AI-Based Software Defect Prediction for Trustworthy Android Apps

Investor logo
Investor logo

Warning

This publication doesn't include Institute of Computer Science. It includes Faculty of Informatics. Official publication website can be found on muni.cz.
Authors

SADAF Saadia IQBAL Danish BÜHNOVÁ Barbora

Year of publication 2022
Type Article in Proceedings
Conference Proceedings of the International Conference on Evaluation and Assessment in Software Engineering 2022
MU Faculty or unit

Faculty of Informatics

Citation
Web https://dl.acm.org/doi/pdf/10.1145/3530019.3531330
Doi http://dx.doi.org/10.1145/3530019.3531330
Keywords Defect Prediction Technique; Software Defect prevention technique; Machine Learning; Artificial Intelligence
Description The present time in the industry is a time where Android Applications are in a wide range with its widespread of the users also. With the increased use of Android applications, the defects in the Android context have also been increasing. The malware of defective software can be any pernicious program with malignant effects. Many techniques based on static, dynamic, and hybrid approaches have been proposed with the combination of Machine learning (ML) or Artificial Intelligence (AI) techniques. In this regard. Scientifically, it is complicated to examine the malignant effects. A single approach cannot predict defects alone, so multiple approaches must be used simultaneously. However, the proposed techniques do not describe the types of defects they address. The paper aims to propose a framework that classifies the defects. The Artificial Intelligence (AI) techniques are described, and the different defects are mapped to them. The mapping of defects to AI techniques is based on the types of defects found in the Android Context. The accuracy of the techniques and the working criteria has been set as the mapping metrics. This will significantly improve the quality and testing of the product. However, the appropriate technique for a particular type of defect could be easily selected. This will reduce the cost and time efforts put into predicting defects.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.

More info