Software defect prediction optimization method based on differential evolution algorithm

Abstract

The present invention discloses a software defect prediction optimization method based on a differential evolution algorithm, and belongs to the field of quality assurance in the software engineering.The method comprises the following steps: arranging modules in the software project, cleaning annotations and the like in the code, and establishing a software defect data code set; arranging the given defect set, including the defect metric design, the defect data marks, and the like, to generate a software defect data set; and with a differential evolution algorithm, creating a ratio of a majority class to a minority class as 2:1 for a defect prediction data set by using a minority class oversampling method, determining an optimal value of the neural network hyper-parameter, using a trainedneural network classification model to test in a test set, and if the performance indicators are satisfied, representing that a software defect prediction model is successfully established. Accordingto the method disclosed by the present invention, corresponding parameter factors in the classification model construction can be automatically classified according to the difference of the data sets, a parameter combination most suitable for the current data set and the classification model can be found, the performance of the software defect prediction model can be improved, and the workload ofparameter searching in the model construction can be reduced.

Description

technical field [0001] The invention belongs to the field of software quality assurance, and in particular relates to a software defect prediction and optimization method based on a differential evolution algorithm. Background technique [0002] The limited software quality assurance resources of software organizations pay more attention to bugs in software modules, such as source codes are more likely to have defects. Therefore, defect detection uses statistical methods or machine learning methods to identify possible errors in source code. The classifiers in these machine learning need to have hyperparameters set in advance. There are no heuristic rules available for these hyperparameters, and many classifiers use default hyperparameters. For example, the number of decision trees in a random forest needs to be configured in advance, and this hyperparameter cannot be obtained through data modeling. The currently available method is to find the parameters that best match t...

AI Technical Summary

Problems solved by technology

[0003] The hyperparameter space search method has the following problems: (1) The hyperparameter space is huge, and it is almost impossible to complete the search of the entire hyperparameter space; (2) The hyperparameter space search cannot be automated

The search of the hyperparameter space is directly related to the establishment of the model, and there is no mature method to propose how to directly find the parameters in the hyperparameter search space and then directly combine them with the existing model training

(3) The hyperparameter space often encounters the problem of class imbalance in the defect prediction data set during the search process

How to effectively combine the two together to solve the problem, there is no mature solution that can be used for reference

Images