{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T20:07:22Z","timestamp":1771445242999,"version":"3.50.1"},"reference-count":29,"publisher":"Walter de Gruyter GmbH","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100014786","name":"Northern Border University","doi-asserted-by":"publisher","award":["NBU-FFR-2025-1580-XX"],"award-info":[{"award-number":["NBU-FFR-2025-1580-XX"]}],"id":[{"id":"10.13039\/501100014786","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Cross-project defect prediction is an important method of identifying defects in a project. We extract knowledge from the source project and apply it to predict labels for the target project in cross-project defect prediction. However, insignificant and irrelevant features can have an impact on model performance. By selecting only significant and relevant features, hybrid feature selection can help achieve high prediction accuracy. Our goal is to investigate the effect of significant feature selection along with CNN classifier on cross-project defect prediction for multi-class datasets using a hybrid approach. We took advantage of the strengths of Random Forest and Recursive Feature Elimination Cross Validation, which can constructively select a few significant features. Our controlled experiment has a 1 Factor 2 Treatments design. Exploratory Data Analysis demonstrates that all versions of the PROMISE repository are multi-class and contain duplicated rows of data, a distribution gap between values, and imbalance classes. After removing duplicated rows, narrowing the data distribution gap, and balancing classes, we chose a significant feature set using a hybrid approach that included Random Forest and Recursive Feature Elimination Cross Validation. To predict Cross project defects, we used Convolutional Neural Network as a classifier, with SoftMax as the final layer. In terms of Area Under Curve, our experimental setup resulted in an average 78\u202f% prediction accuracy measure across all 14 versions. Our experimental results showed that CNN classifier using features selected through Hybrid Feature Selection has a significant impact on defect prediction accuracy for different datasets in the Cross Project.<\/jats:p>","DOI":"10.1515\/jisys-2025-0025","type":"journal-article","created":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T19:35:36Z","timestamp":1771443336000},"source":"Crossref","is-referenced-by-count":0,"title":["Assessing the impact of crucial feature sets in cross-project for defect prediction employing a hybrid feature selection method"],"prefix":"10.1515","volume":"35","author":[{"given":"Sana","family":"Gul","sequence":"first","affiliation":[{"name":"Faculty of Software Engineering NUML University Islamabad , Islamabad , 44000 , Pakistan"}]},{"given":"Rizwan Bin","family":"Faiz","sequence":"additional","affiliation":[{"name":"Department of Software Engineering , Capital University of Science and Technology Islamabad , Islamabad , 44000 , Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9486-3533","authenticated-orcid":false,"given":"Mohammad","family":"Aljaidi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Faculty of Information Technology , 74476 Zarqa University , Zarqa , 13116 , Jordan"}]},{"given":"Muteb","family":"Alshammari","sequence":"additional","affiliation":[{"name":"Department of Information Technology, Computer Science and Cybersecurity Research Unit , Faculty of Computing and Information Technology Northern Border University , Arar , 91431 , Saudia Arabia"}]}],"member":"374","published-online":{"date-parts":[[2026,2,5]]},"reference":[{"key":"2026021819353365873_j_jisys-2025-0025_ref_001","doi-asserted-by":"crossref","unstructured":"T. Hall, S. Beecham, D. Bowes, D. Gray, and S. Counsell, \u201cA systematic literature review on fault prediction performance in software engineering,\u201d IEEE Trans. Softw. Eng., vol.\u00a038, no. 6, pp.\u00a01276\u20131304, 2012, https:\/\/doi.org\/10.1109\/TSE.2011.103.","DOI":"10.1109\/TSE.2011.103"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_002","doi-asserted-by":"crossref","unstructured":"S. Nawaz, A. Zai, S. Imtiaz, and H. Ashraf, \u201cSystematic literature review: Causes of rework in GSD,\u201d Int. Arab J.\u00a0Inf. Technol., vol. 19, no. 1, pp. 97\u2013109, 2022, https:\/\/doi.org\/10.34028\/iajit\/19\/1\/12.","DOI":"10.34028\/iajit\/19\/1\/12"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_003","doi-asserted-by":"crossref","unstructured":"S. Wang, T. Liu, J. Nam, and L. Tan, \u201cDeep semantic feature learning for software defect prediction,\u201d IEEE Trans. Softw. Eng., vol.\u00a046, no. 12, pp.\u00a01267\u20131293, 2020, https:\/\/doi.org\/10.1109\/TSE.2018.2877612.","DOI":"10.1109\/TSE.2018.2877612"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_004","doi-asserted-by":"crossref","unstructured":"T. Menzies, Z. Milton, B. Turhan, B. Cukic, Y. Jiang, and A. Bener, \u201cDefect prediction from static code features: Current results, limitations, new approaches,\u201d Autom. Softw. Eng., vol.\u00a017, no. 4, pp.\u00a0375\u2013407, 2010, https:\/\/doi.org\/10.1007\/s10515-010-0069-5.","DOI":"10.1007\/s10515-010-0069-5"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_005","doi-asserted-by":"crossref","unstructured":"W. Ma, L. Chen, Y. Yang, Y. Zhou, and B. Xu, \u201cEmpirical analysis of network measures for effort-aware fault-proneness prediction,\u201d Inf. Softw. Technol., vol.\u00a069, pp.\u00a050\u201370, 2016, https:\/\/doi.org\/10.1016\/j.infsof.2015.09.001.","DOI":"10.1016\/j.infsof.2015.09.001"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_006","doi-asserted-by":"crossref","unstructured":"S. Herbold, A. Trautsch, and J. Grabowski, \u201cA comparative study to benchmark cross-project defect prediction approaches,\u201d IEEE Trans. Softw. Eng., vol.\u00a044, no. 9, pp.\u00a0811\u2013833, 2018, https:\/\/doi.org\/10.1109\/TSE.2017.2724538.","DOI":"10.1109\/TSE.2017.2724538"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_007","doi-asserted-by":"crossref","unstructured":"M. Kondo, C. P. Bezemer, Y. Kamei, A. E. Hassan, and O. Mizuno, \u201cThe impact of feature reduction techniques on defect prediction models,\u201d Empir. Softw. Eng., vol.\u00a024, no. 4, pp.\u00a01925\u20131963, 2019, https:\/\/doi.org\/10.1007\/s10664-018-9679-5.","DOI":"10.1007\/s10664-018-9679-5"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_008","doi-asserted-by":"crossref","unstructured":"K. Zhu, S. Ying, N. Zhang, and D. Zhu, \u201cSoftware defect prediction based on enhanced metaheuristic feature selection optimization and a hybrid deep neural network,\u201d J.\u00a0Syst. Softw., vol.\u00a0180, p.\u00a0111026, 2021, https:\/\/doi.org\/10.1016\/j.jss.2021.111026.","DOI":"10.1016\/j.jss.2021.111026"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_009","doi-asserted-by":"crossref","unstructured":"J. Li, P. He, J. Zhu, and M. R. Lyu, \u201cSoftware defect prediction via convolutional neural network,\u201d in 2017 IEEE International Conference on Software Quality, Reliability and Security (QRS), Prague, Czech Republic, IEEE, 2017, pp.\u00a0318\u2013328.","DOI":"10.1109\/QRS.2017.42"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_010","doi-asserted-by":"crossref","unstructured":"S. Qiu, H. Xu, J. Deng, S. Jiang, and L. Lu, \u201cTransfer convolutional neural network for cross-project defect prediction,\u201d Appl. Sci., vol.\u00a09, no. 13, p.\u00a02660, 2019, https:\/\/doi.org\/10.3390\/app9132660.","DOI":"10.3390\/app9132660"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_011","doi-asserted-by":"crossref","unstructured":"A. Wang, Y. Zhang, H. Wu, K. Jiang, and M. Wang, \u201cFew-shot learning based balanced distribution adaptation for heterogeneous defect prediction,\u201d IEEE Access, vol.\u00a08, pp.\u00a032989\u201333001, 2020, https:\/\/doi.org\/10.1109\/ACCESS.2020.2973924.","DOI":"10.1109\/ACCESS.2020.2973924"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_012","doi-asserted-by":"crossref","unstructured":"Y. Ren, P. Zhao, Y. Sheng, D. Yao, and Z. Xu, \u201cRobust softmax regression for multi-class classification with self-paced learning,\u201d in Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, Melbourne, Australia, International Joint Conferences on Artificial Intelligence Organization, 2017, pp.\u00a02641\u20132647.","DOI":"10.24963\/ijcai.2017\/368"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_013","unstructured":"W. Liu, Y. Wen, Z. Yu, and M. Yang, \u201cLarge-margin softmax loss for convolutional neural networks,\u201d arXiv, 2016, https:\/\/doi.org\/10.48550\/ARXIV.1612.02295."},{"key":"2026021819353365873_j_jisys-2025-0025_ref_014","doi-asserted-by":"crossref","unstructured":"Y. Sun et al.., \u201cAdversarial learning for cross-project semi-supervised defect prediction,\u201d IEEE Access, vol.\u00a08, pp.\u00a032674\u201332687, 2020, https:\/\/doi.org\/10.1109\/ACCESS.2020.2974527.","DOI":"10.1109\/ACCESS.2020.2974527"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_015","doi-asserted-by":"crossref","unstructured":"S. Hosseini, B. Turhan, and M. M\u00e4ntyl\u00e4, \u201cA benchmark study on the effectiveness of search-based data selection and feature selection for cross project defect prediction,\u201d Inf. Softw. Technol., vol.\u00a095, pp.\u00a0296\u2013312, 2018, https:\/\/doi.org\/10.1016\/j.infsof.2017.06.004.","DOI":"10.1016\/j.infsof.2017.06.004"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_016","doi-asserted-by":"crossref","unstructured":"L. Sheng, L. Lu, and J. Lin, \u201cAn adversarial discriminative convolutional neural network for cross-project defect prediction,\u201d IEEE Access, vol.\u00a08, pp.\u00a055241\u201355253, 2020, https:\/\/doi.org\/10.1109\/ACCESS.2020.2981869.","DOI":"10.1109\/ACCESS.2020.2981869"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_017","doi-asserted-by":"crossref","unstructured":"C. Pan, M. Lu, B. Xu, and H. Gao, \u201cAn improved CNN model for within-project software defect prediction,\u201d Appl. Sci., vol.\u00a09, no. 10, p.\u00a02138, 2019, https:\/\/doi.org\/10.3390\/app9102138.","DOI":"10.3390\/app9102138"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_018","doi-asserted-by":"crossref","unstructured":"A. Jalil, R. B. Faiz, S. Alyahya, and M. Maddeh, \u201cImpact of optimal feature selection using hybrid method for a multiclass problem in cross project defect prediction,\u201d Appl. Sci., vol.\u00a012, no. 23, p.\u00a012167, 2022, https:\/\/doi.org\/10.3390\/app122312167.","DOI":"10.3390\/app122312167"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_019","doi-asserted-by":"crossref","unstructured":"S. Noreen, R. B. Faiz, S. Alyahya, and M. Maddeh, \u201cPerformance evaluation of convolutional neural network for multi-class in cross project defect prediction,\u201d Appl. Sci., vol.\u00a012, no. 23, p.\u00a012269, 2022, https:\/\/doi.org\/10.3390\/app122312269.","DOI":"10.3390\/app122312269"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_020","doi-asserted-by":"crossref","unstructured":"W. M. Shaban, A. H. Rabie, A. I. Saleh, and M. A. Abo-Elsoud, \u201cA new COVID-19 patients detection strategy (CPDS) based on hybrid feature selection and enhanced KNN classifier,\u201d Knowl.-Based Syst., vol.\u00a0205, p.\u00a0106270, 2020, https:\/\/doi.org\/10.1016\/j.knosys.2020.106270.","DOI":"10.1016\/j.knosys.2020.106270"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_021","doi-asserted-by":"crossref","unstructured":"N. Ahmed, J.\u00a0I. Rafiq, and M. R. Islam, \u201cEnhanced human activity recognition based on smartphone sensor data using hybrid feature selection model,\u201d Sensors, vol.\u00a020, no. 1, p.\u00a0317, 2020, https:\/\/doi.org\/10.3390\/s20010317.","DOI":"10.3390\/s20010317"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_022","doi-asserted-by":"crossref","unstructured":"N. Almugren and H. Alshamlan, \u201cA survey on hybrid feature selection methods in microarray gene expression data for cancer classification,\u201d IEEE Access, vol.\u00a07, pp.\u00a078533\u201378548, 2019, https:\/\/doi.org\/10.1109\/ACCESS.2019.2922987.","DOI":"10.1109\/ACCESS.2019.2922987"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_023","doi-asserted-by":"crossref","unstructured":"S. R. Bansal, S. Wadhawan, and R. Goel, \u201cmRMR-PSO: A hybrid feature selection technique with a multiobjective approach for sign language recognition,\u201d Arab. J.\u00a0Sci. Eng., vol.\u00a047, no. 8, pp.\u00a010365\u201310380, 2022, https:\/\/doi.org\/10.1007\/s13369-021-06456-z.","DOI":"10.1007\/s13369-021-06456-z"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_024","doi-asserted-by":"crossref","unstructured":"A. K. Shukla, P. Singh, and M. Vardhan, \u201cA new hybrid feature subset selection framework based on binary genetic algorithm and information theory,\u201d Int. J.\u00a0Comput. Intell. Appl., vol.\u00a018, no. 03, p.\u00a01950020, 2019, https:\/\/doi.org\/10.1142\/S1469026819500202.","DOI":"10.1142\/S1469026819500202"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_025","doi-asserted-by":"crossref","unstructured":"Q. Al-Tashi, S. J. Abdul Kadir, H. M. Rais, S. Mirjalili, and H. Alhussian, \u201cBinary optimization using hybrid grey wolf optimization for feature selection,\u201d IEEE Access, vol.\u00a07, pp.\u00a039496\u201339508, 2019, https:\/\/doi.org\/10.1109\/ACCESS.2019.2906757.","DOI":"10.1109\/ACCESS.2019.2906757"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_026","doi-asserted-by":"crossref","unstructured":"A. Prinzie and D. Van Den Poel, \u201cRandom forests for multiclass classification: Random MultiNomial logit,\u201d Expert Syst. Appl., vol.\u00a034, no. 3, pp.\u00a01721\u20131732, 2008, https:\/\/doi.org\/10.1016\/j.eswa.2007.01.029.","DOI":"10.1016\/j.eswa.2007.01.029"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_027","unstructured":"\u201cSoftware defect prediction dataset.\u201d https:\/\/doi.org\/10.6084\/m9.figshare.13536506.v1."},{"key":"2026021819353365873_j_jisys-2025-0025_ref_028","doi-asserted-by":"crossref","unstructured":"Y. Saeys, T. Abeel, and Y. Van De Peer, \u201cRobust feature selection using ensemble feature selection techniques,\u201d in Machine Learning and Knowledge Discovery in Databases, W. Daelemans, B. Goethals, and K. Morik, Eds., in Lecture Notes in Computer Science, vol.\u00a05212, Berlin, Heidelberg: Springer Berlin Heidelberg, 2008, pp.\u00a0313\u2013325.","DOI":"10.1007\/978-3-540-87481-2_21"},{"key":"2026021819353365873_j_jisys-2025-0025_ref_029","doi-asserted-by":"crossref","unstructured":"R. C. Chen, C. Dewi, S. W. Huang, and R. E. Caraka, \u201cSelecting critical features for data classification based on machine learning methods,\u201d J.\u00a0Big Data, vol.\u00a07, no. 1, p.\u00a052, 2020, https:\/\/doi.org\/10.1186\/s40537-020-00327-4.","DOI":"10.1186\/s40537-020-00327-4"}],"container-title":["Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/jisys-2025-0025\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/jisys-2025-0025\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T19:35:41Z","timestamp":1771443341000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/jisys-2025-0025\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,1]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,2,5]]},"published-print":{"date-parts":[[2026,1,23]]}},"alternative-id":["10.1515\/jisys-2025-0025"],"URL":"https:\/\/doi.org\/10.1515\/jisys-2025-0025","relation":{},"ISSN":["2191-026X"],"issn-type":[{"value":"2191-026X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,1]]},"article-number":"20250025"}}