ECU Software Defect Prediction Model Based on Machine Learning

Qiujun Zhao; Lishuang Zhu; Yu Su; Ziwei Tian; Shuhua Zhou

doi:10.6911/WSRJ.202411_10(11).0005

Authors

Qiujun Zhao
Lishuang Zhu
Yu Su
Ziwei Tian
Shuhua Zhou

DOI:

https://doi.org/10.6911/WSRJ.202411_10(11).0005

Keywords:

Machine Learning; ECU; Software Defects; Prediction Model.

Abstract

With the increasing dependence of the automotive industry on Electronic Control Unit (ECU) software, software defects can lead to serious safety and performance issues. Therefore, developing effective ECU software defect prediction models is crucial for improving software quality and reducing potential risks. This article proposes a machine learning based ECU software defect prediction model, which predicts the existence of software defects by analyzing the source code, historical defect data, and static metrics of the software. Advanced data preprocessing techniques, feature selection methods, and machine learning algorithms are used to improve the accuracy and generalization ability of the model.

Downloads

Download data is not yet available.

References

[1] Wang Tao, Li Weihua, Liu Zun, et al. Software Defect Prediction Model Based on Support Vector Machine [J]. Journal of Northwestern Polytechnical University, 2011, 29 (6): 7.

[2] Fu Yiqi, Dong Wei, Yin Liangze, et al. A software defect prediction model based on combinatorial machine learning algorithm [J]. Computer Research and Development, 2017, 54 (3): 9.

[3] Wang Tao, Li Weihua, Liu Zun, et al. Software Defect Prediction Model Based on Support Vector Machine [J]. Journal of Northwestern Polytechnical University, 2011, 29 (6): 864-870.

[4] Yu Anlei, Pidchang. Software Defect Prediction Model Based on PSO-BP [J]. Computer Engineering and Applications, 2013, 49 (7): 4.

[5] Liu Yang. Research on Software Defect Prediction Based on Machine Learning [J]. Computer Engineering and Applications, 2006, 42 (28): 49-49.

[6] Wang Yuhong, Fan Jing, Lei Min, et al. Software Defect Prediction Model Based on NPE-SVM [J]. Journal of Chengdu University of Information Science and Technology, 2018, 33 (3): 4.

[7] Xie Huaxiang, Gao Jianhua, Huang Zijie. Software Defect Prediction Model Based on SDL LightGBM Ensemble Learning [J]. Computer Engineering and Design, 2024, 45 (3): 769-776.

[8] Yu Anlei, Pidchang. Software Defect Prediction Model Based on PSO-BP, November 26, 2012 [J]. Computer Engineering and Applications, 2012:64-67.

[9] Xue Canguan, Yan Xuefeng. Software defect prediction based on improved deep forest algorithm [J] ComputerScience,2018,45(8):160-165.

[10] Liu Yang. Research on Software Defect Prediction Based on Machine Learning [J]. Computer Engineering and Applications, 2006, 42 (28): 5.

[11] Wei Liangfen. Research on Software Defect Prediction Technology Based on Machine Learning [J]. Journal of Changchun University, 2017, 27 (10): 4.

[12] Wang Hailin, Yu Qian, Li Tong, et al. Research on Software Defect Prediction Model Based on CS-ANN [J]. Computer Application Research, 2017, 34 (2): 7.

[13] Yu Anlei, Pidchang. Software Defect Prediction Model Based on PSO-BP, November 26, 2012 [J]. Computer Engineering and Applications, 2012:64-67.