MULTI VIEW NEURAL NETWORK UNTUK HETEROGENOUS DEFECT PREDICTION BERBASIS BOX-COX

• BOY SETIAWAN
• 14230023

---

ABSTRAK

ABSTRAK

Nama : Boy Setiawan

NIM : 14230023

Program Studi : Ilmu Komputer Fakultas : Teknologi Informasi

Jenjang : Strata Dua (S2)

Peminatan : Software Engineering dan Artificial Intelligence

Judul Tesis : Multi View Neural Network Untuk Heterogenous Defect Prediction Berbasis Box-Cox

 

Arsitektur multi-view neural network mampu memanfaatkan representasi multi-view untuk mengekstraksi informasi yang lebih komprehensif dari heterogenous features hasil univariate feature selection dalam memprediksi software defect. Dalam tesis ini dilakukan eksperimen untuk mengatasi permasalahan dari cross-project defect prediction (CPDP) berupa perbedaan distribusi dari software metrics dengan pendekatan transformasi Box-Cox, serta keterbatasan data yang mendasari permasalahan heterogenous defect prediction dengan early fusion. Hasil penelitian menunjukkan bahwa hasil yang dicapai secara konsisten melampaui metode pembanding pada berbagai skenario dengan hasil yang jauh lebih tinggi dibandingkan metode baseline dari penelitian sebelumnya. Analisis variasi proporsi data target menunjukkan potensi untuk mengatasi cold-start problem untuk proyek software baru.

Kata kunci: Heterogenous Defect Prediction, Multi-View Neural Network, Transformasi Box-Cox, Univariate Feature Selection, Cold-Start Problem.

KATA KUNCI

Multi View Neural Network,Box-Cox

---

DAFTAR PUSTAKA

DAFTAR PUSTAKA

 

[1] S. L. Ahmed Abdu Zhengjun Zhai, Hakim A. Abdo, Redhwan Algabri, “Graph-Based Feature Learning for Cross-Project Software Defect Prediction,” Comput. Mater. Contin., vol. 77, no. 1, pp. 161–180, 2023, doi: 10.32604/cmc.2023.043680.

[2] M. A. Elsabagh, M. S. Farhan, and M. G. Gafar, “Cross-projects software defect prediction using spotted hyena optimizer algorithm,” SN Appl. Sci., vol. 2, no. 4, p. 538, Mar. 2020, doi: 10.1007/s42452-020-2320-4.

[3] X.-Y. Jing, H. Chen, and B. Xu, Intelligent Software Defect Prediction. 2023. doi: 10.1007/978-981-99-2842-2.

[4] V. Kumar and A. S. Baghel, “BERTopic: a model to solve cold start problem in software bug recommendation system,” Int. J. Inf. Technol., vol. 17, no. 5, pp. 3125–3130, Jun. 2025, doi: 10.1007/s41870-025-02470-8.

[5] K. Javed, R. Shengbing, M. Asim, and M. A. Wani, “Cross-Project Defect Prediction Based on Domain Adaptation and LSTM Optimization,” Algorithms, vol. 17, no. 5, 2024, doi: 10.3390/a17050175.

[6] Y. Ma, G. Luo, X. Zeng, and A. Chen, “Transfer learning for cross-company software defect prediction,” Inf. Softw. Technol., vol. 54, no. 3, pp. 248–256, 2012, doi: https://doi.org/10.1016/j.infsof.2011.09.007.

[7] J. Wang, Y. Chen, S. Hao, F. Wenjie, and Z. Shen, Balanced Distribution Adaptation for Transfer Learning. 2017, p. 1134. doi: 10.1109/ICDM.2017.150.

[8] C. Liu, D. Yang, X. Xia, M. Yan, and X. Zhang, “A two-phase transfer learning model for cross-project defect prediction,” Inf. Softw. Technol., vol. 107, pp. 125–136, 2019, doi: https://doi.org/10.1016/j.infsof.2018.11.005.

[9] C. Jin, “Cross-project software defect prediction based on domain adaptation learning and optimization,” Expert Syst. Appl., vol. 171, p. 114637, 2021, doi: https://doi.org/10.1016/j.eswa.2021.114637.

[10] L. Gong, S. Jiang, Q. Yu, and L. Jiang, “Unsupervised Deep Domain Adaptation for Heterogeneous Defect Prediction,” Ieice Trans. Inf. Syst., vol. E102.D, no. 3, pp. 537–549, 2019, doi: 10.1587/transinf.2018edp7289.

[11] X. Yu et al., “Feature Disentanglement Based Heterogeneous Defect Prediction,” ACM Trans. Softw. Eng. Methodol., p. 3742474, Jun. 2025, doi: 10.1145/3742474.

[12] J. Nam, W. Fu, S. Kim, T. Menzies, and L. Tan, “Heterogeneous Defect Prediction,” IEEE Trans. Softw. Eng., vol. 44, no. 9, pp. 874–896, Sep. 2018, doi: 10.1109/TSE.2017.2720603.

[13] Q. Yu, S. Jiang, and Y. Zhang, “A feature matching and transfer approach for crosscompany defect prediction,” J. Syst. Softw., vol. 132, pp. 366–378, Oct. 2017, doi: 10.1016/j.jss.2017.06.070.

[14] X. Jing, F. Wu, X. Dong, F. Qi, and B. Xu, “Heterogeneous cross-company defect prediction by unified metric representation and CCA-based transfer learning,” in Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering, Bergamo Italy: ACM, Aug. 2015, pp. 496–507. doi: 10.1145/2786805.2786813.

[15] H. Z.-Q. JIA Xiu-Yi ZHANG Wen-Zhou, LI Wei-Wei, “Feature Representation Method for Heterogeneous Defect Prediction Based on Variational Autoencoders,” J. Softw., vol. 32, no. 7, pp. 2204–2218, 2021.

[16] Z. Li, X.-Y. Jing, F. Wu, X. Zhu, B. Xu, and S. Ying, “Cost-sensitive transfer kernel canonical correlation analysis for heterogeneous defect prediction,” Autom. Softw. Eng., vol. 25, no. 2, pp. 201–245, Jun. 2018, doi: 10.1007/s10515-017-0220-7.

[17] X. Zong, G. Li, S. Zheng, H. Zou, H. Yu, and S. Gao, “Heterogeneous Cross-Project Defect Prediction via Optimal Transport,” IEEE Access, vol. 11, pp. 12015–12030, 2023, doi: 10.1109/access.2023.3241924.

[18] Z. Li, X.-Y. Jing, X. Zhu, H. Zhang, B. Xu, and S. Ying, “Heterogeneous defect prediction with two-stage ensemble learning,” Autom. Softw. Eng., vol. 26, no. 3, pp. 599–651, Sep. 2019, doi: 10.1007/s10515-019-00259-1.

[19] P. Shen, X. Ding, X. Mu, and J. Xu, “A software defect prediction method based on sampling and integration,” J. Phys. Conf. Ser., vol. 1732, no. 1, p. 012002, Jan. 2021, doi: 10.1088/1742-6596/1732/1/012002.

[20] E. O. Kiyak, D. Birant, and K. U. Birant, “Multi-view learning for software defect prediction,” E-Inform. Softw. Eng. J., vol. 15, no. 1, pp. 163–184, Nov. 2021, doi: 10.37190/e-Inf210108.

[21] J. Zhao, X. Xie, X. Xu, and S. Sun, “Multi-view learning overview: Recent progress and new challenges,” Inf. Fusion, vol. 38, pp. 43–54, Nov. 2017, doi: 10.1016/j.inffus.2017.02.007.

[22] X. Xie and S. Sun, “Multi-view twin support vector machines,” Intell Data Anal, vol. 19, no. 4, pp. 701–712, Jul. 2015, doi: 10.3233/IDA-150740.

[23] Y. Makihara, A. Mansur, D. Muramatsu, M. Uddin, and Y. Yagi, “Multi-view discriminant analysis with tensor representation and its application to cross-view gait recognition,” Jul. 2015, doi: 10.1109/FG.2015.7163131.

[24] H. Alsghaier and M. Akour, “Software fault prediction using particle swarm algorithm with genetic algorithm and support vector machine classifier,” Softw. Pract. Exp., vol. 50, no. 4, pp. 407–427, 2020, doi: https://doi.org/10.1002/spe.2784.

[25] M. Shepperd, Q. Song, Z. Sun, and C. Mair, “Data Quality: Some Comments on the NASA Software Defect Datasets,” IEEE Trans. Softw. Eng., vol. 39, no. 9, pp. 1208–1215, 2013, doi: 10.1109/TSE.2013.11

[26] J. Pachouly, S. Ahirrao, K. Kotecha, G. Selvachandran, and A. Abraham, “A systematic literature review on software defect prediction using artificial intelligence: Datasets, Data Validation Methods, Approaches, and Tools,” Eng. Appl. Artif. Intell., vol. 111, p. 104773, 2022, doi: https://doi.org/10.1016/j.engappai.2022.104773.

[27] Y. JIAN, X. YU, Z. XU, and Z. MA, “A Hybrid Feature Selection Method for Software Fault Prediction,” IEICE Trans. Inf. Syst., vol. E102.D, no. 10, pp. 1966–1975, 2019, doi: 10.1587/transinf.2019EDP7033. [28] A. Wang, L. Yang, H. Wu, and Y. Iwahori, “Heterogeneous Defect Prediction Based on Federated Prototype Learning,” IEEE Access, vol. 11, pp. 98618–98632, 2023, doi: 10.1109/ACCESS.2023.3313001.

[29] M. Jureczko and L. Madeyski, Towards identifying software project clusters with regard to defect prediction, vol. 9. 2010. doi: 10.1145/1868328.1868342.

[30] B. Turhan, T. Menzies, A. B. Bener, and J. Di Stefano, “On the relative value of crosscompany and within-company data for defect prediction,” Empir. Softw. Eng., vol. 14, no. 5, pp. 540–578, Oct. 2009, doi: 10.1007/s10664-008-9103-7.

[31] J. Nam, S. J. Pan, and S. Kim, “Transfer defect learning,” in 2013 35th International Conference on Software Engineering (ICSE), San Francisco, CA, USA: IEEE, May 2013, pp. 382–391. doi: 10.1109/ICSE.2013.6606584.

[32] A. Agrawal and T. Menzies, “Is ‘better data’ better than ‘better data miners’?: on the benefits of tuning SMOTE for defect prediction,” in Proceedings of the 40th International Conference on Software Engineering, Gothenburg Sweden: ACM, May 2018, pp. 1050– 1061. doi: 10.1145/3180155.3180197.