{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T18:14:44Z","timestamp":1760552084529,"version":"3.37.3"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T00:00:00Z","timestamp":1712534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T00:00:00Z","timestamp":1712534400000},"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":["Knowl Inf Syst"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s10115-024-02096-5","type":"journal-article","created":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T03:10:07Z","timestamp":1712545807000},"page":"4437-4461","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Efficient parameter learning for Bayesian Network classifiers following the Apache Spark Dataframes paradigm"],"prefix":"10.1007","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0106-1759","authenticated-orcid":false,"given":"Ioannis","family":"Akarepis","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6063-8562","authenticated-orcid":false,"given":"Agorakis","family":"Bompotas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2571-7449","authenticated-orcid":false,"given":"Christos","family":"Makris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,4,8]]},"reference":[{"key":"2096_CR1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-022-00659-3","author":"H Abdalla","year":"2022","unstructured":"Abdalla H (2022) A brief survey on big data: technologies, terminologies and data-intensive applications. J Big Data. https:\/\/doi.org\/10.1186\/s40537-022-00659-3","journal-title":"J Big Data"},{"issue":"C","key":"2096_CR2","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.knosys.2016.06.013","volume":"117","author":"J Arias","year":"2017","unstructured":"Arias J, Gamez JA, Puerta JM (2017) Learning distributed discrete Bayesian network classifiers under mapreduce with apache spark. Know-Based Syst 117(C):16\u201326. https:\/\/doi.org\/10.1016\/j.knosys.2016.06.013","journal-title":"Know-Based Syst"},{"key":"2096_CR3","doi-asserted-by":"publisher","unstructured":"Armbrust M, Xin RS, Lian C, et al (2015) Spark SQL: relational data processing in spark. In: Proceedings of the 2015 ACM SIGMOD international conference on management of data. ACM, Melbourne Victoria Australia, pp 1383\u20131394, https:\/\/doi.org\/10.1145\/2723372.2742797, https:\/\/dl.acm.org\/doi\/10.1145\/2723372.2742797","DOI":"10.1145\/2723372.2742797"},{"issue":"2","key":"2096_CR4","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/s11749-022-00812-3","volume":"31","author":"D Atienza","year":"2022","unstructured":"Atienza D, Larra\u00f1aga P, Bielza C (2022) Hybrid semiparametric Bayesian networks. TEST Off J Span Soc Stat Oper Res 31(2):299\u2013327. https:\/\/doi.org\/10.1007\/s11749-022-00812-3","journal-title":"TEST Off J Span Soc Stat Oper Res"},{"issue":"1","key":"2096_CR5","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean J, Ghemawat S (2008) MapReduce: simplified data processing on large clusters. Commun ACM 51(1):107\u2013113. https:\/\/doi.org\/10.1145\/1327452.1327492","journal-title":"Commun ACM"},{"key":"2096_CR6","unstructured":"Gonzalez JE, Xin RS, Dave A, et al (2014) GraphX: graph processing in a distributed dataflow framework. In: 11th USENIX symposium on operating systems design and implementation (OSDI 14). USENIX Association, Broomfield, CO, pp 599\u2013613, https:\/\/www.usenix.org\/conference\/osdi14\/technical-sessions\/presentation\/gonzalez"},{"key":"2096_CR7","unstructured":"JohnSnowLabs (2023) spark-nlp. https:\/\/github.com\/JohnSnowLabs\/spark-nlp"},{"key":"2096_CR8","doi-asserted-by":"crossref","unstructured":"Kamaruddin S, Ravi V (2021) Architectures of big data analytics: scaling out data mining algorithms using Hadoop-MapReduce and Spark. https:\/\/www.scopus.com\/inward\/record.uri?eid=2-s2.0-85125967458 &partnerID=40 &md5=8295f7b6cc1dbcc04f6aa38de8ed0657","DOI":"10.1049\/PBPC037F_ch7"},{"issue":"7","key":"2096_CR9","doi-asserted-by":"publisher","first-page":"2561","DOI":"10.1016\/j.jpdc.2014.01.003","volume":"74","author":"K Kambatla","year":"2014","unstructured":"Kambatla K, Kollias G, Kumar V et al (2014) Trends in big data analytics. J Parallel Distrib Comput 74(7):2561\u20132573. https:\/\/doi.org\/10.1016\/j.jpdc.2014.01.003","journal-title":"J Parallel Distrib Comput"},{"key":"2096_CR10","doi-asserted-by":"publisher","DOI":"10.1145\/3301304","author":"A Katib","year":"2019","unstructured":"Katib A, Rao P, Barnard K et al (2019) Fast approximate score computation on large-scale distributed data for learning multinomial bayesian networks. ACM Trans Knowl Discov Data. https:\/\/doi.org\/10.1145\/3301304","journal-title":"ACM Trans Knowl Discov Data"},{"key":"2096_CR11","unstructured":"Kraska T, Talwalkar A, Duchi JC, et al (2013) Mlbase: a distributed machine-learning system. In: Conference on innovative data systems research, https:\/\/api.semanticscholar.org\/CorpusID:9300748"},{"key":"2096_CR12","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.ins.2012.12.051","volume":"233","author":"P Larra\u00f1aga","year":"2013","unstructured":"Larra\u00f1aga P, Karshenas H, Bielza C et al (2013) A review on evolutionary algorithms in Bayesian network learning and inference tasks. Inf Sci 233:109\u2013125. https:\/\/doi.org\/10.1016\/j.ins.2012.12.051","journal-title":"Inf Sci"},{"key":"2096_CR13","unstructured":"Lerner UN (2003) Hybrid Bayesian networks for reasoning about complex systems. Stanford University"},{"key":"2096_CR14","doi-asserted-by":"publisher","unstructured":"Logacjov A, Kongsvold A, Bach K, et al. (2023) Harth. UCI Mach Learn Repos https:\/\/doi.org\/10.24432\/C5NC90","DOI":"10.24432\/C5NC90"},{"key":"2096_CR15","doi-asserted-by":"publisher","first-page":"5247","DOI":"10.1109\/ACCESS.2017.2689040","volume":"5","author":"M Marjani","year":"2017","unstructured":"Marjani M, Nasaruddin F, Gani A et al (2017) Big IoT data analytics: architecture, opportunities, and open research challenges. IEEE Access 5:5247\u20135261. https:\/\/doi.org\/10.1109\/ACCESS.2017.2689040","journal-title":"IEEE Access"},{"issue":"34","key":"2096_CR16","first-page":"1","volume":"17","author":"X Meng","year":"2016","unstructured":"Meng X, Bradley J, Yavuz B et al (2016) Mllib: machine learning in apache spark. J Mach Learn Res 17(34):1\u20137","journal-title":"J Mach Learn Res"},{"key":"2096_CR17","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1007\/978-94-011-5014-9_19","volume-title":"Learning in graphical models","author":"S Monti","year":"1998","unstructured":"Monti S, Cooper GF (1998) Learning hybrid bayesian networks from data. Learning in graphical models. Springer, Berlin, pp 521\u2013540"},{"key":"2096_CR18","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1016\/j.procir.2016.07.038","volume":"55","author":"D Mourtzis","year":"2016","unstructured":"Mourtzis D, Vlachou E, Milas N (2016) Industrial big data as a result of IoT adoption in manufacturing. Proc dia CIRP 55:290\u2013295. https:\/\/doi.org\/10.1016\/j.procir.2016.07.038","journal-title":"Proc dia CIRP"},{"issue":"4","key":"2096_CR19","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1016\/j.jksuci.2017.06.001","volume":"30","author":"A Oussous","year":"2018","unstructured":"Oussous A, Benjelloun FZ, Ait Lahcen A et al (2018) Big data technologies: A survey. J King Saud Univ Comput Inf Sci 30(4):431\u2013448. https:\/\/doi.org\/10.1016\/j.jksuci.2017.06.001","journal-title":"J King Saud Univ Comput Inf Sci"},{"key":"2096_CR20","unstructured":"Papoulis A, Pillai S (2002) Probability, random variables, and stochastic processes. In: McGraw-Hill series in electrical and computer engineering, McGraw-Hill"},{"key":"2096_CR21","unstructured":"Salesforce (2021) Transmogrifai. https:\/\/github.com\/salesforce\/TransmogrifAI"},{"key":"2096_CR22","doi-asserted-by":"publisher","unstructured":"Shouaib M, Metwally K, Badran K (2022) Survey on iot-based big data analytics. In: 2022 13th international conference on electrical engineering (ICEENG), pp 81\u201385, https:\/\/doi.org\/10.1109\/ICEENG49683.2022.9781957","DOI":"10.1109\/ICEENG49683.2022.9781957"},{"key":"2096_CR23","doi-asserted-by":"publisher","unstructured":"Sparks ER, Talwalkar A, Smith V, et al (2013) Mli: An api for distributed machine learning. In: 2013 IEEE 13th international conference on data mining, pp 1187\u20131192, https:\/\/doi.org\/10.1109\/ICDM.2013.158","DOI":"10.1109\/ICDM.2013.158"},{"key":"2096_CR24","doi-asserted-by":"publisher","first-page":"105638","DOI":"10.1016\/j.knosys.2020.105638","volume":"195","author":"S Wang","year":"2020","unstructured":"Wang S, Zhang S, Wu T et al (2020) Fmdbn: a first-order Markov dynamic Bayesian network classifier with continuous attributes. Knowl Based Syst 195:105638. https:\/\/doi.org\/10.1016\/j.knosys.2020.105638","journal-title":"Knowl Based Syst"},{"key":"2096_CR25","doi-asserted-by":"publisher","unstructured":"Whiteson D (2014) HIGGS. UCI Mach Learn Repos https:\/\/doi.org\/10.24432\/C5V312","DOI":"10.24432\/C5V312"},{"key":"2096_CR26","unstructured":"Zaharia M, Chowdhury M, Franklin MJ, et al (2010) Spark: cluster computing with working sets. In: 2nd USENIX workshop on hot topics in cloud computing (HotCloud 10). USENIX Association, Boston, MA, https:\/\/www.usenix.org\/conference\/hotcloud-10\/spark-cluster-computing-working-sets"},{"key":"2096_CR27","unstructured":"Zaharia M, Chowdhury M, Das T, et al (2012) Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing. In: 9th USENIX symposium on networked systems design and implementation (NSDI 12). USENIX Association, San Jose, CA, pp 15\u201328, https:\/\/www.usenix.org\/conference\/nsdi12\/technical-sessions\/presentation\/zaharia"},{"issue":"17","key":"2096_CR28","doi-asserted-by":"publisher","first-page":"18405","DOI":"10.1007\/s11227-022-04594-1","volume":"78","author":"Y Zhong","year":"2022","unstructured":"Zhong Y, Chen L, Dan C et al (2022) A systematic survey of data mining and big data analysis in internet of things. J Supercomput 78(17):18405\u201318453. https:\/\/doi.org\/10.1007\/s11227-022-04594-1","journal-title":"J Supercomput"},{"key":"2096_CR29","unstructured":"Zhu W, Nguyen NLC (2022) Structure learning for hybrid bayesian networks. arXiv:2206.01356"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-024-02096-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10115-024-02096-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-024-02096-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T11:04:02Z","timestamp":1721300642000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10115-024-02096-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,8]]},"references-count":29,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["2096"],"URL":"https:\/\/doi.org\/10.1007\/s10115-024-02096-5","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"type":"print","value":"0219-1377"},{"type":"electronic","value":"0219-3116"}],"subject":[],"published":{"date-parts":[[2024,4,8]]},"assertion":[{"value":"15 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 March 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}