{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:40:25Z","timestamp":1763106025273,"version":"build-2065373602"},"reference-count":67,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":150,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFC0831706"],"award-info":[{"award-number":["2018YFC0831706"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Software"],"published-print":{"date-parts":[[2024,1]]},"abstract":"<jats:p>\n                    Machine learning\u2010based software defect prediction (SDP) approaches have been commonly proposed to help to deliver high\u2010quality software. Unfortunately, all the previous research conducted without effective feature reduction suffers from high\u2010dimensional data, leading to unsatisfactory prediction performance measures. Moreover, without proper feature reduction, the interpretability and generalization ability of machine learning models in SDP may be compromised, hindering their practical utility in diverse software development environments. In this paper, an SDP approach using deep\n                    <jats:italic>Q<\/jats:italic>\n                    \u2010learning network (DQN)\u2010based feature extraction is proposed to eliminate irrelevant, redundant, and noisy features and improve the classification performance. In the data preprocessing phase, the undersampling method of BalanceCascade is applied to divide the original datasets. As the first step of feature extraction, the weight ranking of all the metric elements is calculated according to the expected cross\u2010entropy. Then, the relation matrix is constructed by applying random matrix theory. After that, the reward principle is defined for computing the\n                    <jats:italic>Q<\/jats:italic>\n                    value of\n                    <jats:italic>Q<\/jats:italic>\n                    \u2010learning based on weight ranking, relation matrix, and the number of errors, according to which a convolutional neural network model is trained on datasets until the sequences of metric pairs are generated for all datasets acting as the revised feature set. Various experiments have been conducted on 11 NASA and 11 PROMISE repository datasets. Sensitive analysis experiments show that binary classification algorithms based on SDP approaches using the DQN\u2010based feature extraction outperform those without using it. We also conducted experiments to compare our approach with four state\u2010of\u2010the\u2010art approaches on common datasets, which show that our approach is superior to these methods in precision,\n                    <jats:italic>F<\/jats:italic>\n                    \u2010measure, area under receiver operating characteristics curve, and Matthews correlation coefficient values.\n                  <\/jats:p>","DOI":"10.1049\/2024\/3946655","type":"journal-article","created":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T13:35:09Z","timestamp":1717076109000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Software Defect Prediction Using Deep\n                    <i>Q<\/i>\n                    \u2010Learning Network\u2010Based Feature Extraction"],"prefix":"10.1049","volume":"2024","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3237-1767","authenticated-orcid":false,"given":"Qinhe","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2775-7591","authenticated-orcid":false,"given":"Jiachen","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3408-552X","authenticated-orcid":false,"given":"Tie","family":"Feng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8811-5765","authenticated-orcid":false,"given":"Jialang","family":"Xue","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3879-968X","authenticated-orcid":false,"given":"Xinxin","family":"Zhu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7596-9491","authenticated-orcid":false,"given":"Ningyang","family":"Zhu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6809-0064","authenticated-orcid":false,"given":"Zhiheng","family":"Li","sequence":"additional","affiliation":[]}],"member":"265","published-online":{"date-parts":[[2024,5,30]]},"reference":[{"key":"e_1_2_12_1_2","doi-asserted-by":"publisher","DOI":"10.1109\/MS.2005.149"},{"key":"e_1_2_12_2_2","doi-asserted-by":"publisher","DOI":"10.4018\/IJOSSP.2018010101"},{"key":"e_1_2_12_3_2","doi-asserted-by":"crossref","unstructured":"PhanA. V.andLe NguyenM. Convolutional neural networks on assembly code for predicting software defects 2017 21st Asia Pacific Symposium on Intelligent and Evolutionary Systems (IES) November 2017 Hanoi Vietnam IEEE 37\u201342 https:\/\/doi.org\/10.1109\/IESYS.2017.8233558 2-s2.0-85049243837.","DOI":"10.1109\/IESYS.2017.8233558"},{"key":"e_1_2_12_4_2","doi-asserted-by":"crossref","unstructured":"ChugA.andDhallS. Software defect prediction using supervised learning algorithm and unsupervised learning algorithm Confluence 2013: The Next Generation Information Technology Summit (4th International Conference) September 2013 Noida IET 173\u2013179 https:\/\/doi.org\/10.1049\/cp.2013.2313 2-s2.0-84902086569.","DOI":"10.1049\/cp.2013.2313"},{"key":"e_1_2_12_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2008.35"},{"key":"e_1_2_12_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11219\u2010018\u20109436\u20104"},{"key":"e_1_2_12_7_2","unstructured":"GrayD. BowesD. DaveyN. SunY. andChristiansonB. Using the support vector machine as a classification method for software defect prediction with static code metrics Engineering Applications of Neural Networks: 11th International Conference EANN 2009 August 2009 London UK Springer Berlin Heidelberg 223\u2013234 https:\/\/doi.org\/10.1007\/978\u20103\u2010642\u201003969\u20100_21 2-s2.0-78049356206."},{"key":"e_1_2_12_8_2","doi-asserted-by":"crossref","unstructured":"GhotraB. McIntoshS. andHassanA. E. Revisiting the impact of classification techniques on the performance of defect prediction models 2015 IEEE\/ACM 37th IEEE International Conference on Software Engineering May 2015 Florence Italy IEEE 789\u2013800 https:\/\/doi.org\/10.1109\/ICSE.2015.91 2-s2.0-84951805519.","DOI":"10.1109\/ICSE.2015.91"},{"key":"e_1_2_12_9_2","doi-asserted-by":"crossref","unstructured":"KhoshgoftaarT. M.andSeliyaN. Tree-based software quality estimation models for fault prediction Proceedings Eighth IEEE Symposium on Software Metrics June 2002 Ottawa ON Canada IEEE 203\u2013214 https:\/\/doi.org\/10.1109\/METRIC.2002.1011339 2-s2.0-37349129968.","DOI":"10.1109\/METRIC.2002.1011339"},{"key":"e_1_2_12_10_2","doi-asserted-by":"crossref","unstructured":"WongH.-M. ChenX. TamH.-H. LinJ. ZhangS. YanS. LiX. andWongK.-C. Feature selection and feature extraction: highlights Proceedings of the 2021 5th International Conference on Intelligent Systems Metaheuristics & Swarm Intelligence April 2021 Victoria Seychelles Association for Computing Machinery 49\u201353 https:\/\/doi.org\/10.1145\/3461598.3461606.","DOI":"10.1145\/3461598.3461606"},{"key":"e_1_2_12_11_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_2_12_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2475625"},{"key":"e_1_2_12_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"e_1_2_12_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2980363"},{"key":"e_1_2_12_15_2","doi-asserted-by":"crossref","unstructured":"HesselM. ModayilJ. Van HasseltH. SchaulT. OstrovskiG. DabneyW. HorganD. PiotB. AzarM. andSilverD. Rainbow: combining improvements in deep reinforcement learning Thirty-Second AAAI Conference on Artificial Intelligence 2018 Palo Alto California USA AAAI Press.","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"e_1_2_12_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/s002200000261"},{"volume-title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","year":"2017","author":"Zheng N.","key":"e_1_2_12_17_2"},{"key":"e_1_2_12_18_2","doi-asserted-by":"crossref","unstructured":"RodriguezD. HerraizI. HarrisonR. DoladoJ. andRiquelmeJ. C. Preliminary comparison of techniques for dealing with imbalance in software defect prediction Proceedings of the 18th International Conference on Evaluation and Assessment in Software Engineering May 2014 London England United Kingdom Association for Computing Machinery 1\u201310 https:\/\/doi.org\/10.1145\/2601248.2601294 2-s2.0-84905497841.","DOI":"10.1145\/2601248.2601294"},{"key":"e_1_2_12_19_2","article-title":"The PROMISE repository of software engineering databases","author":"Sayyad Shirabad J.","year":"2005","journal-title":"School of Information Technology and Engineering"},{"key":"e_1_2_12_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.2007853"},{"key":"e_1_2_12_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10515\u2010021\u201000311\u2010z"},{"key":"e_1_2_12_22_2","doi-asserted-by":"crossref","unstructured":"BouguilaN. WangJ. H. andBen HamzaA. A bayesian approach for software quality prediction 2008 4th International IEEE Conference Intelligent Systems September 2008 Varna Bulgaria IEEE 11-49\u201311-54 https:\/\/doi.org\/10.1109\/IS.2008.4670508 2-s2.0-78650474209.","DOI":"10.1109\/IS.2008.4670508"},{"key":"e_1_2_12_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2017.04.016"},{"key":"e_1_2_12_24_2","first-page":"4241","article-title":"Software defect prediction based on classifiers ensemble","volume":"8","author":"Wang T.","year":"2011","journal-title":"Journal of Information and Computational Science"},{"key":"e_1_2_12_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2009.12.056"},{"key":"e_1_2_12_26_2","doi-asserted-by":"crossref","unstructured":"Owhadi-KareshkM. SedaghatY. andAkbarzadeh-TM.-R. Pre-training of an artificial neural network for software fault prediction 2017 7th International Conference on Computer and Knowledge Engineering (ICCKE) October 2017 Mashhad Iran IEEE 223\u2013228 https:\/\/doi.org\/10.1109\/ICCKE.2017.8167880 2-s2.0-85046399655.","DOI":"10.1109\/ICCKE.2017.8167880"},{"key":"e_1_2_12_27_2","unstructured":"MahaweerawatA. SophasathitP. andLursinsapC. Software fault prediction using fuzzy clustering and radial-basis function network 2002."},{"key":"e_1_2_12_28_2","doi-asserted-by":"crossref","unstructured":"Viet PhanA. Le NguyenM. andThu BuiL. Convolutional neural networks over control flow graphs for software defect prediction 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI) November 2017 Boston MA USA IEEE 45\u201352 https:\/\/doi.org\/10.1109\/ICTAI.2017.00019 2-s2.0-85048483561.","DOI":"10.1109\/ICTAI.2017.00019"},{"key":"e_1_2_12_29_2","doi-asserted-by":"publisher","DOI":"10.11896\/j.issn.1002\u2010137X.2017.04.049"},{"key":"e_1_2_12_30_2","doi-asserted-by":"publisher","DOI":"10.3390\/fi11120246"},{"key":"e_1_2_12_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2022.111537"},{"key":"e_1_2_12_32_2","doi-asserted-by":"publisher","DOI":"10.1360\/jos171848"},{"key":"e_1_2_12_33_2","first-page":"23","article-title":"A method of reducing features based on feature selection twice in text classification","volume":"28","author":"Haifeng L.","year":"2009","journal-title":"Journal of the China Society for Scientific and Technical Informatio"},{"key":"e_1_2_12_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005601"},{"key":"e_1_2_12_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2014.01.018"},{"key":"e_1_2_12_36_2","doi-asserted-by":"crossref","unstructured":"ZhangX. BenK. andZengJ. Cross-entropy: a new metric for software defect prediction 2018 IEEE International Conference on Software Quality Reliability and Security (QRS) July 2018 Lisbon Portugal IEEE 111\u2013122 https:\/\/doi.org\/10.1109\/QRS.2018.00025 2-s2.0-85052283984.","DOI":"10.1109\/QRS.2018.00025"},{"key":"e_1_2_12_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45268-0_6"},{"key":"e_1_2_12_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10515\u2010021\u201000289\u20108"},{"key":"e_1_2_12_39_2","doi-asserted-by":"publisher","DOI":"10.3390\/app13020906"},{"key":"e_1_2_12_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10664\u2010020\u201009848\u20101"},{"key":"e_1_2_12_41_2","doi-asserted-by":"publisher","DOI":"10.1049\/iet\u2010sen.2020.0119"},{"key":"e_1_2_12_42_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469\u20101809.1936.tb02137.x"},{"key":"e_1_2_12_43_2","doi-asserted-by":"crossref","unstructured":"MalhotraR.andKhanK. A study on software defect prediction using feature extraction techniques 2020 8th International Conference on Reliability Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO) June 2020 Noida India IEEE 1139\u20131144 https:\/\/doi.org\/10.1109\/ICRITO48877.2020.9197999.","DOI":"10.1109\/ICRITO48877.2020.9197999"},{"key":"e_1_2_12_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2008.05.018"},{"key":"e_1_2_12_45_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11227\u2010019\u201003051\u2010w"},{"key":"e_1_2_12_46_2","doi-asserted-by":"publisher","DOI":"10.1049\/sfw2.12029"},{"key":"e_1_2_12_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2013.11"},{"key":"e_1_2_12_48_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.catena.2019.104396"},{"key":"e_1_2_12_49_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty995"},{"key":"e_1_2_12_50_2","first-page":"383","volume-title":"Emerging Materials and Mechanics Applications","author":"Wu J. Y.","year":"2012"},{"key":"e_1_2_12_51_2","unstructured":"SimonyanK.andZissermanA. Very deep convolutional networks for large-scale image recognition 2014 https:\/\/doi.org\/10.48550\/arXiv.1409.1556."},{"volume-title":"Advances in Neural Information Processing Systems","year":"2012","author":"Krizhevsky A.","key":"e_1_2_12_52_2"},{"key":"e_1_2_12_53_2","unstructured":"GlorotX. BordesA. andBengioY. Deep sparse rectifier neural networks Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics 2011 Fort Lauderdale FL USA PMLR 315\u2013323."},{"key":"e_1_2_12_54_2","unstructured":"ZeilerM. D.andFergusR. Visualizing and understanding convolutional networks Computer Vision\u2013ECCV 2014 2014 Springer Cham 818\u2013833 https:\/\/doi.org\/10.1007\/978\u20103\u2010319\u201010590\u20101_53 2-s2.0-84906489074."},{"key":"e_1_2_12_55_2","unstructured":"UpadhyayU. RudraB. UpadhyayU. UpadhyayU. andRudraB. Face mask recognition system using CNN model 2021."},{"key":"e_1_2_12_56_2","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.143.1.7063747"},{"key":"e_1_2_12_57_2","doi-asserted-by":"publisher","DOI":"10.1021\/ac60091a002"},{"key":"e_1_2_12_58_2","first-page":"1015","volume-title":"Beyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation","author":"Sokolova M.","year":"2006"},{"key":"e_1_2_12_59_2","doi-asserted-by":"publisher","DOI":"10.1016\/0005\u20102795(75)90109\u20109"},{"key":"e_1_2_12_60_2","doi-asserted-by":"publisher","DOI":"10.1049\/sfw2.12012"},{"key":"e_1_2_12_61_2","doi-asserted-by":"publisher","DOI":"10.1049\/iet\u2010sen.2019.0389"},{"key":"e_1_2_12_62_2","doi-asserted-by":"crossref","unstructured":"YangF. ZengG. ZhongF. ZhengW. andXiaoP. Interpretable software defect prediction incorporating multiple rules 2023 IEEE International Conference on Software Analysis Evolution and Reengineering (SANER) March 2023 Taipa Macao IEEE 940\u2013947 https:\/\/doi.org\/10.1109\/SANER56733.2023.00114.","DOI":"10.1109\/SANER56733.2023.00114"},{"key":"e_1_2_12_63_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2021.111026"},{"key":"e_1_2_12_64_2","doi-asserted-by":"crossref","unstructured":"TsunodaM. MondenA. TodaK. TahirA. BenninK. E. NakasaiK. NaguraM. andMatsumotoK. Using bandit algorithms for selecting feature reduction techniques in software defect prediction 2022 IEEE\/ACM 19th International Conference on Mining Software Repositories (MSR) May 2022 Pittsburgh PA USA IEEE 670\u2013681 https:\/\/doi.org\/10.1145\/3524842.3529093.","DOI":"10.1145\/3524842.3529093"},{"key":"e_1_2_12_65_2","first-page":"1929","article-title":"A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava N.","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_2_12_66_2","doi-asserted-by":"publisher","DOI":"10.4018\/IJKSS.2020040102"},{"key":"e_1_2_12_67_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2014.07.005"}],"container-title":["IET Software"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.spj.sciencemag.org\/ietsfw\/2024\/3946655.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/ietsfw\/2024\/3946655.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/2024\/3946655","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T09:05:30Z","timestamp":1762333530000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/2024\/3946655"}},"subtitle":[],"editor":[{"given":"Siti Hafizah","family":"Ab Hamid","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":67,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["10.1049\/2024\/3946655"],"URL":"https:\/\/doi.org\/10.1049\/2024\/3946655","archive":["Portico"],"relation":{},"ISSN":["1751-8806","1751-8814"],"issn-type":[{"type":"print","value":"1751-8806"},{"type":"electronic","value":"1751-8814"}],"subject":[],"published":{"date-parts":[[2024,1]]},"assertion":[{"value":"2023-09-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-30","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-05-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"3946655"}}