A software defect prediction method based on less sample data learning

Abstract

The invention relates to a software defect prediction method based on few sample data learning, and belongs to the field of software engineering. The method comprises the following steps of S1, constructing an SDNN based on a twin network, i.e., a twin full connection network; S2, inputting positive sample data and negative sample data, performing few-sample learning through an SDNN network, and extracting high-level depth features of the samples on the data; S3, performing comparative learning and probability output on the high-level deep features extracted in the step S2 by adopting a metriclearning function, adjusting the proportion of positive and negative samples, and setting function learning parameters, so that the metric learning function more pays more attention to learning of defective data features; S4, obtaining a prediction result. Compared with the prior art, the method adopted by the invention has the advantages that a better prediction effect can be obtained on a limited, high-dimensional and unbalanced data set, and the performance is more stable under different unbalance rates; and a better prediction result can be obtained under the conditions of less data, lesstime and the like.

Description

technical field [0001] The invention belongs to the field of software engineering and relates to a software defect prediction method based on few-sample data learning. Background technique [0002] Software defect prediction is to use the existing historical data to predict whether there are defects in software. It is an important task in software maintenance and directly related to software cost and software quality. At present, machine learning algorithms are mainly used to build models, train and evaluate historical data, and these historical data are often limited, high-dimensional and class imbalanced. Traditional machine learning algorithms not only require a large amount of data to model It is difficult to learn effective deep representations from high-dimensional data, especially in the early stages of software testing. [0003] For limited software defect data, LinChen et al. (L.Chen, B.Fang, Z.Shang, Y.Tang, Negative samples reduction in cross-company software def...

AI Technical Summary

Problems solved by technology

[0006] According to literature analysis, the existing technology has the following problems: 1) The algorithm complexity is high; 2) The performance of the model depends on a large number of training sample data; 3) There is no effective software prediction model that can simultaneously handle limited, high Dimensional and unbalanced software defect history data

Images