{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T02:29:04Z","timestamp":1745980144306,"version":"3.33.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2007,7,4]],"date-time":"2007-07-04T00:00:00Z","timestamp":1183507200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2008,8]]},"DOI":"10.1007\/s00778-007-0054-1","type":"journal-article","created":{"date-parts":[[2007,7,3]],"date-time":"2007-07-03T14:36:59Z","timestamp":1183473419000},"page":"1121-1141","source":"Crossref","is-referenced-by-count":14,"title":["Power-law relationship and self-similarity in the itemset support distribution: analysis and applications"],"prefix":"10.1007","volume":"17","author":[{"given":"Kun-Ta","family":"Chuang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiun-Long","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming-Syan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2007,7,4]]},"reference":[{"key":"54_CR1","unstructured":"Agrawal, R., Srikant, R.: Fast algorithms for mining association rules. In: Proc. of VLDB (1994)"},{"key":"54_CR2","volume-title":"Modern Information Retrieval","author":"R. Baeza-Yates","year":"1999","unstructured":"Baeza-Yates R. and Ribeiro-Neto B. (1999). Modern Information Retrieval. Addison\u2013Wesley, Reading"},{"key":"54_CR3","volume-title":"Statistics for long-memory processes. Monographs on Statistics and Applied Probability","author":"J. Beran","year":"1994","unstructured":"Beran J. (1994). Statistics for long-memory processes. Monographs on Statistics and Applied Probability. Chapman & Hall, London"},{"key":"54_CR4","doi-asserted-by":"crossref","unstructured":"Bi, Z., Faloutsos, C., Korn, F.: The \u201cDGX\u201d Distribution for Mining Massive, Skewed Data. In: Proc. of ACM SIGKDD (2000)","DOI":"10.1145\/502512.502521"},{"key":"54_CR5","unstructured":"Borgelt, C.: Efficient implementations of apriori and eclat. In: Proc. of Workshop on Frequent Itemset Mining Implementations (2004)"},{"key":"54_CR6","doi-asserted-by":"crossref","unstructured":"Breslau, L., Cao, P., Fan, L., Phillips, G., Shenker, S.: Web caching and zipf-like distributions: evidence and implications. In: Proc. of IEEE INFOCOM (1999)","DOI":"10.1109\/INFCOM.1999.749260"},{"key":"54_CR7","unstructured":"Cheung, Y.L., Fu, A.W.: Mining Association Rules without Support Threshold: with and without Item Constraints. In: TKDE (2004)"},{"key":"54_CR8","doi-asserted-by":"crossref","unstructured":"Chuang, K.-T., Chen, M.-S., Yang, W.-C.: Progressive sampling for association rules based on sampling error estimation. In: Proc. of PAKDD (2005)","DOI":"10.1007\/11430919_59"},{"key":"54_CR9","unstructured":"Chuang, K.-T., Huang, J.-L., Chen, M.-S.: Mining Top-k Frequent Patterns in the Presence of the Memory Constraint. In: Technical Report, under submission. A short version is published in Proc. of ACM CIKM (2005)"},{"key":"54_CR10","volume-title":"Sampling Techniques","author":"W.G. Cochran","year":"1977","unstructured":"Cochran W.G. (1977). Sampling Techniques. Wiley, London"},{"key":"54_CR11","doi-asserted-by":"crossref","unstructured":"Cormode, G., Muthukrishnan, S.: Summarizing and mining skewed data streams. In: Proc. of SIAM SDM (2005)","DOI":"10.1137\/1.9781611972757.5"},{"key":"54_CR12","doi-asserted-by":"crossref","unstructured":"Crovella, M.E., Bestavros, A.: Self-Similarity in World Wide Web Traffic: Evidence and Possible Causes. In: Proc. of ACM SIGMETRICS (1996)","DOI":"10.1145\/233013.233038"},{"key":"54_CR13","doi-asserted-by":"crossref","unstructured":"Dill, S., Kumar, R., McCurley, K., Rajagopalan, S., Sivakumar, D., Tomkins, A.: Self-similarity in the web. In: Proc. of VLDB (2001)","DOI":"10.1145\/572326.572328"},{"key":"54_CR14","unstructured":"Egghe, L.: The distribution of n-grams. Scientometrics (2000)"},{"key":"54_CR15","doi-asserted-by":"crossref","unstructured":"Faloutsos, C.: Next Generation Data Mining Tools: Power Laws and Self-similarity for Graphs, Streams and Traditional Data. ECML (2003)","DOI":"10.1007\/978-3-540-39857-8_3"},{"key":"54_CR16","doi-asserted-by":"crossref","unstructured":"Faloutsos, M., Faloutsos, P., Faloutsos, C.: On power-law relationships of the internet topology. In: Proc. of ACM SIGCOMM (1999)","DOI":"10.1145\/316188.316229"},{"key":"54_CR17","doi-asserted-by":"crossref","unstructured":"Geerts, F., Goethals, B., Bussche, J.V.D.: Tight upper bounds on the number of candidate patterns. ACM Trans. Database Syst. (2005)","DOI":"10.1145\/1071610.1071611"},{"key":"54_CR18","unstructured":"Geerts, F., Goethals, B., Bussche, J.V.D.: A tight upper bound on the number of candidate patterns. In: Proc. of IEEE ICDM (2001)"},{"key":"54_CR19","doi-asserted-by":"crossref","unstructured":"Ghoting, A., Buehrer, G., Parthasarathy, S., Y.Chen, Kim, D., Nguyen, A., Dubey, P.: Cache-conscious frequent pattern mining on a modern processor. In: Proc. of VLDB (2005)","DOI":"10.1007\/s00778-006-0025-y"},{"key":"54_CR20","volume-title":"Data Mining: Concepts and Techniques","author":"J. Han","year":"2000","unstructured":"Han J. and Kamber M. (2000). Data Mining: Concepts and Techniques. Morgan Kaufmann, San Francisco"},{"key":"54_CR21","doi-asserted-by":"crossref","unstructured":"Han, J., Pei, J., Yin, Y.: Mining frequent patterns without candidate generation. In: Proc. of ACM SIGMOD (2000)","DOI":"10.1145\/342009.335372"},{"key":"54_CR22","doi-asserted-by":"crossref","unstructured":"Ioannidis, Y.: The history of histograms. In: Proc. of VLDB (2003)","DOI":"10.1016\/B978-012722442-8\/50011-2"},{"key":"54_CR23","volume-title":"The 80\/20 Principle: The Secret of Achieving More With Less","author":"R. Koch","year":"1998","unstructured":"Koch R. (1998). The 80\/20 Principle: The Secret of Achieving More With Less. Nicholas Brealey Publishing, London"},{"issue":"3","key":"54_CR24","first-page":"233","volume":"2","author":"S.D. Lee","year":"1998","unstructured":"Lee S.D., David Cheung W.-L. and Kao B. (1998). Is sampling useful in data mining? A case in the maintenance of discovered association rules. DMKD 2(3): 233\u2013262","journal-title":"DMKD"},{"key":"54_CR25","doi-asserted-by":"crossref","unstructured":"Manku, G.S., Motwani, R.: Approximate frequency counts over streaming data. In: Proc. of VLDB (2002)","DOI":"10.1016\/B978-155860869-6\/50038-X"},{"key":"54_CR26","doi-asserted-by":"crossref","unstructured":"Metwally, A., Agrawal, D., Abbadi, A.E.: Efficient computation of frequent and top-k elements in data streams. In: Proc. of ICDT (2005)","DOI":"10.1007\/978-3-540-30570-5_27"},{"key":"54_CR27","unstructured":"Orlando, S., Lucchese, C., Palmerini, P., Perego, R., Silvestri, F.: kDCI: a Multi-Strategy Algorithm for Mining Frequent Sets. In: Proc. of Workshop on Frequent Itemset Mining Implementations (2004)"},{"key":"54_CR28","doi-asserted-by":"crossref","unstructured":"Orlando, S., Palmerini, P., Perego, R., Silvestri, F.: Adaptive and resource-aware mining of frequent sets. In: Proc. of IEEE ICDM (2002)","DOI":"10.1109\/ICDM.2002.1183921"},{"key":"54_CR29","doi-asserted-by":"crossref","unstructured":"Park, J.-S., Chen, M.-S., Yu, P.S.: An effective hash based algorithm for mining association rules. In: Proc. of ACM SIGMOD (1995)","DOI":"10.1145\/223784.223813"},{"key":"54_CR30","doi-asserted-by":"crossref","unstructured":"Parthasarathy, S.: Efficient progressive sampling for association rules. In: Proc. of IEEE ICDM (2002)","DOI":"10.1109\/ICDM.2002.1183923"},{"key":"54_CR31","doi-asserted-by":"crossref","unstructured":"Provost, F., Jensen, D., Oates, T.: Efficient progressive sampling. In: Proc. of ACM SIGKDD (1999)","DOI":"10.1145\/312129.312188"},{"key":"54_CR32","doi-asserted-by":"crossref","unstructured":"Ramesh, G., Maniatty, W.A., Zaki, M.J.: Feasible itemset distributions in data mining: Theory and application. In: Proc. of ACM PODS (2003)","DOI":"10.1145\/773153.773181"},{"key":"54_CR33","volume-title":"Mathematical statistics and data analysis","author":"J.A. Rice","year":"1995","unstructured":"Rice J.A. (1995). Mathematical statistics and data analysis. Duxbury Press, North Scituate"},{"key":"54_CR34","unstructured":"Toivonen, H.: Sampling large databases for association rules. In: Proc. of VLDB (1996)"},{"key":"54_CR35","doi-asserted-by":"crossref","unstructured":"Uno, T., Asai, T., Uchida, Y., Arimura, H.: Lcm ver. 2: Efficient mining algorithms for frequent\/closed\/maximal itemsets. In: Proc. of Workshop on Frequent Itemset Mining Implementations (2004)","DOI":"10.1145\/1133905.1133916"},{"key":"54_CR36","unstructured":"Wang, J., Han, J., Lu, Y., Tzvetkov, P.: TFP: An Efficient Algorithm for Mining Top-K Frequent Closed Itemsets. In: TKDE (2005)"},{"key":"54_CR37","doi-asserted-by":"crossref","unstructured":"Willinger, W., Taqqu, M.S., Leland, W.E., Wilson, D.V.: Self-similarity in high-speed packet traffic: analysis and modelling of ethernet traffic measurements. Stat. Sci. 10(1) (1995)","DOI":"10.1214\/ss\/1177010131"},{"key":"54_CR38","doi-asserted-by":"crossref","unstructured":"Wong, R.C.-W., Fu, A.W.: Mining top-k itemsets over a sliding window based on zipfian distribution. In: Proc. of SIAM SDM (2005)","DOI":"10.1137\/1.9781611972757.52"},{"key":"54_CR39","doi-asserted-by":"crossref","unstructured":"Yu, J.X., Chong, Z., Lu, H., Zhou, A.: False positive or false negative: Mining frequent itemsets from high speed transactional data streams. In: Proc. of VLDB (2004)","DOI":"10.1016\/B978-012088469-8\/50021-8"},{"key":"54_CR40","doi-asserted-by":"crossref","unstructured":"Zaki, M.J., Parthasarathy, S., Ogihara, M., Li, W.: New algorithms for fast discovery of association rules. In: Proc. of ACM SIGKDD (1997)","DOI":"10.1007\/978-1-4615-5669-5_1"},{"key":"54_CR41","doi-asserted-by":"crossref","unstructured":"Zaki, M.J., Parthasarathy, S., Wei, I., Ogihara, M.: Evaluation of sampling for data mining of association rules. In: Int. Workshop on Research Issues in Data Engineering (1997)","DOI":"10.1109\/RIDE.1997.583696"},{"key":"54_CR42","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Kohavi, R., Mason, L.: Real world performance of association rule algorithms. In: Proc. of SIGKDD (2001)","DOI":"10.1145\/502512.502572"},{"key":"54_CR43","volume-title":"Human Behavior and the Principle of Least Effort","author":"G.K. Zipf","year":"1949","unstructured":"Zipf G.K. (1949). Human Behavior and the Principle of Least Effort. Addison\u2013Wesley, Reading"}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-007-0054-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00778-007-0054-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-007-0054-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T03:54:59Z","timestamp":1737172499000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00778-007-0054-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,7,4]]},"references-count":43,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2008,8]]}},"alternative-id":["54"],"URL":"https:\/\/doi.org\/10.1007\/s00778-007-0054-1","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"type":"print","value":"1066-8888"},{"type":"electronic","value":"0949-877X"}],"subject":[],"published":{"date-parts":[[2007,7,4]]}}}