{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T01:08:34Z","timestamp":1743124114420,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031160714"},{"type":"electronic","value":"9783031160721"}],"license":[{"start":{"date-parts":[[2022,8,31]],"date-time":"2022-08-31T00:00:00Z","timestamp":1661904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,8,31]],"date-time":"2022-08-31T00:00:00Z","timestamp":1661904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-16072-1_55","type":"book-chapter","created":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T20:06:09Z","timestamp":1661889969000},"page":"771-788","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MR-VDENCLUE: Varying Density Clustering Using MapReduce"],"prefix":"10.1007","author":[{"given":"Ghazi","family":"Al-Naymat","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mariam","family":"Khader","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammed Azmi","family":"Al-Betar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raghda","family":"Hriez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Hadi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,8,31]]},"reference":[{"key":"55_CR1","unstructured":"Alkurdi, M.Z.; Malware detection for android applications using simhash algorithm. malware detection for android applications using simhash algorithm (2014)"},{"issue":"9","key":"55_CR2","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1145\/361002.361007","volume":"18","author":"Jon Louis Bentley","year":"1975","unstructured":"Jon Louis Bentley: Multidimensional binary search trees used for associative searching. Commun. ACM 18(9), 509\u2013517 (1975)","journal-title":"Commun. ACM"},{"issue":"1","key":"55_CR3","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/j.patcog.2007.04.010","volume":"41","author":"H Chang","year":"2008","unstructured":"Chang, H., Yeung, D.-Y.: Robust path-based spectral clustering. Pattern Recogn. 41(1), 191\u2013203 (2008)","journal-title":"Pattern Recogn."},{"key":"55_CR4","doi-asserted-by":"crossref","unstructured":"Charikar, M.S.: Similarity estimation techniques from rounding algorithms. In Proceedings of the Thiry-Fourth Annual ACM Symposium on Theory of Computing, STOC 2002, pp. 380\u2013388. Association for Computing Machinery, New York (2002)","DOI":"10.1145\/509907.509965"},{"key":"55_CR5","doi-asserted-by":"crossref","unstructured":"Charikar, M.S.: Similarity estimation techniques from rounding algorithms. In: Proceedings of the Thiry-Fourth Annual ACM Symposium on Theory of Computing, pp. 380\u2013388 (2002)","DOI":"10.1145\/509907.509965"},{"key":"55_CR6","doi-asserted-by":"crossref","unstructured":"Dash, M., Ng, W.: Efficient reservoir sampling for transactional data streams. In: Sixth IEEE International Conference on Data Mining-Workshops (ICDMW 2006), pp. 662\u2013666. IEEE (2006)","DOI":"10.1109\/ICDMW.2006.68"},{"key":"55_CR7","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1007\/978-3-540-68125-0_87","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"C Gong","year":"2008","unstructured":"Gong, C., Huang, Y., Cheng, X., Bai, S.: Detecting near-duplicates in large-scale short text databases. In: Washio, T., Suzuki, E., Ting, K.M., Inokuchi, A. (eds.) PAKDD 2008. LNCS (LNAI), vol. 5012, pp. 877\u2013883. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-68125-0_87"},{"key":"55_CR8","doi-asserted-by":"crossref","unstructured":"Henzinger, M.: Finding near-duplicate web pages: a large-scale evaluation of algorithms. In: Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 284\u2013291 (2006)","DOI":"10.1145\/1148170.1148222"},{"key":"55_CR9","unstructured":"Hinneburg, A., Keim, D.A.: An efficient approach to clustering in large multimedia databases with noise. In Proceedings of the Fourth International Conference on Knowledge Discovery and Data Mining, KDD\u201998, pp. 58\u201365. AAAI Press (1998)"},{"key":"55_CR10","doi-asserted-by":"crossref","unstructured":"Ho, P.-T., Kim, H.-S., Kim, S.-R.: Application of sim-hash algorithm and big data analysis in spam email detection system. In: Proceedings of the 2014 Conference on Research in Adaptive and Convergent Systems, pp. 242\u2013246 (2014)","DOI":"10.1145\/2663761.2664221"},{"key":"55_CR11","unstructured":"joensuu (2019)"},{"key":"55_CR12","doi-asserted-by":"crossref","unstructured":"Khader, M., Al-Naymat, G.: Density-based algorithms for big data clustering using mapreduce framework: a comprehensive study. ACM Comput. Surv. 53(5), September 2020","DOI":"10.1145\/3403951"},{"key":"55_CR13","doi-asserted-by":"crossref","unstructured":"Khader, M., Al-Naymat, Vdenclue, G.: An enhanced variant of denclue algorithm. In: Intelligent Systems and Applications, pp. 1\u201312. Springer Nature Switzerland AG (2021, 2020)","DOI":"10.1007\/978-3-030-55187-2_33"},{"key":"55_CR14","doi-asserted-by":"crossref","unstructured":"Manku, G.S., Jain, A., Das Sarma, A.: Detecting near-duplicates for web crawling. In: Proceedings of the 16th International Conference on World Wide Web, pp. 141\u2013150 (2007)","DOI":"10.1145\/1242572.1242592"},{"key":"55_CR15","unstructured":"Pi, B., Fu, S., Wang, W., Han, S.: Simhash-based effective and efficient detecting of near-duplicate short messages. In: Proceedings of the 2009 International Symposium on Computer Science and Computational Technology (ISCSCI 2009), p. 20. Citeseer (2009)"},{"key":"55_CR16","doi-asserted-by":"crossref","unstructured":"Uddin, S., Roy, C.K., Schneider, K.A., Hindle, A.: On the effectiveness of simhash for detecting near-miss clones in large scale software systems. In: 2011 18th Working Conference on Reverse Engineering, pp. 13\u201322. IEEE (2011)","DOI":"10.1109\/WCRE.2011.12"},{"key":"55_CR17","doi-asserted-by":"crossref","unstructured":"Vitter, J.S.: Random sampling with a reservoir. ACM Trans. Math. Softw. (TOMS) 11(1), 37\u201357 (1985)","DOI":"10.1145\/3147.3165"},{"issue":"12","key":"55_CR18","doi-asserted-by":"publisher","first-page":"3218","DOI":"10.1109\/TKDE.2016.2609423","volume":"28","author":"Y Zhang","year":"2016","unstructured":"Zhang, Y., Chen, S., Yu, G.: Efficient distributed density peaks for clustering large data sets in mapreduce. IEEE Trans. Knowl. Data Eng. 28(12), 3218\u20133230 (2016)","journal-title":"IEEE Trans. Knowl. Data Eng."}],"container-title":["Lecture Notes in Networks and Systems","Intelligent Systems and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-16072-1_55","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T20:12:38Z","timestamp":1661890358000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16072-1_55"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,31]]},"ISBN":["9783031160714","9783031160721"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16072-1_55","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2022,8,31]]},"assertion":[{"value":"31 August 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IntelliSys","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Proceedings of SAI Intelligent Systems Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"intellisys2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/saiconference.com\/IntelliSys","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}