Adaboost software defect unbalanced data classification method based on improvement

Abstract

The invention discloses an Adaboost software defect unbalanced data classification method based on improvement, and mainly solves the problem that an existing software defect data classification method is poor in classification effect on minority classes. The method comprises the following steps that 1, software data is acquired from a software data set and then preprocessed, software module data is divided into a training set and a testing set for training and testing, and cross validation is performed for ten times; 2, feature selection of the software data is performed by combining a genetic algorithm based on improvement with a BP neural network to obtain an optimal feature subset, and then dimension reduction processing is performed on the software features; 3, the unbalancedness of the software defect data is fully considered, and an Adaboost classifier based on improvement is trained to classify software modules. According to the Adaboost software defect unbalanced data classification method based on improvement, the classification precision of the minority classes can be improved, and the software defect modules can be better detected.

Description

technical field [0001] The invention belongs to the field of software engineering applications, and in particular relates to an improved Adaboost-based software defect imbalance data classification method. Background technique [0002] With the rapid development of contemporary information technology, software systems have been applied to national defense construction, various directions and departments of the national economy, and various fields of human activities. The role played by software systems is increasing, and their size is also increasing accordingly. For example, American Telecom needs a system with more than 100 million lines of code to support; the space shuttle's airborne system has nearly 500,000 lines of code, and the ground control system and processing system has about 350,000 lines of code. After the massive reduction, there are still nearly a million lines of code to operate the entire space system. High stability is extremely important for these equi...

AI Technical Summary

Problems solved by technology

However, since there are far fewer defective modules in software modules than non-defective modules, this is also a classification problem for unbalanced data.

At present, the classification technology for balanced data is relatively mature. However, the classification of unbalanced data, especially the classification of software defect data still needs a lot of research.

Images