{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T17:06:51Z","timestamp":1778605611887,"version":"3.51.4"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2006,4,8]],"date-time":"2006-04-08T00:00:00Z","timestamp":1144454400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2007,2]]},"DOI":"10.1007\/s10115-006-0022-x","type":"journal-article","created":{"date-parts":[[2006,4,7]],"date-time":"2006-04-07T10:18:19Z","timestamp":1144405099000},"page":"171-190","source":"Crossref","is-referenced-by-count":56,"title":["The pairwise attribute noise detection algorithm"],"prefix":"10.1007","volume":"11","author":[{"given":"Jason D.","family":"Van Hulse","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taghi M.","family":"Khoshgoftaar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiying","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2006,4,8]]},"reference":[{"key":"22_CR1","volume-title":"Outlier detection for high dimensional data. In: Proceedings of ACM SIGMOD conference on management of data","author":"C Aggarwal","year":"2001","unstructured":"Aggarwal C, Yu P (2001) Outlier detection for high dimensional data. In: Proceedings of ACM SIGMOD conference on management of data, ACM Press, Dallas, TX"},{"key":"22_CR2","unstructured":"Bobrowski M, Marre M, Yankelevich D. A software engineering view of data quality. Available at www.citeseer.ist.psu.edu\/277636.html$"},{"key":"22_CR3","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1613\/jair.606","volume":"11","author":"CE Brodley","year":"1999","unstructured":"Brodley CE, Friedl MA (1999) Identifying mislabeled training data. J Artif Intell Res 11: 131\u2013167","journal-title":"J Artif Intell Res"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Clark P, Niblett T (1991) Rule induction with CN2: some recent improvements. In: Proceedings of the 5th European working session on learning, pp 151\u2013163","DOI":"10.1007\/BFb0017011"},{"key":"22_CR5","unstructured":"Dunagan JD (2002). A geometic theory of outliers and perturbation. Ph.D. Dissertation. Available at http:\/\/research.microsoft.com\/\u223cjdunagan\/thesis.pdf"},{"key":"22_CR6","unstructured":"Fenton NE, Pfleeger SL (1997) Software metrics: a rigorous and practical approach, 2nd edn. PWS Publishing Company: ITP, Boston, MA"},{"key":"22_CR7","volume-title":"An extensible framework for data cleaning. In: Proceedings of 18th international conference on data engineering","author":"H Galhardas","year":"2000","unstructured":"Galhardas H, Florescu D, Shasha D, Simon E (2000) An extensible framework for data cleaning. In: Proceedings of 18th international conference on data engineering, IEEE Computer Society, San Jose, CA"},{"key":"22_CR8","first-page":"199","volume-title":"Noise elimination in inductive concept learning: a case study in medical diagnosis. In: Proceedings of the 7th international workshop on algorithmic learning theory","author":"D Gamberger","year":"1999","unstructured":"Gamberger D, Lavrac N, Dzeroski S (1999) Noise elimination in inductive concept learning: a case study in medical diagnosis. In: Proceedings of the 7th international workshop on algorithmic learning theory, Springer, Berlin Heidelberg Ney York, pp 199\u2013212"},{"key":"22_CR9","first-page":"143","volume-title":"Experiments with noise filtering in a medical domain. In: Proceedings of the 16th international conference on machine learning","author":"D Gamberger","year":"1999","unstructured":"Gamberger D, Lavrac N, Groselj C (1999) Experiments with noise filtering in a medical domain. In: Proceedings of the 16th international conference on machine learning. Morgan Kaufmann, San Mateo, California, pp 143\u2013153"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Hernandez MA, Stolfo SJ (1995) The merge\/purge problem for large databases. In: Proceedings of ACM SIGMOD conference on management of data, ACM, pp 127\u2013138. citeseer.ist.psu.edu\/stolfo95mergepurge.html","DOI":"10.1145\/223784.223807"},{"issue":"1","key":"22_CR11","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1023\/A:1009761603038","volume":"2","author":"MA Hernandez","year":"1998","unstructured":"Hernandez MA, Stolfo, SJ (1998) Real-world data is dirty: data cleansing and the merge\/purge problem. Data Min Knowl Discov 2(1): 9\u201337","journal-title":"Data Min Knowl Discov"},{"key":"22_CR12","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1023\/A:1009736205722","volume":"3","author":"TM Khoshgoftaar","year":"1998","unstructured":"Khoshgoftaar TM, Allen EB (1998) Classifcation of fault-prone software modules: prior probabilities, costs and model evaluation. Empiric Software Eng 3: 275\u2013298","journal-title":"Empiric Software Eng"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Khoshgoftaar TM, Bullard LA, Gao K (2003) Detecting outliers using rule-based modeling for improving CBR-based software quality classification models. In: Ashley KD, Bridge DG (eds) Proceedings of the 16th international conference on case-based reasoning. LNAI, vol 1689. Springer-Verlag, Berlin Heidelberg New York, pp 216\u2013230","DOI":"10.1007\/3-540-45006-8_19"},{"key":"22_CR14","first-page":"369","volume-title":"Generarting multiple noise elimination filters with the ensemble-partitioning filter. In: Proceedings of the IEEE international conference on information reuse and integration","author":"TM Khoshgoftaar","year":"2004","unstructured":"Khoshgoftaar TM, Rebours P (2004) Generarting multiple noise elimination filters with the ensemble-partitioning filter. In: Proceedings of the IEEE international conference on information reuse and integration, IEEE Systems, Man and Cybernetics Society, Las Vegas, NV, USA, pp 369\u2013375"},{"key":"22_CR15","first-page":"119","volume-title":"The necessity of assuring quality in software measurement data. In: Proceedings of 10th international software metrics symposium","author":"TM Khoshgoftaar","year":"2004","unstructured":"Khoshgoftaar TM, Seliya N (2004) The necessity of assuring quality in software measurement data. In: Proceedings of 10th international software metrics symposium, IEEE Computer Society, Chicago, IL, pp 119\u2013130"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Khoshgoftaar TM, Seliya N, Gao K (2005) Detecting noisy instances with the rule-based classification model. Intell Data Anal 9(4):347\u2013364","DOI":"10.3233\/IDA-2005-9403"},{"issue":"1","key":"22_CR17","doi-asserted-by":"crossref","first-page":"3","DOI":"10.3233\/IDA-2005-9102","volume":"9","author":"TM Khoshgoftaar","year":"2005","unstructured":"Khoshgoftaar TM, Zhong S, Joshi V (2005). Noise elimination with ensemble-classifier filtering for software quality estimation. Intell Data Anal 9(1): 3\u201327","journal-title":"Intell Data Anal"},{"key":"22_CR18","unstructured":"Knorr E, Ng R (1997) A unified notion of outliers: Properties and computation. In Proceedings of knowledge discovery and data mining. American Association for Artificial Intelligence, Newport Beach, CA, pp 219\u2013222"},{"key":"22_CR19","unstructured":"Knorr E, Ng R (1998) Algorithms for mining distance-based outliers in large datasets. In: Proceedings of 24th international conference on very large databases, New York, NY, pp 392\u2013403"},{"key":"22_CR20","first-page":"589","volume-title":"Ordinal association rules for error identification in datasets. In: Proceedings of 10th international conference on information and knowledge management","author":"A Marcus","year":"2001","unstructured":"Marcus A, Maletic J, Lin K-I (2001) Ordinal association rules for error identification in datasets. In: Proceedings of 10th international conference on information and knowledge management. ACM Press, Atlanta, GA, pp 589\u2013591"},{"key":"22_CR21","unstructured":"Murphy, PM, Aha DW (1998) UCI repository of machine learning databases. University of California, Irvine, Department of Information and Computer Science. http:\/\/www.ics.uci.edu\/\u223cmlearn\/MLRepository.html"},{"key":"22_CR22","volume-title":"C4.5: programs for machine learning","author":"JR Quinlan","year":"1993","unstructured":"Quinlan JR (1993) C4.5: programs for machine learning. Morgan Kaufmann, San Mateo, California"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Ramasway S, Rastogi R, Shim K (2000) Efficient algorithms for mining outliers from large datasets. In: Proceedings of ACM SIGMOD conference on management of data, ACM, pp 427\u2013438","DOI":"10.1145\/335191.335437"},{"key":"22_CR24","unstructured":"SAS Institute (2004) SAS\/STAT user's guide. SAS Institute Inc"},{"key":"22_CR25","doi-asserted-by":"crossref","first-page":"451","DOI":"10.3233\/IDA-2002-6505","volume":"6","author":"S Shekhar","year":"2002","unstructured":"Shekhar S, Lu C, Zhang P (2002) Detecting graph-based spatial outliers. Intell Data Anal 6: 451\u2013458","journal-title":"Intell Data Anal"},{"issue":"5","key":"22_CR26","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1145\/253769.253804","volume":"40","author":"D Strong","year":"1997","unstructured":"Strong D, Lee Y, Wang R (1997) Data quality in context. Commun ACM 40(5): 103\u2013110","journal-title":"Commun ACM"},{"key":"22_CR27","first-page":"239","volume-title":"Correcting noisy data. In: Proceedings of 6th international conference machine learning (ICML 99)","author":"CM Teng","year":"1999","unstructured":"Teng CM (1999) Correcting noisy data. In: Proceedings of 6th international conference machine learning (ICML 99). Morgan Kaufmann, San Mateo, California, pp 239\u2013248"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Yang Y, Wu X, Zhu X (2004) Dealing with predictive-but-unpredictable attributes in noisy data sources. In: Proceedings of 8th European conference on principles and practice of knowledge discovery in databases, Pisa, Italy","DOI":"10.1007\/978-3-540-30116-5_43"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Zhong S, Khoshgoftaar TM, Seliya N (2004) Analyzing software measurement data with clustering techniques. IEEE Intell Syst, pp 22\u201329","DOI":"10.1109\/MIS.2004.1274907"},{"issue":"3\u20134","key":"22_CR30","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1007\/s10462-004-0751-8","volume":"22","author":"X Zhu","year":"2004","unstructured":"Zhu X, Wu X (2004) Class noise vs attribute noise: a quantitative study of their impacts. Artif Intell Rev 22(3\u20134): 177\u2013210","journal-title":"Artif Intell Rev"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-006-0022-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-006-0022-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-006-0022-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,29]],"date-time":"2019-05-29T06:10:15Z","timestamp":1559110215000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-006-0022-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,4,8]]},"references-count":30,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2007,2]]}},"alternative-id":["22"],"URL":"https:\/\/doi.org\/10.1007\/s10115-006-0022-x","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006,4,8]]}}}