Other formats:
BibTeX
LaTeX
RIS
@inproceedings{2211032,
author = {Sadaf, Saadia and Iqbal, Danish and Bühnová, Barbora},
address = {New York, USA},
booktitle = {Proceedings of the International Conference on Evaluation and Assessment in Software Engineering 2022},
doi = {http://dx.doi.org/10.1145/3530019.3531330},
keywords = {Defect Prediction Technique; Software Defect prevention technique; Machine Learning; Artificial Intelligence},
howpublished = {elektronická verze "online"},
language = {eng},
location = {New York, USA},
isbn = {978-1-4503-9613-4},
pages = {393-398},
publisher = {ACM},
title = {AI-Based Software Defect Prediction for Trustworthy Android Apps},
url = {https://dl.acm.org/doi/pdf/10.1145/3530019.3531330},
year = {2022}
}
TY - JOUR
ID - 2211032
AU - Sadaf, Saadia - Iqbal, Danish - Bühnová, Barbora
PY - 2022
TI - AI-Based Software Defect Prediction for Trustworthy Android Apps
PB - ACM
CY - New York, USA
SN - 9781450396134
KW - Defect Prediction Technique
KW - Software Defect prevention technique
KW - Machine Learning
KW - Artificial Intelligence
UR - https://dl.acm.org/doi/pdf/10.1145/3530019.3531330
N2 - 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.
ER -
SADAF, Saadia, Danish IQBAL and Barbora BÜHNOVÁ. AI-Based Software Defect Prediction for Trustworthy Android Apps. Online. In \textit{Proceedings of the International Conference on Evaluation and Assessment in Software Engineering 2022}. New York, USA: ACM, 2022, p.~393-398. ISBN~978-1-4503-9613-4. Available from: https://dx.doi.org/10.1145/3530019.3531330.
|
