Combating class imbalance problem in semi-supervised defect detection

Detection of defect-prone software modules is an important topic in software quality research, and widely studied under enough defect data circumstance. An improved semi-supervised learning approach for defect detection involving class imbalanced and limited labeled data problem has been proposed. T...

Full description

Saved in:
Bibliographic Details
Main Authors: Ying Ma, Guangchun Luo, Jiong Li, Aiguo Chen
Format: Conference Proceeding
Language:English
Subjects:
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 622
container_issue
container_start_page 619
container_title
container_volume
creator Ying Ma
Guangchun Luo
Jiong Li
Aiguo Chen
description Detection of defect-prone software modules is an important topic in software quality research, and widely studied under enough defect data circumstance. An improved semi-supervised learning approach for defect detection involving class imbalanced and limited labeled data problem has been proposed. This approach employs random under-sampling technique to resample the original training set and updating training set in each round for co-train style algorithm. In comparison with conventional machine learning approaches, our method has significant superior performance in the aspect of AUC (area under the receiver operating characteristic) metric. Experimental results also show that with the proposed learning approach, it is possible to design better method to tackle the class imbalanced problem in semi-supervised learning.
doi_str_mv 10.1109/ICCPS.2011.6092260
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6092260</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6092260</ieee_id><sourcerecordid>6092260</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-ec0bc3a65ae14fef15def80a2882bc0f16d462786df885ae97adaaafdab6f2ff3</originalsourceid><addsrcrecordid>eNpVj91KxDAUhCOyoKx9gfUmL9B6krZpeill1YUFBfd-OUlOJNI_mir49gbcG-fmY4ZhYBjbCSiEgPbh0HVv74UEIQoFrZQKrljWNlpUddOASvn1Py_1Dcti_IQkpbSuqlu276bB4BrGD257jJGHZHscLfF5mUxPAw8jjzSEPH7NtHyHSI478mTXhDUhTOMd23jsI2UXbtnpaX_qXvLj6_OhezzmoYU1JwvGlqhqJFF58qJOOxpQai2NBS-Uq5RstHJe61RqG3SI6B0a5aX35Zbd_80GIjrPSxhw-Tlfvpe_0lhPHg</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Combating class imbalance problem in semi-supervised defect detection</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Ying Ma ; Guangchun Luo ; Jiong Li ; Aiguo Chen</creator><creatorcontrib>Ying Ma ; Guangchun Luo ; Jiong Li ; Aiguo Chen</creatorcontrib><description>Detection of defect-prone software modules is an important topic in software quality research, and widely studied under enough defect data circumstance. An improved semi-supervised learning approach for defect detection involving class imbalanced and limited labeled data problem has been proposed. This approach employs random under-sampling technique to resample the original training set and updating training set in each round for co-train style algorithm. In comparison with conventional machine learning approaches, our method has significant superior performance in the aspect of AUC (area under the receiver operating characteristic) metric. Experimental results also show that with the proposed learning approach, it is possible to design better method to tackle the class imbalanced problem in semi-supervised learning.</description><identifier>ISBN: 9781457706028</identifier><identifier>ISBN: 1457706024</identifier><identifier>EISBN: 9781457706011</identifier><identifier>EISBN: 1457706008</identifier><identifier>EISBN: 9781457706035</identifier><identifier>EISBN: 1457706032</identifier><identifier>EISBN: 9781457706004</identifier><identifier>EISBN: 1457706016</identifier><identifier>DOI: 10.1109/ICCPS.2011.6092260</identifier><language>eng</language><publisher>IEEE</publisher><subject>Classification algorithms ; Machine learning ; Software algorithms ; Software quality ; Training ; Training data</subject><ispartof>2011 International Conference on Computational Problem-Solving (ICCP), 2011, p.619-622</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6092260$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,27899,54892</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6092260$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Ying Ma</creatorcontrib><creatorcontrib>Guangchun Luo</creatorcontrib><creatorcontrib>Jiong Li</creatorcontrib><creatorcontrib>Aiguo Chen</creatorcontrib><title>Combating class imbalance problem in semi-supervised defect detection</title><title>2011 International Conference on Computational Problem-Solving (ICCP)</title><addtitle>ICCPS</addtitle><description>Detection of defect-prone software modules is an important topic in software quality research, and widely studied under enough defect data circumstance. An improved semi-supervised learning approach for defect detection involving class imbalanced and limited labeled data problem has been proposed. This approach employs random under-sampling technique to resample the original training set and updating training set in each round for co-train style algorithm. In comparison with conventional machine learning approaches, our method has significant superior performance in the aspect of AUC (area under the receiver operating characteristic) metric. Experimental results also show that with the proposed learning approach, it is possible to design better method to tackle the class imbalanced problem in semi-supervised learning.</description><subject>Classification algorithms</subject><subject>Machine learning</subject><subject>Software algorithms</subject><subject>Software quality</subject><subject>Training</subject><subject>Training data</subject><isbn>9781457706028</isbn><isbn>1457706024</isbn><isbn>9781457706011</isbn><isbn>1457706008</isbn><isbn>9781457706035</isbn><isbn>1457706032</isbn><isbn>9781457706004</isbn><isbn>1457706016</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2011</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNpVj91KxDAUhCOyoKx9gfUmL9B6krZpeill1YUFBfd-OUlOJNI_mir49gbcG-fmY4ZhYBjbCSiEgPbh0HVv74UEIQoFrZQKrljWNlpUddOASvn1Py_1Dcti_IQkpbSuqlu276bB4BrGD257jJGHZHscLfF5mUxPAw8jjzSEPH7NtHyHSI478mTXhDUhTOMd23jsI2UXbtnpaX_qXvLj6_OhezzmoYU1JwvGlqhqJFF58qJOOxpQai2NBS-Uq5RstHJe61RqG3SI6B0a5aX35Zbd_80GIjrPSxhw-Tlfvpe_0lhPHg</recordid><startdate>201110</startdate><enddate>201110</enddate><creator>Ying Ma</creator><creator>Guangchun Luo</creator><creator>Jiong Li</creator><creator>Aiguo Chen</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201110</creationdate><title>Combating class imbalance problem in semi-supervised defect detection</title><author>Ying Ma ; Guangchun Luo ; Jiong Li ; Aiguo Chen</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-ec0bc3a65ae14fef15def80a2882bc0f16d462786df885ae97adaaafdab6f2ff3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Classification algorithms</topic><topic>Machine learning</topic><topic>Software algorithms</topic><topic>Software quality</topic><topic>Training</topic><topic>Training data</topic><toplevel>online_resources</toplevel><creatorcontrib>Ying Ma</creatorcontrib><creatorcontrib>Guangchun Luo</creatorcontrib><creatorcontrib>Jiong Li</creatorcontrib><creatorcontrib>Aiguo Chen</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ying Ma</au><au>Guangchun Luo</au><au>Jiong Li</au><au>Aiguo Chen</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Combating class imbalance problem in semi-supervised defect detection</atitle><btitle>2011 International Conference on Computational Problem-Solving (ICCP)</btitle><stitle>ICCPS</stitle><date>2011-10</date><risdate>2011</risdate><spage>619</spage><epage>622</epage><pages>619-622</pages><isbn>9781457706028</isbn><isbn>1457706024</isbn><eisbn>9781457706011</eisbn><eisbn>1457706008</eisbn><eisbn>9781457706035</eisbn><eisbn>1457706032</eisbn><eisbn>9781457706004</eisbn><eisbn>1457706016</eisbn><abstract>Detection of defect-prone software modules is an important topic in software quality research, and widely studied under enough defect data circumstance. An improved semi-supervised learning approach for defect detection involving class imbalanced and limited labeled data problem has been proposed. This approach employs random under-sampling technique to resample the original training set and updating training set in each round for co-train style algorithm. In comparison with conventional machine learning approaches, our method has significant superior performance in the aspect of AUC (area under the receiver operating characteristic) metric. Experimental results also show that with the proposed learning approach, it is possible to design better method to tackle the class imbalanced problem in semi-supervised learning.</abstract><pub>IEEE</pub><doi>10.1109/ICCPS.2011.6092260</doi><tpages>4</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 9781457706028
ispartof 2011 International Conference on Computational Problem-Solving (ICCP), 2011, p.619-622
issn
language eng
recordid cdi_ieee_primary_6092260
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Classification algorithms
Machine learning
Software algorithms
Software quality
Training
Training data
title Combating class imbalance problem in semi-supervised defect detection
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-03-04T10%3A10%3A02IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Combating%20class%20imbalance%20problem%20in%20semi-supervised%20defect%20detection&rft.btitle=2011%20International%20Conference%20on%20Computational%20Problem-Solving%20(ICCP)&rft.au=Ying%20Ma&rft.date=2011-10&rft.spage=619&rft.epage=622&rft.pages=619-622&rft.isbn=9781457706028&rft.isbn_list=1457706024&rft_id=info:doi/10.1109/ICCPS.2011.6092260&rft.eisbn=9781457706011&rft.eisbn_list=1457706008&rft.eisbn_list=9781457706035&rft.eisbn_list=1457706032&rft.eisbn_list=9781457706004&rft.eisbn_list=1457706016&rft_dat=%3Cieee_6IE%3E6092260%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i90t-ec0bc3a65ae14fef15def80a2882bc0f16d462786df885ae97adaaafdab6f2ff3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6092260&rfr_iscdi=true