{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T04:50:59Z","timestamp":1749185459017,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031206269"},{"type":"electronic","value":"9783031206276"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20627-6_16","type":"book-chapter","created":{"date-parts":[[2022,10,24]],"date-time":"2022-10-24T23:03:36Z","timestamp":1666652616000},"page":"165-176","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["HoloCleanX: A Multi-source Heterogeneous Data Cleaning Solution Based on Lakehouse"],"prefix":"10.1007","author":[{"given":"Qin","family":"Cui","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenkui","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wang","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"XiangYang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,25]]},"reference":[{"issue":"6","key":"16_CR1","doi-asserted-by":"publisher","first-page":"102324","DOI":"10.1016\/j.ipm.2020.102324","volume":"57","author":"Y Zhang","year":"2020","unstructured":"Zhang, Y., et al.: Hkgb: an inclusive, extensible, intelligent, semi-auto-constructed knowledge graph framework for healthcare with clinicians\u2019 expertise incorporated. Inf. Process. Manage. 57(6), 102324 (2020)","journal-title":"Inf. Process. Manage."},{"issue":"1","key":"16_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13755-019-0084-2","volume":"7","author":"J Du","year":"2019","unstructured":"Du, J., Michalska, S., Subramani, S., Wang, H., Zhang, Y.: Neural attention with character embeddings for hay fever detection from Twitter. Health Inf. Sci. Syst. 7(1), 1\u20137 (2019). https:\/\/doi.org\/10.1007\/s13755-019-0084-2","journal-title":"Health Inf. Sci. Syst."},{"issue":"1","key":"16_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13755-020-00129-1","volume":"8","author":"S Supriya","year":"2020","unstructured":"Supriya, S., Siuly, S., Wang, H., Zhang, Y.: Automated epilepsy detection techniques from electroencephalogram signals: a review study. Health Inf. Sci. Syst. 8(1), 1\u201315 (2020). https:\/\/doi.org\/10.1007\/s13755-020-00129-1","journal-title":"Health Inf. Sci. Syst."},{"issue":"1","key":"16_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13755-020-00125-5","volume":"8","author":"R Sarki","year":"2020","unstructured":"Sarki, R., Ahmed, K., Wang, H., Zhang, Y.: Automated detection of mild and multi-class diabetic eye diseases using deep learning. Health Inf. Sci. Syst. 8(1), 1\u20139 (2020). https:\/\/doi.org\/10.1007\/s13755-020-00125-5","journal-title":"Health Inf. Sci. Syst."},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Wang, C., Feng, S.: Research on the collection and preprocessing of multisource heterogeneous elevator data. In: 2020 IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS), pp. 490\u2013493. IEEE (2020)","DOI":"10.1109\/ICPICS50287.2020.9202267"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Liu, W., Zhang, C., Yu, B., Li, Y.: A general multi-source data fusion framework. In: Proceedings of the 2019 11th International Conference on Machine Learning and Computing, pp. 285\u2013289 (2019)","DOI":"10.1145\/3318299.3318394"},{"key":"16_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1007\/978-3-030-87571-8_63","volume-title":"Web Information Systems and Applications","author":"P Ren","year":"2021","unstructured":"Ren, P., et al.: Mhdp: an efficient data lake platform for medical multi-source heterogeneous data. In: Xing, C., Fu, X., Zhang, Y., Zhang, G., Borjigin, C. (eds.) WISA 2021. LNCS, vol. 12999, pp. 727\u2013738. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87571-8_63"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Chen, C.S., Hu, H.R., Fang, L.L., Xiang, Y.X.: Research on equipment situation display based on multi-source data fusion. In: 2020 International Conference on Computer Engineering and Intelligent Control (ICCEIC), pp. 207\u2013211. IEEE (2020)","DOI":"10.1109\/ICCEIC51584.2020.00048"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Sun, R., et al.: Research on multi-source heterogeneous data cleaning technology based on integrating neural network with fuzzy rules for renewable energy accommodation. In: 2020 IEEE 4th Conference on Energy Internet and Energy System Integration (EI2), pp. 3024\u20133027. IEEE (2020)","DOI":"10.1109\/EI250167.2020.9346757"},{"issue":"4","key":"16_CR10","first-page":"3","volume":"23","author":"E Rahm","year":"2000","unstructured":"Rahm, E., Do, H.H.: Data cleaning: problems and current approaches. IEEE Data Eng. Bull. 23(4), 3\u201313 (2000)","journal-title":"IEEE Data Eng. Bull."},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Rekatsinas, T., Chu, X., Ilyas, I.F., R\u00e9, C.: Holoclean: Holistic data repairs with probabilistic inference. arXiv preprint arXiv:1702.00820 (2017)","DOI":"10.14778\/3137628.3137631"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Jiming, H., Wei, S.: An object-centric multi-source heterogeneous data fusion scheme. In: 2021 IEEE International Conference on Information Communication and Software Engineering (ICICSE), pp. 24\u201329. IEEE (2021)","DOI":"10.1109\/ICICSE52190.2021.9404095"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Li, H., Zhou, G., Zhou, S., Chen, S., Mao, S., Jin, T.: Multi-source heterogeneous log fusion technology of power information system based on big data and imprecise reasoning theory. In: 2020 IEEE 20th International Conference on Communication Technology (ICCT), pp. 1609\u20131614. IEEE (2020)","DOI":"10.1109\/ICCT50939.2020.9295848"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Gledson, A., Dhafari, T.B., Paton, N., Keane, J.: A smart city dashboard for combining and analysing multi-source data streams. In: 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS), pp. 1366\u20131373. IEEE (2018)","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2018.00226"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Yuan, Q., Pi, Y., Kou, L., Zhang, F., Li, Y., Zhang, Z.: Multi-source data processing and fusion method for power distribution internet of things based on edge intelligence. arXiv preprint arXiv:2203.17230 (2022)","DOI":"10.3389\/fenrg.2022.891867"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Lv, Z., Deng, W., Zhang, Z., Guo, N., Yan, G.: A data fusion and data cleaning system for smart grids big data. In: 2019 IEEE Intl Conference on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA\/BDCloud\/SocialCom\/SustainCom), pp. 802\u2013807. IEEE (2019)","DOI":"10.1109\/ISPA-BDCloud-SustainCom-SocialCom48970.2019.00119"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Ying, Z., Huang, Y., Chen, K., Yu, T.: Big data cleaning model of multi-source heterogeneous power grid based on machine learning classification algorithm. In: Journal of Physics: Conference Series, vol. 2087, p. 012095. IOP Publishing (2021)","DOI":"10.1088\/1742-6596\/2087\/1\/012095"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Deshpande, P., Rasin, A., Tchoua, R., Furst, J., Raicu, D., Antani, S.: Enhancing recall using data cleaning for biomedical big data. In: 2020 IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS), pp. 265\u2013270. IEEE (2020)","DOI":"10.1109\/CBMS49503.2020.00057"},{"issue":"1","key":"16_CR19","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/s10115-018-1284-9","volume":"61","author":"C Ye","year":"2019","unstructured":"Ye, C., Li, Q., Zhang, H., Wang, H., Gao, J., Li, J.: AutoRepair: an automatic repairing approach over multi-source data. Knowl. Inf. Syst. 61(1), 227\u2013257 (2019)","journal-title":"Knowl. Inf. Syst."},{"key":"16_CR20","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1016\/j.ins.2019.08.044","volume":"507","author":"C Ye","year":"2020","unstructured":"Ye, C., Wang, H., Zheng, K., Gao, J., Li, J.: Multi-source data repairing powered by integrity constraints and source reliability. Inf. Sci. 507, 386\u2013403 (2020)","journal-title":"Inf. Sci."},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Heidari, A., McGrath, J., Ilyas, I.F., Rekatsinas, T.: HoloDetect: few-shot learning for error detection. In: Proceedings of the 2019 International Conference on Management of Data, pp. 829\u2013846 (2019)","DOI":"10.1145\/3299869.3319888"},{"key":"16_CR22","unstructured":"Krishnan, S., Wu, E.: AlphaClean: automatic generation of data cleaning pipelines. arXiv preprint arXiv:1904.11827 (2019)"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Mahdavi, M., et al.: Raha: a configuration-free error detection system. In: Proceedings of the 2019 International Conference on Management of Data, pp. 865\u2013882 (2019)","DOI":"10.1145\/3299869.3324956"},{"key":"16_CR24","unstructured":"Lew, A., Agrawal, M., Sontag, D., Mansinghka, V.: PClean: Bayesian data cleaning at scale with domain-specific probabilistic programming. In: International Conference on Artificial Intelligence and Statistics, pp. 1927\u20131935. PMLR (2021)"}],"container-title":["Lecture Notes in Computer Science","Health Information Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20627-6_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,24]],"date-time":"2022-10-24T23:43:29Z","timestamp":1666655009000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20627-6_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031206269","9783031206276"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20627-6_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"25 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"HIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Health Information Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"his22022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/his-conferences.org\/2022\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"54","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"20","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"9","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"37% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}