How much can k-means be improved by using better initialization and repeats?
•K-means clustering algorithm can be significantly improved by using a better initialization technique, and by repeating (re-starting) the algorithm.•When the data has overlapping clusters, k-means can improve the results of the initialization technique.•When the data has well separated clusters, th...
Uloženo v:
| Vydáno v: | Pattern recognition Ročník 93; s. 95 - 112 |
|---|---|
| Hlavní autoři: | , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Ltd
01.09.2019
|
| Témata: | |
| ISSN: | 0031-3203, 1873-5142 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | •K-means clustering algorithm can be significantly improved by using a better initialization technique, and by repeating (re-starting) the algorithm.•When the data has overlapping clusters, k-means can improve the results of the initialization technique.•When the data has well separated clusters, the performance of k-means depends completely on the goodness of the initialization.•Initialization using simple furthest point heuristic (Maxmin) reduces the clustering error of k-means from 15% to 6%, on average.
In this paper, we study what are the most important factors that deteriorate the performance of the k-means algorithm, and how much this deterioration can be overcome either by using a better initialization technique, or by repeating (restarting) the algorithm. Our main finding is that when the clusters overlap, k-means can be significantly improved using these two tricks. Simple furthest point heuristic (Maxmin) reduces the number of erroneous clusters from 15% to 6%, on average, with our clustering benchmark. Repeating the algorithm 100 times reduces it further down to 1%. This accuracy is more than enough for most pattern recognition applications. However, when the data has well separated clusters, the performance of k-means depends completely on the goodness of the initialization. Therefore, if high clustering accuracy is needed, a better algorithm should be used instead. |
|---|---|
| AbstractList | •K-means clustering algorithm can be significantly improved by using a better initialization technique, and by repeating (re-starting) the algorithm.•When the data has overlapping clusters, k-means can improve the results of the initialization technique.•When the data has well separated clusters, the performance of k-means depends completely on the goodness of the initialization.•Initialization using simple furthest point heuristic (Maxmin) reduces the clustering error of k-means from 15% to 6%, on average.
In this paper, we study what are the most important factors that deteriorate the performance of the k-means algorithm, and how much this deterioration can be overcome either by using a better initialization technique, or by repeating (restarting) the algorithm. Our main finding is that when the clusters overlap, k-means can be significantly improved using these two tricks. Simple furthest point heuristic (Maxmin) reduces the number of erroneous clusters from 15% to 6%, on average, with our clustering benchmark. Repeating the algorithm 100 times reduces it further down to 1%. This accuracy is more than enough for most pattern recognition applications. However, when the data has well separated clusters, the performance of k-means depends completely on the goodness of the initialization. Therefore, if high clustering accuracy is needed, a better algorithm should be used instead. |
| Author | Fränti, Pasi Sieranoja, Sami |
| Author_xml | – sequence: 1 givenname: Pasi orcidid: 0000-0002-9554-2827 surname: Fränti fullname: Fränti, Pasi email: pasi.franti@uef.fi – sequence: 2 givenname: Sami surname: Sieranoja fullname: Sieranoja, Sami email: sami.sieranoja@uef.fi, samisi@cs.uef.fi |
| BookMark | eNqFkEFOwzAQRS0EEm3hBix8gQQ7TkjKAoQqoEiV2MDassfj4tI4ke0WldOTUlYsYDXSfL2vmTcmx77zSMgFZzln_OpylfcqQbfMC8anOStzxssjMuJNLbKKl8UxGTEmeCYKJk7JOMYVY7weghFZzLsP2m7gjYLy9D1rUflINVLX9qHboqF6RzfR-eWwTAkDdd4lp9buUyXXeaq8oQF7VCnenpETq9YRz3_mhLw-3L_M5tni-fFpdrfIQFRFyiyvNGhruACtlBC2KhBqWzKhRFUyg0MMDdf11ADoBhtdGFAIYKyFyigxIdeHXghdjAGtBJe-z0lBubXkTO69yJU8eJF7L5KVcvAywOUvuA-uVWH3H3ZzwHB4bOswyAgOPaBxASFJ07m_C74A6JOEJA |
| CitedBy_id | crossref_primary_10_1007_s11634_022_00514_6 crossref_primary_10_1109_ACCESS_2023_3327640 crossref_primary_10_1016_j_patcog_2024_110772 crossref_primary_10_1016_j_eswa_2021_114971 crossref_primary_10_1016_j_knosys_2020_105982 crossref_primary_10_1007_s00521_021_06689_x crossref_primary_10_1017_S1748499523000283 crossref_primary_10_1038_s41598_023_48220_3 crossref_primary_10_1097_JPN_0000000000000865 crossref_primary_10_1016_j_nucengdes_2020_110756 crossref_primary_10_1007_s10994_021_06021_7 crossref_primary_10_1016_j_conbuildmat_2022_128802 crossref_primary_10_1016_j_csbj_2023_07_041 crossref_primary_10_1007_s10115_024_02066_x crossref_primary_10_1109_TMC_2023_3277333 crossref_primary_10_1155_2024_7086878 crossref_primary_10_3390_electronics8101141 crossref_primary_10_1016_j_eswa_2025_126738 crossref_primary_10_1038_s42949_023_00112_1 crossref_primary_10_1007_s40192_023_00293_8 crossref_primary_10_1016_j_ins_2022_11_139 crossref_primary_10_3390_math12233787 crossref_primary_10_3390_e21101013 crossref_primary_10_1007_s13198_021_01424_0 crossref_primary_10_3390_ijgi11020133 crossref_primary_10_1080_03610926_2021_1872639 crossref_primary_10_3390_app11010177 crossref_primary_10_1016_j_ins_2021_10_048 crossref_primary_10_1016_j_procs_2020_08_022 crossref_primary_10_1088_1742_6596_1727_1_012018 crossref_primary_10_5194_nhess_23_1743_2023 crossref_primary_10_3390_jimaging9070146 crossref_primary_10_1080_00343404_2024_2417704 crossref_primary_10_1016_j_patcog_2024_110639 crossref_primary_10_1109_TIT_2025_3532280 crossref_primary_10_1016_j_ress_2021_107807 crossref_primary_10_1080_10447318_2022_2112077 crossref_primary_10_1097_EDE_0000000000001554 crossref_primary_10_1007_s00500_020_04988_4 crossref_primary_10_1016_j_ijepes_2024_109861 crossref_primary_10_3390_su14052744 crossref_primary_10_1016_j_patcog_2020_107589 crossref_primary_10_1109_TVT_2021_3121217 crossref_primary_10_3390_su142416718 crossref_primary_10_3390_jimaging8100274 crossref_primary_10_1109_ACCESS_2024_3412950 crossref_primary_10_1016_j_pmcj_2022_101614 crossref_primary_10_1007_s10489_021_02527_8 crossref_primary_10_1016_j_ins_2023_119634 crossref_primary_10_1007_s10237_023_01779_2 crossref_primary_10_1109_ACCESS_2019_2939481 crossref_primary_10_2196_35422 crossref_primary_10_1152_jn_00411_2021 crossref_primary_10_1093_iwc_iwac022 crossref_primary_10_1007_s42488_024_00127_y crossref_primary_10_1109_ACCESS_2022_3230935 crossref_primary_10_1007_s00500_020_05247_2 crossref_primary_10_1186_s44167_024_00045_9 crossref_primary_10_1155_2020_2498487 crossref_primary_10_1007_s00521_022_07554_1 crossref_primary_10_3390_s25010162 crossref_primary_10_1016_j_engappai_2025_111981 crossref_primary_10_1007_s13177_023_00350_8 crossref_primary_10_1016_j_oceaneng_2025_122694 crossref_primary_10_1002_wics_1551 crossref_primary_10_1016_j_applthermaleng_2020_115810 crossref_primary_10_1007_s10514_025_10199_3 crossref_primary_10_1016_j_ins_2024_121204 crossref_primary_10_3390_rs12244152 crossref_primary_10_1155_2020_8881112 crossref_primary_10_1088_1361_6501_ab934e crossref_primary_10_1007_s10044_024_01228_5 crossref_primary_10_1186_s40537_023_00798_1 crossref_primary_10_4018_IJIRR_289954 crossref_primary_10_1016_j_renene_2022_11_048 crossref_primary_10_1007_s12145_024_01303_9 crossref_primary_10_1016_j_eswa_2022_118862 crossref_primary_10_1016_j_eswa_2020_113682 crossref_primary_10_1108_IJHG_05_2020_0052 crossref_primary_10_1016_j_energy_2023_126703 crossref_primary_10_3390_a16070349 crossref_primary_10_1016_j_neucom_2023_126286 crossref_primary_10_3390_math13081285 crossref_primary_10_1155_2020_2816102 crossref_primary_10_1007_s00603_024_04351_1 crossref_primary_10_3390_math9050542 crossref_primary_10_1007_s10489_021_03134_3 crossref_primary_10_1089_brain_2022_0077 crossref_primary_10_7717_peerj_cs_2286 crossref_primary_10_1016_j_cie_2019_106087 crossref_primary_10_1038_s41524_021_00565_x crossref_primary_10_3390_math12131930 crossref_primary_10_1002_cpe_7894 crossref_primary_10_1016_j_applthermaleng_2022_119633 crossref_primary_10_1016_j_patcog_2023_109454 crossref_primary_10_1109_TWC_2023_3294530 crossref_primary_10_3390_sym14061237 crossref_primary_10_1007_s12530_022_09447_z crossref_primary_10_4178_epih_e2024043 crossref_primary_10_3390_math11173637 crossref_primary_10_1186_s12870_024_05542_2 crossref_primary_10_1109_ACCESS_2024_3463712 crossref_primary_10_3390_en15155333 crossref_primary_10_1109_TKDE_2024_3483572 crossref_primary_10_1109_ACCESS_2022_3179803 crossref_primary_10_1002_cyto_a_24901 crossref_primary_10_1016_j_neucom_2024_128198 crossref_primary_10_1007_s11063_020_10298_5 crossref_primary_10_1142_S0218126624501846 crossref_primary_10_1007_s11334_021_00400_y crossref_primary_10_52080_rvgluz_30_especial13_42 crossref_primary_10_3390_s23084120 crossref_primary_10_1155_2022_5807690 crossref_primary_10_3934_aci_2022004 crossref_primary_10_1080_02331888_2025_2505576 crossref_primary_10_1109_TITS_2022_3202011 crossref_primary_10_1155_2022_3958423 crossref_primary_10_1016_j_inffus_2021_05_011 crossref_primary_10_3390_a14010006 crossref_primary_10_1007_s00778_021_00716_y crossref_primary_10_1007_s10639_024_12480_x crossref_primary_10_1007_s41748_024_00409_w crossref_primary_10_1007_s10115_021_01623_y crossref_primary_10_1109_ACCESS_2023_3312287 crossref_primary_10_1016_j_jhydrol_2021_126841 crossref_primary_10_1109_ACCESS_2025_3571807 crossref_primary_10_3390_rs13183665 crossref_primary_10_1007_s10044_021_01045_0 crossref_primary_10_1007_s10044_022_01065_4 crossref_primary_10_3390_agriculture13030629 crossref_primary_10_1007_s12652_022_04428_1 crossref_primary_10_1007_s42087_024_00445_y crossref_primary_10_1016_j_jmapro_2024_04_009 crossref_primary_10_3390_s23198164 crossref_primary_10_3390_math8030373 crossref_primary_10_2478_acss_2023_0001 crossref_primary_10_1007_s10489_022_03698_8 crossref_primary_10_1016_j_patcog_2020_107713 crossref_primary_10_3390_a16120572 crossref_primary_10_1108_K_06_2023_1044 crossref_primary_10_1109_ACCESS_2022_3229582 crossref_primary_10_3390_rs17061065 crossref_primary_10_7717_peerj_14706 crossref_primary_10_1109_TPAMI_2024_3367912 crossref_primary_10_1186_s12942_023_00348_1 crossref_primary_10_3390_sym13050837 crossref_primary_10_1109_ACCESS_2021_3084057 crossref_primary_10_1109_JSEN_2023_3268794 crossref_primary_10_1016_j_procs_2023_01_392 crossref_primary_10_1016_j_patcog_2022_109269 crossref_primary_10_1016_j_patcog_2019_107063 crossref_primary_10_1109_TFUZZ_2023_3247912 crossref_primary_10_3390_rs16010102 crossref_primary_10_1002_cpe_7185 crossref_primary_10_3390_rs12223745 crossref_primary_10_3390_app12157378 crossref_primary_10_3390_app12105125 crossref_primary_10_1109_TKDE_2022_3144294 crossref_primary_10_1186_s12913_023_09375_x crossref_primary_10_1016_j_ijdrr_2023_103528 crossref_primary_10_3389_fnins_2022_895637 crossref_primary_10_3390_ijgi10070479 crossref_primary_10_1111_jiec_13174 crossref_primary_10_1155_2021_6653816 crossref_primary_10_1007_s41748_024_00516_8 crossref_primary_10_1016_j_knosys_2022_109374 crossref_primary_10_1007_s10479_022_04818_w crossref_primary_10_1007_s11280_021_00945_9 crossref_primary_10_1016_j_patcog_2022_109036 crossref_primary_10_2139_ssrn_3805831 crossref_primary_10_1016_j_tranpol_2022_02_015 crossref_primary_10_3390_ijgi9110661 crossref_primary_10_3390_math11234800 crossref_primary_10_1016_j_buildenv_2023_111155 crossref_primary_10_1016_j_suscom_2021_100561 crossref_primary_10_1016_j_jss_2025_112576 crossref_primary_10_3390_s23094178 crossref_primary_10_1016_j_ufug_2025_128978 crossref_primary_10_1016_j_trf_2022_08_012 crossref_primary_10_1109_TCAD_2023_3346274 crossref_primary_10_1007_s10489_021_02909_y crossref_primary_10_3390_a14070197 crossref_primary_10_1016_j_patcog_2020_107625 crossref_primary_10_3390_app13095675 crossref_primary_10_1109_ACCESS_2024_3388720 crossref_primary_10_1016_j_patcog_2022_108875 crossref_primary_10_1007_s10044_025_01463_4 crossref_primary_10_1134_S1995080222010188 crossref_primary_10_1080_02664763_2025_2495718 crossref_primary_10_3390_atmos13101715 crossref_primary_10_1049_ell2_70212 crossref_primary_10_32604_cmc_2025_057693 crossref_primary_10_1007_s10489_024_05636_2 crossref_primary_10_1108_JAMR_07_2021_0242 crossref_primary_10_1038_s41598_023_39058_w crossref_primary_10_1007_s10107_023_02021_8 crossref_primary_10_1016_j_cageo_2022_105241 crossref_primary_10_1016_j_patcog_2022_109290 crossref_primary_10_1109_ACCESS_2021_3080821 crossref_primary_10_1007_s11634_025_00639_4 crossref_primary_10_1016_j_fuel_2019_116178 crossref_primary_10_3390_math8071090 crossref_primary_10_3390_sym14030623 crossref_primary_10_1007_s42452_020_3129_x crossref_primary_10_1038_s41598_021_03941_1 crossref_primary_10_1175_JCLI_D_21_0562_1 crossref_primary_10_1016_j_apenergy_2022_119032 crossref_primary_10_1016_j_jksuci_2023_101731 crossref_primary_10_1016_j_knosys_2021_107443 crossref_primary_10_1007_s00521_022_06956_5 crossref_primary_10_1016_j_patcog_2022_109062 crossref_primary_10_1080_10298436_2025_2450098 crossref_primary_10_1007_s11042_025_21119_z crossref_primary_10_1155_2021_6618505 crossref_primary_10_1016_j_patcog_2021_108250 crossref_primary_10_1016_j_patcog_2020_107206 crossref_primary_10_1088_1742_6596_1752_1_012014 crossref_primary_10_1007_s00357_022_09422_y crossref_primary_10_1109_ACCESS_2025_3581901 crossref_primary_10_1080_01605682_2020_1830724 crossref_primary_10_1109_LRA_2024_3416790 crossref_primary_10_1016_j_ins_2022_07_101 crossref_primary_10_1080_22797254_2023_2214690 crossref_primary_10_1007_s42979_025_04353_y crossref_primary_10_1016_j_ecoinf_2025_103390 crossref_primary_10_1016_j_patcog_2021_107849 crossref_primary_10_1109_ACCESS_2025_3561293 crossref_primary_10_3390_math10224301 crossref_primary_10_1109_TEVC_2022_3144134 crossref_primary_10_1007_s41870_024_02340_9 crossref_primary_10_1016_j_neucom_2021_12_019 crossref_primary_10_1016_j_jenvman_2021_113540 crossref_primary_10_1016_j_scitotenv_2021_149728 crossref_primary_10_3390_su17188321 crossref_primary_10_1287_ijoc_2022_1166 crossref_primary_10_1007_s12065_022_00720_3 crossref_primary_10_1016_j_jhydrol_2025_133585 crossref_primary_10_1038_s41598_024_56931_4 crossref_primary_10_3390_en16052367 crossref_primary_10_1016_j_simpat_2022_102712 crossref_primary_10_1016_j_tra_2024_103987 crossref_primary_10_32604_jai_2023_043229 crossref_primary_10_1080_10618600_2023_2210174 crossref_primary_10_1007_s12517_021_06448_1 crossref_primary_10_1109_ACCESS_2021_3050547 crossref_primary_10_1109_ACCESS_2020_2993295 crossref_primary_10_1155_2022_3109609 crossref_primary_10_3390_math11143063 crossref_primary_10_1007_s10898_022_01267_4 crossref_primary_10_1016_j_ins_2024_120661 crossref_primary_10_1371_journal_pone_0255684 crossref_primary_10_1080_10618600_2024_2414889 crossref_primary_10_3389_fenrg_2022_920885 crossref_primary_10_3390_a15040117 crossref_primary_10_1016_j_tranpol_2021_09_013 crossref_primary_10_1109_TCE_2024_3475821 crossref_primary_10_1007_s41748_024_00514_w crossref_primary_10_3934_aci_2024016 crossref_primary_10_1016_j_eswa_2021_115558 crossref_primary_10_1016_j_segan_2022_100757 crossref_primary_10_3390_app15031032 crossref_primary_10_1007_s42087_025_00495_w crossref_primary_10_1109_TPWRS_2022_3207926 crossref_primary_10_1109_TKDE_2020_3002926 crossref_primary_10_1186_s12909_025_07818_z crossref_primary_10_1080_23737484_2021_1911719 crossref_primary_10_1109_JSYST_2025_3532508 crossref_primary_10_1007_s11162_025_09844_8 crossref_primary_10_3390_en13174368 |
| Cites_doi | 10.3233/IDA-2007-11402 10.1109/3477.764879 10.1016/j.eswa.2011.02.086 10.1007/s100440070007 10.1016/S0167-8655(99)00133-6 10.1016/j.knosys.2016.06.031 10.1145/1557019.1557118 10.1126/science.1242072 10.1016/S0167-8655(99)00069-0 10.20982/tqmp.09.1.p015 10.1016/j.eswa.2009.01.060 10.1016/j.spl.2013.09.026 10.1109/83.210871 10.1016/j.patcog.2014.03.017 10.1016/j.knosys.2017.11.025 10.1016/j.ins.2018.06.008 10.1016/j.eswa.2012.07.021 10.1016/j.patrec.2009.09.011 10.1016/0196-6774(91)90039-2 10.1016/j.patrec.2007.01.001 10.1037/1082-989X.8.3.294 10.1016/j.patcog.2017.06.023 10.1109/83.841516 10.1016/0304-3975(85)90224-5 10.1109/83.855429 10.14778/2180912.2180915 10.1117/1.601531 10.1109/TCOM.1980.1094577 10.1109/97.329844 10.1109/TIT.1982.1056489 10.1016/j.asoc.2017.08.032 10.3390/a11020019 10.1016/j.patrec.2011.07.011 10.1016/j.camwa.2009.04.017 10.1016/j.patcog.2018.05.028 10.1007/s10489-018-1238-7 10.1109/TIT.2014.2375327 10.1109/TKDE.2016.2551240 10.1177/0960327117695635 10.1007/s00357-007-0003-0 10.1016/j.datak.2014.07.008 10.1016/j.patrec.2011.06.023 10.1016/S0031-3203(02)00060-2 10.1109/TPAMI.2006.227 10.1016/j.patcog.2013.11.014 10.1016/j.patcog.2018.04.020 10.1016/0167-8655(95)00119-0 10.1080/01621459.1963.10500845 10.1016/j.patcog.2018.09.016 10.1007/s00357-010-9049-5 10.1109/82.257335 10.1145/3274656 10.1145/116890.116892 10.1016/j.patcog.2018.05.027 10.1016/j.patcog.2018.05.011 10.1002/bs.3830120210 10.1142/S0218001412500188 10.1109/TFUZZ.2011.2182354 10.1023/A:1009740529316 10.1109/TPAMI.2002.1008381 |
| ContentType | Journal Article |
| Copyright | 2019 The Authors |
| Copyright_xml | – notice: 2019 The Authors |
| DBID | 6I. AAFTH AAYXX CITATION |
| DOI | 10.1016/j.patcog.2019.04.014 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1873-5142 |
| EndPage | 112 |
| ExternalDocumentID | 10_1016_j_patcog_2019_04_014 S0031320319301608 |
| GroupedDBID | --K --M -D8 -DT -~X .DC .~1 0R~ 123 1B1 1RT 1~. 1~5 29O 4.4 457 4G. 53G 5VS 6I. 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAFTH AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABEFU ABFNM ABFRF ABHFT ABJNI ABMAC ABTAH ABXDB ABYKQ ACBEA ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADMXK ADTZH AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FD6 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q G8K GBLVA GBOLZ HLZ HVGLF HZ~ H~9 IHE J1W JJJVA KOM KZ1 LG9 LMP LY1 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SBC SDF SDG SDP SDS SES SEW SPC SPCBC SST SSV SSZ T5K TN5 UNMZH VOH WUQ XJE XPP ZMT ZY4 ~G- 9DU AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD |
| ID | FETCH-LOGICAL-c352t-f15bcbfd13cbaa33f52ec7f403a3540de5bcc81b79dccb8e8b2dcaeccdffc5da3 |
| ISICitedReferencesCount | 306 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000472697800008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0031-3203 |
| IngestDate | Sat Nov 29 07:30:07 EST 2025 Tue Nov 18 22:04:10 EST 2025 Fri Feb 23 02:45:45 EST 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | K-means Initialization Prototype selection Clustering algorithms Clustering accuracy |
| Language | English |
| License | This is an open access article under the CC BY license. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c352t-f15bcbfd13cbaa33f52ec7f403a3540de5bcc81b79dccb8e8b2dcaeccdffc5da3 |
| ORCID | 0000-0002-9554-2827 |
| OpenAccessLink | https://dx.doi.org/10.1016/j.patcog.2019.04.014 |
| PageCount | 18 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_patcog_2019_04_014 crossref_primary_10_1016_j_patcog_2019_04_014 elsevier_sciencedirect_doi_10_1016_j_patcog_2019_04_014 |
| PublicationCentury | 2000 |
| PublicationDate | September 2019 2019-09-00 |
| PublicationDateYYYYMMDD | 2019-09-01 |
| PublicationDate_xml | – month: 09 year: 2019 text: September 2019 |
| PublicationDecade | 2010 |
| PublicationTitle | Pattern recognition |
| PublicationYear | 2019 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Fränti, Kaukoranta, Nevalainen (bib0046) 1997; 36 Fränti, Virmajoki, Hautamäki (bib0047) 2006; 28 Katsavounidis, Kuo, Zhang (bib0057) 1994; 1 M. Rezaei and P. Fränti Can the number of clusters be solved by external index? manuscript. (submitted) Melnykov, Melnykov (bib0042) 2014; 84 Wang, Pan (bib0004) 2014; 47 Liang, Bai, Dang F. Cao (bib0041) 2012; 20 Linde, Buzo, Gray (bib0085) 1980; 28 Al-Daoud, Roberts (bib0076) 1996; 17 B. Thiesson, C. Meek, D.M. Chickering, and D. Heckerman, Learning mixtures of Bayesian networks, Technical Report MSR-TR-97-30 Cooper & Moral, 1997. Luxburg (bib0050) 2010; 2 Capo, A, Lozano (bib0006) 2017; 117 Boutsidis, Zouzias, Mahoney, Drineas (bib0005) 2015; 61 Zhu, Ting, Carman (bib0035) 2018; 83 Márquez, Otero, Félix, García (bib0037) 2018; 82 Dong, Moses, Li (bib0081) 2011 Gourgaris, Makris (bib0077) 2015 Arthur, Vassilvitskii (bib0059) January 2007 Norušis (bib0053) 2011 Chiang, Mirkin (bib0055) 2010; 27 Steinley (bib0029) 2003; 8 Redmond, Heneghan (bib0051) 2007; 28 Curti, Wainschenker (bib0083) 2018; 462 Lemke, Keller (bib0049) 2018; 11 Gonzalez (bib0026) 1985; 38 Wu (bib0075) 1991; 12 Bai, Cheng, Liang, Shen, Guo (bib0015) 2017; 71 Kaukoranta, Fränti, Nevalainen (bib0089) 2000; 9 Melnykov, Michael, Melnykov (bib0043) 2015 Huang, Chao, Wang (bib0038) 2019; 86 Celebi, Kingravi, Vela (bib0022) 2013; 40 Cao, Liang, Bai (bib0058) 2009; 36 Al-Daoud (bib0065) 2005 MacQueen (bib0002) 1967; 1 He, Lan, Tan, Sung, Low (bib0020) 2004 Fränti (bib0010) 2000; 21 Astrahan (bib0063) 1970 Yan, Huang, Jordan (bib0014) 2009 Erisoglu, Calis, Sakallioglu (bib0060) 2011; 32 Fränti, Sieranoja (bib0082) June 2018 Huang, Li, Rao, Liu, Huang, Ma, Wang (bib0007) 2018; 37 Xie, Xiong, Zhang, Feng, Ma (bib0084) 2018; 142 Morissette, Chartier (bib0040) 2013; 9 Wu, Zhang (bib0068) 1991 Duda, Hart (bib0032) 1973 Gonzalez (bib0054) 1985; 38 Steinbach, Karypis, Kumar (bib0086) 2000; vol. 400 Yedla, Pathakota, Srinivasa (bib0066) 2010; 1 Rezaei, Fränti (bib0044) 2016; 28 Ward (bib0027) 1963; 58 Krishna, M.N (bib0009) 1999; 29 Zhao, Fränti (bib0017) 2014; 92 Sieranoja, Fränti (bib0072) June 2018 Yu, Chu, Wang, Chan, Chang (bib0087) 2018; 68 Cao, Liang, Jiang (bib0064) 2009; 58 Likas, Vlassis, Verbeek (bib0028) 2003; 36 Hämäläinen, Kärkkäinen (bib0056) 2016 Kaufman, Rousseeuw (bib0023) 1990 Huang, Harris (bib0069) 1993; 2 Lloyd (bib0003) 1982; 28 Fränti, Kaukoranta, Shen, Chang (bib0030) 2000; 9 Steinley, Brusco (bib0021) 2007; 24 Tou, Gonzales (bib0025) 1974 Su, Dy (bib0067) 2007; 11 Jain (bib0008) 2010; 31 Kinnunen, Sidoroff, Tuononen, Fränti (bib0016) 2011; 32 Bicego, Figueiredo (bib0033) 2018; 83 Tezuka, Equyer (bib0052) 1991; 1 Boley (bib0070) 1998; 2 Rodriquez, Laio (bib0078) 2014; 344 Celebi, Kingravi (bib0071) 2012; 26 Frandsen, Calcott, Mayer, Lanfear (bib0036) 2015; 15 Fränti, Kivijärvi (bib0011) 2000; 3 Cleju, Fränti, Wu (bib0074) 2005; vol. 3540 Peña, Lozano, Larrañaga (bib0019) 1999; 20 Bahmani, Mosley, Vattani, Kumar, Vassilvitski, k-means (bib0088) 2012; 5 Karmitsa, Bagirov, Taheri (bib0034) 2018; 83 Gingles, Celebi (bib0061) May 2014 Fränti, Sieranoja (bib0039) 2018; 48 Kalyani, Swarup (bib0013) 2011; 32 Forgy (bib0001) 1965; 21 Fränti, Rezaei, Zhao (bib0045) 2014; 47 Mitra, Murthy, Pal (bib0079) 2002; 24 Fränti (bib0012) 2018; 5 Hartigan, Wong (bib0062) 1979; 28 Ball, Hall (bib0048) 1967; 12 Bradley, Fayyad (bib0031) 1998 Sieranoja, Fränti (bib0080) 2018; 23 Ra, Kim (bib0073) 1993; 40 Melnykov (10.1016/j.patcog.2019.04.014_bib0043) 2015 Forgy (10.1016/j.patcog.2019.04.014_bib0001) 1965; 21 Kalyani (10.1016/j.patcog.2019.04.014_bib0013) 2011; 32 Yan (10.1016/j.patcog.2019.04.014_bib0014) 2009 Morissette (10.1016/j.patcog.2019.04.014_bib0040) 2013; 9 Boutsidis (10.1016/j.patcog.2019.04.014_bib0005) 2015; 61 Tezuka (10.1016/j.patcog.2019.04.014_bib0052) 1991; 1 Sieranoja (10.1016/j.patcog.2019.04.014_bib0080) 2018; 23 Erisoglu (10.1016/j.patcog.2019.04.014_bib0060) 2011; 32 Tou (10.1016/j.patcog.2019.04.014_bib0025) 1974 Rezaei (10.1016/j.patcog.2019.04.014_bib0044) 2016; 28 Celebi (10.1016/j.patcog.2019.04.014_bib0071) 2012; 26 Kaukoranta (10.1016/j.patcog.2019.04.014_bib0089) 2000; 9 Peña (10.1016/j.patcog.2019.04.014_bib0019) 1999; 20 Gourgaris (10.1016/j.patcog.2019.04.014_bib0077) 2015 Cleju (10.1016/j.patcog.2019.04.014_bib0074) 2005; vol. 3540 Xie (10.1016/j.patcog.2019.04.014_bib0084) 2018; 142 MacQueen (10.1016/j.patcog.2019.04.014_bib0002) 1967; 1 Gonzalez (10.1016/j.patcog.2019.04.014_bib0054) 1985; 38 Likas (10.1016/j.patcog.2019.04.014_bib0028) 2003; 36 Al-Daoud (10.1016/j.patcog.2019.04.014_bib0065) 2005 Sieranoja (10.1016/j.patcog.2019.04.014_bib0072) 2018 Hartigan (10.1016/j.patcog.2019.04.014_bib0062) 1979; 28 Boley (10.1016/j.patcog.2019.04.014_bib0070) 1998; 2 Rodriquez (10.1016/j.patcog.2019.04.014_bib0078) 2014; 344 Gingles (10.1016/j.patcog.2019.04.014_bib0061) 2014 Yu (10.1016/j.patcog.2019.04.014_bib0087) 2018; 68 Astrahan (10.1016/j.patcog.2019.04.014_bib0063) 1970 Cao (10.1016/j.patcog.2019.04.014_bib0064) 2009; 58 Linde (10.1016/j.patcog.2019.04.014_bib0085) 1980; 28 Fränti (10.1016/j.patcog.2019.04.014_bib0046) 1997; 36 Frandsen (10.1016/j.patcog.2019.04.014_bib0036) 2015; 15 10.1016/j.patcog.2019.04.014_bib0018 Bradley (10.1016/j.patcog.2019.04.014_bib0031) 1998 Lemke (10.1016/j.patcog.2019.04.014_bib0049) 2018; 11 Kaufman (10.1016/j.patcog.2019.04.014_bib0023) 1990 Huang (10.1016/j.patcog.2019.04.014_bib0069) 1993; 2 Curti (10.1016/j.patcog.2019.04.014_bib0083) 2018; 462 Fränti (10.1016/j.patcog.2019.04.014_bib0045) 2014; 47 Jain (10.1016/j.patcog.2019.04.014_bib0008) 2010; 31 Krishna (10.1016/j.patcog.2019.04.014_bib0009) 1999; 29 Fränti (10.1016/j.patcog.2019.04.014_bib0030) 2000; 9 Ra (10.1016/j.patcog.2019.04.014_bib0073) 1993; 40 Duda (10.1016/j.patcog.2019.04.014_bib0032) 1973 Luxburg (10.1016/j.patcog.2019.04.014_bib0050) 2010; 2 Hämäläinen (10.1016/j.patcog.2019.04.014_bib0056) 2016 Gonzalez (10.1016/j.patcog.2019.04.014_bib0026) 1985; 38 Kinnunen (10.1016/j.patcog.2019.04.014_bib0016) 2011; 32 Steinley (10.1016/j.patcog.2019.04.014_bib0021) 2007; 24 Wu (10.1016/j.patcog.2019.04.014_bib0068) 1991 10.1016/j.patcog.2019.04.014_bib0024 Fränti (10.1016/j.patcog.2019.04.014_bib0047) 2006; 28 Arthur (10.1016/j.patcog.2019.04.014_bib0059) 2007 Katsavounidis (10.1016/j.patcog.2019.04.014_bib0057) 1994; 1 Yedla (10.1016/j.patcog.2019.04.014_bib0066) 2010; 1 Bahmani (10.1016/j.patcog.2019.04.014_bib0088) 2012; 5 Huang (10.1016/j.patcog.2019.04.014_bib0038) 2019; 86 Wu (10.1016/j.patcog.2019.04.014_bib0075) 1991; 12 Lloyd (10.1016/j.patcog.2019.04.014_bib0003) 1982; 28 Huang (10.1016/j.patcog.2019.04.014_bib0007) 2018; 37 Melnykov (10.1016/j.patcog.2019.04.014_bib0042) 2014; 84 Mitra (10.1016/j.patcog.2019.04.014_bib0079) 2002; 24 Karmitsa (10.1016/j.patcog.2019.04.014_bib0034) 2018; 83 Ward (10.1016/j.patcog.2019.04.014_bib0027) 1963; 58 Fränti (10.1016/j.patcog.2019.04.014_bib0082) 2018 Cao (10.1016/j.patcog.2019.04.014_bib0058) 2009; 36 Steinley (10.1016/j.patcog.2019.04.014_bib0029) 2003; 8 Bicego (10.1016/j.patcog.2019.04.014_bib0033) 2018; 83 Fränti (10.1016/j.patcog.2019.04.014_bib0039) 2018; 48 Dong (10.1016/j.patcog.2019.04.014_bib0081) 2011 Márquez (10.1016/j.patcog.2019.04.014_bib0037) 2018; 82 Celebi (10.1016/j.patcog.2019.04.014_bib0022) 2013; 40 Zhu (10.1016/j.patcog.2019.04.014_bib0035) 2018; 83 Liang (10.1016/j.patcog.2019.04.014_bib0041) 2012; 20 Chiang (10.1016/j.patcog.2019.04.014_bib0055) 2010; 27 Steinbach (10.1016/j.patcog.2019.04.014_bib0086) 2000; vol. 400 Capo (10.1016/j.patcog.2019.04.014_bib0006) 2017; 117 He (10.1016/j.patcog.2019.04.014_bib0020) 2004 Norušis (10.1016/j.patcog.2019.04.014_bib0053) 2011 Redmond (10.1016/j.patcog.2019.04.014_bib0051) 2007; 28 Su (10.1016/j.patcog.2019.04.014_bib0067) 2007; 11 Fränti (10.1016/j.patcog.2019.04.014_bib0011) 2000; 3 Zhao (10.1016/j.patcog.2019.04.014_bib0017) 2014; 92 Al-Daoud (10.1016/j.patcog.2019.04.014_bib0076) 1996; 17 Fränti (10.1016/j.patcog.2019.04.014_bib0012) 2018; 5 Ball (10.1016/j.patcog.2019.04.014_bib0048) 1967; 12 Bai (10.1016/j.patcog.2019.04.014_bib0015) 2017; 71 Wang (10.1016/j.patcog.2019.04.014_bib0004) 2014; 47 Fränti (10.1016/j.patcog.2019.04.014_bib0010) 2000; 21 |
| References_xml | – volume: 9 start-page: 773 year: 2000 end-page: 777 ident: bib0030 article-title: Fast and memory efficient implementation of the exact PNN publication-title: IEEE Trans. Image Process. – volume: 32 start-page: 1701 year: 2011 end-page: 1705 ident: bib0060 article-title: A new algorithm for initial cluster centers in k-means algorithm publication-title: Pattern Recognit. Lett. – start-page: 680 year: June 2018 end-page: 689 ident: bib0072 article-title: Random projection for k-means clustering publication-title: Int. Conf. Artificial Intelligence and Soft Computing (ICAISC) – volume: 11 start-page: 19 year: 2018 ident: bib0049 article-title: Common nearest neighbor clustering: a benchmark publication-title: Algorithms – start-page: 392 year: 1991 end-page: 401 ident: bib0068 article-title: A better tree-structured vector quantizer publication-title: IEEE Data Compression Conference – year: 1970 ident: bib0063 article-title: Speech Analysis by Clustering, Or the Hyperphome Method, Stanford Artificial Intelligence Project Memorandum AIM-124 – volume: 28 start-page: 1875 year: 2006 end-page: 1881 ident: bib0047 article-title: Fast agglomerative clustering using a k-nearest neighbor graph publication-title: IEEE Trans. Pattern Anal. Mach. Intel. – reference: M. Rezaei and P. Fränti Can the number of clusters be solved by external index? manuscript. (submitted) – volume: 15 year: 2015 ident: bib0036 article-title: Automatic selection of partitioning schemes for phylogenetic analyses using iterative k-means clustering of site rates publication-title: BMC Evol. Biol. – year: 2011 ident: bib0053 article-title: IBM SPSS Statistics 19 Guide to Data Analysis – volume: 58 start-page: 474 year: 2009 end-page: 483 ident: bib0064 article-title: An initialization method for the k-means algorithm using neighborhood model publication-title: Comput. Math. Appl. – volume: 11 start-page: 319 year: 2007 end-page: 338 ident: bib0067 article-title: In search of deterministic methods for initializing k-means and gaussian mixture clustering publication-title: Intel. Data Anal. – year: 2015 ident: bib0077 article-title: A Density Based K-Means Initialization Scheme – volume: 1 start-page: 281 year: 1967 end-page: 297 ident: bib0002 article-title: Some methods for classification and analysis of multivariate observations publication-title: Berkeley Symposium on Mathematical Statistics and Probability – year: January 2007 ident: bib0059 article-title: K-means++: the advantages of careful seeding publication-title: ACM-SIAM Symp. on Discrete Algorithms (SODA’07) – volume: 2 start-page: 325 year: 1998 end-page: 344 ident: bib0070 article-title: Principal direction divisive partitioning publication-title: Data Min. Knowl. Discov. – volume: 29 start-page: 433 year: 1999 end-page: 439 ident: bib0009 article-title: Genetic k-means algorithm publication-title: IEEE Trans. Syst. Man Cybern. Part B – volume: 23 start-page: 1 year: 2018 end-page: 21 ident: bib0080 article-title: Constructing a high-dimensional kNN-graph using a Z-order curve publication-title: ACM J. Exp. Algorithmics – volume: 21 start-page: 61 year: 2000 end-page: 68 ident: bib0010 article-title: Genetic algorithm with deterministic crossover for vector quantization publication-title: Pattern Recognit. Lett. – year: 2004 ident: bib0020 article-title: Initialization of Cluster Refinement Algorithms: a review and comparative study publication-title: IEEE Int. Joint Conf. Neural Netw. – start-page: 907 year: 2009 end-page: 916 ident: bib0014 article-title: Fast approximate spectral clustering publication-title: ACM SIGKDD Int. Conf. Knowl. Discov. Data Min. – volume: 17 start-page: 451 year: 1996 end-page: 455 ident: bib0076 article-title: New methods for the initialisation of clusters publication-title: Pattern Recognit. Lett. – reference: B. Thiesson, C. Meek, D.M. Chickering, and D. Heckerman, Learning mixtures of Bayesian networks, Technical Report MSR-TR-97-30 Cooper & Moral, 1997. – volume: 8 start-page: 294 year: 2003 end-page: 304 ident: bib0029 article-title: Local optima in k-means clustering: what you don't know may hurt you publication-title: Psychol. Methods – volume: 12 start-page: 153 year: 1967 end-page: 155 ident: bib0048 article-title: A clustering technique for summarizing multivariate data publication-title: Syst. Res. Behav. Sci. – volume: 28 start-page: 129 year: 1982 end-page: 137 ident: bib0003 article-title: Least squares quantization in PCM publication-title: IEEE Trans. Inf. Theory – volume: 83 start-page: 245 year: 2018 end-page: 259 ident: bib0034 article-title: Clustering in large data sets with the limited memory bundle method publication-title: Pattern Recognit. – volume: 40 start-page: 200 year: 2013 end-page: 210 ident: bib0022 article-title: A comparative study of efficient initialization methods for the k-means clustering algorithm publication-title: Expert Syst. Appl. – volume: 5 start-page: 622 year: 2012 end-page: 633 ident: bib0088 publication-title: Proc. VLDB Endow. – volume: vol. 3540 start-page: 872 year: 2005 end-page: 881 ident: bib0074 article-title: Clustering based on principal curve publication-title: Scandinavian Conf. On Image Analysis, LNCS – volume: 28 start-page: 84 year: 1980 end-page: 95 ident: bib0085 article-title: An algorithm for vector quantizer design publication-title: IEEE Trans. Commun. – year: 1973 ident: bib0032 article-title: Pattern Classification and Scene Analysis – volume: 47 start-page: 1917 year: 2014 end-page: 1925 ident: bib0004 article-title: Robust level set image segmentation via a local correntropy-based k-means clustering publication-title: Pattern Recognit. – volume: 61 start-page: 1045 year: 2015 end-page: 1062 ident: bib0005 article-title: Randomized dimensionality reduction for k-means clustering publication-title: IEEE Trans. Inf. Theory – volume: 1 start-page: 99 year: 1991 end-page: 112 ident: bib0052 article-title: Efficient portable combined Tausworthe random number generators publication-title: ACM Trans. Model. Comput. Simul. – volume: 36 start-page: 451 year: 2003 end-page: 461 ident: bib0028 article-title: The global k-means clustering algorithm publication-title: Pattern Recognit. – volume: 21 start-page: 768 year: 1965 end-page: 780 ident: bib0001 article-title: Cluster analysis of multivariate data: efficiency vs. interpretability of classification publication-title: Biometrics – volume: 37 start-page: 285 year: 2018 end-page: 294 ident: bib0007 article-title: Development of a data-processing method based on Bayesian k-means clustering to discriminate aneugens and clastogens in a high-content micronucleus assay publication-title: Hum. Exp. Toxicol. – start-page: 577 year: 2011 end-page: 586 ident: bib0081 article-title: Efficient k-nearest neighbor graph construction for generic similarity measures publication-title: Proceedings of the ACM International Conference on World wide web – year: 1990 ident: bib0023 article-title: Finding Groups in data: An introduction to Cluster Analysis – volume: 83 start-page: 230 year: 2018 end-page: 244 ident: bib0035 article-title: Grouping points by shared subspaces for effective subspace clustering publication-title: Pattern Recognit. – volume: 9 start-page: 15 year: 2013 end-page: 24 ident: bib0040 article-title: The k-means clustering technique: general considerations and implementation in Mathematica publication-title: Tutor. Quant. Methods Psychol. – volume: 5 start-page: 1 year: 2018 end-page: 29 ident: bib0012 article-title: Efficiency of random swap clustering publication-title: J. Big Data – volume: 36 start-page: 3043 year: 1997 end-page: 3051 ident: bib0046 article-title: On the splitting method for VQ codebook generation publication-title: Opt. Eng. – volume: 12 start-page: 663 year: 1991 end-page: 673 ident: bib0075 article-title: Optimal quantization by matrix searching publication-title: J. Algorithms – volume: 26 year: 2012 ident: bib0071 article-title: Deterministic initialization of the k-means algorithm using hierarchical clustering publication-title: Int. J. Pattern Recognit Artif Intell. – year: 1974 ident: bib0025 article-title: Pattern Recognition Principles – start-page: 343 year: June 2018 end-page: 353 ident: bib0082 article-title: Dimensionally distributed density estimation publication-title: Int. Conf. Artificial Intelligence and Soft Computing (ICAISC) – start-page: 74 year: 2005 end-page: 76 ident: bib0065 article-title: A new algorithm for cluster initialization publication-title: World Enformatika Conference – volume: 82 start-page: 16 year: 2018 end-page: 30 ident: bib0037 article-title: A novel and simple strategy for evolving prototype based clustering publication-title: Pattern Recognit. – volume: 1 start-page: 121 year: 2010 end-page: 125 ident: bib0066 article-title: Enhancing k-means clustering algorithm with improved initial center publication-title: Int. J. Comput. Sci. Inf. Technol. – volume: 40 start-page: 576 year: 1993 end-page: 579 ident: bib0073 article-title: A fast mean-distance-ordered partial codebook search algorithm for image vector quantization publication-title: IEEE Trans. Circuits Syst. – volume: 1 start-page: 144 year: 1994 end-page: 146 ident: bib0057 article-title: A new initialization technique for generalized Lloyd iteration publication-title: IEEE Signal Process Lett. – year: May 2014 ident: bib0061 article-title: Histogram-based method for effective initialization of the k-means clustering algorithm publication-title: Florida Artificial Intelligence Research Society Conference – volume: vol. 400 start-page: 525 year: 2000 end-page: 526 ident: bib0086 article-title: A comparison of document clustering techniques publication-title: KDD workshop on text mining – year: 2016 ident: bib0056 article-title: Initialization of big data clustering using distributionally balanced folding, Proceedings of the European Symposium on Artificial Neural Networks publication-title: Comput. Intel. Mach. Learn.-ESANN – volume: 83 start-page: 52 year: 2018 end-page: 63 ident: bib0033 article-title: Clustering via binary embedding publication-title: Pattern Recognit. – volume: 24 start-page: 99 year: 2007 end-page: 121 ident: bib0021 article-title: Initializing k-means batch clustering: a critical evaluation of several techniques publication-title: J. Classification – volume: 47 start-page: 3034 year: 2014 end-page: 3045 ident: bib0045 article-title: Centroid index: cluster level similarity measure publication-title: Pattern Recognit. – volume: 36 start-page: 10223 year: 2009 end-page: 10228 ident: bib0058 article-title: A new initialization method for categorical data clustering publication-title: Expert Syst. Appl. – volume: 32 start-page: 10839 year: 2011 end-page: 10846 ident: bib0013 article-title: Particle swarm optimization based K-means clustering approach for security assessment in power systems publication-title: Expert Syst. Appl. – volume: 68 start-page: 747 year: 2018 end-page: 755 ident: bib0087 article-title: Two improved k-means algorithms publication-title: Appl. Soft Comput. – volume: 9 start-page: 1337 year: 2000 end-page: 1342 ident: bib0089 article-title: A fast exact GLA based on code vector activity detection publication-title: IEEE Trans. Image Process. – volume: 38 start-page: 293 year: 1985 end-page: 306 ident: bib0054 article-title: Clustering to minimize the maximum intercluster distance publication-title: Theor. Comput. Sci. – volume: 28 start-page: 2173 year: 2016 end-page: 2186 ident: bib0044 article-title: Set-matching methods for external cluster validity publication-title: IEEE Trans. Knowl. Data Eng. – volume: 2 start-page: 108 year: 1993 end-page: 112 ident: bib0069 article-title: A comparison of several vector quantization codebook generation approaches publication-title: IEEE Trans. Image Process. – volume: 20 start-page: 1027 year: 1999 end-page: 1040 ident: bib0019 article-title: An empirical comparison of four initialization methods for the k-means algorithm publication-title: Pattern Recognit. Lett. – volume: 20 start-page: 728 year: 2012 end-page: 745 ident: bib0041 article-title: The k-means-type algorithms versus imbalanced data distributions publication-title: IEEE Trans. Fuzzy Syst. – volume: 117 start-page: 56 year: 2017 end-page: 69 ident: bib0006 article-title: An efficient approximation to the k-means clustering for massive data publication-title: Knowl.-Based Syst. – volume: 38 start-page: 293 year: 1985 end-page: 306 ident: bib0026 article-title: Clustering to minimize the maximum intercluster distance publication-title: Theor. Comput. Sci. – volume: 344 start-page: 1492 year: 2014 end-page: 1496 ident: bib0078 article-title: Clustering by fast search and find of density peaks publication-title: Science – volume: 24 start-page: 734 year: 2002 end-page: 747 ident: bib0079 article-title: Density-based multiscale data condensation publication-title: IEEE Trans. Pattern Anal. Mach. Intel. – volume: 2 start-page: 235 year: 2010 end-page: 274 ident: bib0050 article-title: Clustering stability: an overview publication-title: Found. Trends Mach. Learn. – start-page: 91 year: 1998 end-page: 99 ident: bib0031 article-title: Refining initial points for k-means clustering publication-title: International Conference on Machine Learning – volume: 58 start-page: 236 year: 1963 end-page: 244 ident: bib0027 article-title: Hierarchical grouping to optimize an objective function publication-title: J. Am. Stat. Assoc. – volume: 48 start-page: 4743 year: 2018 end-page: 4759 ident: bib0039 article-title: K-means properties on six clustering benchmark datasets publication-title: Appl. Intel. – volume: 84 start-page: 88 year: 2014 end-page: 95 ident: bib0042 article-title: On k-means algorithm with the use of Mahalanobis distances publication-title: Stat. Probab. Lett. – year: 2015 ident: bib0043 article-title: Recent developments in model-based clustering with applications publication-title: Partitional Clustering Algorithms – volume: 3 start-page: 358 year: 2000 end-page: 369 ident: bib0011 article-title: Randomized local search algorithm for the clustering problem publication-title: Pattern Anal. Appl. – volume: 92 start-page: 77 year: 2014 end-page: 89 ident: bib0017 article-title: WB-index: a sum-of-squares based index for cluster validity publication-title: Data Knowl. Eng. – volume: 27 start-page: 3 year: 2010 end-page: 40 ident: bib0055 article-title: Intelligent choice of the number of clusters in k-means clustering: an experimental study with different cluster spreads publication-title: J. Classification – volume: 462 start-page: 182 year: 2018 end-page: 203 ident: bib0083 article-title: FAUM: fast Autonomous Unsupervised Multidimensional classification publication-title: Inf. Sci. – volume: 32 start-page: 1604 year: 2011 end-page: 1617 ident: bib0016 article-title: Comparison of clustering methods: a case study of text-independent speaker modeling publication-title: Pattern Recognit. Lett. – volume: 28 start-page: 965 year: 2007 end-page: 973 ident: bib0051 article-title: A method for initialising the K-means clustering algorithm using kd-trees publication-title: Pattern Recognit. Lett. – volume: 142 start-page: 68 year: 2018 end-page: 70 ident: bib0084 article-title: Density core-based clustering algorithm with dynamic scanning radius publication-title: Knowl.-Based Syst. – volume: 31 start-page: 651 year: 2010 end-page: 666 ident: bib0008 article-title: Data clustering: 50 years beyond K-means publication-title: Pattern Recognit. Lett. – volume: 86 start-page: 344 year: 2019 end-page: 353 ident: bib0038 article-title: Multi-view intact space clustering publication-title: Pattern Recognit. – volume: 28 start-page: 100 year: 1979 end-page: 108 ident: bib0062 article-title: Algorithm AS 136: a k-means clustering algorithm publication-title: J. R. Stat. Soc. C – volume: 71 start-page: 375 year: 2017 end-page: 386 ident: bib0015 article-title: Fast density clustering strategies based on the k-means algorithm publication-title: Pattern Recognit. – start-page: 91 year: 1998 ident: 10.1016/j.patcog.2019.04.014_bib0031 article-title: Refining initial points for k-means clustering – volume: 2 start-page: 235 issue: 3 year: 2010 ident: 10.1016/j.patcog.2019.04.014_bib0050 article-title: Clustering stability: an overview publication-title: Found. Trends Mach. Learn. – volume: 11 start-page: 319 issue: 4 year: 2007 ident: 10.1016/j.patcog.2019.04.014_bib0067 article-title: In search of deterministic methods for initializing k-means and gaussian mixture clustering publication-title: Intel. Data Anal. doi: 10.3233/IDA-2007-11402 – year: 2015 ident: 10.1016/j.patcog.2019.04.014_bib0077 – volume: 29 start-page: 433 issue: 3 year: 1999 ident: 10.1016/j.patcog.2019.04.014_bib0009 article-title: Genetic k-means algorithm publication-title: IEEE Trans. Syst. Man Cybern. Part B doi: 10.1109/3477.764879 – volume: 32 start-page: 10839 issue: 9 year: 2011 ident: 10.1016/j.patcog.2019.04.014_bib0013 article-title: Particle swarm optimization based K-means clustering approach for security assessment in power systems publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2011.02.086 – volume: 3 start-page: 358 issue: 4 year: 2000 ident: 10.1016/j.patcog.2019.04.014_bib0011 article-title: Randomized local search algorithm for the clustering problem publication-title: Pattern Anal. Appl. doi: 10.1007/s100440070007 – year: 1970 ident: 10.1016/j.patcog.2019.04.014_bib0063 – volume: 21 start-page: 61 issue: 1 year: 2000 ident: 10.1016/j.patcog.2019.04.014_bib0010 article-title: Genetic algorithm with deterministic crossover for vector quantization publication-title: Pattern Recognit. Lett. doi: 10.1016/S0167-8655(99)00133-6 – volume: 117 start-page: 56 year: 2017 ident: 10.1016/j.patcog.2019.04.014_bib0006 article-title: An efficient approximation to the k-means clustering for massive data publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2016.06.031 – start-page: 907 year: 2009 ident: 10.1016/j.patcog.2019.04.014_bib0014 article-title: Fast approximate spectral clustering publication-title: ACM SIGKDD Int. Conf. Knowl. Discov. Data Min. doi: 10.1145/1557019.1557118 – volume: 344 start-page: 1492 issue: 6191 year: 2014 ident: 10.1016/j.patcog.2019.04.014_bib0078 article-title: Clustering by fast search and find of density peaks publication-title: Science doi: 10.1126/science.1242072 – volume: vol. 400 start-page: 525 year: 2000 ident: 10.1016/j.patcog.2019.04.014_bib0086 article-title: A comparison of document clustering techniques – volume: 20 start-page: 1027 issue: 10, October year: 1999 ident: 10.1016/j.patcog.2019.04.014_bib0019 article-title: An empirical comparison of four initialization methods for the k-means algorithm publication-title: Pattern Recognit. Lett. doi: 10.1016/S0167-8655(99)00069-0 – volume: 9 start-page: 15 issue: 1 year: 2013 ident: 10.1016/j.patcog.2019.04.014_bib0040 article-title: The k-means clustering technique: general considerations and implementation in Mathematica publication-title: Tutor. Quant. Methods Psychol. doi: 10.20982/tqmp.09.1.p015 – volume: 1 start-page: 281 year: 1967 ident: 10.1016/j.patcog.2019.04.014_bib0002 article-title: Some methods for classification and analysis of multivariate observations – volume: 36 start-page: 10223 issue: 7 year: 2009 ident: 10.1016/j.patcog.2019.04.014_bib0058 article-title: A new initialization method for categorical data clustering publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2009.01.060 – volume: 84 start-page: 88 issue: January year: 2014 ident: 10.1016/j.patcog.2019.04.014_bib0042 article-title: On k-means algorithm with the use of Mahalanobis distances publication-title: Stat. Probab. Lett. doi: 10.1016/j.spl.2013.09.026 – volume: 5 start-page: 1 issue: 13 year: 2018 ident: 10.1016/j.patcog.2019.04.014_bib0012 article-title: Efficiency of random swap clustering publication-title: J. Big Data – start-page: 680 year: 2018 ident: 10.1016/j.patcog.2019.04.014_bib0072 article-title: Random projection for k-means clustering – volume: 2 start-page: 108 issue: 1 year: 1993 ident: 10.1016/j.patcog.2019.04.014_bib0069 article-title: A comparison of several vector quantization codebook generation approaches publication-title: IEEE Trans. Image Process. doi: 10.1109/83.210871 – volume: 47 start-page: 3034 issue: 9 year: 2014 ident: 10.1016/j.patcog.2019.04.014_bib0045 article-title: Centroid index: cluster level similarity measure publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2014.03.017 – volume: 142 start-page: 68 year: 2018 ident: 10.1016/j.patcog.2019.04.014_bib0084 article-title: Density core-based clustering algorithm with dynamic scanning radius publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2017.11.025 – volume: 462 start-page: 182 year: 2018 ident: 10.1016/j.patcog.2019.04.014_bib0083 article-title: FAUM: fast Autonomous Unsupervised Multidimensional classification publication-title: Inf. Sci. doi: 10.1016/j.ins.2018.06.008 – volume: 21 start-page: 768 year: 1965 ident: 10.1016/j.patcog.2019.04.014_bib0001 article-title: Cluster analysis of multivariate data: efficiency vs. interpretability of classification publication-title: Biometrics – volume: 40 start-page: 200 year: 2013 ident: 10.1016/j.patcog.2019.04.014_bib0022 article-title: A comparative study of efficient initialization methods for the k-means clustering algorithm publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2012.07.021 – volume: 31 start-page: 651 year: 2010 ident: 10.1016/j.patcog.2019.04.014_bib0008 article-title: Data clustering: 50 years beyond K-means publication-title: Pattern Recognit. Lett. doi: 10.1016/j.patrec.2009.09.011 – volume: 12 start-page: 663 issue: 4 year: 1991 ident: 10.1016/j.patcog.2019.04.014_bib0075 article-title: Optimal quantization by matrix searching publication-title: J. Algorithms doi: 10.1016/0196-6774(91)90039-2 – volume: 28 start-page: 965 issue: 8 year: 2007 ident: 10.1016/j.patcog.2019.04.014_bib0051 article-title: A method for initialising the K-means clustering algorithm using kd-trees publication-title: Pattern Recognit. Lett. doi: 10.1016/j.patrec.2007.01.001 – volume: 8 start-page: 294 year: 2003 ident: 10.1016/j.patcog.2019.04.014_bib0029 article-title: Local optima in k-means clustering: what you don't know may hurt you publication-title: Psychol. Methods doi: 10.1037/1082-989X.8.3.294 – year: 2004 ident: 10.1016/j.patcog.2019.04.014_bib0020 article-title: Initialization of Cluster Refinement Algorithms: a review and comparative study publication-title: IEEE Int. Joint Conf. Neural Netw. – start-page: 577 year: 2011 ident: 10.1016/j.patcog.2019.04.014_bib0081 article-title: Efficient k-nearest neighbor graph construction for generic similarity measures – ident: 10.1016/j.patcog.2019.04.014_bib0024 – volume: 71 start-page: 375 year: 2017 ident: 10.1016/j.patcog.2019.04.014_bib0015 article-title: Fast density clustering strategies based on the k-means algorithm publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2017.06.023 – volume: 9 start-page: 773 issue: 5, May year: 2000 ident: 10.1016/j.patcog.2019.04.014_bib0030 article-title: Fast and memory efficient implementation of the exact PNN publication-title: IEEE Trans. Image Process. doi: 10.1109/83.841516 – volume: 38 start-page: 293 issue: 2–3 year: 1985 ident: 10.1016/j.patcog.2019.04.014_bib0026 article-title: Clustering to minimize the maximum intercluster distance publication-title: Theor. Comput. Sci. doi: 10.1016/0304-3975(85)90224-5 – volume: 9 start-page: 1337 issue: 8, August year: 2000 ident: 10.1016/j.patcog.2019.04.014_bib0089 article-title: A fast exact GLA based on code vector activity detection publication-title: IEEE Trans. Image Process. doi: 10.1109/83.855429 – volume: 5 start-page: 622 issue: 7 year: 2012 ident: 10.1016/j.patcog.2019.04.014_bib0088 publication-title: Proc. VLDB Endow. doi: 10.14778/2180912.2180915 – volume: 36 start-page: 3043 issue: 11, November year: 1997 ident: 10.1016/j.patcog.2019.04.014_bib0046 article-title: On the splitting method for VQ codebook generation publication-title: Opt. Eng. doi: 10.1117/1.601531 – volume: 28 start-page: 84 issue: 1, January year: 1980 ident: 10.1016/j.patcog.2019.04.014_bib0085 article-title: An algorithm for vector quantizer design publication-title: IEEE Trans. Commun. doi: 10.1109/TCOM.1980.1094577 – year: 2015 ident: 10.1016/j.patcog.2019.04.014_bib0043 article-title: Recent developments in model-based clustering with applications – volume: 1 start-page: 144 issue: 10 year: 1994 ident: 10.1016/j.patcog.2019.04.014_bib0057 article-title: A new initialization technique for generalized Lloyd iteration publication-title: IEEE Signal Process Lett. doi: 10.1109/97.329844 – volume: 28 start-page: 129 issue: 2 year: 1982 ident: 10.1016/j.patcog.2019.04.014_bib0003 article-title: Least squares quantization in PCM publication-title: IEEE Trans. Inf. Theory doi: 10.1109/TIT.1982.1056489 – start-page: 74 year: 2005 ident: 10.1016/j.patcog.2019.04.014_bib0065 article-title: A new algorithm for cluster initialization – start-page: 392 year: 1991 ident: 10.1016/j.patcog.2019.04.014_bib0068 article-title: A better tree-structured vector quantizer – volume: 68 start-page: 747 year: 2018 ident: 10.1016/j.patcog.2019.04.014_bib0087 article-title: Two improved k-means algorithms publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2017.08.032 – volume: 11 start-page: 19 issue: 2 year: 2018 ident: 10.1016/j.patcog.2019.04.014_bib0049 article-title: Common nearest neighbor clustering: a benchmark publication-title: Algorithms doi: 10.3390/a11020019 – volume: 32 start-page: 1701 issue: 14 year: 2011 ident: 10.1016/j.patcog.2019.04.014_bib0060 article-title: A new algorithm for initial cluster centers in k-means algorithm publication-title: Pattern Recognit. Lett. doi: 10.1016/j.patrec.2011.07.011 – volume: 58 start-page: 474 year: 2009 ident: 10.1016/j.patcog.2019.04.014_bib0064 article-title: An initialization method for the k-means algorithm using neighborhood model publication-title: Comput. Math. Appl. doi: 10.1016/j.camwa.2009.04.017 – year: 1990 ident: 10.1016/j.patcog.2019.04.014_bib0023 – volume: 83 start-page: 245 year: 2018 ident: 10.1016/j.patcog.2019.04.014_bib0034 article-title: Clustering in large data sets with the limited memory bundle method publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2018.05.028 – volume: 48 start-page: 4743 issue: 12 year: 2018 ident: 10.1016/j.patcog.2019.04.014_bib0039 article-title: K-means properties on six clustering benchmark datasets publication-title: Appl. Intel. doi: 10.1007/s10489-018-1238-7 – year: 2007 ident: 10.1016/j.patcog.2019.04.014_bib0059 article-title: K-means++: the advantages of careful seeding – year: 1974 ident: 10.1016/j.patcog.2019.04.014_bib0025 – year: 2011 ident: 10.1016/j.patcog.2019.04.014_bib0053 – volume: 1 start-page: 121 issue: 2 year: 2010 ident: 10.1016/j.patcog.2019.04.014_bib0066 article-title: Enhancing k-means clustering algorithm with improved initial center publication-title: Int. J. Comput. Sci. Inf. Technol. – volume: 61 start-page: 1045 issue: 2, February year: 2015 ident: 10.1016/j.patcog.2019.04.014_bib0005 article-title: Randomized dimensionality reduction for k-means clustering publication-title: IEEE Trans. Inf. Theory doi: 10.1109/TIT.2014.2375327 – volume: 28 start-page: 2173 issue: 8, August year: 2016 ident: 10.1016/j.patcog.2019.04.014_bib0044 article-title: Set-matching methods for external cluster validity publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2016.2551240 – volume: 37 start-page: 285 issue: 3 year: 2018 ident: 10.1016/j.patcog.2019.04.014_bib0007 article-title: Development of a data-processing method based on Bayesian k-means clustering to discriminate aneugens and clastogens in a high-content micronucleus assay publication-title: Hum. Exp. Toxicol. doi: 10.1177/0960327117695635 – volume: 24 start-page: 99 year: 2007 ident: 10.1016/j.patcog.2019.04.014_bib0021 article-title: Initializing k-means batch clustering: a critical evaluation of several techniques publication-title: J. Classification doi: 10.1007/s00357-007-0003-0 – ident: 10.1016/j.patcog.2019.04.014_bib0018 – volume: 92 start-page: 77 issue: July year: 2014 ident: 10.1016/j.patcog.2019.04.014_bib0017 article-title: WB-index: a sum-of-squares based index for cluster validity publication-title: Data Knowl. Eng. doi: 10.1016/j.datak.2014.07.008 – volume: 32 start-page: 1604 issue: 13, October year: 2011 ident: 10.1016/j.patcog.2019.04.014_bib0016 article-title: Comparison of clustering methods: a case study of text-independent speaker modeling publication-title: Pattern Recognit. Lett. doi: 10.1016/j.patrec.2011.06.023 – volume: 36 start-page: 451 year: 2003 ident: 10.1016/j.patcog.2019.04.014_bib0028 article-title: The global k-means clustering algorithm publication-title: Pattern Recognit. doi: 10.1016/S0031-3203(02)00060-2 – volume: 28 start-page: 1875 issue: 11, November year: 2006 ident: 10.1016/j.patcog.2019.04.014_bib0047 article-title: Fast agglomerative clustering using a k-nearest neighbor graph publication-title: IEEE Trans. Pattern Anal. Mach. Intel. doi: 10.1109/TPAMI.2006.227 – volume: 47 start-page: 1917 year: 2014 ident: 10.1016/j.patcog.2019.04.014_bib0004 article-title: Robust level set image segmentation via a local correntropy-based k-means clustering publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2013.11.014 – volume: 38 start-page: 293 issue: 2–3 year: 1985 ident: 10.1016/j.patcog.2019.04.014_bib0054 article-title: Clustering to minimize the maximum intercluster distance publication-title: Theor. Comput. Sci. doi: 10.1016/0304-3975(85)90224-5 – volume: 82 start-page: 16 year: 2018 ident: 10.1016/j.patcog.2019.04.014_bib0037 article-title: A novel and simple strategy for evolving prototype based clustering publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2018.04.020 – volume: 17 start-page: 451 issue: 5 year: 1996 ident: 10.1016/j.patcog.2019.04.014_bib0076 article-title: New methods for the initialisation of clusters publication-title: Pattern Recognit. Lett. doi: 10.1016/0167-8655(95)00119-0 – start-page: 343 year: 2018 ident: 10.1016/j.patcog.2019.04.014_bib0082 article-title: Dimensionally distributed density estimation – volume: 58 start-page: 236 issue: 301 year: 1963 ident: 10.1016/j.patcog.2019.04.014_bib0027 article-title: Hierarchical grouping to optimize an objective function publication-title: J. Am. Stat. Assoc. doi: 10.1080/01621459.1963.10500845 – volume: 28 start-page: 100 issue: 1 year: 1979 ident: 10.1016/j.patcog.2019.04.014_bib0062 article-title: Algorithm AS 136: a k-means clustering algorithm publication-title: J. R. Stat. Soc. C – year: 1973 ident: 10.1016/j.patcog.2019.04.014_bib0032 – volume: 86 start-page: 344 year: 2019 ident: 10.1016/j.patcog.2019.04.014_bib0038 article-title: Multi-view intact space clustering publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2018.09.016 – volume: 27 start-page: 3 year: 2010 ident: 10.1016/j.patcog.2019.04.014_bib0055 article-title: Intelligent choice of the number of clusters in k-means clustering: an experimental study with different cluster spreads publication-title: J. Classification doi: 10.1007/s00357-010-9049-5 – volume: 40 start-page: 576 issue: September year: 1993 ident: 10.1016/j.patcog.2019.04.014_bib0073 article-title: A fast mean-distance-ordered partial codebook search algorithm for image vector quantization publication-title: IEEE Trans. Circuits Syst. doi: 10.1109/82.257335 – volume: vol. 3540 start-page: 872 year: 2005 ident: 10.1016/j.patcog.2019.04.014_bib0074 article-title: Clustering based on principal curve – volume: 23 start-page: 1 issue: 1, October year: 2018 ident: 10.1016/j.patcog.2019.04.014_bib0080 article-title: Constructing a high-dimensional kNN-graph using a Z-order curve publication-title: ACM J. Exp. Algorithmics doi: 10.1145/3274656 – volume: 1 start-page: 99 year: 1991 ident: 10.1016/j.patcog.2019.04.014_bib0052 article-title: Efficient portable combined Tausworthe random number generators publication-title: ACM Trans. Model. Comput. Simul. doi: 10.1145/116890.116892 – volume: 83 start-page: 230 year: 2018 ident: 10.1016/j.patcog.2019.04.014_bib0035 article-title: Grouping points by shared subspaces for effective subspace clustering publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2018.05.027 – volume: 83 start-page: 52 year: 2018 ident: 10.1016/j.patcog.2019.04.014_bib0033 article-title: Clustering via binary embedding publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2018.05.011 – volume: 12 start-page: 153 issue: 2, March year: 1967 ident: 10.1016/j.patcog.2019.04.014_bib0048 article-title: A clustering technique for summarizing multivariate data publication-title: Syst. Res. Behav. Sci. doi: 10.1002/bs.3830120210 – year: 2016 ident: 10.1016/j.patcog.2019.04.014_bib0056 article-title: Initialization of big data clustering using distributionally balanced folding, Proceedings of the European Symposium on Artificial Neural Networks publication-title: Comput. Intel. Mach. Learn.-ESANN – volume: 26 issue: 07 year: 2012 ident: 10.1016/j.patcog.2019.04.014_bib0071 article-title: Deterministic initialization of the k-means algorithm using hierarchical clustering publication-title: Int. J. Pattern Recognit Artif Intell. doi: 10.1142/S0218001412500188 – volume: 20 start-page: 728 issue: 4, August year: 2012 ident: 10.1016/j.patcog.2019.04.014_bib0041 article-title: The k-means-type algorithms versus imbalanced data distributions publication-title: IEEE Trans. Fuzzy Syst. doi: 10.1109/TFUZZ.2011.2182354 – volume: 2 start-page: 325 issue: 4 year: 1998 ident: 10.1016/j.patcog.2019.04.014_bib0070 article-title: Principal direction divisive partitioning publication-title: Data Min. Knowl. Discov. doi: 10.1023/A:1009740529316 – volume: 15 issue: 13 year: 2015 ident: 10.1016/j.patcog.2019.04.014_bib0036 article-title: Automatic selection of partitioning schemes for phylogenetic analyses using iterative k-means clustering of site rates publication-title: BMC Evol. Biol. – volume: 24 start-page: 734 issue: 6 year: 2002 ident: 10.1016/j.patcog.2019.04.014_bib0079 article-title: Density-based multiscale data condensation publication-title: IEEE Trans. Pattern Anal. Mach. Intel. doi: 10.1109/TPAMI.2002.1008381 – year: 2014 ident: 10.1016/j.patcog.2019.04.014_bib0061 article-title: Histogram-based method for effective initialization of the k-means clustering algorithm |
| SSID | ssj0017142 |
| Score | 2.6922736 |
| Snippet | •K-means clustering algorithm can be significantly improved by using a better initialization technique, and by repeating (re-starting) the algorithm.•When the... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 95 |
| SubjectTerms | Clustering accuracy Clustering algorithms Initialization K-means Prototype selection |
| Title | How much can k-means be improved by using better initialization and repeats? |
| URI | https://dx.doi.org/10.1016/j.patcog.2019.04.014 |
| Volume | 93 |
| WOSCitedRecordID | wos000472697800008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: ScienceDirect database customDbUrl: eissn: 1873-5142 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017142 issn: 0031-3203 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LTxsxELZa6KEX6FMF2sqH3iJXu2tv1ntCCIHaCqFIpSi3lV_bJiWbKA8E_56xx5sEqOhD6mW12sTZaObzeDz-ZoaQD6JbJ07kksHqqpkoDWfSWrjToH9uYEsUeh2enxSnp7LfL3uxoMIstBMomkZeXZWT_6pqeAbK9qmzf6Hu5Y_CA7gHpcMV1A7XP1K8bxI3Wpgfns_V-clGDhajjnY-H3I6vkSHcxEiBDqk8nQGnj-kLmJCJhLO3QRs9OwO668XanH6_JdIOlod4R_jibtokB3QU7PBMnYDC69qxkOFAejRYD3QkK6YVDH61WbArOhGwaLylPEsQSPl0IjKgjNwxG5Z2ZKvmUnsqxkX3BR51PdsOYYVhh8nsCaNv3sWXhmq0mLS6Z0q2V-xCKXPyeK-aJ58TDazIi_B0G0efD7qf1keLRWpwBLy8Y-3-ZSB9Hf_Xb_2V9Z8kLNnZCtuHugBKv05eeSaF2S7bcxBo51-SU4AA9RjgAIGaMQA1Y62GKD6mgYMUMQAvY0BChigEQP7r8i346Ozw08sts1gBrzpOavTXBtdW5hqWinO6zxzpqhFwpUP8lkHHxvYrRSlNUZLJ3VmjYKpbOva5Fbx12SjGTfuDaGlL86UdJ3KHRemzjR4606avGudEFqYHcJb4VQm1pT3rU0uqpY8OKxQpJUXaZWICkS6Q9hy1ARrqvzm-0Ur9yr6hejvVQCVB0fu_vPIPfJ0NQfeko35dOHekSfmcj6YTd9HTN0AYQuKLw |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=How+much+can+k-means+be+improved+by+using+better+initialization+and+repeats%3F&rft.jtitle=Pattern+recognition&rft.au=Fr%C3%A4nti%2C+Pasi&rft.au=Sieranoja%2C+Sami&rft.date=2019-09-01&rft.pub=Elsevier+Ltd&rft.issn=0031-3203&rft.eissn=1873-5142&rft.volume=93&rft.spage=95&rft.epage=112&rft_id=info:doi/10.1016%2Fj.patcog.2019.04.014&rft.externalDocID=S0031320319301608 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-3203&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-3203&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-3203&client=summon |