{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T22:57:43Z","timestamp":1725836263880},"publisher-location":"Cham","reference-count":49,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319259352"},{"type":"electronic","value":"9783319259369"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-25936-9_5","type":"book-chapter","created":{"date-parts":[[2015,10,30]],"date-time":"2015-10-30T06:45:04Z","timestamp":1446187504000},"page":"62-80","source":"Crossref","is-referenced-by-count":1,"title":["Accurate Data Cleansing through Model Checking and Machine Learning Techniques"],"prefix":"10.1007","author":[{"given":"Roberto","family":"Boselli","sequence":"first","affiliation":[]},{"given":"Mirko","family":"Cesarini","sequence":"additional","affiliation":[]},{"given":"Fabio","family":"Mercorio","sequence":"additional","affiliation":[]},{"given":"Mario","family":"Mezzanzanica","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,10,31]]},"reference":[{"key":"5_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-0005-6","volume-title":"Handbook of Massive Data Sets","author":"J Abello","year":"2002","unstructured":"Abello, J., Pardalos, P.M., Resende, M.G.: Handbook of Massive Data Sets, vol. 4. Springer, US (2002)"},{"issue":"2","key":"5_CR2","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1145\/1147376.1147391","volume":"35","author":"L Bertossi","year":"2006","unstructured":"Bertossi, L.: Consistent query answering in databases. ACM Sigmod Rec. 35(2), 68\u201376 (2006)","journal-title":"ACM Sigmod Rec."},{"key":"5_CR3","volume-title":"Pattern Recognition and Machine Learning","author":"CM Bishop","year":"2006","unstructured":"Bishop, C.M., et al.: Pattern Recognition and Machine Learning, vol. 1. Springer, New York (2006)"},{"issue":"1","key":"5_CR4","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/S0004-3702(97)00063-5","volume":"97","author":"AL Blum","year":"1997","unstructured":"Blum, A.L., Langley, P.: Selection of relevant features and examples in machine learning. Artif. Intell. 97(1), 245\u2013271 (1997)","journal-title":"Artif. Intell."},{"key":"5_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/978-3-642-39146-0_17","volume-title":"Human-Computer Interaction and Knowledge Discovery in Complex, Unstructured, Big Data","author":"R Boselli","year":"2013","unstructured":"Boselli, R., Cesarini, M., Mercorio, F., Mezzanzanica, M.: Inconsistency knowledge discovery for longitudinal data management: a model-based approach. In: Holzinger, A., Pasi, G. (eds.) HCI-KDD 2013. LNCS, vol. 7947, pp. 183\u2013194. Springer, Heidelberg (2013)"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Boselli, R., Cesarini, M., Mercorio, F., Mezzanzanica, M.: Planning meets data cleansing. In: The 24th International Conference on Automated Planning and Scheduling (ICAPS), pp. 439\u2013443. AAAI (2014)","DOI":"10.1609\/icaps.v24i1.13667"},{"key":"5_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1007\/978-3-662-43968-5_8","volume-title":"Interactive Knowledge Discovery and Data Mining in Biomedical Informatics","author":"R Boselli","year":"2014","unstructured":"Boselli, R., Cesarini, M., Mercorio, F., Mezzanzanica, M.: A policy-based cleansing and integration framework for labour and healthcare data. In: Holzinger, A., Jurisica, I. (eds.) Knowledge Discovery and Data Mining. LNCS, vol. 8401, pp. 141\u2013168. Springer, Heidelberg (2014)"},{"issue":"1","key":"5_CR8","doi-asserted-by":"crossref","first-page":"57","DOI":"10.3233\/IA-140061","volume":"8","author":"R Boselli","year":"2014","unstructured":"Boselli, R., Cesarini, M., Mercorio, F., Mezzanzanica, M.: Towards data cleansing via planning. Intelligenza Artificiale 8(1), 57\u201369 (2014)","journal-title":"Intelligenza Artificiale"},{"issue":"1","key":"5_CR9","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.ic.2004.04.007","volume":"197","author":"J Chomicki","year":"2005","unstructured":"Chomicki, J., Marcinkowski, J.: Minimal-change integrity maintenance using tuple deletions. Inf. Comput. 197(1), 90\u2013121 (2005)","journal-title":"Inf. Comput."},{"key":"5_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/978-3-540-30597-2_5","volume-title":"Inconsistency Tolerance","author":"J Chomicki","year":"2005","unstructured":"Chomicki, J., Marcinkowski, J.: On the computational complexity of minimal-change integrity maintenance in relational databases. In: Bertossi, L., Hunter, A., Schaub, T. (eds.) Inconsistency Tolerance. LNCS, vol. 3300, pp. 119\u2013150. Springer, Heidelberg (2005)"},{"key":"5_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1007\/978-3-642-35236-2_60","volume-title":"Active Media Technology","author":"P Clemente","year":"2012","unstructured":"Clemente, P., Kaba, B., Rouzaud-Cornabas, J., Alexandre, M., Aujay, G.: SPTrack: visual analysis of information flows within SELinux policies and attack logs. In: Huang, R., Ghorbani, A.A., Pasi, G., Yamaguchi, T., Yen, N.Y., Jin, B. (eds.) AMT 2012. LNCS, vol. 7669, pp. 596\u2013605. Springer, Heidelberg (2012)"},{"key":"5_CR12","unstructured":"Cong, G., Fan, W., Geerts, F., Jia, X., Ma, S.: Improving data quality: consistency and accuracy. In: Proceedings of the 33rd International Conference on Very Large Data Bases, pp. 315\u2013326. VLDB Endowment (2007)"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Dallachiesa, M., Ebaid, A., Eldawy, A., Elmagarmid, A.K., Ilyas, I.F., Ouzzani, M., Tang, N.: Nadeef: a commodity data cleaning system. In: Ross, K.A., Srivastava, D., Papadias, D. (eds.) SIGMOD Conference, pp. 541\u2013552. ACM (2013)","DOI":"10.1145\/2463676.2465327"},{"key":"5_CR14","unstructured":"De Silva, V., Carlsson, G.: Topological estimation using witness complexes. In: Proceedings of the First Eurographics Conference on Point-Based Graphics, pp. 157\u2013166. Eurographics Association (2004)"},{"issue":"4","key":"5_CR15","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1080\/07421222.2000.11518265","volume":"16","author":"S Devaraj","year":"2000","unstructured":"Devaraj, S., Kohli, R.: Information technology payoff in the health-care industry: a longitudinal study. J. Manag. Inf. Syst. 16(4), 41\u201368 (2000)","journal-title":"J. Manag. Inf. Syst."},{"issue":"1","key":"5_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TKDE.2007.250581","volume":"19","author":"AK Elmagarmid","year":"2007","unstructured":"Elmagarmid, A.K., Ipeirotis, P.G., Verykios, V.S.: Duplicate record detection: a survey. IEEE Trans. Knowl. Data Eng. 19(1), 1\u201316 (2007)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Fan, W., Li, J., Ma, S., Tang, N., Yu, W.: Towards certain fixes with editing rules and master data. In: Proceedings of the VLDB Endowment, vol. 3(1\u20132), pp. 173\u2013184 (2010)","DOI":"10.14778\/1920841.1920867"},{"issue":"11","key":"5_CR18","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1145\/240455.240464","volume":"39","author":"U Fayyad","year":"1996","unstructured":"Fayyad, U., Piatetsky-Shapiro, G., Smyth, P.: The kdd process for extracting useful knowledge from volumes of data. Commun. ACM 39(11), 27\u201334 (1996)","journal-title":"Commun. ACM"},{"issue":"353","key":"5_CR19","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1080\/01621459.1976.10481472","volume":"71","author":"IP Fellegi","year":"1976","unstructured":"Fellegi, I.P., Holt, D.: A systematic approach to automatic edit and imputation. J. Am. Stat. Assoc. 71(353), 17\u201335 (1976)","journal-title":"J. Am. Stat. Assoc."},{"key":"5_CR20","volume-title":"Introduction to Information Quality","author":"C Fisher","year":"2012","unstructured":"Fisher, C., Laur\u00eda, E., Chengalur-Smith, S., Wang, R.: Introduction to Information Quality. AuthorHouse, USA (2012)"},{"issue":"2\u20133","key":"5_CR21","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1023\/A:1007601113994","volume":"39","author":"D Freitag","year":"2000","unstructured":"Freitag, D.: Machine learning for information extraction in informal domains. Mach. Learn. 39(2\u20133), 169\u2013202 (2000)","journal-title":"Mach. Learn."},{"issue":"5","key":"5_CR22","doi-asserted-by":"publisher","first-page":"1101","DOI":"10.1016\/j.ipm.2004.04.016","volume":"41","author":"P Hansen","year":"2005","unstructured":"Hansen, P., J\u00e4rvelin, K.: Collaborative information retrieval in an information-intensive domain. Inf. Process. Manag. 41(5), 1101\u20131119 (2005)","journal-title":"Inf. Process. Manag."},{"key":"5_CR23","unstructured":"Holzinger, A.: On knowledge discovery and interactive intelligent visualization of biomedical data - challenges in human-computer interaction & biomedical informatics. In: Helfert, M., Francalanci, C., Filipe, J. (eds.) DATA. SciTePress (2012)"},{"key":"5_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1007\/978-3-642-40511-2_34","volume-title":"Availability, Reliability, and Security in Information Systems and HCI","author":"A Holzinger","year":"2013","unstructured":"Holzinger, A., Bruschi, M., Eder, W.: On interactive data visualization of physiological low-cost-sensor data with focus on mental stress. In: Cuzzocrea, A., Kittl, C., Simos, D.E., Weippl, E., Xu, L. (eds.) CD-ARES 2013. LNCS, vol. 8127, pp. 469\u2013480. Springer, Heidelberg (2013)"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Holzinger, A., Yildirim, P., Geier, M., Simonic, K.M.: Quality-based knowledge discovery from medical text on the web. In: Pasi et al. [38], pp. 145\u2013158","DOI":"10.1007\/978-3-642-37688-7_7"},{"key":"5_CR26","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1186\/1471-2105-14-191","volume":"14","author":"A Holzinger","year":"2013","unstructured":"Holzinger, A., Zupan, M.: Knodwat: a scientific framework application for testing knowledge discovery methods for the biomedical domain. BMC Bioinf. 14, 191 (2013)","journal-title":"BMC Bioinf."},{"issue":"2","key":"5_CR27","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1016\/S0021-8693(03)00167-4","volume":"264","author":"I Kapovich","year":"2003","unstructured":"Kapovich, I., Myasnikov, A., Schupp, P., Shpilrain, V.: Generic-case complexity, decision problems in group theory, and random walks. J. Algebra 264(2), 665\u2013694 (2003)","journal-title":"J. Algebra"},{"key":"5_CR28","unstructured":"Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th International Joint Conference on Artificial Intelligence, IJCAI 1995, vol. 2, pp. 1137\u20131143. Morgan Kaufmann Publishers Inc., San Francisco (1995). http:\/\/dl.acm.org\/citation.cfm?id=1643031.1643047"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Kolahi, S., Lakshmanan, L.V.: On approximating optimum repairs for functional dependency violations. In: Proceedings of the 12th International Conference on Database Theory, pp. 53\u201362. ACM (2009)","DOI":"10.1145\/1514894.1514901"},{"issue":"2","key":"5_CR30","doi-asserted-by":"publisher","first-page":"989","DOI":"10.1007\/s11135-011-9578-y","volume":"47","author":"PG Lovaglio","year":"2013","unstructured":"Lovaglio, P.G., Mezzanzanica, M.: Classification of longitudinal career paths. Qual. Quant. 47(2), 989\u20131008 (2013)","journal-title":"Qual. Quant."},{"issue":"1","key":"5_CR31","first-page":"2:1","volume":"1","author":"SE Madnick","year":"2009","unstructured":"Madnick, S.E., Wang, R.Y., Lee, Y.W., Zhu, H.: Overview and framework for data and information quality research. J. Data Inf. Qual. 1(1), 2:1\u20132:22 (2009)","journal-title":"J. Data Inf. Qual."},{"key":"5_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1007\/978-3-642-24800-9_26","volume-title":"Advances in Intelligent Data Analysis X","author":"M Mezzanzanica","year":"2011","unstructured":"Mezzanzanica, M., Boselli, R., Cesarini, M., Mercorio, F.: Data Quality through Model Checking Techniques. In: Gama, J., Bradley, E., Hollm\u00e9n, J. (eds.) IDA 2011. LNCS, vol. 7014, pp. 270\u2013281. Springer, Heidelberg (2011)"},{"key":"5_CR33","unstructured":"Mezzanzanica, M., Boselli, R., Cesarini, M., Mercorio, F.: Data quality sensitivity analysis on aggregate indicators. In: Helfert, M., Francalanci , C., Filipe, J. (eds.) DATA 2012-The International Conference on Data Technologies and Applications, pp. 97-108. SciTePress (2012). 10.5220\/0004040300970108"},{"key":"5_CR34","unstructured":"Mezzanzanica, M., Boselli, R., Cesarini, M., Mercorio, F.: Automatic synthesis of data cleansing activities. In: Helfert, M., Francalanci, C. (eds.) The 2nd International Conference on Data Management Technologies and Applications (DATA), pp. 138\u2013149. Scitepress (2013)"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Mezzanzanica, M., Boselli, R., Cesarini, M., Mercorio, F.: Improving data cleansing accuracy: a model-based approach. In: The 3rd International Conference on Data Technologies and Applications, pp. 189\u2013201. Insticc (2014)","DOI":"10.5220\/0005004901890201"},{"issue":"2","key":"5_CR36","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1016\/j.ipm.2014.07.007","volume":"51","author":"M Mezzanzanica","year":"2015","unstructured":"Mezzanzanica, M., Boselli, R., Cesarini, M., Mercorio, F.: A model-based evaluation of data quality activities in KDD. Inf. Process. Manag. 51(2), 144\u2013166 (2015). doi: 10.1016\/j.ipm.2014.07.007","journal-title":"Inf. Process. Manag."},{"issue":"4","key":"5_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2641575","volume":"5","author":"M Mezzanzanica","year":"2015","unstructured":"Mezzanzanica, M., Boselli, R., Cesarini, M., Mercorio, F.: A model-based approach for developing data cleansing solutions. ACM J. Data Inf. Qual. 5(4), 1\u201328 (2015). doi: 10.1145\/2641575","journal-title":"ACM J. Data Inf. Qual."},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Ng, A.Y.: Feature selection, l 1 vs. l 2 regularization, and rotational invariance. In: Proceedings of the Twenty-first International Conference on Machine Learning, p. 78. ACM (2004)","DOI":"10.1145\/1015330.1015435"},{"issue":"3","key":"5_CR39","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1109\/TVCG.2003.1207445","volume":"9","author":"MCF Oliveira de","year":"2003","unstructured":"de Oliveira, M.C.F., Levkowitz, H.: From visual data exploration to visual data mining: a survey. IEEE Trans. Vis. Comput. Graph. 9(3), 378\u2013394 (2003)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Pasi, G., Bordogna, G., Jain, L.C.: An introduction to quality issues in the management of web information. In: Quality Issues in the Management of Web Information [38], pp. 1\u20133","DOI":"10.1007\/978-3-642-37688-7_1"},{"key":"5_CR41","series-title":"Intelligent Systems Reference Library","volume-title":"Quality Issues in the Management of Web Information","year":"2013","unstructured":"Pasi, G., Bordogna, G., Jain, L.C. (eds.): Quality Issues in the Management of Web Information. Intelligent Systems Reference Library, vol. 50. Springer, Heidelberg (2013)"},{"key":"5_CR42","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR43","unstructured":"Penna, G.D., Intrigila, B., Magazzeni, D., Mercorio, F.: UPMurphi: a tool for universal planning on pddl+ problems. In: Proceedings of the 19th International Conference on Automated Planning and Scheduling (ICAPS 2009), pp. 106\u2013113. AAAI Press, Thessaloniki, Greece (2009). http:\/\/aaai.org\/ocs\/index.php\/ICAPS\/ICAPS09\/paper\/view\/707"},{"issue":"4","key":"5_CR44","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1007\/s10489-011-0306-z","volume":"36","author":"GD Penna","year":"2012","unstructured":"Penna, G.D., Magazzeni, D., Mercorio, F.: A universal planning system for hybrid domains. Appl. Intell. 36(4), 932\u2013959 (2012). doi: 10.1007\/s10489-011-0306-z","journal-title":"Appl. Intell."},{"issue":"3","key":"5_CR45","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/s10844-009-0106-7","volume":"36","author":"A Prinzie","year":"2011","unstructured":"Prinzie, A., Van den Poel, D.: odeling complex longitudinal consumer behavior with dynamic bayesian networks: an acquisition pattern analysis application. J. Intell. Inf. Syst. 36(3), 283\u2013304 (2011)","journal-title":"J. Intell. Inf. Syst."},{"issue":"4","key":"5_CR46","first-page":"3","volume":"23","author":"E Rahm","year":"2000","unstructured":"Rahm, E., Do, H.: Data cleaning: problems and current approaches. IEEE Data Eng. Bull. 23(4), 3\u201313 (2000)","journal-title":"IEEE Data Eng. Bull."},{"key":"5_CR47","first-page":"171","volume-title":"Trends in Theoretical Computer Science","author":"M Vardi","year":"1987","unstructured":"Vardi, M.: Fundamentals of dependency theory. In: Borger, E. (ed.) Trends in Theoretical Computer Science, pp. 171\u2013224. Computer Science Press, Rockville (1987)"},{"issue":"4","key":"5_CR48","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1080\/07421222.1996.11518099","volume":"12","author":"RY Wang","year":"1996","unstructured":"Wang, R.Y., Strong, D.M.: Beyond accuracy: what data quality means to data consumers. J. Manag. Inf. Syst. 12(4), 5\u201333 (1996)","journal-title":"J. Manag. Inf. Syst."},{"key":"5_CR49","doi-asserted-by":"crossref","unstructured":"Yakout, M., Berti-\u00c9quille, L., Elmagarmid, A.K.: Don\u2019t be scared: use scalable automatic repairing with maximal likelihood and bounded changes. In: Proceedings of the 2013 International Conference on Management of Data, pp. 553\u2013564. ACM (2013)","DOI":"10.1145\/2463676.2463706"}],"container-title":["Communications in Computer and Information Science","Data Management Technologies and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-25936-9_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,15]],"date-time":"2023-08-15T17:47:20Z","timestamp":1692121640000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-25936-9_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319259352","9783319259369"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-25936-9_5","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2015]]}}}