{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T13:04:36Z","timestamp":1763643876726},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"18","license":[{"start":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T00:00:00Z","timestamp":1686528000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T00:00:00Z","timestamp":1686528000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Jilin Youth Fund Project","award":["20190104156"],"award-info":[{"award-number":["20190104156"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s11227-023-05443-5","type":"journal-article","created":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T17:02:04Z","timestamp":1686589324000},"page":"20235-20262","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Economic mining of thermal power plant based on improved Hadoop-based framework and Spark-based algorithms"],"prefix":"10.1007","volume":"79","author":[{"given":"Xiaoqiang","family":"Wen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhibin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengchong","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianguo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lifeng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,12]]},"reference":[{"key":"5443_CR1","doi-asserted-by":"crossref","unstructured":"Pradeep Kumar J, Sheikh Gouse P, Amarendra R (2018) Migration of big data analysis from Hadoop\u2019s mapreduce to spark. In: 1st International Conference on Artificial Intelligence and Cognitive Computing, 815: 473\u2013484.","DOI":"10.1007\/978-981-13-1580-0_46"},{"key":"5443_CR2","doi-asserted-by":"publisher","first-page":"2552","DOI":"10.3390\/su10072552","volume":"10","author":"ML Ma","year":"2018","unstructured":"Ma ML, Su M, Li SY et al (2018) Predicting coal consumption in south africa based on linear (metabolic grey model), nonlinear (non-linear grey model), and combined (metabolic grey model-autoregressive integrated moving average model) models. Sustainablility 10:2552","journal-title":"Sustainablility"},{"key":"5443_CR3","doi-asserted-by":"publisher","first-page":"5706","DOI":"10.3390\/en14185706","volume":"14","author":"S Jendrysik","year":"2021","unstructured":"Jendrysik S, Bartoszek S, Balaga D et al (2021) Study of energy consumption of a bucket conveyor in a jig concentrator plant in a hard coal mine. Energies 14:5706","journal-title":"Energies"},{"key":"5443_CR4","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1590\/S0103-21002009000500014","volume":"22","author":"GN Dreyer","year":"2009","unstructured":"Dreyer GN, de F\u00e1tima MH (2009) Data mining: a literature review. Acta Paulista de Enfermagem 22:686\u2013690","journal-title":"Acta Paulista de Enfermagem"},{"key":"5443_CR5","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1504\/EJIE.2012.044810","volume":"6","author":"ZH Che","year":"2012","unstructured":"Che ZH (2012) A hybrid algorithm for fuzzy clustering. Eur J Ind Eng 6:50\u201367","journal-title":"Eur J Ind Eng"},{"key":"5443_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5391\/IJFIS.2008.8.1.001","volume":"8","author":"L SeungJoo","year":"2008","unstructured":"SeungJoo L, SungHae J (2008) A comparison study of classification algorithms in data mining. Int J Fuzzy Logic Intell Syst 8:1\u20135","journal-title":"Int J Fuzzy Logic Intell Syst"},{"key":"5443_CR7","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1007\/s11227-020-03328-5","volume":"77","author":"A Mostafaeipour","year":"2021","unstructured":"Mostafaeipour A, Rafsanjani AJ, Ahmadi M et al (2021) Investigating the performance of Hadoop and Spark platforms on machine learning algorithms. J Supercomput 77:1273\u20131300","journal-title":"J Supercomput"},{"key":"5443_CR8","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1007\/s11227-013-1050-4","volume":"68","author":"WK Lai","year":"2014","unstructured":"Lai WK, Chen YU, Wu TY et al (2014) Towards a framework for large-scale multimedia data storage and processing on Hadoop platform. J Supercomput 68:488\u2013507","journal-title":"J Supercomput"},{"key":"5443_CR9","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1186\/s13742-015-0043-z","volume":"4","author":"A Siretskiy","year":"2015","unstructured":"Siretskiy A, Sundqvist T, Voznesenskiy M et al (2015) A quantitative assessment of the Hadoop framework for analyzing massively parallel DNA sequencing data. GIGAScience 4:6","journal-title":"GIGAScience"},{"key":"5443_CR10","unstructured":"Wan X, Hu N, et al. (2016) Research on application of big data mining technology in performance optimization of steam turbines. In: Proceedings of the CSEE vol 6: pp 459\u2013467"},{"key":"5443_CR11","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1016\/j.compeleceng.2017.10.008","volume":"67","author":"S Singh","year":"2018","unstructured":"Singh S, Garg R, Mishra PK et al (2018) Performance optimization of MapReduce-based Apriori algorithm on Hadoop cluster. J Comput Electr Eng 67:348\u2013364","journal-title":"J Comput Electr Eng"},{"key":"5443_CR12","first-page":"513","volume":"2","author":"A Ezhilvathani","year":"2013","unstructured":"Ezhilvathani A, Raja K (2013) Implementation of parallel Apriori algorithm on Hadoop cluster. Int J Comput Sci Mob Comput 2:513\u2013516","journal-title":"Int J Comput Sci Mob Comput"},{"key":"5443_CR13","unstructured":"Singh S, Garg R, Mishra P K (2016) Performance optimization of mapreduce- based Apriori algorithm on Hadoop cluster. In: 2016 International Conference on Computing, Communication and Automation (ICCCA), Apr. 29\u201330, Greater Noida, India"},{"key":"5443_CR14","doi-asserted-by":"publisher","first-page":"100035","DOI":"10.1016\/j.array.2020.100035","volume":"7","author":"S Bagui","year":"2020","unstructured":"Bagui S, Devulapalli K, Coffey J (2020) A heuristic approach for load balancing the FP-Growth algorithm On MapReduce. Array 7:100035","journal-title":"Array"},{"key":"5443_CR15","first-page":"111","volume":"11","author":"J Ragaventhiran","year":"2019","unstructured":"Ragaventhiran J, Kavithadevi MK et al (2019) Map-optimize-reduce: CAN tree assisted FP-growth algorithm for clusters based FP mining on Hadoop. J Future Gener Comput Syst 11:111\u2013112","journal-title":"J Future Gener Comput Syst"},{"key":"5443_CR16","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1016\/j.ins.2017.11.064","volume":"432","author":"MD Rezaul Karim","year":"2018","unstructured":"Rezaul Karim MD, Cochez M et al (2018) Mining maximal frequent patterns in transactional databases and dynamic data streams: a spark-based approach. Inf Sci 432:278\u2013300","journal-title":"Inf Sci"},{"key":"5443_CR17","first-page":"3593","volume":"20","author":"M Kang","year":"2017","unstructured":"Kang M, Lee JG (2017) An experimental analysis of limitations of MapReduce for iterative algorithms on Spark. Clust Comput- J Netw Softw Tools Appl 20:3593\u20133604","journal-title":"Clust Comput- J Netw Softw Tools Appl"},{"key":"5443_CR18","doi-asserted-by":"publisher","first-page":"80716","DOI":"10.1109\/ACCESS.2020.2988796","volume":"8","author":"KP Sinaga","year":"2020","unstructured":"Sinaga KP, Yang MS (2020) Unsupervised K-Means clustering algorithm. IEEE Access 8:80716\u201380727","journal-title":"IEEE Access"},{"key":"5443_CR19","first-page":"1322","volume":"40","author":"Z Alamgir","year":"2021","unstructured":"Alamgir Z, Naveed H (2021) Efficient density-based partitional clustering algorithm. Comput Inf 40:1322\u20131344","journal-title":"Comput Inf"},{"key":"5443_CR20","first-page":"1618","volume":"34","author":"M Capo","year":"2022","unstructured":"Capo M, Perez A, Antonio JA (2022) An efficient split-merge re-start for the K-means algorithm. IEEE Trans Knowl Data Eng 34:1618\u20131627","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"5443_CR21","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1109\/TEC.2007.914183","volume":"23","author":"Z Song","year":"2008","unstructured":"Song Z (2008) Clustering-based performance optimization of the boiler-turbine system. IEEE Trans Energy Convers 23:651\u2013657","journal-title":"IEEE Trans Energy Convers"},{"key":"5443_CR22","doi-asserted-by":"publisher","first-page":"11897","DOI":"10.1109\/ACCESS.2018.2810267","volume":"6","author":"K Peng","year":"2018","unstructured":"Peng K, Huang Q et al (2018) Clustering approach based on mini batch K-means for intrusion detection system over big data. IEEE Access 6:11897\u201311906","journal-title":"IEEE Access"},{"key":"5443_CR23","first-page":"85","volume":"17","author":"S Singh","year":"2018","unstructured":"Singh S, Garg R, Mishra PK (2018) Performance optimization of MapReduce-based Apriori algorithm on Hadoop cluster. Comput Electr Eng 17:85\u201394","journal-title":"Comput Electr Eng"},{"key":"5443_CR24","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.is.2017.11.006","volume":"79","author":"D Glushkova","year":"2017","unstructured":"Glushkova D, Jovanovic P, Abell\u00f3 A (2017) MapReduce performance models for Hadoop 2.x. Inf Syst 79:32\u201343","journal-title":"Inf Syst"},{"key":"5443_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2020.103425","author":"R Zhang","year":"2020","unstructured":"Zhang R, Hu Z (2020) Comparative research on active learning of big aata based on MapReduce and spark. Microprocess Microsyst: https:\/\/doi.org\/10.1016\/j.micpro.2020.103425","journal-title":"Microprocess Microsyst:"},{"key":"5443_CR26","doi-asserted-by":"publisher","first-page":"1604","DOI":"10.1016\/j.patcog.2012.12.007","volume":"46","author":"XB Zhi","year":"2013","unstructured":"Zhi XB, Fan JL, Zhao F (2013) Fuzzy linear discriminant analysis-guided maximum entropy fuzzy clustering algorithm. Pattern Recogn 46:1604\u20131615","journal-title":"Pattern Recogn"},{"key":"5443_CR27","first-page":"105523","volume":"97","author":"A Ak","year":"2019","unstructured":"Ak A, Skp B, Apsa C (2019) Hybridization of chaos and flower pollination algorithm over K-Means for data clustering. Appl Soft Comput 97:105523","journal-title":"Appl Soft Comput"},{"key":"5443_CR28","doi-asserted-by":"publisher","first-page":"e1008625","DOI":"10.1371\/journal.pcbi.1008625","volume":"17","author":"SC Hicks","year":"2021","unstructured":"Hicks SC, Liu RX, Ni YW et al (2021) Fast clustering for single cell data using mini-batch k-means. PLoS Comput Biol 17:e1008625","journal-title":"PLoS Comput Biol"},{"key":"5443_CR29","doi-asserted-by":"publisher","first-page":"7401","DOI":"10.1007\/s10586-017-1576-y","volume":"22","author":"W Feng","year":"2019","unstructured":"Feng W, Zhu Q, Zhuang J et al (2019) An expert recommendation algorithm based on Pearson correlation coefficient and FP-growth. Clust Comput 22:7401\u20137412","journal-title":"Clust Comput"},{"key":"5443_CR30","doi-asserted-by":"publisher","first-page":"107697","DOI":"10.1016\/j.patcog.2020.107697","volume":"112","author":"S Lall","year":"2021","unstructured":"Lall S, Sinha D, Ghosh A et al (2021) Stable feature selection using copula based mutual information. Pattern Recogn 112:107697","journal-title":"Pattern Recogn"},{"key":"5443_CR31","doi-asserted-by":"publisher","first-page":"1518","DOI":"10.1126\/science.1205438","volume":"334","author":"DN Reshef","year":"2011","unstructured":"Reshef DN, Reshef YA, Finucane HK et al (2011) Detecting novel associations in large data sets. Science 334:1518\u20131524","journal-title":"Science"},{"key":"5443_CR32","doi-asserted-by":"publisher","first-page":"4492","DOI":"10.1038\/s41598-018-22573-6","volume":"8","author":"MS Morelli","year":"2018","unstructured":"Morelli MS, Greco A, Valenza G et al (2018) Analysis of generic coupling between EEG activity and PETCO2 in free breathing and breath-hold tasks using Maximal Information Coefficient (MIC). Sci Rep 8:4492","journal-title":"Sci Rep"},{"key":"5443_CR33","first-page":"1739","volume":"34","author":"L Jizheng","year":"2013","unstructured":"Jizheng L, Meng G, You Lv et al (2013) Overview on the steady-state detection methods of process operating data. Chin J Sci Instrum 34:1739\u20131748","journal-title":"Chin J Sci Instrum"},{"key":"5443_CR34","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/0898-1221(95)00153-P","volume":"30","author":"CK Ko\u00e7","year":"1995","unstructured":"Ko\u00e7 CK (1995) Analysis of sliding window techniques for exponentiation. Comput Math Appl 30:17\u201324","journal-title":"Comput Math Appl"},{"key":"5443_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmst.2023.04.001","author":"Y Xie","year":"2023","unstructured":"Xie Y, Xuning W, Hou Z et al (2023) Gleaning insights from German energy transition and large-scale underground energy storage for China\u2019s carbon neutrality. Int J Min Sci Technol. https:\/\/doi.org\/10.1016\/j.ijmst.2023.04.001. ((in press))","journal-title":"Int J Min Sci Technol"},{"key":"5443_CR36","doi-asserted-by":"publisher","first-page":"4466","DOI":"10.3390\/en15124466","volume":"15","author":"Y Xie","year":"2022","unstructured":"Xie Y, Qi J, Zhang R et al (2022) Toward a carbon-neutral state: a carbon-energy-water NexusPerspective of China\u2019s coal power industry. Energies 15:4466","journal-title":"Energies"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05443-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-023-05443-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05443-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T23:53:06Z","timestamp":1702597986000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-023-05443-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,12]]},"references-count":36,"journal-issue":{"issue":"18","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["5443"],"URL":"https:\/\/doi.org\/10.1007\/s11227-023-05443-5","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,12]]},"assertion":[{"value":"27 May 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 June 2023","order":2,"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 that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}