{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T09:08:34Z","timestamp":1775812114201,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":37,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642402692","type":"print"},{"value":"9783642402708","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-40270-8_1","type":"book-chapter","created":{"date-parts":[[2013,8,17]],"date-time":"2013-08-17T05:41:48Z","timestamp":1376718108000},"page":"1-15","source":"Crossref","is-referenced-by-count":125,"title":["From Big Data to Big Data Mining: Challenges, Issues, and Opportunities"],"prefix":"10.1007","author":[{"given":"Dunren","family":"Che","sequence":"first","affiliation":[]},{"given":"Mejdl","family":"Safran","sequence":"additional","affiliation":[]},{"given":"Zhiyong","family":"Peng","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"1_CR1","first-page":"1","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"U.M. Fayyad","year":"1996","unstructured":"Fayyad, U.M., Gregory, P.S., Padhraic, S.: From Data Mining to Knowledge Discovery: an Overview. In: Advances in Knowledge Discovery and Data Mining, pp. 1\u201336. AAAI Press, Menlo Park (1996)"},{"key":"1_CR2","volume-title":"3rd International Conference on Computing for Geospatial Research and Applications, article no. 26","author":"S. Berkovich","year":"2012","unstructured":"Berkovich, S., Liao, D.: On Clusterization of big data Streams. In: 3rd International Conference on Computing for Geospatial Research and Applications, article no. 26. ACM Press, New York (2012)"},{"key":"1_CR3","unstructured":"Beyer, M.A., Laney, D.: The Importance of \u2018Big Data\u2019: a Definition. Gartner (2012)"},{"issue":"3","key":"1_CR4","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/MIC.2012.50","volume":"16","author":"S. Madden","year":"2012","unstructured":"Madden, S.: From Databases to big data. IEEE Internet Computing\u00a016(3), 4\u20136 (2012)","journal-title":"IEEE Internet Computing"},{"key":"1_CR5","unstructured":"Dean, J., Ghemawat, S.: MapReduce: Simplified Data Processing on Large Clusters. In: 6th Symposium on Operating System Design and Implementation (OSDI), pp. 137\u2013150 (2004)"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Ghemawat, S., Gobioff, H., Leung, S.T.: The Google File System. In: 19th ACM Symposium on Operating Systems Principles, Bolton Landing, New York, pp. 29\u201343 (2003)","DOI":"10.1145\/1165389.945450"},{"issue":"1","key":"1_CR7","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1145\/1629175.1629198","volume":"53","author":"J. Dean","year":"2010","unstructured":"Dean, J., Ghemawat, S.: MapReduce: a Flexible Data Processing Tool. Communication of the ACM\u00a053(1), 72\u201377 (2010)","journal-title":"Communication of the ACM"},{"key":"1_CR8","first-page":"205","volume-title":"7th Symposium on Operating Systems Design and Implementation","author":"F. Chang","year":"2006","unstructured":"Chang, F., Dean, J., Ghemawat, S., et al.: Bigtable: A Distributed Storage System for Structured Data. In: 7th Symposium on Operating Systems Design and Implementation, vol.\u00a07, pp. 205\u2013218. USENIX Association Berkeley, CA (2006)"},{"key":"1_CR9","first-page":"14","volume-title":"21st ACM SIGOPS Symposium on Operating Systems Principles","author":"G. DeCandia","year":"2007","unstructured":"DeCandia, G., Hastorun, D.: Jampani, et al: Dynamo: Amazon\u2019s Highly Available Key-Value Store. In: 21st ACM SIGOPS Symposium on Operating Systems Principles, pp. 14\u201317. Stevenson, Washington (2007)"},{"key":"1_CR10","volume-title":"Data Mining for Business Intelligence: Concepts, Techniques, and Applications in Microsoft Office Excel with XLMiner","author":"G. Shmueli","year":"2010","unstructured":"Shmueli, G., Patel, N.R., Bruce, P.C.: Data Mining for Business Intelligence: Concepts, Techniques, and Applications in Microsoft Office Excel with XLMiner, 2nd edn. Wiley & Sons, Hoboken (2010)","edition":"2"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Ghoting, A., Kambadur, P., Pednault, E., Kannan, R.: NIMBLE: a Toolkit for the Implementation of Parallel Data Mining and Machine Learning Algorithms on MapReduce. In: 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Diego, California, USA, pp. 334\u2013342 (2011)","DOI":"10.1145\/2020408.2020464"},{"key":"1_CR12","unstructured":"Mahout, \n                    \n                      http:\/\/lucene.apache.org\/mahout\/"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Yu, L., Zheng, J., Shen, W.C., et al.: BC-PDM: Data Mining, Social Network Analysis and Text Mining System Based on Cloud Computing. In: 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1496\u20131499 (2012)","DOI":"10.1145\/2339530.2339764"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Kang, U., Tsourakakis, C.E., Faloutsos, C.: PEGASUS: A Peta-Scale Graph Mining System Implementation and Observations. In: 9th IEEE International Conference on Data Mining, pp. 229\u2013238 (2009)","DOI":"10.1109\/ICDM.2009.14"},{"key":"1_CR15","unstructured":"Apache Giraph Project, \n                    \n                      http:\/\/giraph.apache.org\/"},{"issue":"8","key":"1_CR16","first-page":"71","volume":"5","author":"Y. Low","year":"2012","unstructured":"Low, Y., Bickson, D., Gonzalez, J., Guestrin, C., Kyrola, A., Hellerstein, J.M.: Distributed GraphLab: A Framework for Machine Learning and Data Mining in the Cloud. VLDB Endowment\u00a05(8), 71\u2013727 (2012)","journal-title":"VLDB Endowment"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Brown, P.G.: Overview of SciDB: Large Scale Array Storage, Processing and Analysis. In: ACM SIGMOD International Conference on Management of Data, pp. 963\u2013968 (2010)","DOI":"10.1145\/1807167.1807271"},{"key":"1_CR18","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1088\/1742-6596\/16\/1\/077","volume":"16","author":"K. Wu","year":"2005","unstructured":"Wu, K.: FastBit: An Efficient Indexing Technology for Accelerating Data-intensive Science. Journal of Physics, Conference Series\u00a016, 550\u2013560 (2005)","journal-title":"Journal of Physics, Conference Series"},{"issue":"1","key":"1_CR19","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1145\/2331042.2331057","volume":"19","author":"V.R. Borkar","year":"2012","unstructured":"Borkar, V.R., Carey, M.J., Li, C.: big data Platforms: What\u2019s Next? ACM Crossroads\u00a019(1), 44\u201349 (2012)","journal-title":"ACM Crossroads"},{"issue":"12","key":"1_CR20","doi-asserted-by":"crossref","first-page":"2022","DOI":"10.14778\/2367502.2367566","volume":"5","author":"Y. Sun","year":"2012","unstructured":"Sun, Y., Han, J., Yan, X., Yu, P.S.: Mining Knowledge from Interconnected Data: A Heterogeneous Information Network Analysis Approach. VLDB Endowment\u00a05(12), 2022\u20132023 (2012)","journal-title":"VLDB Endowment"},{"key":"1_CR21","unstructured":"Obradovic, Z., Vucetic, S.: Challenges in Scientific Data Mining: Heterogeneous, Biased, and Large Samples. Technical Report, Center for Information Science and Technology Temple University, ch. 1, pp. 1\u201324 (2004)"},{"key":"1_CR22","unstructured":"Vucetic, S., Obradovic, Z.: Discovering Homogeneous Regions in Spatial Data through Competition. In: 17th International Conference of Machine Learning, Stanford, CA, pp. 1095\u20131102 (2000)"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Wu, K., Ahern, S.: Bethel, et al: FastBit: Interactively Searching Massive Data. SciDAC\u00a0180 (2009)","DOI":"10.1088\/1742-6596\/180\/1\/012053"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Cai, D., Shao, Z., He, X., Yan, X., Han, J.: Mining Hidden Communities in Heterogeneous Social Network. In: 3rd International Workshop Link Discovery (LinkKDD), pp. 58\u201365 (2005)","DOI":"10.1145\/1134271.1134280"},{"key":"1_CR25","unstructured":"Apache Hive, \n                    \n                      http:\/\/hive.apache.org\/"},{"key":"1_CR26","unstructured":"Berkeley Data Analytics Stack (BDAS), \n                    \n                      https:\/\/amplab.cs.berkeley.edu\/bdas\/"},{"key":"1_CR27","unstructured":"Xin, R.S., Rosen, J., Zaharia, M., Franklin, M., Shenker, S., Stoica, I.: Shark: SQL and Rich Analytics at Scale. In: ACM SIGMOD Conference (accepted, 2013)"},{"key":"1_CR28","unstructured":"Agrawal, D., Bernstein, P., Bertino, E., et al.: Challenges and Opportunities With big data \u2013 A Community White Paper Developed by Leading Researchers Across the United States (2012), \n                    \n                      http:\/\/cra.org\/ccc\/docs\/init\/bigdatawhitepaper.pdf"},{"key":"1_CR29","unstructured":"Laney, D.: 3D Data Management: Controlling Data Volume, Velocity and Variety. Gartner (2001)"},{"key":"1_CR30","first-page":"17","volume-title":"1st International Workshop on Cloud Data Management","author":"X. Zhang","year":"2009","unstructured":"Zhang, X., Ai, J., Wang, Z., Lu, J., Meng, X.: An Efficient Multi-dimensional Index for Cloud Data Management. In: 1st International Workshop on Cloud Data Management, pp. 17\u201324. ACM Press, Hong Kong (2009)"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Yin, X., Han, J., Yu, P.S.: Truth Discovery with Multiple Conflicting Information Providers on the Web. In: 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Jose, California, pp. 1048\u20131052 (2007)","DOI":"10.1145\/1281192.1281309"},{"issue":"1","key":"1_CR32","doi-asserted-by":"crossref","first-page":"550","DOI":"10.14778\/1687627.1687690","volume":"2","author":"X.L. Dong","year":"2009","unstructured":"Dong, X.L., Berti-Equille, L., Srivastava, D.: Integrating Conflicting Data: The Role of Source Dependence. VLDB Endowment\u00a02(1), 550\u2013561 (2009)","journal-title":"VLDB Endowment"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Yin, X., Tan, W.: Semi-Supervised Truth Discovery. In: 20th International Conference on World Wide Web, Hyderabad, India, pp. 217\u2013226 (2011)","DOI":"10.1145\/1963405.1963439"},{"key":"1_CR34","first-page":"63","volume":"64","author":"O. Tene","year":"2012","unstructured":"Tene, O., Polonetsky, J.: Privacy in the Age of big data: A Time for Big Decisions. Stanford Law Review Online\u00a064, 63\u201369 (2012)","journal-title":"Stanford Law Review Online"},{"key":"1_CR35","unstructured":"Pedreschi, D., Calders, T., Custers, B., et al.: big data Mining, Fairness and Privacy - A Vision Statement Towards an Interdisciplinary Roadmap of Research. Data Mining and Analytics Software, KDnuggets Review Online\u00a011(26) (2011)"},{"key":"1_CR36","unstructured":"NewVantage Partners: Big Data Executive Survey (2013), \n                    \n                      http:\/\/newvantage.com\/wp-content\/uploads\/2013\/02\/NVP-Big-Data-Survey-2013-Summary-Report.pdf"},{"issue":"12","key":"1_CR37","doi-asserted-by":"publisher","first-page":"2205","DOI":"10.1016\/j.fusengdes.2012.02.128","volume":"87","author":"M. Greenwald","year":"2012","unstructured":"Greenwald, M., Fredian, T., Schissel, D., Stillerman, J.: A Metadata Catalog for Organization and Systemization of Fusion Simulation Data. Fusion Engineering & Design\u00a087(12), 2205\u20132208 (2012)","journal-title":"Fusion Engineering & Design"}],"container-title":["Lecture Notes in Computer Science","Database Systems for Advanced Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-40270-8_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,16]],"date-time":"2019-05-16T18:03:56Z","timestamp":1558029836000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-40270-8_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642402692","9783642402708"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-40270-8_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013]]}}}