Cross-version depth defect prediction method capable of relieving class overlapping problem

Abstract

The invention discloses a cross-version deep defect prediction method capable of relieving a class overlapping problem. The method comprises 1, a deep semantic learning-oriented overall framework in cross-version software defect prediction; 2, a semantic feature learning model based on a convolutional neural network; 3, a hybrid nearest neighbor cleaning strategy for deep semantic learning. According to the method, a hybrid nearest neighbor cleaning strategy is adopted to relieve the class overlapping problem existing in semantic features learned by deep learning. Specifically, for an abstractsyntax tree corresponding to a source code, a convolutional neural network is adopted to learn deep semantic features, and then a hybrid nearest neighbor cleaning strategy is adopted to perform resampling and data cleaning on a labeled data set. By adopting the hybrid nearest neighbor cleaning strategy, the class imbalance problem and the class overlapping problem can be processed, and the statistical analysis result of the data shows that the strategy can improve the performance of software defect prediction based on deep semantic learning.

Description

technical field [0001] The invention specifically relates to a cross-version deep defect prediction method that can alleviate the class overlapping problem. Background technique [0002] Software defect prediction is used to identify software defects in the software development process. The historical data generated during the software development process constitutes the training data of the software defect prediction classifier, and these data can be labeled from multiple granularities such as files and classes. From the perspective of the software process (software process), historical data-oriented metrics are artificially designed to build classification models, including metrics based on lines of code, Halstead scientific metrics, and McCabe cycle complex Degree (cyclomatic complexity) and so on. The traditional intra-item defect prediction model focuses on the static metric, and the classification model is constructed based on the metric, based on the fact that poten...

AI Technical Summary

Problems solved by technology

However, these strategies are all based on traditional static metrics, and there are few studies on class overlap for semantic learning-based software defect prediction.

Images