{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T16:41:28Z","timestamp":1790181688425,"version":"4.1.0"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2017,3,20]],"date-time":"2017-03-20T00:00:00Z","timestamp":1489968000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001868","name":"National Science Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001868","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1007\/s10115-017-1037-1","type":"journal-article","created":{"date-parts":[[2017,3,20]],"date-time":"2017-03-20T04:56:48Z","timestamp":1489985808000},"page":"365-390","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Distributed and scalable sequential pattern mining through stream processing"],"prefix":"10.1007","volume":"53","author":[{"given":"Chun-Chieh","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong-Han","family":"Shuai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming-Syan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,3,20]]},"reference":[{"key":"1037_CR1","unstructured":"Hadoop A (2012) \n                        http:\/\/hadoop.apache.org\/"},{"key":"1037_CR2","unstructured":"Hama A (2012) \n                        http:\/\/hama.apache.org\/"},{"key":"1037_CR3","doi-asserted-by":"crossref","unstructured":"Agrawal R, Srikant R (1995) Mining sequential patterns. In: Proceedings of the 11th international conference on data engineering (ICDE\u201995), pp 3\u201314","DOI":"10.1109\/ICDE.1995.380415"},{"key":"1037_CR4","doi-asserted-by":"crossref","unstructured":"Ayres J, Flannick J, Gehrke J et al (2002) Sequential pattern mining using a bitmap representation. In: Proceedings of the 8th ACM SIGKDD international conference on knowledge discovery and data mining (KDD\u201902), pp 429\u2013435","DOI":"10.1145\/775047.775109"},{"key":"1037_CR5","first-page":"1","volume":"63","author":"I Batal","year":"2013","unstructured":"Batal I, Valizadegan H, Cooper GF et al (2013) A temporal pattern mining approach for classifying electronic health record data. Trans Intell Syst Technol (TIST\u201913) 63:1\u201322","journal-title":"Trans Intell Syst Technol (TIST\u201913)"},{"key":"1037_CR6","doi-asserted-by":"crossref","unstructured":"Bu Y, Howe B, Balazinska M et al (2010) Haloop: efficient iterative data processing on large clusters. In: Proceedings of the VLDB endowment (PVLDB\u201910), pp 285\u2013296","DOI":"10.14778\/1920841.1920881"},{"key":"1037_CR7","doi-asserted-by":"crossref","unstructured":"Chen CC, Tseng CY, Chen MS (2013) Highly scalable sequential pattern mining based on MapReduce model on the cloud. IEEE international congress on big data (BigData Congress\u201913), pp 310\u2013317","DOI":"10.1109\/BigData.Congress.2013.48"},{"key":"1037_CR8","unstructured":"Chen CC , Shuai HH, and Chen MS (2016) Appendix of distributed and scalable sequential pattern mining through stream processing. \n                        https:\/\/www.csie.ntu.edu.tw\/~d96944011\/kais2016\/appendix"},{"key":"1037_CR9","doi-asserted-by":"crossref","unstructured":"Dean J, Ghemawat S (2008) MapReduce: simplified data processing on large clusters. Commun ACM (CACM\u201908) 51:107\u2013113","DOI":"10.1145\/1327452.1327492"},{"key":"1037_CR10","doi-asserted-by":"crossref","unstructured":"Ekanayake J, Li H, Zhang B et al (2010) Twister: a runtime for iterative MapReduce. In: Proceeding of the 19th ACM international symposium on high performance distributed computing (HPDC\u201910), pp 810\u2013818","DOI":"10.1145\/1851476.1851593"},{"key":"1037_CR11","doi-asserted-by":"crossref","unstructured":"Fang W, Lu M, Xiao X et al (2009) Frequent itemset mining on graphics processors. In: Proceedings of the 5th international workshop on data management on new hardware (DaMoN\u201909), pp 34\u201342","DOI":"10.1145\/1565694.1565702"},{"key":"1037_CR12","doi-asserted-by":"crossref","unstructured":"Gomariz A, Campos M, Marin R et al (2013) ClaSP: an efficient algorithm for mining frequent closed sequences. In: Proceedings of the 17th Pacific-Asia conference on knowledge discovery and data mining (PAKDD\u201913), pp 50\u201361","DOI":"10.1007\/978-3-642-37453-1_5"},{"key":"1037_CR13","first-page":"33","volume":"35","author":"K Goodhope","year":"2012","unstructured":"Goodhope K, Koshy J, Kreps J et al (2012) Building LinkedIn\u2019s real-time activity data pipeline. IEEE Data Eng Bull (Data Eng Bull\u201912) 35:33\u201345","journal-title":"IEEE Data Eng Bull (Data Eng Bull\u201912)"},{"key":"1037_CR14","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1016\/j.parco.2004.03.003","volume":"30","author":"V Guralnik","year":"2004","unstructured":"Guralnik V, Karypis G (2004) Parallel tree-projection-based sequence mining algorithms. Parallel Comput (PARALLEL COMPUT\u201904) 30:443\u2013472","journal-title":"Parallel Comput (PARALLEL COMPUT\u201904)"},{"key":"1037_CR15","doi-asserted-by":"crossref","unstructured":"Han J, Pei J, Mortazavi-Asl B et al (2000) FreeSpan: frequent pattern-projected sequential pattern mining. In: Proceedings of the 6th ACM SIGKDD international conference on knowledge discovery and data mining (KDD\u201900), pp 355\u2013359","DOI":"10.1145\/347090.347167"},{"key":"1037_CR16","volume-title":"Sequential pattern mining by pattern-growth: principles and extension. Foundations and advances in data mining","author":"J Han","year":"2005","unstructured":"Han J, Pei J, Yan X (2005) Sequential pattern mining by pattern-growth: principles and extension. Foundations and advances in data mining. Springer, Berlin"},{"key":"1037_CR17","unstructured":"Ho J, Lukov L, Chawla S (2005) Sequential pattern mining with constraints on large protein databases. In: Proceedings of the 12th international conference on management of data (COMAD\u201905), pp 89\u2013100"},{"key":"1037_CR18","doi-asserted-by":"crossref","first-page":"1153","DOI":"10.1109\/TKDE.2008.37","volume":"20","author":"JW Huang","year":"2008","unstructured":"Huang JW, Tseng CY, Ou JC et al (2008) A general model for sequential pattern mining with a progressive database. IEEE Trans Knowl Data Eng (TKDE\u201908) 20:1153\u20131167","journal-title":"IEEE Trans Knowl Data Eng (TKDE\u201908)"},{"key":"1037_CR19","doi-asserted-by":"crossref","unstructured":"Huang JW, Lin SC, Chen MS (2010) DPSP: distributed progressive sequential pattern mining on the cloud. 14th Pacific\u2013Asia conference on knowledge discovery and data mining (PAKDD\u201910), pp 27\u201334","DOI":"10.1007\/978-3-642-13672-6_3"},{"key":"1037_CR20","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1145\/1272998.1273005","volume":"41","author":"M Isard","year":"2007","unstructured":"Isard M, Budiu M, Yu Y et al (2007) Dryad: distributed data-parallel programs from sequential building blocks. ACM SIGOPS Oper Syst Rev (SIGOPS\u201907) 41:59\u201372","journal-title":"ACM SIGOPS Oper Syst Rev (SIGOPS\u201907)"},{"key":"1037_CR21","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1007\/s10115-006-0038-2","volume":"11","author":"X Ji","year":"2007","unstructured":"Ji X, Bailey J, Dong G (2007) Mining minimal distinguishing subsequence patterns with gap constraints. Knowl Inf Syst (KAIS\u201907) 11:259\u2013286","journal-title":"Knowl Inf Syst (KAIS\u201907)"},{"key":"1037_CR22","unstructured":"Kreps J, Narkhede N, Rao J (2011) Kafka: a distributed messaging system for log processing. NetDB workshop"},{"key":"1037_CR23","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1007\/s10115-012-0602-x","volume":"38","author":"CC Liao","year":"2014","unstructured":"Liao CC, Chen MS (2014) DFSP: a Depth-First SPelling algorithm for sequential pattern mining of biological sequences. Knowl Inf Syst (KAIS\u201914) 38:623\u2013639","journal-title":"Knowl Inf Syst (KAIS\u201914)"},{"key":"1037_CR24","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1007\/s10115-006-0056-0","volume":"15","author":"C Luo","year":"2008","unstructured":"Luo C, Chung S (2008) A scalable algorithm for mining maximal frequent sequences using a sample. Knowl Inf Syst (KAIS\u201908) 15:149\u2013179","journal-title":"Knowl Inf Syst (KAIS\u201908)"},{"key":"1037_CR25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1824795.1824798","volume":"43","author":"NR Mabroukeh","year":"2010","unstructured":"Mabroukeh NR, Ezeife CI (2010) A taxonomy of sequential pattern mining algorithms. ACM Comput Surv (CSUR\u201910) 43:1\u201341","journal-title":"ACM Comput Surv (CSUR\u201910)"},{"key":"1037_CR26","doi-asserted-by":"crossref","unstructured":"Mane RV (2013) A comparative study of Spam and PrefixSpan sequential pattern mining algorithm for protein sequences. In: Proceedings of the 3rd international conference on advances in computing, communication, and control (ICAC3\u201913), pp 147\u2013155","DOI":"10.1007\/978-3-642-36321-4_13"},{"key":"1037_CR27","doi-asserted-by":"crossref","unstructured":"Miliaraki I, Berberich K, Gemulla R et al (2013) Mind the gap: large-scale frequent sequence mining. In: Proceedings of the 2013 ACM SIGMOD international conference on management of data (SIGMOD\u201913), pp 797\u2013808","DOI":"10.1145\/2463676.2465285"},{"key":"1037_CR28","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1007\/s10115-009-0196-0","volume":"21","author":"P Papapetrou","year":"2009","unstructured":"Papapetrou P, Kollios G, Sclaroff S et al (2009) Mining frequent arrangements of temporal intervals. Knowl Inf Syst (KAIS\u201909) 21:133\u2013171","journal-title":"Knowl Inf Syst (KAIS\u201909)"},{"key":"1037_CR29","first-page":"601","volume":"4","author":"M Parimala","year":"2012","unstructured":"Parimala M, Sathiyabama S (2012) SPMLS: an efficient sequential pattern mining algorithm with candidate generation and frequency testing. Int J Comput Sci Eng (IJCSE\u201912) 4:601\u2013607","journal-title":"Int J Comput Sci Eng (IJCSE\u201912)"},{"key":"1037_CR30","unstructured":"Pei J, Han J, Mortazavi-asl B et al (2001) PrefixSpan: mining sequential patterns efficiently by prefix-projected pattern growth. In: Proceedings of the 7th ACM SIGKDD international conference on knowledge discovery and data mining (KDD\u201901), pp 215\u2013224"},{"key":"1037_CR31","doi-asserted-by":"crossref","unstructured":"Perer A, Wang F (2014) Frequence: interactive mining and visualization of temporal frequent event sequences. In: Proceedings of the 19th ACM international conference on intelligent user interfaces (IUI\u201914), pp 153\u2013162","DOI":"10.1145\/2557500.2557508"},{"key":"1037_CR32","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1007\/s00778-014-0370-1","volume":"23","author":"M Sahli","year":"2014","unstructured":"Sahli M, Mansour E, Kalnis P (2014) ACME: a scalable parallel system for extracting frequent patterns from a very long sequence. VLDB J (VLDBJ\u201914) 23:871\u2013893","journal-title":"VLDB J (VLDBJ\u201914)"},{"key":"1037_CR33","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1007\/s10115-012-0483-z","volume":"37","author":"BE Shie","year":"2013","unstructured":"Shie BE, Hsiao HF, Tseng V (2013) Efficient algorithms for discovering high utility user behavior patterns in mobile commerce environments. Knowl Inf Syst (KAIS\u201913) 37:363\u2013387","journal-title":"Knowl Inf Syst (KAIS\u201913)"},{"key":"1037_CR34","doi-asserted-by":"crossref","unstructured":"Srikant R, Agrawal R (1996) Mining sequential patterns: generalizations and performance improvements. In: Proceedings of the 5th international conference on extending database technology (EDBT\u201996), pp 3\u201317","DOI":"10.1007\/BFb0014140"},{"key":"1037_CR35","unstructured":"Samza (2013) \n                        https:\/\/samza.incubator.apache.org\/"},{"key":"1037_CR36","unstructured":"Storm: distributed and fault\u2013tolerant realtime computation (2012) \n                        http:\/\/storm.incubator.apache.org\/"},{"key":"1037_CR37","unstructured":"Spark: Lightning-fast cluster computing (2013) \n                        https:\/\/spark.incubator.apache.org\/"},{"key":"1037_CR38","unstructured":"S4: Distributed Stream Computing Platform (2010) \n                        https:\/\/incubator.apache.org\/s4\/"},{"key":"1037_CR39","unstructured":"Twister: iterative MapReduce (2012) \n                        https:\/\/iterativemapreduce.org\/"},{"key":"1037_CR40","volume-title":"Hadoop: the definitive guide","author":"Tom White","year":"2009","unstructured":"White Tom (2009) Hadoop: the definitive guide. O\u2019Reilly Media, Newton"},{"key":"1037_CR41","doi-asserted-by":"crossref","unstructured":"Wang K, Xu Y, Yu JX (2004) Scalable sequential pattern mining for biological sequences. In: Proceedings of the 13th ACM international conference on information and knowledge management (CIKM\u201904), pp 178\u2013187","DOI":"10.1145\/1031171.1031209"},{"key":"1037_CR42","doi-asserted-by":"crossref","unstructured":"Wang X, Wang J, Wang T et al (2010) Parallel sequential pattern mining by transaction decomposition. International conference on fuzzy systems and knowledge discovery (FSKD\u201910), pp 1746\u20131750","DOI":"10.1109\/FSKD.2010.5569404"},{"key":"1037_CR43","doi-asserted-by":"publisher","unstructured":"Weng L, Menczer F, Ahn YY (2013) Virality prediction and community structure in social networks. Sci Rep 3. doi:\n                        10.1038\/srep02522","DOI":"10.1038\/srep02522"},{"key":"1037_CR44","unstructured":"Wu K, Otoo EJ, Shoshani A (2002) Compressing bitmap indexes for faster search operations. In: Proceedings of 14th international conference on scientific and statistical database management (SSDBM\u201902), pp 99\u2013108"},{"key":"1037_CR45","doi-asserted-by":"crossref","unstructured":"Yu D, Wu W, Zheng S et al (2012) BIDE-based parallel mining of frequent closed sequences with MapReduce. In: Proceedings of the 12th international conference on algorithms and architectures for parallel processing (ICA3PP\u201912), pp 177\u2013186","DOI":"10.1007\/978-3-642-33065-0_19"},{"key":"1037_CR46","doi-asserted-by":"crossref","first-page":"129","DOI":"10.14257\/ijdta.2014.7.4.10","volume":"7","author":"D Yu","year":"2014","unstructured":"Yu D, Zhu Q, Shao J et al (2014) Parallel execution of data-intensive web services based on data-flow constructs and I\/O operation ratio. Int J Database Theory Appl (IJDTA\u201914) 7:129\u2013138","journal-title":"Int J Database Theory Appl (IJDTA\u201914)"},{"key":"1037_CR47","unstructured":"Zaharia M, Chowdhury M, Das T et al (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 (NSDI\u201912), p 2"},{"key":"1037_CR48","unstructured":"Zaharia M, Chowdhury M, Das T et al (2012) Discretized streams: an efficient and fault-tolerant model for stream processing on large clusters. In: Proceedings of the 4th USENIX conference on hot topics in cloud computing (HotCloud\u201912), pp 215\u2013224"},{"key":"1037_CR49","doi-asserted-by":"crossref","unstructured":"Zaki MJ (1998) Efficient enumeration of frequent sequences. In: Proceedings of the 7th ACM international conference on information and knowledge management (CIKM\u201998), pp 68\u201375","DOI":"10.1145\/288627.288643"},{"key":"1037_CR50","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1006\/jpdc.2000.1695","volume":"61","author":"MJ Zaki","year":"2001","unstructured":"Zaki MJ (2001) Parallel sequence mining on shared-memory machines. J Parallel Distrib Comput (JPDC\u201901) 61:401\u2013426","journal-title":"J Parallel Distrib Comput (JPDC\u201901)"},{"key":"1037_CR51","unstructured":"Zhao Q, Bhowmick SS (2003) Sequential pattern matching: a survey. ITechnical report CAIS Nayang Technological University Singapore, pp 1\u201326"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-017-1037-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-017-1037-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-017-1037-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,9,21]],"date-time":"2017-09-21T05:16:51Z","timestamp":1505971011000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-017-1037-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3,20]]},"references-count":51,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2017,11]]}},"alternative-id":["1037"],"URL":"https:\/\/doi.org\/10.1007\/s10115-017-1037-1","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,3,20]]}}}