Class imbalance software defect prediction method based on data resampling

Abstract

The invention provides a class imbalance software defect prediction method based on data resampling. According to the invention, the minority class data and the majority class data which are closest to the minority class data are screened out by calculating the Euclidean distance between the minority class data set and the majority class elements and the Euclidean distance between the minority class data set and the majority class elements, and distance parameters of the minority class data are obtained through the Euclidean distance; the method also includes marking the minority class data in the minority class data set according to the distance parameter, and obtaining a minority data point type; calculating a K neighbor point set of each few element in the minority class data set, counting the number of majority class data and the number of minority class data in K neighbor points, and obtaining the number of newly generated minority class data; and respectively selecting two classifiers, carrying out confidence evaluation on newly generated software defect prediction minority class data to obtain a training data set, training the selected classifiers, and carrying out weighted voting to obtain a final prediction result. According to the invention, the class imbalance problem in the software defect prediction process can be well solved.

Description

technical field [0001] The invention belongs to the field of software defect prediction, in particular to a class imbalance software defect prediction method based on data resampling. Background technique [0002] With the development of society and the improvement of science and technology, the Internet has been deeply integrated into all aspects of our lives. Whether it is online shopping, going out by car, smart home, restaurant ordering, etc., various activities in our daily life can be done through The software is complete, and the usage scenarios of the software have penetrated into all aspects of our food, clothing, housing and transportation. In the process of software development, the demand for software functions is constantly increasing, the number of people served by software is constantly increasing, and the time of software development is constantly being compressed. Various problems lead to software defects in the process of software development. The occurren...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to solve the class imbalance problem in software defect prediction and propose a class imbalance problem software defect prediction method, which is generally applicable to software defect prediction

Images