@inproceedings{ca5b20b75247478f9aba4d823a84dc06,
title = "Intelligent Radar Software Defect Prediction Approach and Its Application",
abstract = "Radar software defects are not used and applied effectively and sufficiently in the testing process. As a result, defects often occur repeatedly, which causes safety hazards in software operation. To resolve this problem, this paper proposed a novel intelligent defect prediction approach for radar software by using Na{\"i}ve Bayesian to classify defect data and predict defects according to radar software requirements. We apply the proposed approach on the typical radar software. The experiment results show that the defect prediction precision rate of the proposed defect prediction approach is 75\%, and the prediction recall rate is 70\%, approx. The experiment results are better compared to the defect prediction methods without Na{\"i}ve Bayesian and defect classification. Therefore, the proposed defect prediction approach can be applied on radar software effectively and applicably to improve the effectiveness of radar software testing and provide the positive feedback to the radar software design process significantly.",
keywords = "Defect Prediction, Intelligent, Na{\"i}ve Bayesian, Radar Software",
author = "Liu Xi and Li Haifeng and Xie Xuyang",
note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 20th IEEE International Conference on Software Quality, Reliability, and Security, QRS 2020 ; Conference date: 11-12-2020 Through 14-12-2020",
year = "2020",
month = dec,
doi = "10.1109/QRS-C51114.2020.00017",
language = "英语",
series = "Proceedings - Companion of the 2020 IEEE 20th International Conference on Software Quality, Reliability, and Security, QRS-C 2020",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "32--37",
booktitle = "Proceedings - Companion of the 2020 IEEE 20th International Conference on Software Quality, Reliability, and Security, QRS-C 2020",
address = "美国",
}