Evaluation index system construction method based on distance classification of images and principal component analysis

Abstract

The invention discloses an evaluation index system construction method based on distance classification of images and principal component analysis. The method comprises the steps of selecting initial evaluation indexes; performing index classification based on distance classification of images; performing index screening based on principal component analysis; and obtaining a simplified index system. Elements with high correlation are divided into a class by using a classification method of combining correlation coefficients with the shortest path in the graph theory, namely an image distance classification method, and index representative elements are selected from each class for principal component analysis, so that the information processing workload is reduced. Retention indexes in the principal component analysis and indexes belonging to the same class as the retention indexes are selected as important indexes for constructing an index system, so that missing of important indexes is avoided.

Description

technical field [0001] The invention belongs to the technical field of information processing, and relates to a method for constructing an evaluation index system based on graph-based distance classification and principal component analysis. Background technique [0002] The selection of evaluation indicators and whether the index system is reasonable have a crucial impact on the evaluation results. Then, how to select indicators in the complex and huge indicator system is a difficult problem in the construction of the evaluation indicator system. If all indicators are evaluated, the workload of information processing will be greatly increased due to too many indicators; if only some indicators are selected separately, a lot of original data information may be lost, resulting in inaccurate evaluation results. [0003] Literature: "Construction of Human Comprehensive Development Evaluation Index System Based on Correlation-Principal Component Analysis" System Engineering The...

AI Technical Summary

Problems solved by technology

[0025] 1) The correlation coefficient obtained from the correlation analysis only reflects the correlation between the data, and does not represent the correlation of the degree of influence between the indicators

The correlation coefficient between A and B is very large, but the impact of the two on the evaluation object is independent. If only one of them is deleted based on the correlation, it may cause the loss of important indicators;

[0026] 2) Principal component analysis is carried out in the case of various and complex indicators. If no classification is carried out, the workload of principal component analysis information processing will be increased, and some components discarded during data analysis may also have a degree of correlation with the main elements in the selected principal components. High elements affect the evaluation results

The degree of correlation between A and B is very high. During data analysis, if A has a significant impact on the evaluation results, then B should also have a significant impact on the evaluation results. element, and B is to discard the elements in the principal component, it will inevitably remove B, which will cause the absence of important index B

Images