Manifold alignment-based software defect prediction method and system
A software defect prediction and manifold technology, applied in software testing/debugging, computer components, error detection/correction, etc., can solve the problem of low prediction accuracy and achieve the effect of improving the prediction effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0049] This embodiment provides a software defect prediction method based on manifold alignment, the method comprising:
[0050] S1: Obtain source project data and test project data;
[0051] S2: Preprocessing the source item data and the test item data, and dividing the preprocessed source item data into a training set and a verification set;
[0052] S3: Embed the preprocessed project data and training set into the manifold, perform manifold feature learning, and obtain the manifold feature conversion kernel, where the manifold feature conversion kernel is used to make the source project data and the test project The distribution of the data is closer;
[0053] S4: Analyze the distribution difference between the source item data embedded in the manifold and the test item data embedded in the manifold, and obtain the distribution alignment function, where the distribution alignment function is used to align the source item data embedded in the manifold Perform an alignment ...
Embodiment 2
[0095] Based on the same inventive concept, this embodiment provides a software defect prediction system based on manifold alignment, which includes:
[0096] A data acquisition module, configured to acquire source project data and project-to-be-test data;
[0097] A preprocessing module is used to preprocess the source item data and the test item data, and divide the preprocessed source item data into a training set and a verification set;
[0098] The embedding module is used to embed the preprocessed project data and training set into the manifold, perform manifold feature learning, and obtain the manifold feature conversion kernel, wherein the manifold feature conversion kernel is used to make the source item data and The distribution of the data of the project to be tested is closer;
[0099] The difference distribution analysis module is used to analyze the distribution difference between the source item data embedded in the manifold and the test item data embedded in t...
Embodiment 3
[0105] Based on the same inventive concept, the present application also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed, the method as described in the first embodiment is implemented.
[0106] Since the computer-readable storage medium introduced in the third embodiment of the present invention is a computer-readable storage medium used to implement the software defect prediction method based on manifold alignment in the first embodiment of the present invention, based on the introduction in the first embodiment of the present invention method, those skilled in the art can understand the specific structure and deformation of the computer-readable storage medium, so details are not repeated here. All computer-readable storage media used in the method in Embodiment 1 of the present invention fall within the scope of protection intended by the present invention.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More