{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T16:46:55Z","timestamp":1762015615480},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2017,12,12]],"date-time":"2017-12-12T00:00:00Z","timestamp":1513036800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1007\/s10489-017-1093-y","type":"journal-article","created":{"date-parts":[[2017,12,12]],"date-time":"2017-12-12T05:23:29Z","timestamp":1513056209000},"page":"2546-2567","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Scalable aggregation predictive analytics"],"prefix":"10.1007","volume":"48","author":[{"given":"Christos","family":"Anagnostopoulos","sequence":"first","affiliation":[]},{"given":"Fotis","family":"Savva","sequence":"additional","affiliation":[]},{"given":"Peter","family":"Triantafillou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,12,12]]},"reference":[{"issue":"2","key":"1093_CR1","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1145\/304181.304198","volume":"28","author":"A Aboulnaga","year":"1999","unstructured":"Aboulnaga A, Chaudhuri S (1999) Self-tuning histograms: building histograms without looking at data. ACM SIGMOD Record 28(2):181\u2013192","journal-title":"ACM SIGMOD Record"},{"issue":"4","key":"1093_CR2","doi-asserted-by":"crossref","first-page":"1034","DOI":"10.1007\/s10489-016-0807-x","volume":"45","author":"C Anagnostopoulos","year":"2016","unstructured":"Anagnostopoulos C (2016) Quality-optimized predictive analytics. Appl Intell 45(4):1034\u20131046","journal-title":"Appl Intell"},{"key":"1093_CR3","doi-asserted-by":"crossref","unstructured":"Anagnostopoulos C, Triantafillou P (2014) Scaling out big data missing value imputations: Pythia vs. godzilla. In: Proceedings of the 20th ACM SIGKDD international conference on knowledge discovery and data mining, KDD \u201914. ACM, New York, pp 651\u2013660","DOI":"10.1145\/2623330.2623615"},{"key":"1093_CR4","doi-asserted-by":"crossref","unstructured":"Anagnostopoulos C, Triantafillou P (2015) Learning set cardinality in distance nearest neighbours. In: 2015 IEEE international conference on data mining, pp 691\u2013696","DOI":"10.1109\/ICDM.2015.17"},{"key":"1093_CR5","doi-asserted-by":"publisher","unstructured":"Anagnostopoulos C, Triantafillou P (2015) Learning to accurately count with query-driven predictive analytics. In: 2015 IEEE international conference on big data (big data), pp 14\u201323. \n                        https:\/\/doi.org\/10.1109\/BigData.2015.7363736","DOI":"10.1109\/BigData.2015.7363736"},{"key":"1093_CR6","doi-asserted-by":"crossref","unstructured":"Anagnostopoulos C, Triantafillou P (2017) Efficient scalable accurate regression queries in in-dbms analytics. In: 2017 IEEE 33rd international conference on data engineering (ICDE), pp 559\u2013570","DOI":"10.1109\/ICDE.2017.111"},{"issue":"4","key":"1093_CR7","doi-asserted-by":"publisher","first-page":"47:1","DOI":"10.1145\/3059177","volume":"11","author":"C Anagnostopoulos","year":"2017","unstructured":"Anagnostopoulos C, Triantafillou P (2017) Query-driven learning for predictive analytics of data subspace cardinality. ACM Trans Knowl Discov Data 11(4):47:1\u201347:46. \n                        https:\/\/doi.org\/10.1145\/3059177","journal-title":"ACM Trans Knowl Discov Data"},{"issue":"1","key":"1093_CR8","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/0169-2070(92)90008-W","volume":"8","author":"J Armstrong","year":"1992","unstructured":"Armstrong J, Collopy F (1992) Error measures for generalizing about forecasting methods: empirical comparisons. Int J Forecast 8(1):69\u201380","journal-title":"Int J Forecast"},{"key":"1093_CR9","doi-asserted-by":"crossref","unstructured":"Balac N, Sipes T, Wolter N, Nunes K, Sinkovits B, Karimabadi H (2013) Large scale predictive analytics for real-time energy management. In: 2013 IEEE international conference on big data. IEEE, pp 657\u2013664","DOI":"10.1109\/BigData.2013.6691635"},{"key":"1093_CR10","unstructured":"Bousquet O, Bottou L (2008) The tradeoffs of large scale learning. In: Advances in neural information processing systems, pp 161\u2013168"},{"key":"1093_CR11","doi-asserted-by":"crossref","unstructured":"Bruno N, Chaudhuri S, Gravano L (2001) Stholes: a multidimensional workload-aware histogram. In: ACM SIGMOD Record, vol 30. ACM, pp 211\u2013222","DOI":"10.1145\/375663.375686"},{"key":"1093_CR12","doi-asserted-by":"crossref","unstructured":"Chaudhuri A, Wei TH, Lee TY, Shen HW, Peterka T (2014) Efficient range distribution query for visualizing scientific data. In: 2014 IEEE pacific visualization symposium. IEEE, pp 201\u2013208","DOI":"10.1109\/PacificVis.2014.60"},{"issue":"1\u20133","key":"1093_CR13","first-page":"1","volume":"4","author":"G Cormode","year":"2012","unstructured":"Cormode G, Garofalakis M, Haas PJ, Jermaine C (2012) Synopses for massive data: samples, histograms, wavelets, sketches. Foundations and Trends in Databases 4(1\u20133):1\u2013294","journal-title":"Foundations and Trends in Databases"},{"issue":"1","key":"1093_CR14","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1145\/1629175.1629198","volume":"53","author":"J Dean","year":"2010","unstructured":"Dean J, Ghemawat S (2010) Mapreduce: a flexible data processing tool. Commun ACM 53(1):72\u201377. \n                        https:\/\/do.org\/10.1145\/1629175.1629198","journal-title":"Commun ACM"},{"issue":"2","key":"1093_CR15","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s00778-003-0090-4","volume":"14","author":"D Gunopulos","year":"2005","unstructured":"Gunopulos D, Kollios G, Tsotras J, Domeniconi C (2005) Selectivity estimators for multidimensional range queries over real attributes. The VLDB J Int J Very Large Data Bases 14(2):137\u2013154","journal-title":"The VLDB J Int J Very Large Data Bases"},{"key":"1093_CR16","doi-asserted-by":"crossref","unstructured":"Haas PJ, Swami AN (1992) Sequential sampling procedures for query size estimation, vol 21 ACM","DOI":"10.1145\/130283.130335"},{"issue":"1","key":"1093_CR17","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1007\/s10618-010-0201-y","volume":"23","author":"E Ikonomovska","year":"2011","unstructured":"Ikonomovska E, Gama J, D\u017eeroski S (2011) Learning model trees from evolving data streams. Data Min Knowl Disc 23(1):128\u2013168","journal-title":"Data Min Knowl Disc"},{"key":"1093_CR18","doi-asserted-by":"crossref","unstructured":"Indyk P, Motwani R (1998) Approximate nearest neighbors: towards removing the curse of dimensionality. In: Proceedings of the thirtieth annual ACM symposium on theory of computing, STOC \u201998. ACM, New York, pp 604\u2013613","DOI":"10.1145\/276698.276876"},{"issue":"1","key":"1093_CR19","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/S0925-2312(98)00031-9","volume":"21","author":"T Kohonen","year":"1998","unstructured":"Kohonen T, Somervuo P (1998) Self-organizing maps of symbol strings. Neurocomputing 21(1):19\u201330","journal-title":"Neurocomputing"},{"issue":"4","key":"1093_CR20","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.bdr.2015.02.001","volume":"2","author":"K Kolomvatsos","year":"2015","unstructured":"Kolomvatsos K, Anagnostopoulos C, Hadjiefthymiades S (2015) An efficient time optimized scheme for progressive analytics in big data. Big Data Res 2(4):155\u2013165","journal-title":"Big Data Res"},{"issue":"5","key":"1093_CR21","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1109\/72.134289","volume":"2","author":"B Kosko","year":"1991","unstructured":"Kosko B (1991) Stochastic competitive learning. IEEE Trans Neural Netw 2(5):522\u2013529","journal-title":"IEEE Trans Neural Netw"},{"issue":"1","key":"1093_CR22","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1186\/s40537-015-0032-1","volume":"2","author":"S Landset","year":"2015","unstructured":"Landset S, Khoshgoftaar TM, Richter AN, Hasanin T (2015) A survey of open source tools for machine learning with big data in the hadoop ecosystem. J Big Data 2(1):24. \n                        https:\/\/doi.org\/10.1186\/s40537-015-0032-1","journal-title":"J Big Data"},{"key":"1093_CR23","doi-asserted-by":"crossref","unstructured":"Lin CY, Tsai CH, Lee CP, Lin CJ (2014) Large-scale logistic regression and linear support vector machines using spark. In: 2014 IEEE international conference on big data (big data). IEEE, pp 519\u2013528","DOI":"10.1109\/BigData.2014.7004269"},{"issue":"11","key":"1093_CR24","doi-asserted-by":"crossref","first-page":"2683","DOI":"10.1162\/089976603322385117","volume":"15","author":"J Ma","year":"2003","unstructured":"Ma J, Theiler J, Perkins S (2003) Accurate on-line support vector regression. Neural Comput 15 (11):2683\u20132703","journal-title":"Neural Comput"},{"issue":"4","key":"1093_CR25","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1016\/0169-2070(93)90079-3","volume":"9","author":"S Makridakis","year":"1993","unstructured":"Makridakis S (1993) Accuracy measures: theoretical and practical concerns. Int J Forecast 9(4):527\u2013529","journal-title":"Int J Forecast"},{"key":"1093_CR26","doi-asserted-by":"crossref","unstructured":"Ong BT, Sugiura K, Zettsu K (2014) Dynamic pre-training of deep recurrent neural networks for predicting environmental monitoring data. In: 2014 IEEE international conference on big data (big data). IEEE, pp 760\u2013765","DOI":"10.1109\/BigData.2014.7004302"},{"key":"1093_CR27","doi-asserted-by":"crossref","unstructured":"Srivastava U, Haas PJ, Markl V, Kutsch M, Tran TM (2006) Isomer: consistent histogram construction using query feedback. In: 22nd international conference on data engineering (ICDE\u201906). IEEE, pp 39\u201339","DOI":"10.1109\/ICDE.2006.84"},{"key":"1093_CR28","doi-asserted-by":"crossref","unstructured":"To H, Chiang K, Shahabi C (2013) Entropy-based histograms for selectivity estimation. In: Proceedings of the 22nd ACM international conference on information & knowledge management. ACM, pp 1939\u20131948","DOI":"10.1145\/2505515.2505756"},{"key":"1093_CR29","doi-asserted-by":"publisher","unstructured":"Vavilapalli VK, Murthy AC, Douglas C, Agarwal S, Konar M, Evans R, Graves T, Lowe J, Shah H, Seth S, Saha B, Curino C, O\u2019Malley O, Radia S, Reed B, Baldeschwieler E (2013) Apache hadoop yarn: yet another resource negotiator. In: Proceedings of the 4th annual symposium on cloud computing, SOCC \u201913. ACM, New York, pp 5:1\u20135:16. \n                        https:\/\/doi.org\/10.1145\/2523616.2523633","DOI":"10.1145\/2523616.2523633"},{"key":"1093_CR30","unstructured":"Viswanathan R, Jain P, Laxman S, Arasu A (2011) A learning framework for self-tuning histograms. arXiv:\n                        1111.7295"},{"key":"1093_CR31","doi-asserted-by":"crossref","unstructured":"Vitter JS, Wang M, Iyer B (1998) Data cube approximation and histograms via wavelets. In: Proceedings of the seventh international conference on information and knowledge management. ACM, pp 96\u2013104","DOI":"10.1145\/288627.288645"},{"key":"1093_CR32","unstructured":"Zaharia M, Chowdhury M, Das T, Dave A, Ma J, McCauley M, Franklin MJ, Shenker S, Stoica I (2012) Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing. In: Proceedings of the 9th USENIX conference on networked systems design and implementation. USENIX Association, pp 2\u20132"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10489-017-1093-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-017-1093-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-017-1093-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,8,14]],"date-time":"2018-08-14T04:18:27Z","timestamp":1534220307000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10489-017-1093-y"}},"subtitle":["A query-driven machine learning approach"],"short-title":[],"issued":{"date-parts":[[2017,12,12]]},"references-count":32,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2018,9]]}},"alternative-id":["1093"],"URL":"https:\/\/doi.org\/10.1007\/s10489-017-1093-y","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,12,12]]}}}