{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T06:43:52Z","timestamp":1740120232834,"version":"3.37.3"},"reference-count":27,"publisher":"World Scientific Pub Co Pte Ltd","issue":"03","funder":[{"name":"Doctoral Program of Weifang University","award":["2016BS03"],"award-info":[{"award-number":["2016BS03"]}]},{"name":"Industry-University Collaborative Education Program granted by Ministry of Education of China","award":["201801304014"],"award-info":[{"award-number":["201801304014"]}]},{"name":"The Nature Science Foundation of China under","award":["61471269"],"award-info":[{"award-number":["61471269"]}]},{"name":"Science and Technology Development Program of Weifang","award":["2018GX009","2018GX004","2018GX014"],"award-info":[{"award-number":["2018GX009","2018GX004","2018GX014"]}]},{"name":"Project of Shandong Province Higher Educational Science and Technology Program","award":["J18KA130","J17KB184","J16LN68"],"award-info":[{"award-number":["J18KA130","J17KB184","J16LN68"]}]},{"name":"Nature Sciecne Foundation of Shandong Province","award":["ZR2019PF023"],"award-info":[{"award-number":["ZR2019PF023"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Patt. Recogn. Artif. Intell."],"published-print":{"date-parts":[[2020,3]]},"abstract":"<jats:p> As a classical clustering model, Gaussian Mixture Model (GMM) can be the footstone of dominant machine learning methods like transfer learning. Evolving GMM is an approximation to the classical GMM under time-critical or memory-critical application scenarios. Such applications often have constraints on time-to-answer or high data volume, and raise high computation demand. A prominent approach to address the demand is GPGPU-powered computing. However, the existing evolving GMM algorithms are confronted with a dilemma between clustering accuracy and parallelism. Point-wise algorithms achieve high accuracy but exhibit limited parallelism due to point-evolutionary pattern. Block-wise algorithms tend to exhibit higher parallelism. Whereas, it is challenging to achieve high accuracy under a block-evolutionary pattern due to the fact that it is difficult to track evolving process of the mixture model in fine granularity. Consequently, the existing block-wise algorithm suffers from significant accuracy degradation, compared to its batch-mode counterpart: the standard EM algorithm. To cope with this dilemma, we focus on the accuracy issue and develop an improved block-evolutionary GMM algorithm for GPGPU-powered computing systems. Our algorithm leverages evolving history of the model to estimate the latest model order in each incremental clustering step. With this model order as a constraint, we can perform similarity test in an elastic manner. Finally, we analyze the evolving history of both mixture components and the data points, and propose our method to merge similar components. Experiments on real images show that our algorithm significantly improves accuracy of the original general purpose bock-wise algorithm. The accuracy of our algorithm is at least comparable to that of the standard EM algorithm and even outperforms the latter under certain scenarios. <\/jats:p>","DOI":"10.1142\/s0218001420500068","type":"journal-article","created":{"date-parts":[[2019,5,10]],"date-time":"2019-05-10T03:16:51Z","timestamp":1557458211000},"page":"2050006","source":"Crossref","is-referenced-by-count":3,"title":["Improving Accuracy of Evolving GMM Under GPGPU-Friendly Block-Evolutionary Pattern"],"prefix":"10.1142","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2343-7980","authenticated-orcid":false,"given":"Chunlei","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer Engineering, Weifang University, Weifang 261061, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengduan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Weifang University, Weifang 261061, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinkui","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Weifang University, Weifang 261061, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Qi","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Weifang Vocational College, Weifang 261041, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangyan","family":"Dai","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Weifang University, Weifang 261061, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghui","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Weifang University, Weifang 261061, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Weifang University, Weifang 261061, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2019,8,6]]},"reference":[{"key":"S0218001420500068BIB001","doi-asserted-by":"publisher","DOI":"10.1016\/B978-012722442-8\/50016-1"},{"volume-title":"8th Int. Conf. Fun with Algorithms","year":"2016","author":"Cambi F.","key":"S0218001420500068BIB002"},{"key":"S0218001420500068BIB003","first-page":"2064","volume-title":"12th IEEE Int. Conf. Computer Vision","author":"Charron C.","year":"2009"},{"key":"S0218001420500068BIB004","first-page":"1937","volume-title":"IEEE 26th Int. Distributed Parallel Process. Symp.","author":"Chen C.","year":"2012"},{"key":"S0218001420500068BIB005","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16138-4_9"},{"key":"S0218001420500068BIB006","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001419510054"},{"key":"S0218001420500068BIB007","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2794998"},{"key":"S0218001420500068BIB008","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1016\/j.patcog.2015.10.019","volume":"52","author":"He L.","year":"2015","journal-title":"Pattern Recognit."},{"key":"S0218001420500068BIB009","doi-asserted-by":"publisher","DOI":"10.1109\/LARS.2010.13"},{"key":"S0218001420500068BIB011","doi-asserted-by":"publisher","DOI":"10.2991\/jimec-17.2017.31"},{"key":"S0218001420500068BIB012","doi-asserted-by":"publisher","DOI":"10.1007\/11894841_16"},{"key":"S0218001420500068BIB013","doi-asserted-by":"publisher","DOI":"10.1109\/5326.661089"},{"key":"S0218001420500068BIB014","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.03.019"},{"key":"S0218001420500068BIB015","first-page":"25","volume-title":"13th Computer Vision Winter Workshop","author":"Kristan M.","year":"2008"},{"key":"S0218001420500068BIB016","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2017.126"},{"key":"S0218001420500068BIB017","doi-asserted-by":"publisher","DOI":"10.1007\/s12530-016-9152-x"},{"key":"S0218001420500068BIB018","doi-asserted-by":"publisher","DOI":"10.1007\/s12530-012-9046-5"},{"issue":"10","key":"S0218001420500068BIB019","volume":"10","author":"Pinto R. C.","year":"2015","journal-title":"Plos One"},{"key":"S0218001420500068BIB020","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2002.801921"},{"key":"S0218001420500068BIB021","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176344136"},{"key":"S0218001420500068BIB022","first-page":"174","volume":"5803","author":"Song M.","year":"2005","journal-title":"Intell. Comput. Theory Appl. III"},{"key":"S0218001420500068BIB023","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2011.97"},{"volume-title":"The 12th Int. Conf. Availability, Reliability and Security","year":"2017","author":"Wurzenberger M.","key":"S0218001420500068BIB024"},{"journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.","year":"2019","author":"Zhang C.","key":"S0218001420500068BIB025"},{"key":"S0218001420500068BIB026","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2769799"},{"key":"S0218001420500068BIB027","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-007-0070-x"},{"key":"S0218001420500068BIB028","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001418560049"}],"container-title":["International Journal of Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218001420500068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,8]],"date-time":"2020-04-08T09:08:11Z","timestamp":1586336891000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S0218001420500068"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,6]]},"references-count":27,"journal-issue":{"issue":"03","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["10.1142\/S0218001420500068"],"URL":"https:\/\/doi.org\/10.1142\/s0218001420500068","relation":{},"ISSN":["0218-0014","1793-6381"],"issn-type":[{"type":"print","value":"0218-0014"},{"type":"electronic","value":"1793-6381"}],"subject":[],"published":{"date-parts":[[2019,8,6]]}}}