{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T16:58:37Z","timestamp":1743008317147,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030596118"},{"type":"electronic","value":"9783030596125"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-59612-5_1","type":"book-chapter","created":{"date-parts":[[2020,9,17]],"date-time":"2020-09-17T15:56:47Z","timestamp":1600358207000},"page":"3-12","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Entropy-Based Approach to Efficient Cleaning of Big Data in Hierarchical Databases"],"prefix":"10.1007","author":[{"given":"Eugene","family":"Levner","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boris","family":"Kriheli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arriel","family":"Benis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Ptuskin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amir","family":"Elalouf","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sharon","family":"Hovav","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shai","family":"Ashkenazi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,9,18]]},"reference":[{"key":"1_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"751","DOI":"10.1007\/3-540-48309-8_70","volume-title":"Database and Expert Systems Applications","author":"ML Lee","year":"1999","unstructured":"Lee, M.L., Lu, H., Ling, T.W., Ko, Y.T.: Cleansing data for mining and warehousing. In: Bench-Capon, T.J.M., Soda, G., Tjoa, A.M. (eds.) DEXA 1999. LNCS, vol. 1677, pp. 751\u2013760. Springer, Heidelberg (1999). https:\/\/doi.org\/10.1007\/3-540-48309-8_70"},{"key":"1_CR2","first-page":"1","volume":"23","author":"E Rahm","year":"2000","unstructured":"Rahm, E., Do, H.H.: Data cleaning: problems and current approaches. IEEE Data Eng. Bull. 23, 1\u201311 (2000)","journal-title":"IEEE Data Eng. Bull."},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Volkovs, M, Chiang, F., Szlichta J., Miller, R.J.: Continuous data cleaning. In: 2014 IEEE 30th International Conference on Data Engineering, pp. 244\u2013255 (2014)","DOI":"10.1109\/ICDE.2014.6816655"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Khedri, R., Chiang, F., Sabri, K.E.: An algebraic approach towards data cleaning. Procedia Comput. Sci. 21, 50\u201359 (2013). https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1877050913008028#aep-article-footnote-id2","DOI":"10.1016\/j.procs.2013.09.009"},{"key":"1_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1007\/11896548_24","volume-title":"Current Trends in Database Technology \u2013 EDBT 2006","author":"TJ Green","year":"2006","unstructured":"Green, T.J., Tannen, V.: Models for incomplete and probabilistic information. In: Grust, T., et al. (eds.) EDBT 2006. LNCS, vol. 4254, pp. 278\u2013296. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11896548_24"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Zimielinski, T., Lipski, W.: Incomplete information in relational databases. In: Readings in Artificial Intelligence and Databases, pp. 342\u2013360 (1989)","DOI":"10.1016\/B978-0-934613-53-8.50027-3"},{"issue":"1","key":"1_CR7","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1145\/584091.584093","volume":"5","author":"CE Shannon","year":"2001","unstructured":"Shannon, C.E.: A mathematical theory of communication. ACM SIGMOBILE Mob. Comput. Commun. Rev. 5(1), 3\u201355 (2001)","journal-title":"ACM SIGMOBILE Mob. Comput. Commun. Rev."},{"key":"1_CR8","unstructured":"Stone, J.V.: Information Theory. University of Sheffield, England (2014)"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Zhou, X., Zhang, Y., Hao, S., Li, S.: A new approach for noise data detection based on cluster and information entropy. In: Proceedings of the 2015 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), Shenyang, China, pp. 1416\u20131419 (2015)","DOI":"10.1109\/CYBER.2015.7288150"},{"issue":"9","key":"1_CR10","doi-asserted-by":"publisher","first-page":"142","DOI":"10.5539\/mas.v4n9p142","volume":"4","author":"V Kumar","year":"2010","unstructured":"Kumar, V., Rajendran, G.: Entropy based measurement of text dissimilarity for duplicate-detection. Mod. Appl. Sci. 4(9), 142\u2013146 (2010)","journal-title":"Mod. Appl. Sci."},{"issue":"3","key":"1_CR11","first-page":"267","volume":"3","author":"A Hebron","year":"2012","unstructured":"Hebron, A., Levner, E., Hovav, S., Lin, S.: Selection of most informative components in risk mitigation analysis of supply networks: an information-gain approach. Int. J. Innov. Manag. Technol. 3(3), 267\u2013271 (2012)","journal-title":"Int. J. Innov. Manag. Technol."},{"issue":"8","key":"1_CR12","doi-asserted-by":"publisher","first-page":"2297","DOI":"10.1080\/00207540802647327","volume":"48","author":"S Allesina","year":"2010","unstructured":"Allesina, S., Azzi, A., Battini, D., Regattieri, A.: Performance measurement in supply chains: new network analysis and entropic indexes. Int. J. Prod. Res. 48(8), 2297\u20132321 (2010)","journal-title":"Int. J. Prod. Res."},{"issue":"22","key":"1_CR13","doi-asserted-by":"publisher","first-page":"6888","DOI":"10.1080\/00207543.2014.934400","volume":"53","author":"E Levner","year":"2015","unstructured":"Levner, E., Ptuskin, A.: An entropy-based approach to identifying vulnerable components in a supply chain. Int. J. Prod. Res. 53(22), 6888\u20136902 (2015)","journal-title":"Int. J. Prod. Res."},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Hovav, S., Tell, H., Levner, E., Ptuskin, A., Herbon, A.: Healthcare analytics and big data management in influenza vaccination programs: use of information-entropy approach. In: Rodriguez-Taborda, E. (ed.) The Analytics Process: Strategic and Tactical Steps, pp. 211\u2013237. Taylor & Francis, CRC Press, Boca Raton (2017)","DOI":"10.1201\/9781315161501-11"},{"issue":"12","key":"1_CR15","doi-asserted-by":"publisher","first-page":"3681","DOI":"10.1080\/00207540902810593","volume":"48","author":"F Isik","year":"2010","unstructured":"Isik, F.: An entropy-based approach for measuring complexity in supply chains. Int. J. Prod. Res. 48(12), 3681\u20133696 (2010)","journal-title":"Int. J. Prod. Res."},{"issue":"4","key":"1_CR16","doi-asserted-by":"publisher","first-page":"923","DOI":"10.1080\/00207543.1992.9728465","volume":"30","author":"A Karp","year":"1992","unstructured":"Karp, A., Ronen, B.: Improving shop floor control: an entropy model approach. Int. J. Prod. Res. 30(4), 923\u2013938 (1992)","journal-title":"Int. J. Prod. Res."},{"issue":"11","key":"1_CR17","doi-asserted-by":"publisher","first-page":"e10734","DOI":"10.2196\/10734","volume":"7","author":"A Benis","year":"2018","unstructured":"Benis, A., Harel, N., Barak Barkan, R., Srulovici, E., Key, C.: Patterns of patients\u2019 interactions with a health care organization and their impacts on health duality measurements: protocol for a retrospective cohort study. JMIR Res. Protoc. 7(11), e10734 (2018)","journal-title":"JMIR Res. Protoc."},{"key":"1_CR18","first-page":"38","volume":"244","author":"A Benis","year":"2017","unstructured":"Benis, A.: Identification and description of healthcare customer communication patterns among individuals with diabetes in Clalit Health Services: A retrospective database study for applied epidemiological research. Stud. Health Technol. Inform. 244, 38\u201342 (2017)","journal-title":"Stud. Health Technol. Inform."},{"key":"1_CR19","doi-asserted-by":"publisher","DOI":"10.4135\/9781849208802","volume-title":"Data Collection and Analysis","author":"R Sapsford","year":"2006","unstructured":"Sapsford, R., Jupp, V.: Data Collection and Analysis. SAGE Publications, London (2006)"},{"issue":"4","key":"1_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/a11040035","volume":"11","author":"B Kriheli","year":"2018","unstructured":"Kriheli, B., Levner, E.: Entropy-based algorithm for supply-chain complexity assessment. Algorithms 11(4), 1\u201315 (2018)","journal-title":"Algorithms"}],"container-title":["Lecture Notes in Computer Science","Big Data \u2013 BigData 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-59612-5_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T12:32:59Z","timestamp":1726662779000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-59612-5_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030596118","9783030596125"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-59612-5_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"18 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BIGDATA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Honolulu, HI","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bigdata2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.bigdatacongress.org\/2020\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}