High-dimensional multi-objective evaluation method and system

Abstract

The invention discloses a high-dimensional multi-objective evaluation method, which comprises the following steps that: obtaining a high-dimensional multi-objective set to be evaluated, wherein the high-dimensional multi-objective set to be evaluated consists of the attribute values of a plurality of individual multi-dimensional objectives; according to dependency between objectives, sorting eachobjective in the high-dimensional multi-objective set to be evaluated; according to a set, of which the target is sorted, to be evaluated, mapping each individual into a two-dimensional space point set; determining a distance between the geometric center of a polygon formed by the two-dimensional space point set corresponding to each individual and the original point of a rectangular coordinate system, and marking as a first evaluation index; determining the area of the polygon formed by the two-dimensional space point set corresponding to each individual, and marking as a second evaluation index; and according to the first evaluation index and the second evaluation index, evaluating the high-dimensional multi-objective set to be evaluated. By use of the high-dimensional multi-objective evaluation method and system, the scientificity and the effectiveness of evaluation can be guaranteed.

Description

technical field [0001] The invention relates to the field of multi-high-dimensional object optimization, in particular to a high-dimensional multi-objective evaluation method and system. Background technique [0002] The optimization problems involved in practical engineering applications often have multiple conflicting and coupled optimization objectives. When there are more than four objective functions, it is called a high-dimensional multi-objective optimization problem. Due to the existence of multiple conflicting and coupled optimization objectives, high-dimensional multi-objective optimization problems are often unfavorable for decision makers. Visualization technology uses methods such as computer graphics, image processing, and signal processing to express the internal structure, information, and knowledge of data. choose. [0003] High-dimensional multi-objective visualization techniques mainly include global visualization and dimensionality reduction visualizati...

AI Technical Summary

Problems solved by technology

Dimensionality reduction visualization technology is convenient for visualization in low-dimensional space, but it will lose the effective information of the set and affect the correctness of decision-making

Images