Enhanced relationship classifier based on representative samples

Abstract

The invention relates to an enhanced relationship classifier based on representative samples. The method mainly comprises two steps: first, selecting representative samples to form a new training sample set Xnew according to the clustering membership of samples; and then, constructing a fuzzy relationship matrix R with a Phi composite operator about the clustering membership and the class membership of Xnew. The enhanced relationship classifier is mainly characterized in that (1) the matrix R can reveal the inherent logic relationship between a cluster and a class; (2) the computation complexity of the matrix R decreases from O(NLc) to O(MLc), wherein L is the number of classes, c is the number of clusters, N is the number of samples of the original dataset X, M is the number of samples of Xnew, and N is greater than M; and (3) when sufficient judgment information cannot be found in certain areas in the sample space, the classifier rejects to make strategies for test samples falling into the areas, so as to guarantee the confidence level of classification results.

Description

technical field [0001] The invention belongs to the field of pattern recognition, in particular to a relation classifier based on cluster analysis. Background technique [0002] The main task of pattern recognition is to process and analyze various forms of information representing transactions or phenomena, so as to classify (or group) and explain things or phenomena. The field of traditional pattern recognition contains two important research topics, namely unsupervised clustering and supervised classification. [0003] Supervised classification aims to design a class discriminant function based on the given data and its class label, so that it can make correct predictions for the class of unknown samples. This type of method focuses on the category assignment of samples, which can lead to relatively good generalization for unseen samples. However, this type of algorithm only emphasizes the classification of sample individuals, while ignoring the mining of hidden structu...

AI Technical Summary

Problems solved by technology

When the data set contains many class overlapping regions, R constructed in this way cannot correctly and truly reflect the logical relationship between categories and structures, resulting in the following defects in FRC: lack of robustness of classification; degradation of classification performance; computational burden Heavy

The reason for this phenomenon is that the samples falling into the class overlapping area make the final generated relationship matrix R unable to correctly reflect the distribution characteristics of the data

Images