingMethodologies_PATTERNRECOGNITION Binary classification Learning methods Artificial intelligence 0101 mathematics business Cluster analysis |
Zdroj: | Arabian Journal for Science and Engineering. 44:2933-2944 |
ISSN: | 2191-4281 2193-567X |
Popis: | The novel model namely semi-supervised clustering in the fuzzy min–max neural network is proposed. This model is based on fuzzy min–max neural network and semi-supervised learning method. This model is able to consider as a binary classifier in order to determine an input sample affected the liver disease or not. The proposed model is implemented on a real data including 4.156 samples of patients from Gang Thep Hospital and Thai Nguyen National Hospital and four other datasets from UCI. In this method, all input samples are unlabeled samples. Thus, the expense of labeling the data is omitted. This means that the cost of diagnosis progress from collecting data to making decision is low. Experimental results show that the performance of the proposed model on datasets is higher than other compared ones. |
Databáze: | OpenAIRE |
Externí odkaz: |