High-dimensional feature selection algorithm based on Bayesian rough set and cuckoo algorithm

Abstract

The invention discloses a high-dimensional feature selection algorithm based on a Bayesian rough set and a cuckoo algorithm, and the algorithm comprises the steps: obtaining a lung tumor image, carrying out the target contour segmentation, and obtaining a segmented ROI image; extracting a high-dimensional feature component of the segmented ROI image, and constructing a decision information table containing feature attributes based on the feature component; and reducing the original feature space by adopting a BRSGA algorithm to obtain an optimal feature subset, optimizing a penalty factor anda kernel function parameter of the SVM by utilizing a CS algorithm, and inputting the reduced feature subset into the optimized SVM to obtain a classification and identification result. According to the method, the optimal feature subset is generated through the genetic algorithm and the BRS, the feature dimension is reduced on the premise that the classification accuracy is not reduced, the constraint of manual parameter setting is eliminated, and the time consumption is reduced. According to the method, global optimization is carried out on SVM parameters through CS, search space can be explored more effectively, population diversity is enriched, and good robustness and high global search capacity are achieved.

Description

technical field [0001] The invention relates to the technical field of medical image recognition, in particular to a high-dimensional feature selection algorithm based on a Bayesian rough set and a cuckoo algorithm. Background technique [0002] With the development of computer aided diagnosis (CAD) research, medical image processing technology has been developed rapidly. However, the multi-modality, ambiguity and uncertainty of the medical image itself make the missed diagnosis rate and misdiagnosis rate high in the single-modal medical imaging diagnosis process. Therefore, different modal medical image processing technologies emerged as the times require, which are divided into pixel level, feature level and decision level according to different levels. The feature-level processing can realize the compression of the amount of information on the basis of retaining important information, and the processing speed is faster. In the feature-level processing of medical images,...

AI Technical Summary

Problems solved by technology

Many studies on BRS are still in the stage of theoretical analysis, lack of mature and independent models, and have no

Images