Within-project and cross-project just-in-time defect prediction based on denoising autoencoder and convolutional neural network
Just-in-time defect prediction is an important and useful branch in software defect prediction. At present, deep learning is a research hotspot in the field of artificial intelligence, which can combine basic defect features into deep semantic features and make up for the shortcomings of machine lea...
Uloženo v:
| Vydáno v: | IET software Ročník 14; číslo 3; s. 185 - 195 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
The Institution of Engineering and Technology
01.06.2020
|
| Témata: | |
| ISSN: | 1751-8806, 1751-8814, 1751-8814 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Just-in-time defect prediction is an important and useful branch in software defect prediction. At present, deep learning is a research hotspot in the field of artificial intelligence, which can combine basic defect features into deep semantic features and make up for the shortcomings of machine learning algorithms. However, the mainstream deep learning techniques have not been applied yet in just-in-time defect prediction. Therefore, the authors propose a novel just-in-time defect prediction model named DAECNN-JDP based on denoising autoencoder and convolutional neural network in this study, which has three main advantages: (i) Different weights for the position vector of each dimension feature are set, which can be automatically trained by adaptive trainable vector. (ii) Through the training of denoising autoencoder, the input features that are not contaminated by noise can be obtained, thus learning more robust feature representation. (iii) The authors leverage a powerful representation-learning technique, convolution neural network, to construct the basic change features into the abstract deep semantic features. To evaluate the performance of the DAECNN-JDP model, they conduct extensive within-project and cross-project defect prediction experiments on six large open source projects. The experimental results demonstrate that the superiority of DAECNN-JDP on five evaluation metrics. |
|---|---|
| AbstractList | Just-in-time defect prediction is an important and useful branch in software defect prediction. At present, deep learning is a research hotspot in the field of artificial intelligence, which can combine basic defect features into deep semantic features and make up for the shortcomings of machine learning algorithms. However, the mainstream deep learning techniques have not been applied yet in just-in-time defect prediction. Therefore, the authors propose a novel just-in-time defect prediction model named DAECNN-JDP based on denoising autoencoder and convolutional neural network in this study, which has three main advantages: (i) Different weights for the position vector of each dimension feature are set, which can be automatically trained by adaptive trainable vector. (ii) Through the training of denoising autoencoder, the input features that are not contaminated by noise can be obtained, thus learning more robust feature representation. (iii) The authors leverage a powerful representation-learning technique, convolution neural network, to construct the basic change features into the abstract deep semantic features. To evaluate the performance of the DAECNN-JDP model, they conduct extensive within-project and cross-project defect prediction experiments on six large open source projects. The experimental results demonstrate that the superiority of DAECNN-JDP on five evaluation metrics. Just‐in‐time defect prediction is an important and useful branch in software defect prediction. At present, deep learning is a research hotspot in the field of artificial intelligence, which can combine basic defect features into deep semantic features and make up for the shortcomings of machine learning algorithms. However, the mainstream deep learning techniques have not been applied yet in just‐in‐time defect prediction. Therefore, the authors propose a novel just‐in‐time defect prediction model named DAECNN‐JDP based on denoising autoencoder and convolutional neural network in this study, which has three main advantages: (i) Different weights for the position vector of each dimension feature are set, which can be automatically trained by adaptive trainable vector. (ii) Through the training of denoising autoencoder, the input features that are not contaminated by noise can be obtained, thus learning more robust feature representation. (iii) The authors leverage a powerful representation‐learning technique, convolution neural network, to construct the basic change features into the deep semantic features. To evaluate the performance of the DAECNN‐JDP model, they conduct extensive within‐project and cross‐project defect prediction experiments on six large open source projects. The experimental results demonstrate that the superiority of DAECNN‐JDP on five evaluation metrics. |
| Author | Zhu, Dandan Ying, Shi Zhu, Kun Zhang, Nana |
| Author_xml | – sequence: 1 givenname: Kun surname: Zhu fullname: Zhu, Kun organization: 1School of Computer Science, Wuhan University, No.299 Bayi Road, Wuhan, People's Republic of China – sequence: 2 givenname: Nana surname: Zhang fullname: Zhang, Nana organization: 1School of Computer Science, Wuhan University, No.299 Bayi Road, Wuhan, People's Republic of China – sequence: 3 givenname: Shi surname: Ying fullname: Ying, Shi email: yingshl@whu.edu.cn organization: 1School of Computer Science, Wuhan University, No.299 Bayi Road, Wuhan, People's Republic of China – sequence: 4 givenname: Dandan surname: Zhu fullname: Zhu, Dandan organization: 2Artificial Intelligence Institute, Shanghai Jiaotong University, No.800 Dongchuan Road, Shanghai, People's Republic of China |
| BookMark | eNqFkMtOwzAQRS1UJErhA9jlB1L8iPNgBxUFpEosAHUZufEEHFK7sh2qrvh1nAZ1waKsZjS6Zzw-52ikjQaErgieEpwU1wp87EBPKSbFFNMsP0FjknES5zlJRocep2fo3LkGY845K8boe6n8h9LxxpoGKh8JLaPKGucOk6ZzPg4Jr9YQSaj72caCVJVXRkcr4UBGoZGgjXJKv0ei8wZ0ZSTYYZ_RX6bt-rhoIw2d3Re_NfbzAp3WonVw-Vsn6G1-_zp7jBfPD0-z20VcMZYksWCM06KWSU4TRigAzSQPjUjSAnJY1XnGMyA4LTivixRoSmXGBKtTmmYEKjZB2bB3_zkLdVkpL_qTvBWqLQkue49l8FgGj2Xvsew9BpL8ITdWrYXdHWVuBmarWtj9D5Qv8yW9m2NM8yTA8QD3scZ0NlhzRx77ARrrnjs |
| CitedBy_id | crossref_primary_10_1016_j_knosys_2022_108852 crossref_primary_10_1002_spe_3274 crossref_primary_10_1007_s11227_021_04113_8 crossref_primary_10_1007_s40747_022_00676_y crossref_primary_10_1007_s10515_022_00344_y crossref_primary_10_1007_s11831_022_09787_8 crossref_primary_10_1007_s10844_023_00793_1 crossref_primary_10_1016_j_ins_2021_11_029 crossref_primary_10_1007_s11432_023_4127_5 crossref_primary_10_1109_ACCESS_2024_3388489 crossref_primary_10_1007_s10664_023_10335_6 crossref_primary_10_3390_aerospace11050393 crossref_primary_10_1016_j_jss_2022_111537 crossref_primary_10_1145_3567550 crossref_primary_10_1007_s10515_024_00465_6 crossref_primary_10_1371_journal_pone_0299585 crossref_primary_10_1109_TSE_2022_3173346 crossref_primary_10_1016_j_infsof_2021_106588 crossref_primary_10_1109_TSE_2022_3150153 crossref_primary_10_1145_3664607 crossref_primary_10_3390_su17146284 crossref_primary_10_1142_S0218194025500226 crossref_primary_10_1007_s00521_024_10937_1 crossref_primary_10_1007_s42979_023_01906_x crossref_primary_10_1049_2024_5358773 crossref_primary_10_1016_j_ins_2021_05_008 crossref_primary_10_1109_ACCESS_2023_3343329 crossref_primary_10_1155_2022_5058461 crossref_primary_10_1007_s10664_024_10495_z crossref_primary_10_1016_j_ins_2024_120595 crossref_primary_10_1016_j_jss_2024_112214 crossref_primary_10_1049_sfw2_12029 crossref_primary_10_1007_s00521_024_09930_5 |
| Cites_doi | 10.1145/2970276.2970357 10.1145/3106237.3106257 10.1109/ICSE.2017.9 10.1109/TSE.2008.90 10.1109/ICSE.2009.5070510 10.1007/s10664-015-9400-x 10.1109/32.859533 10.1145/1390156.1390294 10.1145/2597073.2597075 10.1109/TR.2016.2588139 10.1007/s10664-018-9661-2 10.1145/1134285.1134349 10.1109/ICASSP.2017.7953077 10.1145/2884781.2884804 10.1613/jair.953 10.1109/MSR.2019.00016 10.1162/NECO_a_00142 10.1109/TSE.2012.70 10.1145/2025113.2025121 10.1145/2950290.2950353 10.1002/bltj.2229 10.1007/s11063-018-9831-7 10.1007/s10664-017-9522-4 10.1016/j.neunet.2018.04.016 10.1007/s10664-012-9228-6 10.1016/j.neucom.2014.08.092 10.1145/1062455.1062514 10.1109/TSE.2010.81 10.1145/2950290.2950334 10.1145/2567948.2577348 10.1016/j.infsof.2017.03.007 10.1109/CVPR.2015.7298932 10.1109/QRS.2015.14 10.1109/ASE.2015.73 10.1145/2393596.2393670 10.1109/TSE.2005.74 |
| ContentType | Journal Article |
| Copyright | The Institution of Engineering and Technology 2020 The Institution of Engineering and Technology |
| Copyright_xml | – notice: The Institution of Engineering and Technology – notice: 2020 The Institution of Engineering and Technology |
| DBID | AAYXX CITATION |
| DOI | 10.1049/iet-sen.2019.0278 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1751-8814 |
| EndPage | 195 |
| ExternalDocumentID | 10_1049_iet_sen_2019_0278 SFW2BF00284 |
| Genre | article |
| GrantInformation_xml | – fundername: Innovative Research Group Project of the National Natural Science Foundation of China grantid: 61672392 – fundername: Innovative Research Group Project of the National Natural Science Foundation of China grantid: 61373038 – fundername: Innovative Research Group Project of the National Natural Science Foundation of China funderid: 61672392 – fundername: Innovative Research Group Project of the National Natural Science Foundation of China funderid: 61373038 |
| GroupedDBID | 0R 24P 29I 3V. 4.4 4IJ 5GY 6IK 8AL 8FE 8FG 8VB AAJGR ABJCF ABPTK ABUWG ACDCL ACGFS ACIWK AENEX AFKRA ALMA_UNASSIGNED_HOLDINGS ARAPS AZQEC BENPR BFFAM BGLVJ BPHCQ CS3 DU5 DWQXO EBS EJD ESX GNUQQ GOZPB GRPMH HCIFZ HZ IFIPE IPLJI JAVBF K6V K7- L6V LAI LOTEE LXI M0N M43 M7S MS NADUK NXXTH O9- OCL P62 PQEST PQQKQ PQUKI PROAC PTHSS QWB RIE RNS RUI U5U UNMZH UNR ZL0 .DC 0R~ 0ZK 1OC 2QL 96U AAHJG AAMMB ABMDY ABQXS ACCMX ACESK ACGFO ACXQS ADEYR AEFGJ AEGXH AFAZI AGXDD AIDQK AIDYY ALUQN AVUZU CCPQU F8P GROUPED_DOAJ HZ~ IAO IDLOA ITC K1G MCNEO MS~ OK1 PHGZM PHGZT PQGLB PUEGO WIN AAYXX AFFHD CITATION |
| ID | FETCH-LOGICAL-c3344-a33529fd4824312ee27d5312a469e8ebf8757e106955f96e262d73a3f62671ec3 |
| IEDL.DBID | 24P |
| ISICitedReferencesCount | 39 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000585778800002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1751-8806 1751-8814 |
| IngestDate | Wed Oct 29 21:13:20 EDT 2025 Tue Nov 18 22:00:25 EST 2025 Tue Sep 09 05:10:10 EDT 2025 Tue Jan 05 21:44:07 EST 2021 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Keywords | mainstream deep learning techniques just-in-time defect prediction model cross-project defect prediction experiments denoising autoencoder basic defect features learning (artificial intelligence) autoencoder convolutional neural network neural nets software defect prediction convolution neural network |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c3344-a33529fd4824312ee27d5312a469e8ebf8757e106955f96e262d73a3f62671ec3 |
| PageCount | 11 |
| ParticipantIDs | wiley_primary_10_1049_iet_sen_2019_0278_SFW2BF00284 iet_journals_10_1049_iet_sen_2019_0278 crossref_citationtrail_10_1049_iet_sen_2019_0278 crossref_primary_10_1049_iet_sen_2019_0278 |
| ProviderPackageCode | RUI |
| PublicationCentury | 2000 |
| PublicationDate | 20200600 June 2020 2020-06-00 |
| PublicationDateYYYYMMDD | 2020-06-01 |
| PublicationDate_xml | – month: 6 year: 2020 text: 20200600 |
| PublicationDecade | 2020 |
| PublicationTitle | IET software |
| PublicationYear | 2020 |
| Publisher | The Institution of Engineering and Technology |
| Publisher_xml | – name: The Institution of Engineering and Technology |
| References | Wang, M.; Wu, Z.; Sun, X. (C18) 2019; 49 Huang, Q.; Xia, X.; Lo, D. (C2) 2018; 24 Kamei, Y.; Fukushima, T.; Mcintosh, S. (C1) 2016; 21 Kamei, Y.; Shihab, E.; Adams, B. (C4) 2013; 39 Huang, Q.; Shihab, E.; Xia, X. (C38) 2017; 23 Shin, Y.; Meneely, A.; Williams, L. (C32) 2011; 37 Yang, X.; Lo, D.; Xia, X. (C3) 2017; 87 Ferles, C.; Papanikolaou, Y.; Naidoo, K.J. (C16) 2018; 105 Xia, X.; Lo, D.; Wang, X. (C37) 2016; 65 Vincent, P. (C17) 2011; 23 Chawla, N.V.; Bowyer, K.W.; Hall, L.O. (C34) 2002; 16 Shiha, E.; Ihara, A.; Kamei, Y. (C39) 2013; 18 Purushothaman, R.; Perry, D.E. (C30) 2005; 31 Mockus, A.; Weiss, D.M. (C10) 2000; 5 Koru, A.G.; Zhang, D.; Emam, K.E. (C29) 2009; 35 Li, J.; Struzik, Z.; Zhang, L. (C15) 2015; 165 Graves, T.L.; Karr, A.F.; Marron, J.S. (C31) 2000; 26 2002; 16 2012 2000; 5 2018; 105 2000; 26 2011 2017; 87 2015; 165 2017; 23 2009 2008 2006 2005 2011; 37 2018; 24 2013; 18 2009; 35 2013; 39 2016; 21 2016; 65 2019 2019; 49 2005; 31 2017 2016 2015 2011; 23 2014 e_1_2_10_23_1 e_1_2_10_24_1 e_1_2_10_21_1 e_1_2_10_22_1 e_1_2_10_20_1 e_1_2_10_41_1 e_1_2_10_40_1 e_1_2_10_2_1 e_1_2_10_4_1 e_1_2_10_18_1 e_1_2_10_3_1 e_1_2_10_19_1 e_1_2_10_6_1 e_1_2_10_16_1 e_1_2_10_39_1 e_1_2_10_5_1 e_1_2_10_17_1 e_1_2_10_38_1 e_1_2_10_8_1 e_1_2_10_14_1 e_1_2_10_37_1 e_1_2_10_7_1 e_1_2_10_15_1 e_1_2_10_36_1 e_1_2_10_12_1 e_1_2_10_35_1 e_1_2_10_9_1 e_1_2_10_13_1 e_1_2_10_34_1 e_1_2_10_10_1 e_1_2_10_33_1 e_1_2_10_11_1 e_1_2_10_32_1 e_1_2_10_31_1 e_1_2_10_30_1 e_1_2_10_29_1 e_1_2_10_27_1 e_1_2_10_28_1 e_1_2_10_25_1 e_1_2_10_26_1 |
| References_xml | – volume: 87 start-page: 206 year: 2017 end-page: 220 ident: C3 article-title: TLEL: a two-layer ensemble learning approach for just-in-time defect prediction publication-title: Inf. Softw. Technol. – volume: 39 start-page: 757 issue: 6 year: 2013 end-page: 773 ident: C4 article-title: A large-scale empirical study of just-in-time quality assurance publication-title: IEEE Trans. Softw. Eng. – volume: 35 start-page: 293 issue: 2 year: 2009 end-page: 304 ident: C29 article-title: An investigation into the functional form of the size-defect relationship for software modules publication-title: IEEE Trans. Softw. Eng. – volume: 37 start-page: 772 issue: 6 year: 2011 end-page: 787 ident: C32 article-title: Evaluating complexity, code churn, and developer activity metrics as indicators of software vulnerabilities publication-title: IEEE Trans. Softw. Eng. – volume: 49 start-page: 835 issue: 2 year: 2019 end-page: 849 ident: C18 article-title: Trust-aware collaborative filtering with a denoising autoencoder publication-title: Neural Process. Lett. – volume: 26 start-page: 653 issue: 7 year: 2000 end-page: 661 ident: C31 article-title: Predicting fault incidence using software change history publication-title: IEEE Trans. Softw. Eng. – volume: 21 start-page: 2072 issue: 5 year: 2016 end-page: 2106 ident: C1 article-title: Studying just-in-time defect prediction using cross-project models publication-title: Empir. Softw. Eng. – volume: 18 start-page: 1005 issue: 5 year: 2013 end-page: 1042 ident: C39 article-title: Studying re-opened bugs in open source software publication-title: Empir. Softw. Eng. – volume: 23 start-page: 1661 issue: 7 year: 2011 end-page: 1674 ident: C17 article-title: A connection between score matching and denoising autoencoders publication-title: Neural Comput. – volume: 23 start-page: 418 year: 2017 end-page: 451 ident: C38 article-title: Identifying self-admitted technical debt in open source projects using text mining publication-title: Empir. Softw. Eng. – volume: 24 start-page: 2823 issue: 5 year: 2018 end-page: 2862 ident: C2 article-title: Revisiting supervised and unsupervised models for effort-aware just-in-time defect prediction publication-title: Empir. Softw. Eng. – volume: 105 start-page: 112 year: 2018 end-page: 131 ident: C16 article-title: Denoising autoencoder self-organizing map (DASOM) publication-title: Neural Netw. – volume: 65 start-page: 1 issue: 4 year: 2016 end-page: 20 ident: C37 article-title: Collective personalized change classification with multiobjective search publication-title: IEEE Trans. Reliab. – volume: 5 start-page: 169 issue: 2 year: 2000 end-page: 180 ident: C10 article-title: Predicting risk of software changes publication-title: Bell Labs Tech. J. – volume: 31 start-page: 511 issue: 6 year: 2005 end-page: 526 ident: C30 article-title: Toward understanding the rhetoric of small source code changes publication-title: IEEE Trans. Softw. Eng. – volume: 16 start-page: 321 year: 2002 end-page: 357 ident: C34 article-title: SMOTE: synthetic minority over-sampling technique publication-title: J. Artif. Intell. Res. – volume: 165 start-page: 23 year: 2015 end-page: 31 ident: C15 article-title: Feature learning from incomplete EEG with denoising autoencoder publication-title: Neurocomputing – year: 2016 article-title: Effort-aware just-in-time defect prediction: simple unsupervised models could be better than supervised models – year: 2014 article-title: A convolutional neural network for modelling sentences – volume: 105 start-page: 112 year: 2018 end-page: 131 article-title: Denoising autoencoder self-organizing map (DASOM) publication-title: Neural Netw. – year: 2017 article-title: Revisiting unsupervised learning for defect prediction – volume: 21 start-page: 2072 issue: 5 year: 2016 end-page: 2106 article-title: Studying just-in-time defect prediction using cross-project models publication-title: Empir. Softw. Eng. – volume: 23 start-page: 1661 issue: 7 year: 2011 end-page: 1674 article-title: A connection between score matching and denoising autoencoders publication-title: Neural Comput. – year: 2016 article-title: Automatically learning semantic features for defect prediction – year: 2005 article-title: Use of relative code churn measures to predict system defect density – volume: 87 start-page: 206 year: 2017 end-page: 220 article-title: TLEL: a two-layer ensemble learning approach for just-in-time defect prediction publication-title: Inf. Softw. Technol. – volume: 39 start-page: 757 issue: 6 year: 2013 end-page: 773 article-title: A large-scale empirical study of just-in-time quality assurance publication-title: IEEE Trans. Softw. Eng. – year: 2019 article-title: Code churn: a neglected metric in effort-aware just-in-time defect prediction – volume: 26 start-page: 653 issue: 7 year: 2000 end-page: 661 article-title: Predicting fault incidence using software change history publication-title: IEEE Trans. Softw. Eng. – volume: 65 start-page: 1 issue: 4 year: 2016 end-page: 20 article-title: Collective personalized change classification with multiobjective search publication-title: IEEE Trans. Reliab. – volume: 35 start-page: 293 issue: 2 year: 2009 end-page: 304 article-title: An investigation into the functional form of the size-defect relationship for software modules publication-title: IEEE Trans. Softw. Eng. – volume: 31 start-page: 511 issue: 6 year: 2005 end-page: 526 article-title: Toward understanding the rhetoric of small source code changes publication-title: IEEE Trans. Softw. Eng. – year: 2006 article-title: Mining metrics to predict component failures – year: 2015 article-title: Deep visual-semantic alignments for generating image descriptions – year: 2012 article-title: An industrial study on the risk of software changes – year: 2017 article-title: Very deep convolutional networks for end-to-end speech recognition – year: 2008 article-title: Extracting and composing robust features with denoising autoencoders – volume: 165 start-page: 23 year: 2015 end-page: 31 article-title: Feature learning from incomplete EEG with denoising autoencoder publication-title: Neurocomputing – year: 2015 article-title: Combining deep learning with information retrieval to localize buggy files for bug reports – volume: 16 start-page: 321 year: 2002 end-page: 357 article-title: SMOTE: synthetic minority over-sampling technique publication-title: J. Artif. Intell. Res. – year: 2014 article-title: An empirical study of just-in-time defect prediction using cross-project models – year: 2015 article-title: Deep learning for just-in-time defect prediction – year: 2014 article-title: Learning semantic representations using convolutional neural networks for web search – year: 2016 article-title: Learning unified features from natural and programming languages for locating buggy source code – year: 2009 article-title: Predicting faults using the complexity of code changes – volume: 18 start-page: 1005 issue: 5 year: 2013 end-page: 1042 article-title: Studying re-opened bugs in open source software publication-title: Empir. Softw. Eng. – volume: 37 start-page: 772 issue: 6 year: 2011 end-page: 787 article-title: Evaluating complexity, code churn, and developer activity metrics as indicators of software vulnerabilities publication-title: IEEE Trans. Softw. Eng. – year: 2016 article-title: Deep API learning – volume: 49 start-page: 835 issue: 2 year: 2019 end-page: 849 article-title: Trust-aware collaborative filtering with a denoising autoencoder publication-title: Neural Process. Lett. – volume: 23 start-page: 418 year: 2017 end-page: 451 article-title: Identifying self-admitted technical debt in open source projects using text mining publication-title: Empir. Softw. Eng. – year: 2019 article-title: DeepJIT: an end-to-end deep learning framework for just-in-time defect prediction – year: 2017 article-title: Semantically enhanced software traceability using deep learning techniques – volume: 24 start-page: 2823 issue: 5 year: 2018 end-page: 2862 article-title: Revisiting supervised and unsupervised models for effort-aware just-in-time defect prediction publication-title: Empir. Softw. Eng. – year: 2016 article-title: Predicting semantically linkable knowledge in developer online forums via convolutional neural network – year: 2011 article-title: How do fixes become bugs? – year: 2017 article-title: Domain adaptation for test report classification in crowdsourced testing – volume: 5 start-page: 169 issue: 2 year: 2000 end-page: 180 article-title: Predicting risk of software changes publication-title: Bell Labs Tech. J. – ident: e_1_2_10_25_1 doi: 10.1145/2970276.2970357 – ident: e_1_2_10_36_1 doi: 10.1145/3106237.3106257 – ident: e_1_2_10_26_1 doi: 10.1109/ICSE.2017.9 – ident: e_1_2_10_30_1 doi: 10.1109/TSE.2008.90 – ident: e_1_2_10_28_1 doi: 10.1109/ICSE.2009.5070510 – ident: e_1_2_10_2_1 doi: 10.1007/s10664-015-9400-x – ident: e_1_2_10_32_1 doi: 10.1109/32.859533 – ident: e_1_2_10_10_1 doi: 10.1145/1390156.1390294 – ident: e_1_2_10_13_1 doi: 10.1145/2597073.2597075 – ident: e_1_2_10_38_1 doi: 10.1109/TR.2016.2588139 – ident: e_1_2_10_3_1 doi: 10.1007/s10664-018-9661-2 – ident: e_1_2_10_27_1 doi: 10.1145/1134285.1134349 – ident: e_1_2_10_6_1 doi: 10.1109/ICASSP.2017.7953077 – ident: e_1_2_10_20_1 doi: 10.1145/2884781.2884804 – ident: e_1_2_10_35_1 doi: 10.1613/jair.953 – ident: e_1_2_10_15_1 doi: 10.1109/MSR.2019.00016 – ident: e_1_2_10_18_1 doi: 10.1162/NECO_a_00142 – ident: e_1_2_10_5_1 doi: 10.1109/TSE.2012.70 – ident: e_1_2_10_24_1 – ident: e_1_2_10_8_1 – ident: e_1_2_10_34_1 doi: 10.1145/2025113.2025121 – ident: e_1_2_10_41_1 doi: 10.1145/2950290.2950353 – ident: e_1_2_10_11_1 doi: 10.1002/bltj.2229 – ident: e_1_2_10_19_1 doi: 10.1007/s11063-018-9831-7 – ident: e_1_2_10_37_1 – ident: e_1_2_10_39_1 doi: 10.1007/s10664-017-9522-4 – ident: e_1_2_10_17_1 doi: 10.1016/j.neunet.2018.04.016 – ident: e_1_2_10_40_1 doi: 10.1007/s10664-012-9228-6 – ident: e_1_2_10_16_1 doi: 10.1016/j.neucom.2014.08.092 – ident: e_1_2_10_29_1 doi: 10.1145/1062455.1062514 – ident: e_1_2_10_33_1 doi: 10.1109/TSE.2010.81 – ident: e_1_2_10_23_1 doi: 10.1145/2950290.2950334 – ident: e_1_2_10_9_1 doi: 10.1145/2567948.2577348 – ident: e_1_2_10_4_1 doi: 10.1016/j.infsof.2017.03.007 – ident: e_1_2_10_7_1 doi: 10.1109/CVPR.2015.7298932 – ident: e_1_2_10_12_1 doi: 10.1109/QRS.2015.14 – ident: e_1_2_10_21_1 doi: 10.1109/ASE.2015.73 – ident: e_1_2_10_22_1 – ident: e_1_2_10_14_1 doi: 10.1145/2393596.2393670 – ident: e_1_2_10_31_1 doi: 10.1109/TSE.2005.74 |
| SSID | ssj0055539 |
| Score | 2.439142 |
| Snippet | Just-in-time defect prediction is an important and useful branch in software defect prediction. At present, deep learning is a research hotspot in the field of... Just‐in‐time defect prediction is an important and useful branch in software defect prediction. At present, deep learning is a research hotspot in the field of... |
| SourceID | crossref wiley iet |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 185 |
| SubjectTerms | autoencoder convolutional neural network basic defect features convolution neural network cross-project defect prediction experiments denoising autoencoder just-in-time defect prediction model learning (artificial intelligence) mainstream deep learning techniques neural nets software defect prediction Special Issue: Knowledge Discovery for Software Development (KDSD) |
| Title | Within-project and cross-project just-in-time defect prediction based on denoising autoencoder and convolutional neural network |
| URI | http://digital-library.theiet.org/content/journals/10.1049/iet-sen.2019.0278 https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fiet-sen.2019.0278 |
| Volume | 14 |
| WOSCitedRecordID | wos000585778800002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVWIB databaseName: Wiley Online Library Open Access customDbUrl: eissn: 1751-8814 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0055539 issn: 1751-8806 databaseCode: 24P dateStart: 20130101 isFulltext: true titleUrlDefault: https://authorservices.wiley.com/open-science/open-access/browse-journals.html providerName: Wiley-Blackwell – providerCode: PRVWIB databaseName: Wiley Online Library Open Access customDbUrl: eissn: 1751-8814 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0055539 issn: 1751-8806 databaseCode: WIN dateStart: 20130101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LaxsxEBZO2kMvTfqibpqgQ-ihoNYraR86JqZLAsEY0mLfFu1qlm4o62Cvfe6t1_zG_JLMaNemJuBCyWUfWkkrZjSaGT2-Yew0Tga5KvNYaFCl0HmkhNUuEpAPCq1z1BGFh8y_ikejZDo14x4brs_CtPgQmwk3kgw_XpOA27yNQoJGLTKxgkYsgCBMA_OF1s_22LMgUAnFb5B6vB6OwzD04cRQTQYiSQK9Wdo0Xx9VsaWc9vDztsnqdU568CStPWQvO5OTn7V95BXrQf2aHazDOfBOut-wP5Oq-VnV97_vuukZbmvHfUv_SrtZLhp89fkoMD13QDtC-O2clnyIzZw0o-P4gGParKLJCG6XzYwgMx3-0Nc6q1ddp8emEaimv_kt6W_Zj_Tb9-GF6OI0iEIprYWlc1umdDqRaI5IABk7FG1p0fWGBPKSQPMBfU8ThqWJQEbSxcqqEp2pOIBCvWP79ayG94zHhKcWhs7GErQuwbhBWEbW2BwNSTCmzwZrBmVFB2JOsTR-ZX4xXZsMCZ0hoTMidEaE7rPPmyK3LYLHrsyfKK2T48WujMqz-99VZtfpRJ6n5NzqD_9V6oi9kOTl-7mfj2y_mS_hmD0vVk21mJ_43o7XyeXoAVJ5CZk |
| linkProvider | Wiley-Blackwell |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3Nb9MwFH_qBhJc2MaYGIPhw8QByaO1nQ8fN6BaRVdNYqi7RU78omWa0qlNd-bGlb-Rv2TvuWnFhDQkxCmJ4zjWs5_fl_17AAdJ2s11mSfSoC6lyWMtnfGxxLxbGJOTjCgCZP4wGY3Siwt71oFPy7MwC3yIlcONOSOs18zg7JBeGJyGQTIrbOQMGcO0Zw85gLYGjwwpHJzAYTwYLdfjKIpCPjGSkz2Zpj2zim3aD380cU86rdHr-zprEDr9jf_T3U141iqd4mgxS7agg_Vz2FgmdBAtf2_Dj3HVXFb1r-8_WweNcLUXoau_lV3NZw09hnqcml545D0h4mbKQR8eaMGy0Qu6oVVtUrE7Qrh5M2HQTE8_DK1O6tt22lPXGFYzXMKm9Bfwrf_5_OOJbDM1yEJrY6Tjk1u29CZVpJAoRJV4Ym7lyPjGFPOSYfORrE8bRaWNUcXKJ9rpksyppIeF3oH1elLjSxAJI6pFkXeJQmNKtL4blbGzLidVEq3dhe5yhLKihTHnbBrXWQinG5sRoTMidMaEzpjQu_B-9cnNAsPjocrvuKzl5NlDFXUY7783mX3tj9Vxn81b8-qfvnoLT07OT4fZcDD6sgdPFdv8wRP0Gtab6RzfwOPitqlm0_0w9e8Ac2QM4g |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwEB61BaFeKE-1UMAHxAHJsPEjjo99EIGoVisBam-RE49FEMqudrM9c-PKb-SX4PFmV1RIRUKckjiOY9kznpf9DcBzU4xqGWrDFcrAVZ1L7pTPOdajRqk6yogmQeafmfG4uLiwky04XZ-FWeFDbBxuxBlpvSYGx5kPK4NTEUhmiz1fIGGYZvYVBdC24YbSJiPaFmqyXo-11imfWJSTGS-KTG1im_b1H01ckU7b8fVVnTUJnXLv_3T3DtwelE52tKKSu7CF3T3YWyd0YAN_34fv523_ue1-fvsxOGiY6zxLXf2t7Mty0cfHVI9S0zOPtCeEzeYU9KGJZiQbPYs3cVWbtuSOYG7ZTwk008cfplan3eVA9rFrBKuZLmlT-gP4VL75ePKWD5kaeCOlUtzRyS0bvCpEVEgEojA-Mrdw0fjGAutAsPkYrU-rdbA5ilx4I50M0ZwyGTbyIex00w73gRlCVNPaOyNQqYDWj3TInXV1VCXR2gMYrWeoagYYc8qm8bVK4XRlqzjQVRzoiga6ooE-gJebT2YrDI_rKr-gsoGTF9dVlGm-_95k9aE8F8clmbfq0T999QxuTU7L6uzd-P1j2BVk8idH0CHs9PMlPoGbzWXfLuZPE-X_AmotC_k |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Within-project+and+cross-project+just-in-time+defect+prediction+based+on+denoising+autoencoder+and+convolutional+neural+network&rft.jtitle=IET+software&rft.au=Zhu%2C+Kun&rft.au=Zhang%2C+Nana&rft.au=Ying%2C+Shi&rft.au=Zhu%2C+Dandan&rft.date=2020-06-01&rft.pub=The+Institution+of+Engineering+and+Technology&rft.issn=1751-8806&rft.eissn=1751-8814&rft.volume=14&rft.issue=3&rft.spage=185&rft.epage=195&rft_id=info:doi/10.1049%2Fiet-sen.2019.0278&rft.externalDocID=10_1049_iet_sen_2019_0278 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1751-8806&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1751-8806&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1751-8806&client=summon |