Paper Info
Title
A precise classifier for the substances in urinary sediment images based on neural networks and fuzzy reasoning
Abstract
A new method is proposed to classify the substances in urinary sediment images based on the combination of neural networks and fuzzy reasoning. First, the features of normal substance for each one are collected. Second, based on these features, each kind of the normal substance can be classified from all substances in the urinary sediment images by using the BP-NN. One structure of NN is designed for each substance and all of them are trained separately. After that, if abnormal substances cannot be separated properly by NN, they are classified further by using fuzzy reasoning. A database is created for storing the different types of substances which include normal and abnormal substances used as standard patterns. Then the similarity degrees between the standard patterns and tested substances are calculated. Furthermore, other features such as the textures are used for creating "If - then" knowledge base based on the experiences of expert. Finally, the knowledge base for each substance is applied to evaluate the abnormal substance by using fuzzy reasoning. As a result, the accuracy of the automatic classification is improved.
Year
DOI
Venue
2000
10.1109/ICSMC.2000.886395
IEEE International Conference on Systems Man and Cybernetics Conference Proceedings
Keywords
Field
DocType
image classification,database,backpropagation,neural networks,knowledge base,neural nets,shape,sediments,image recognition,neural network,intelligent networks
Neuro-fuzzy,Fuzzy reasoning,Computer science,Urinary sediment,Artificial intelligence,Knowledge base,Backpropagation,Classifier (linguistics),Artificial neural network,Contextual image classification,Machine learning
Conference
ISSN
Citations 
PageRank 
1062-922X
1
0.37
References 
Authors
1
5
Name
Order
Citations
PageRank
n f zhen110.37
keiji taniguchi210.37
shigetaka watanabe310.37
yutaka nakano410.37
Hiroyuki Nakamoto55816.86