A comparison of random forest variable selection methods for classification prediction modeling
•We compare performance for random forest variable selection methods.•VSURF or Jiang's method are preferable for most datasets.•varSelRF or Boruta perform well for data with >50 predictors.•Methods with conditional random forest usually have similar performance.•Type of methods, test- or per...
Saved in:
| Published in | Expert systems with applications Vol. 134; pp. 93 - 101 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
New York
Elsevier Ltd
15.11.2019
Elsevier BV |
| Subjects | |
| Online Access | Get full text |
| ISSN | 0957-4174 1873-6793 |
| DOI | 10.1016/j.eswa.2019.05.028 |
Cover
Loading…
| Abstract | •We compare performance for random forest variable selection methods.•VSURF or Jiang's method are preferable for most datasets.•varSelRF or Boruta perform well for data with >50 predictors.•Methods with conditional random forest usually have similar performance.•Type of methods, test- or performance-based, is not likely to impact performance.
Random forest classification is a popular machine learning method for developing prediction models in many research settings. Often in prediction modeling, a goal is to reduce the number of variables needed to obtain a prediction in order to reduce the burden of data collection and improve efficiency. Several variable selection methods exist for the setting of random forest classification; however, there is a paucity of literature to guide users as to which method may be preferable for different types of datasets. Using 311 classification datasets freely available online, we evaluate the prediction error rates, number of variables, computation times and area under the receiver operating curve for many random forest variable selection methods. We compare random forest variable selection methods for different types of datasets (datasets with binary outcomes, datasets with many predictors, and datasets with imbalanced outcomes) and for different types of methods (standard random forest versus conditional random forest methods and test based versus performance based methods). Based on our study, the best variable selection methods for most datasets are Jiang's method and the method implemented in the VSURF R package. For datasets with many predictors, the methods implemented in the R packages varSelRF and Boruta are preferable due to computational efficiency. A significant contribution of this study is the ability to assess different variable selection techniques in the setting of random forest classification in order to identify preferable methods based on applications in expert and intelligent systems. |
|---|---|
| AbstractList | Random forest classification is a popular machine learning method for developing prediction models in many research settings. Often in prediction modeling, a goal is to reduce the number of variables needed to obtain a prediction in order to reduce the burden of data collection and improve efficiency. Several variable selection methods exist for the setting of random forest classification; however, there is a paucity of literature to guide users as to which method may be preferable for different types of datasets. Using 311 classification datasets freely available online, we evaluate the prediction error rates, number of variables, computation times and area under the receiver operating curve for many random forest variable selection methods. We compare random forest variable selection methods for different types of datasets (datasets with binary outcomes, datasets with many predictors, and datasets with imbalanced outcomes) and for different types of methods (standard random forest versus conditional random forest methods and test based versus performance based methods). Based on our study, the best variable selection methods for most datasets are Jiang's method and the method implemented in the VSURF R package. For datasets with many predictors, the methods implemented in the R packages varSelRF and Boruta are preferable due to computational efficiency. A significant contribution of this study is the ability to assess different variable selection techniques in the setting of random forest classification in order to identify preferable methods based on applications in expert and intelligent systems.Random forest classification is a popular machine learning method for developing prediction models in many research settings. Often in prediction modeling, a goal is to reduce the number of variables needed to obtain a prediction in order to reduce the burden of data collection and improve efficiency. Several variable selection methods exist for the setting of random forest classification; however, there is a paucity of literature to guide users as to which method may be preferable for different types of datasets. Using 311 classification datasets freely available online, we evaluate the prediction error rates, number of variables, computation times and area under the receiver operating curve for many random forest variable selection methods. We compare random forest variable selection methods for different types of datasets (datasets with binary outcomes, datasets with many predictors, and datasets with imbalanced outcomes) and for different types of methods (standard random forest versus conditional random forest methods and test based versus performance based methods). Based on our study, the best variable selection methods for most datasets are Jiang's method and the method implemented in the VSURF R package. For datasets with many predictors, the methods implemented in the R packages varSelRF and Boruta are preferable due to computational efficiency. A significant contribution of this study is the ability to assess different variable selection techniques in the setting of random forest classification in order to identify preferable methods based on applications in expert and intelligent systems. •We compare performance for random forest variable selection methods.•VSURF or Jiang's method are preferable for most datasets.•varSelRF or Boruta perform well for data with >50 predictors.•Methods with conditional random forest usually have similar performance.•Type of methods, test- or performance-based, is not likely to impact performance. Random forest classification is a popular machine learning method for developing prediction models in many research settings. Often in prediction modeling, a goal is to reduce the number of variables needed to obtain a prediction in order to reduce the burden of data collection and improve efficiency. Several variable selection methods exist for the setting of random forest classification; however, there is a paucity of literature to guide users as to which method may be preferable for different types of datasets. Using 311 classification datasets freely available online, we evaluate the prediction error rates, number of variables, computation times and area under the receiver operating curve for many random forest variable selection methods. We compare random forest variable selection methods for different types of datasets (datasets with binary outcomes, datasets with many predictors, and datasets with imbalanced outcomes) and for different types of methods (standard random forest versus conditional random forest methods and test based versus performance based methods). Based on our study, the best variable selection methods for most datasets are Jiang's method and the method implemented in the VSURF R package. For datasets with many predictors, the methods implemented in the R packages varSelRF and Boruta are preferable due to computational efficiency. A significant contribution of this study is the ability to assess different variable selection techniques in the setting of random forest classification in order to identify preferable methods based on applications in expert and intelligent systems. Random forest classification is a popular machine learning method for developing prediction models in many research settings. Often in prediction modeling, a goal is to reduce the number of variables needed to obtain a prediction in order to reduce the burden of data collection and improve efficiency. Several variable selection methods exist for the setting of random forest classification; however, there is a paucity of literature to guide users as to which method may be preferable for different types of datasets. Using 311 classification datasets freely available online, we evaluate the prediction error rates, number of variables, computation times and area under the receiver operating curve for many random forest variable selection methods. We compare random forest variable selection methods for different types of datasets (datasets with binary outcomes, datasets with many predictors, and datasets with imbalanced outcomes) and for different types of methods (standard random forest versus conditional random forest methods and test based versus performance based methods). Based on our study, the best variable selection methods for most datasets are Jiang’s method and the method implemented in the VSURF R package. For datasets with many predictors, the methods implemented in the R packages varSelRF and Boruta are preferable due to computational efficiency. A significant contribution of this study is the ability to assess different variable selection techniques in the setting of random forest classification in order to identify preferable methods based on applications in expert and intelligent systems. Random forest classification is a popular machine learning method for developing prediction models in many research settings. Often in prediction modeling, a goal is to reduce the number of variables needed to obtain a prediction in order to reduce the burden of data collection and improve efficiency. Several variable selection methods exist for the setting of random forest classification; however, there is a paucity of literature to guide users as to which method may be preferable for different types of datasets. Using 311 classification datasets freely available online, we evaluate the prediction error rates, number of variables, computation times and area under the receiver operating curve for many random forest variable selection methods. We compare random forest variable selection methods for different types of datasets (datasets with binary outcomes, datasets with many predictors, and datasets with imbalanced outcomes) and for different types of methods (standard random forest versus conditional random forest methods and test based versus performance based methods). Based on our study, the best variable selection methods for most datasets are Jiang's method and the method implemented in the VSURF R package. For datasets with many predictors, the methods implemented in the R packages varSelRF and Boruta are preferable due to computational efficiency. A significant contribution of this study is the ability to assess different variable selection techniques in the setting of random forest classification in order to identify preferable methods based on applications in expert and intelligent systems. |
| Author | Speiser, Jaime Lynn Ip, Edward Miller, Michael E. Tooze, Janet |
| AuthorAffiliation | c Department of Biostatistical Sciences, Wake Forest School of Medicine, Winston-Salem, NC 27157, USA a Department of Biostatistical Sciences, Wake Forest School of Medicine, Winston-Salem, NC 27157, USA b Department of Biostatistical Sciences, Wake Forest School of Medicine, Winston-Salem, NC 27157, USA d Department of Biostatistical Sciences, Wake Forest School of Medicine, Winston-Salem, NC 27157, USA |
| AuthorAffiliation_xml | – name: b Department of Biostatistical Sciences, Wake Forest School of Medicine, Winston-Salem, NC 27157, USA – name: d Department of Biostatistical Sciences, Wake Forest School of Medicine, Winston-Salem, NC 27157, USA – name: c Department of Biostatistical Sciences, Wake Forest School of Medicine, Winston-Salem, NC 27157, USA – name: a Department of Biostatistical Sciences, Wake Forest School of Medicine, Winston-Salem, NC 27157, USA |
| Author_xml | – sequence: 1 givenname: Jaime Lynn surname: Speiser fullname: Speiser, Jaime Lynn email: jspeiser@wakehealth.edu – sequence: 2 givenname: Michael E. surname: Miller fullname: Miller, Michael E. email: mmiller@wakehealth.edu – sequence: 3 givenname: Janet surname: Tooze fullname: Tooze, Janet email: jtooze@wakehealth.edu – sequence: 4 givenname: Edward surname: Ip fullname: Ip, Edward email: eip@wakehealth.edu |
| BookMark | eNp9kUtr3DAUhUVJaSZp_0BXhm668VRvWVAKIfQFgW7a9UWWrxMNtjSVPBP676t5dNEsshLonnOkc78rchFTRELeMrpmlOkPmzWWR7fmlNk1VWvKuxdkxTojWm2suCArapVpJTPyklyVsqGUGUrNK3IpuNWdEGpF4Kbxad66HEqKTRqb7OKQ5mZMGcvS7OvA9RM2BSf0S6iaGZeHNJSDovGTKyWMwbvjaJtxCGdVGnAK8f41eTm6qeCb83lNfn35_PP2W3v34-v325u71ismlpabTihr-5HTwWs5KtnLDrUWrN7pXlJtpdV977mWXS3PBttpZhhn4zgotOKafDrlbnf9jIPHuGQ3wTaH2eU_kFyA_ycxPMB92oNRtBOM1oD354Ccfu9qd5hD8ThNLmLaFeBSKmuEoKZK3z2RbtIux1oPeP0fU4wdA7uTyudUSsYRfFiOe6rvhwkYhQNF2MCBIhwoAlVQKVYrf2L91-NZ08eTCeua9wEzFB8w-ookV3QwpPCc_S-7R7gR |
| CitedBy_id | crossref_primary_10_3389_fendo_2023_1305473 crossref_primary_10_1007_s42044_023_00166_5 crossref_primary_10_3390_diagnostics13223441 crossref_primary_10_1007_s12206_024_1101_1 crossref_primary_10_3390_f14091889 crossref_primary_10_1039_D4NR01861C crossref_primary_10_1108_IJESM_12_2019_0009 crossref_primary_10_3390_rs15194644 crossref_primary_10_3390_rs15194886 crossref_primary_10_1109_ACCESS_2024_3419009 crossref_primary_10_1016_j_cj_2023_01_002 crossref_primary_10_1177_1352458520968038 crossref_primary_10_1016_j_jenvman_2024_121921 crossref_primary_10_3390_foods13111676 crossref_primary_10_1016_j_apsoil_2025_105995 crossref_primary_10_1016_j_jksuci_2022_11_008 crossref_primary_10_1016_j_ijhm_2024_103711 crossref_primary_10_3390_e24081157 crossref_primary_10_1007_s00357_024_09494_y crossref_primary_10_1016_j_revpalbo_2023_105041 crossref_primary_10_1007_s40808_023_01895_z crossref_primary_10_32604_cmc_2021_018236 crossref_primary_10_3390_rs16173349 crossref_primary_10_3389_fgene_2023_1210722 crossref_primary_10_1111_gcb_15514 crossref_primary_10_3389_fonc_2023_1147805 crossref_primary_10_3390_jpm13071065 crossref_primary_10_1080_01431161_2024_2387132 crossref_primary_10_1016_j_procs_2023_10_027 crossref_primary_10_1016_j_energy_2023_129550 crossref_primary_10_2139_ssrn_5011125 crossref_primary_10_1016_j_foreco_2021_119631 crossref_primary_10_1016_j_ijmedinf_2024_105660 crossref_primary_10_1109_ACCESS_2024_3425727 crossref_primary_10_1016_j_forsciint_2021_110998 crossref_primary_10_1016_j_compchemeng_2024_108805 crossref_primary_10_1093_ehjdh_ztad059 crossref_primary_10_2174_1574893617666220221120618 crossref_primary_10_1111_exsy_13735 crossref_primary_10_3390_s24030898 crossref_primary_10_1016_j_jwpe_2024_105717 crossref_primary_10_3389_fmed_2022_807382 crossref_primary_10_1016_j_envpol_2022_120926 crossref_primary_10_1021_acsomega_4c09634 crossref_primary_10_1038_s41388_024_03123_z crossref_primary_10_1186_s12933_022_01561_1 crossref_primary_10_1109_TGRS_2024_3395438 crossref_primary_10_1016_j_jairtraman_2024_102632 crossref_primary_10_1109_ACCESS_2024_3467996 crossref_primary_10_1016_j_ijmedinf_2023_105143 crossref_primary_10_3390_agronomy13071796 crossref_primary_10_3389_fenvs_2022_1054235 crossref_primary_10_1002_mmce_23191 crossref_primary_10_1038_s41598_021_91941_6 crossref_primary_10_1007_s10238_023_01164_4 crossref_primary_10_3389_fpls_2022_945291 crossref_primary_10_1016_j_eswa_2023_119897 crossref_primary_10_1177_14604582241272771 crossref_primary_10_1016_j_jhydrol_2024_130742 crossref_primary_10_1111_lang_12667 crossref_primary_10_1093_comjnl_bxab145 crossref_primary_10_3390_biom14080911 crossref_primary_10_1186_s13007_023_00982_7 crossref_primary_10_1109_TGRS_2024_3383217 crossref_primary_10_3390_drones9010032 crossref_primary_10_3389_fncom_2024_1435956 crossref_primary_10_3390_app10228281 crossref_primary_10_1109_TED_2024_3378220 crossref_primary_10_3390_math11081856 crossref_primary_10_3390_a15110431 crossref_primary_10_1111_ffe_14410 crossref_primary_10_1007_s12145_025_01757_5 crossref_primary_10_1007_s11571_024_10136_7 crossref_primary_10_3390_app12136569 crossref_primary_10_1186_s13244_023_01477_8 crossref_primary_10_1088_1402_4896_ad6fde crossref_primary_10_1016_j_csda_2022_107689 crossref_primary_10_3390_molecules28020809 crossref_primary_10_1016_j_compag_2022_107113 crossref_primary_10_1016_j_wroa_2025_100333 crossref_primary_10_1109_TIM_2024_3470961 crossref_primary_10_1016_j_atech_2024_100734 crossref_primary_10_1016_j_knosys_2020_106673 crossref_primary_10_1038_s41598_023_36333_8 crossref_primary_10_1016_j_eswa_2021_115781 crossref_primary_10_1088_2632_2153_ad020e crossref_primary_10_1016_j_asoc_2024_111523 crossref_primary_10_3390_aerospace10030291 crossref_primary_10_1016_j_fuel_2024_131321 crossref_primary_10_1186_s12920_023_01462_6 crossref_primary_10_1016_j_carbpol_2021_117766 crossref_primary_10_7235_HORT_20240022 crossref_primary_10_1007_s00521_023_08606_w crossref_primary_10_3233_JIFS_221412 crossref_primary_10_3390_diagnostics13172835 crossref_primary_10_1016_j_catena_2022_106703 crossref_primary_10_1002_aisy_202400828 crossref_primary_10_1016_j_ress_2024_110652 crossref_primary_10_1016_j_istruc_2025_108227 crossref_primary_10_1002_rra_4245 crossref_primary_10_1016_j_agwat_2022_108115 crossref_primary_10_1016_j_tifs_2025_104964 crossref_primary_10_3389_fcimb_2022_893294 crossref_primary_10_1007_s11255_023_03662_6 crossref_primary_10_1038_s41598_024_81502_y crossref_primary_10_1016_j_agsy_2023_103846 crossref_primary_10_3390_app13179706 crossref_primary_10_1186_s12889_024_17803_8 crossref_primary_10_1007_s11069_023_06298_y crossref_primary_10_1109_TAI_2023_3240114 crossref_primary_10_1016_j_jisa_2025_103984 crossref_primary_10_1016_j_ces_2024_121164 crossref_primary_10_2196_58812 crossref_primary_10_1016_j_ecoinf_2024_102479 crossref_primary_10_1142_S0129065721500209 crossref_primary_10_3390_jmse12020288 crossref_primary_10_1088_1742_6596_2483_1_012044 crossref_primary_10_3389_fnins_2021_710133 crossref_primary_10_1016_j_foodres_2021_110817 crossref_primary_10_1007_s11042_023_14979_w crossref_primary_10_3390_en13164236 crossref_primary_10_3390_math11071636 crossref_primary_10_3390_app13116818 crossref_primary_10_1016_j_agwat_2024_108946 crossref_primary_10_3390_soilsystems8010022 crossref_primary_10_3390_su17062627 crossref_primary_10_1016_j_jenvman_2023_118898 crossref_primary_10_1016_j_scitotenv_2024_175632 crossref_primary_10_3389_fmed_2023_1292761 crossref_primary_10_1080_0305215X_2023_2255527 crossref_primary_10_1080_17480930_2025_2459238 crossref_primary_10_1109_ACCESS_2020_2971591 crossref_primary_10_3389_fonc_2023_1244585 crossref_primary_10_1016_j_scitotenv_2023_166863 crossref_primary_10_1590_1809_4430_eng_agric_v42nepe20210153_2022 crossref_primary_10_1057_s41271_022_00363_9 crossref_primary_10_1098_rsos_211399 crossref_primary_10_1016_j_microc_2022_107928 crossref_primary_10_3390_electronics13122345 crossref_primary_10_1016_j_jag_2020_102236 crossref_primary_10_3390_agronomy13123079 crossref_primary_10_1080_17538947_2023_2270459 crossref_primary_10_1016_j_dim_2024_100086 crossref_primary_10_1515_htmp_2022_0261 crossref_primary_10_1016_j_jmgm_2024_108818 crossref_primary_10_1080_01431161_2024_2371618 crossref_primary_10_1155_2024_1635337 crossref_primary_10_1108_IMEFM_08_2020_0408 crossref_primary_10_1016_j_envres_2023_117755 crossref_primary_10_1016_j_inffus_2023_101970 crossref_primary_10_1016_j_scitotenv_2024_171097 crossref_primary_10_1136_bmjopen_2022_062596 crossref_primary_10_1016_j_dajour_2025_100550 crossref_primary_10_1016_j_ijin_2020_12_006 crossref_primary_10_1111_age_13396 crossref_primary_10_1016_j_jpowsour_2021_229561 crossref_primary_10_1016_j_nanoen_2025_110897 crossref_primary_10_32604_iasc_2023_031987 crossref_primary_10_1007_s10515_023_00388_8 crossref_primary_10_1021_acs_est_2c03027 crossref_primary_10_1016_j_chroma_2024_465330 crossref_primary_10_1016_j_procs_2024_11_184 crossref_primary_10_1063_5_0025594 crossref_primary_10_1016_j_jenvman_2024_120829 crossref_primary_10_32604_cmc_2020_011969 crossref_primary_10_1016_j_idairyj_2024_106143 crossref_primary_10_1109_JSTARS_2024_3394574 crossref_primary_10_2478_pomr_2025_0008 crossref_primary_10_3389_ffgc_2022_1007473 crossref_primary_10_1016_j_ecoinf_2023_102143 crossref_primary_10_1186_s12874_023_02023_2 crossref_primary_10_3390_info14040217 crossref_primary_10_1016_j_ijbiomac_2023_126871 crossref_primary_10_2139_ssrn_3922636 crossref_primary_10_1016_j_measurement_2025_116954 crossref_primary_10_48084_etasr_7774 crossref_primary_10_1073_pnas_2405160121 crossref_primary_10_1007_s41064_024_00329_4 crossref_primary_10_1016_j_jenvman_2024_121907 crossref_primary_10_1016_j_rvsc_2024_105201 crossref_primary_10_1016_j_scitotenv_2023_164004 crossref_primary_10_1007_s11069_024_06521_4 crossref_primary_10_1016_j_sna_2024_115265 crossref_primary_10_3390_rs14143260 crossref_primary_10_2166_hydro_2023_246 crossref_primary_10_1002_joom_1228 crossref_primary_10_1016_j_fsigen_2022_102722 crossref_primary_10_2196_52691 crossref_primary_10_17392_1684_23 crossref_primary_10_3390_buildings14030615 crossref_primary_10_3390_electronics11193166 crossref_primary_10_1016_j_eswa_2021_115025 crossref_primary_10_1161_HYPERTENSIONAHA_124_23817 crossref_primary_10_3390_drones9040235 crossref_primary_10_1080_07038992_2020_1789852 crossref_primary_10_3390_en15093198 crossref_primary_10_1515_geo_2022_0436 crossref_primary_10_1007_s10668_023_03131_1 crossref_primary_10_1016_j_cscm_2023_e02766 crossref_primary_10_3390_f14071357 crossref_primary_10_1016_j_scitotenv_2022_154412 crossref_primary_10_1016_j_scitotenv_2024_170246 crossref_primary_10_1016_j_ecolind_2023_109998 crossref_primary_10_1016_j_aej_2025_01_067 crossref_primary_10_1016_j_jksus_2023_102792 crossref_primary_10_1590_s1678_3921_pab2022_v57_03015 crossref_primary_10_3390_batteries10040139 crossref_primary_10_3233_THC_220295 crossref_primary_10_1016_j_ecoenv_2024_117210 crossref_primary_10_3390_f14071361 crossref_primary_10_3390_jrfm17030104 crossref_primary_10_1016_j_eswa_2023_121490 crossref_primary_10_1088_1361_648X_ad6bdb crossref_primary_10_1016_j_energy_2024_132572 crossref_primary_10_1007_s10489_021_02762_z crossref_primary_10_3390_app15031343 crossref_primary_10_24883_IberoamericanIC_v13i_439 crossref_primary_10_1016_j_agrformet_2023_109757 crossref_primary_10_1080_09593330_2024_2415722 crossref_primary_10_1109_JSTARS_2024_3522662 crossref_primary_10_1177_20552076231178425 crossref_primary_10_1007_s13042_024_02197_1 crossref_primary_10_1016_j_ecolind_2025_113121 crossref_primary_10_1016_j_acags_2022_100104 crossref_primary_10_1016_j_pediatrneurol_2025_03_007 crossref_primary_10_1016_j_rse_2024_114454 crossref_primary_10_1080_14942119_2024_2398943 crossref_primary_10_1016_j_undsp_2023_01_006 crossref_primary_10_1016_j_ejso_2023_107113 crossref_primary_10_3233_IDT_240041 crossref_primary_10_3390_rs15051404 crossref_primary_10_1016_j_scitotenv_2024_178186 crossref_primary_10_1016_j_aap_2025_107990 crossref_primary_10_1002_mde_3345 crossref_primary_10_2478_amns_2025_0805 crossref_primary_10_1007_s10462_022_10171_y crossref_primary_10_1155_2023_7798674 crossref_primary_10_1016_j_egycc_2024_100169 crossref_primary_10_1038_s41598_023_51053_9 crossref_primary_10_3389_fpls_2022_1020309 crossref_primary_10_1007_s00262_021_03076_2 crossref_primary_10_1016_j_ecolind_2022_108599 crossref_primary_10_3390_rs12071210 crossref_primary_10_1038_s41598_023_45462_z crossref_primary_10_2139_ssrn_4833804 crossref_primary_10_1016_j_ecoinf_2024_102610 crossref_primary_10_1016_j_saa_2024_124693 crossref_primary_10_1109_ACCESS_2019_2962515 crossref_primary_10_3390_healthcare9020138 crossref_primary_10_3390_horticulturae9121317 crossref_primary_10_3390_rs15184492 crossref_primary_10_1016_j_compenvurbsys_2021_101637 crossref_primary_10_1016_j_eswa_2024_125940 crossref_primary_10_1007_s11356_023_31022_5 crossref_primary_10_1109_TMECH_2023_3322269 crossref_primary_10_1155_2022_5790185 crossref_primary_10_1371_journal_pone_0307332 crossref_primary_10_1109_TASE_2023_3321049 crossref_primary_10_3390_w15193369 crossref_primary_10_3390_telecom4030025 crossref_primary_10_1093_braincomms_fcab164 crossref_primary_10_1016_j_desal_2024_117850 crossref_primary_10_1007_s00170_024_14585_6 crossref_primary_10_1111_deci_12650 crossref_primary_10_25046_aj080303 crossref_primary_10_1038_s41612_024_00833_9 crossref_primary_10_3390_rs12233850 crossref_primary_10_3390_ani13121959 crossref_primary_10_3390_app13137872 crossref_primary_10_1186_s13020_024_01026_5 crossref_primary_10_1038_s41598_023_47783_5 crossref_primary_10_1080_03036758_2024_2329228 crossref_primary_10_1016_j_tranon_2022_101367 crossref_primary_10_3390_biomedinformatics3040057 crossref_primary_10_1002_gj_4683 crossref_primary_10_1002_edn3_70001 crossref_primary_10_3390_diagnostics13020288 crossref_primary_10_1016_j_jastp_2024_106381 crossref_primary_10_1080_23311975_2025_2451127 crossref_primary_10_2139_ssrn_4165885 crossref_primary_10_3389_fmolb_2024_1483326 crossref_primary_10_3390_rs12081270 crossref_primary_10_1016_j_foodcont_2025_111219 crossref_primary_10_1016_j_geoen_2023_212335 crossref_primary_10_1177_03611981211033295 crossref_primary_10_1016_j_ijhydene_2021_08_003 crossref_primary_10_47456_bjpe_v9i4_42073 crossref_primary_10_1016_j_coldregions_2021_103421 crossref_primary_10_1109_TCYB_2023_3295852 crossref_primary_10_1016_j_foreco_2025_122619 crossref_primary_10_1109_ACCESS_2023_3284678 crossref_primary_10_1142_S0219686725500179 crossref_primary_10_1016_j_marpolbul_2025_117564 crossref_primary_10_1007_s12031_023_02147_6 crossref_primary_10_1186_s12890_023_02499_0 crossref_primary_10_3390_rs13050998 crossref_primary_10_3389_fnins_2021_800764 crossref_primary_10_3390_rs13204092 crossref_primary_10_3390_rs13204091 crossref_primary_10_1080_0969594X_2025_2457687 crossref_primary_10_1007_s40195_024_01803_z crossref_primary_10_1038_s41598_025_92777_0 crossref_primary_10_1016_j_measurement_2025_117072 crossref_primary_10_1016_j_indcrop_2023_116718 crossref_primary_10_1038_s41598_024_51988_7 crossref_primary_10_3390_app12168156 crossref_primary_10_1016_j_heliyon_2024_e37650 crossref_primary_10_1016_j_corsci_2025_112875 crossref_primary_10_1007_s10614_024_10808_w crossref_primary_10_1093_gastro_goad014 crossref_primary_10_1016_j_jhazmat_2025_137276 crossref_primary_10_3390_forecast6040051 crossref_primary_10_1016_j_bspc_2021_102784 crossref_primary_10_1016_j_compeleceng_2024_109611 crossref_primary_10_3390_app15010250 crossref_primary_10_1016_j_micres_2025_128109 crossref_primary_10_1016_j_chemosphere_2023_138434 crossref_primary_10_1016_j_energy_2023_129954 crossref_primary_10_1016_j_catena_2023_107754 crossref_primary_10_1016_j_gce_2024_08_008 crossref_primary_10_2478_rrlm_2023_0023 crossref_primary_10_3390_cancers15123237 crossref_primary_10_1016_j_foodchem_2023_136915 crossref_primary_10_21595_jme_2024_24408 crossref_primary_10_1016_j_iswa_2024_200472 crossref_primary_10_3390_diagnostics13203204 crossref_primary_10_1016_j_ijdrr_2024_104901 crossref_primary_10_1016_j_jclepro_2024_144058 crossref_primary_10_1007_s41064_022_00219_7 crossref_primary_10_1155_adce_1832390 crossref_primary_10_3390_f14061193 crossref_primary_10_3389_fnins_2024_1380886 crossref_primary_10_1002_sam_11705 crossref_primary_10_3390_agronomy14112688 crossref_primary_10_1002_jocb_1524 crossref_primary_10_1002_clc_23963 crossref_primary_10_3390_en16073184 crossref_primary_10_1016_j_exer_2023_109726 crossref_primary_10_1186_s42408_023_00233_z crossref_primary_10_1007_s00500_024_09669_0 crossref_primary_10_1186_s12944_024_02141_w crossref_primary_10_1016_j_cities_2024_105631 crossref_primary_10_1088_2752_664X_ad4bec crossref_primary_10_1109_TIM_2024_3470252 crossref_primary_10_1016_j_scs_2025_106277 crossref_primary_10_3390_su151813852 crossref_primary_10_1016_j_acra_2024_04_012 crossref_primary_10_17671_gazibtd_1424960 crossref_primary_10_3390_jtaer18040110 crossref_primary_10_1080_19475705_2024_2314565 crossref_primary_10_3390_w12113231 crossref_primary_10_1016_j_agee_2023_108599 crossref_primary_10_1016_j_ins_2023_120047 crossref_primary_10_1016_j_jag_2024_103738 crossref_primary_10_3390_diagnostics12092144 crossref_primary_10_1021_acs_jafc_3c05029 crossref_primary_10_1007_s00521_024_10950_4 crossref_primary_10_1080_15389588_2024_2404715 crossref_primary_10_1080_17538947_2024_2372321 crossref_primary_10_3389_fgene_2022_825318 crossref_primary_10_1016_j_eswa_2023_119607 crossref_primary_10_1094_PHYTO_10_22_0380_R crossref_primary_10_1109_TTE_2020_2995745 crossref_primary_10_3389_fphy_2024_1476618 crossref_primary_10_3390_app112110396 crossref_primary_10_3390_buildings12122111 crossref_primary_10_3390_app14114369 crossref_primary_10_1021_acssensors_4c01582 crossref_primary_10_2478_pomr_2024_0030 crossref_primary_10_1186_s12885_024_12753_1 crossref_primary_10_1007_s11269_022_03207_z crossref_primary_10_1051_bioconf_20249301017 crossref_primary_10_1007_s40948_024_00846_x crossref_primary_10_1007_s12243_025_01073_5 crossref_primary_10_1007_s11356_022_24328_3 crossref_primary_10_2139_ssrn_4052657 crossref_primary_10_3390_jmse13040624 crossref_primary_10_1016_j_jclepro_2023_138534 crossref_primary_10_1057_s41599_022_01407_x crossref_primary_10_3390_f15071161 crossref_primary_10_2174_1874447802115010241 crossref_primary_10_1038_s41598_025_92248_6 crossref_primary_10_1007_s00414_024_03210_6 crossref_primary_10_1016_j_ecolind_2021_107830 crossref_primary_10_1155_2022_5868630 crossref_primary_10_3390_rs15010268 crossref_primary_10_3389_fneur_2022_1005650 crossref_primary_10_1007_s13721_021_00302_w crossref_primary_10_1016_j_ins_2021_06_059 crossref_primary_10_1007_s11356_022_20196_z crossref_primary_10_1088_2051_672X_ac929b crossref_primary_10_1007_s00170_022_08884_z crossref_primary_10_1007_s41870_025_02465_5 crossref_primary_10_1016_j_vibspec_2023_103628 crossref_primary_10_1016_j_applthermaleng_2024_123784 crossref_primary_10_3390_f14122366 crossref_primary_10_1007_s13369_022_07412_1 crossref_primary_10_1016_j_cej_2025_161634 crossref_primary_10_1002_cpe_6817 crossref_primary_10_1016_j_enganabound_2022_08_004 crossref_primary_10_3390_ai3020023 crossref_primary_10_1016_j_compag_2023_107929 crossref_primary_10_1021_acs_nanolett_4c04385 crossref_primary_10_1177_00420980241270987 crossref_primary_10_1109_JSTARS_2024_3379216 crossref_primary_10_1080_12265934_2024_2346166 crossref_primary_10_2139_ssrn_3981732 crossref_primary_10_1109_ACCESS_2024_3446992 crossref_primary_10_54097_hset_v45i_7582 crossref_primary_10_1155_2020_8855509 crossref_primary_10_1371_journal_pone_0277085 crossref_primary_10_1016_j_engappai_2024_108849 crossref_primary_10_1016_j_jbi_2021_103763 crossref_primary_10_1371_journal_pone_0302359 crossref_primary_10_3390_diagnostics12040817 crossref_primary_10_1016_j_jenvman_2023_119474 crossref_primary_10_1051_e3sconf_202448402009 crossref_primary_10_3102_10769986231193327 crossref_primary_10_3390_ijgi12030107 crossref_primary_10_1016_j_foreco_2023_121579 crossref_primary_10_1371_journal_pone_0314381 crossref_primary_10_1002_1878_0261_13747 crossref_primary_10_1016_j_indcrop_2019_111952 crossref_primary_10_1007_s13202_024_01820_9 crossref_primary_10_3390_rs14092068 crossref_primary_10_1007_s00330_022_09217_0 crossref_primary_10_3390_environments11070139 crossref_primary_10_1016_j_atech_2024_100453 crossref_primary_10_3390_s23073679 crossref_primary_10_1016_j_comnet_2024_110838 crossref_primary_10_1109_TNNLS_2023_3271327 crossref_primary_10_3389_fevo_2023_1254143 crossref_primary_10_3390_electronics12071533 crossref_primary_10_3390_f14061083 crossref_primary_10_1016_j_measen_2024_101245 crossref_primary_10_3390_healthcare9040422 crossref_primary_10_1007_s10489_021_02824_2 crossref_primary_10_1016_j_jag_2022_102906 crossref_primary_10_1186_s12911_024_02813_8 crossref_primary_10_3390_su15129452 crossref_primary_10_1109_ACCESS_2023_3308928 crossref_primary_10_1007_s13042_022_01613_8 crossref_primary_10_12677_HJDM_2022_123003 crossref_primary_10_1080_08874417_2024_2395913 crossref_primary_10_4018_JDM_321739 crossref_primary_10_1016_j_scitotenv_2024_176261 crossref_primary_10_3389_fenvs_2021_689745 crossref_primary_10_3389_fimmu_2024_1539465 crossref_primary_10_1097_CORR_0000000000002283 crossref_primary_10_1016_j_cjche_2022_12_013 crossref_primary_10_1016_j_epsr_2020_106885 crossref_primary_10_3389_fenvs_2023_1324742 crossref_primary_10_1016_j_apgeog_2023_102870 crossref_primary_10_1016_j_jfca_2021_104137 crossref_primary_10_1016_j_asoc_2022_109427 crossref_primary_10_1016_j_eswa_2021_114756 crossref_primary_10_1021_acs_energyfuels_2c03033 crossref_primary_10_15675_gepros_2965 crossref_primary_10_1097_st9_0000000000000059 crossref_primary_10_1016_j_eswa_2023_122707 crossref_primary_10_1039_D4TA09222H crossref_primary_10_3390_su141710710 crossref_primary_10_1038_s41598_022_13579_2 crossref_primary_10_3389_fimmu_2023_1289700 crossref_primary_10_3390_drones8100585 crossref_primary_10_3389_fcimb_2024_1488505 crossref_primary_10_1016_j_compenvurbsys_2022_101854 crossref_primary_10_1016_j_foodres_2023_113085 crossref_primary_10_1080_15623599_2022_2045862 crossref_primary_10_1016_j_fufo_2024_100500 crossref_primary_10_3233_MGS_230007 crossref_primary_10_3389_fonc_2022_848425 crossref_primary_10_3390_rs15194761 crossref_primary_10_1111_ejss_13586 crossref_primary_10_1016_j_radphyschem_2021_109636 crossref_primary_10_18100_ijamec_1035749 crossref_primary_10_12677_AG_2019_910098 crossref_primary_10_3233_MAS_220405 crossref_primary_10_3390_nano14020165 crossref_primary_10_1007_s10742_021_00255_7 crossref_primary_10_1007_s11069_023_05836_y crossref_primary_10_1016_j_asoc_2022_109209 crossref_primary_10_3233_THC_220563 crossref_primary_10_1016_j_sab_2024_107001 crossref_primary_10_2147_IJGM_S354741 crossref_primary_10_1002_ppj2_20054 crossref_primary_10_1016_j_cie_2022_108363 crossref_primary_10_3390_s20247248 crossref_primary_10_1016_j_flowmeasinst_2024_102609 crossref_primary_10_1016_j_biortech_2024_131509 crossref_primary_10_1007_s12555_020_0978_4 crossref_primary_10_1109_ACCESS_2024_3355448 crossref_primary_10_3390_math12142231 crossref_primary_10_3390_math10152772 crossref_primary_10_1016_j_coldregions_2024_104354 crossref_primary_10_1016_j_renene_2024_122029 crossref_primary_10_3389_frai_2024_1473837 crossref_primary_10_56294_dm2024391 crossref_primary_10_1016_j_jenvman_2024_124001 crossref_primary_10_3390_e25071035 crossref_primary_10_3390_rs13214333 crossref_primary_10_18632_aging_204463 crossref_primary_10_1007_s44196_023_00390_8 crossref_primary_10_1016_j_jafr_2024_101179 crossref_primary_10_3390_rs14194981 crossref_primary_10_1016_j_ijhydene_2023_11_325 crossref_primary_10_1109_ACCESS_2021_3103319 crossref_primary_10_1155_2021_4430730 crossref_primary_10_1016_j_ress_2025_110829 crossref_primary_10_3390_rs16132321 crossref_primary_10_1152_ajplung_00250_2022 crossref_primary_10_1016_j_seppur_2024_127790 crossref_primary_10_1016_j_jenvman_2024_122095 crossref_primary_10_1016_j_procs_2024_03_276 crossref_primary_10_29137_umagd_1116295 crossref_primary_10_1109_JSTARS_2024_3494058 crossref_primary_10_3390_gels10020148 crossref_primary_10_1186_s12938_024_01295_z crossref_primary_10_3390_app15020861 crossref_primary_10_1126_scitranslmed_adk9149 crossref_primary_10_3390_app12178536 crossref_primary_10_1016_j_envsoft_2022_105326 crossref_primary_10_1155_2021_6684435 crossref_primary_10_3390_app12094181 crossref_primary_10_54691_bcpbm_v38i_4204 crossref_primary_10_1016_j_jhydrol_2021_126358 crossref_primary_10_5114_hpr_156937 crossref_primary_10_1016_j_ifacol_2020_12_2855 crossref_primary_10_1016_j_heliyon_2024_e41059 crossref_primary_10_1186_s40001_024_01675_0 crossref_primary_10_3390_s22093244 crossref_primary_10_1136_bmjopen_2019_033109 crossref_primary_10_1093_bib_bbaf096 crossref_primary_10_1021_acs_jcim_4c01234 crossref_primary_10_3390_ijerph17010049 crossref_primary_10_1140_epjqt_s40507_025_00335_4 crossref_primary_10_1186_s13638_022_02117_3 crossref_primary_10_3389_ffgc_2022_995537 crossref_primary_10_1016_j_foodchem_2024_141950 crossref_primary_10_3389_fpls_2025_1539068 crossref_primary_10_1016_j_artmed_2025_103099 crossref_primary_10_3390_nu15153340 crossref_primary_10_3390_s22197461 crossref_primary_10_24883_eagleSustainable_v13i_439 crossref_primary_10_12720_jait_11_3_181_185 crossref_primary_10_48084_etasr_6347 crossref_primary_10_1007_s00170_023_10918_z crossref_primary_10_3390_s24144716 crossref_primary_10_1007_s10489_022_04160_5 crossref_primary_10_3390_machines13030248 crossref_primary_10_1016_j_heliyon_2023_e19092 crossref_primary_10_1016_j_coldregions_2024_104305 crossref_primary_10_1016_j_pce_2024_103569 crossref_primary_10_1159_000524729 crossref_primary_10_3389_fonc_2021_706733 crossref_primary_10_3390_pr13040934 crossref_primary_10_1007_s42729_023_01598_5 crossref_primary_10_1016_j_procs_2024_10_034 crossref_primary_10_3390_rs14194909 crossref_primary_10_1007_s00202_024_02821_x crossref_primary_10_1016_j_measurement_2023_113196 crossref_primary_10_1016_j_swevo_2022_101148 crossref_primary_10_1016_j_saa_2024_123982 crossref_primary_10_3389_fimmu_2022_1043111 crossref_primary_10_1007_s00414_023_02981_8 crossref_primary_10_3390_e26121059 crossref_primary_10_1016_j_isci_2023_106299 crossref_primary_10_1080_02770903_2023_2263071 crossref_primary_10_3390_pr12071420 crossref_primary_10_1016_j_mineng_2023_108448 crossref_primary_10_1080_15324982_2020_1867935 crossref_primary_10_1016_j_crsust_2023_100239 crossref_primary_10_3390_rs12030562 crossref_primary_10_1109_ACCESS_2025_3551270 crossref_primary_10_1109_JPHOTOV_2022_3221003 crossref_primary_10_3233_JIFS_230032 crossref_primary_10_3390_info11050270 crossref_primary_10_1016_j_ecoinf_2023_102027 crossref_primary_10_1038_s41598_024_73536_z crossref_primary_10_3390_rs14205206 crossref_primary_10_3390_f16010021 crossref_primary_10_2166_nh_2024_154 crossref_primary_10_1016_j_eswa_2024_123947 crossref_primary_10_1007_s44288_024_00037_x crossref_primary_10_3390_foods13244044 crossref_primary_10_3389_fonc_2024_1369051 crossref_primary_10_3390_foods12234267 crossref_primary_10_3390_su162410845 crossref_primary_10_1016_j_eswa_2023_122557 crossref_primary_10_1088_1361_6501_ad0868 crossref_primary_10_3389_fendo_2025_1495306 crossref_primary_10_3390_sym14122629 crossref_primary_10_1080_01431161_2023_2264496 crossref_primary_10_1088_1361_6501_ad5ab9 crossref_primary_10_1016_j_pdpdt_2023_103708 crossref_primary_10_3390_biomedinformatics4020077 crossref_primary_10_3892_etm_2023_11903 crossref_primary_10_1016_j_eswa_2022_117854 crossref_primary_10_2147_IPRP_S492422 crossref_primary_10_3390_pr11092603 crossref_primary_10_1007_s12517_022_10615_3 crossref_primary_10_3389_fcvm_2022_911987 crossref_primary_10_2147_CMAR_S342352 crossref_primary_10_3390_ijerph18168327 crossref_primary_10_1007_s00521_023_09003_z crossref_primary_10_1007_s10726_025_09920_5 crossref_primary_10_1016_j_scitotenv_2022_157825 crossref_primary_10_1016_j_robot_2024_104893 crossref_primary_10_3390_rs14215338 crossref_primary_10_1007_s13369_024_08923_9 crossref_primary_10_1016_j_cie_2024_110046 crossref_primary_10_1080_15366367_2023_2246111 crossref_primary_10_1186_s13040_021_00269_4 crossref_primary_10_3390_land14020265 crossref_primary_10_1016_j_envpol_2024_124389 crossref_primary_10_1134_S1063778822090241 crossref_primary_10_1186_s12967_023_04487_8 crossref_primary_10_3390_app132212147 crossref_primary_10_1002_cem_3346 crossref_primary_10_1007_s11356_024_32807_y crossref_primary_10_1016_j_comnet_2023_110093 crossref_primary_10_1002_pro_4918 crossref_primary_10_1016_j_apenergy_2024_123586 crossref_primary_10_1016_j_catena_2024_108616 crossref_primary_10_3390_rs16162913 crossref_primary_10_1109_ACCESS_2024_3505254 crossref_primary_10_1007_s12555_024_0081_3 crossref_primary_10_1080_00032719_2024_2354904 crossref_primary_10_1016_j_nantod_2025_102660 crossref_primary_10_1109_ACCESS_2024_3444907 crossref_primary_10_1016_j_ijcce_2021_09_001 crossref_primary_10_2196_48295 crossref_primary_10_1109_TMC_2023_3267853 crossref_primary_10_1108_IJICC_07_2023_0167 crossref_primary_10_1016_j_agwat_2023_108468 crossref_primary_10_1109_JIOT_2024_3398418 crossref_primary_10_1080_01431161_2021_1931539 crossref_primary_10_1021_acs_est_2c00470 crossref_primary_10_1186_s12911_024_02491_6 crossref_primary_10_1016_j_ymssp_2022_110022 crossref_primary_10_1007_s00371_024_03635_5 crossref_primary_10_1016_j_heliyon_2024_e36051 crossref_primary_10_1016_j_scitotenv_2024_170587 crossref_primary_10_1007_s40031_022_00787_7 crossref_primary_10_1007_s40789_022_00519_8 crossref_primary_10_1016_j_jclepro_2021_126427 crossref_primary_10_3390_fi16070229 crossref_primary_10_1109_JBHI_2024_3355111 crossref_primary_10_32628_IJSRSET24113100 crossref_primary_10_1016_j_catena_2024_108633 crossref_primary_10_12677_sa_2024_134147 crossref_primary_10_3390_biom14091155 crossref_primary_10_1109_ACCESS_2021_3105321 crossref_primary_10_1186_s40854_024_00625_3 crossref_primary_10_1038_s41598_024_51586_7 crossref_primary_10_1002_tee_24164 crossref_primary_10_1371_journal_pone_0297015 crossref_primary_10_1021_acsnano_4c12538 crossref_primary_10_1016_j_ecolind_2025_113237 crossref_primary_10_1016_j_bbih_2025_100957 crossref_primary_10_1109_ACCESS_2021_3088612 crossref_primary_10_3389_fpls_2022_963170 crossref_primary_10_1016_j_jenvman_2025_124971 crossref_primary_10_1016_j_rsase_2022_100782 crossref_primary_10_1002_cem_3393 crossref_primary_10_1111_jebm_12632 crossref_primary_10_3390_ijerph20053821 crossref_primary_10_3390_math11143204 crossref_primary_10_3389_fpls_2024_1429879 crossref_primary_10_1016_j_scitotenv_2024_176946 crossref_primary_10_1016_j_procs_2022_12_314 crossref_primary_10_3390_rs16234497 crossref_primary_10_3389_fninf_2022_893788 crossref_primary_10_1016_j_apgeog_2020_102319 crossref_primary_10_1016_j_mtcomm_2024_108945 crossref_primary_10_1109_ACCESS_2024_3415350 crossref_primary_10_1007_s11069_024_06829_1 crossref_primary_10_1093_jcde_qwab058 crossref_primary_10_1093_cercor_bhae446 crossref_primary_10_3389_fmars_2022_947394 crossref_primary_10_2166_aqua_2024_311 crossref_primary_10_1007_s40948_023_00690_5 crossref_primary_10_1016_j_sna_2021_113271 crossref_primary_10_1093_bioinformatics_btae497 crossref_primary_10_1186_s12859_022_04634_w crossref_primary_10_1016_j_jclepro_2021_128411 crossref_primary_10_1039_D2GC04341F crossref_primary_10_1016_j_foodchem_2025_143555 crossref_primary_10_1016_j_asoc_2023_110018 crossref_primary_10_3390_w14203220 crossref_primary_10_3390_d15101061 crossref_primary_10_4018_JCIT_296263 crossref_primary_10_3390_app10238620 crossref_primary_10_1038_s41598_024_81601_w crossref_primary_10_1080_19475705_2022_2147455 crossref_primary_10_1016_j_eswa_2024_124518 crossref_primary_10_1371_journal_pone_0254519 crossref_primary_10_1109_ACCESS_2023_3320687 crossref_primary_10_1080_1062936X_2024_2440903 crossref_primary_10_1063_5_0201613 crossref_primary_10_1016_j_rasd_2023_102258 crossref_primary_10_1109_ACCESS_2023_3243203 crossref_primary_10_3390_su151310101 crossref_primary_10_3390_pr13020346 crossref_primary_10_1016_j_bspc_2024_106854 crossref_primary_10_3390_land12091696 crossref_primary_10_1186_s12936_024_04877_3 crossref_primary_10_1038_s41598_025_93495_3 crossref_primary_10_1016_j_infrared_2021_103731 crossref_primary_10_3390_s24134259 crossref_primary_10_1016_j_nanoen_2023_108559 crossref_primary_10_1155_2022_5416726 crossref_primary_10_3389_fdgth_2023_1187578 crossref_primary_10_1016_j_eswa_2024_123451 crossref_primary_10_1038_s41598_024_71053_7 crossref_primary_10_1016_j_snb_2025_137239 crossref_primary_10_3389_fpsyt_2024_1519930 crossref_primary_10_1016_j_ecoinf_2025_103054 crossref_primary_10_1111_ejed_12805 crossref_primary_10_1108_MEQ_07_2023_0196 crossref_primary_10_1016_j_jlp_2024_105511 crossref_primary_10_1177_08850666241258960 crossref_primary_10_1186_s13040_024_00388_8 crossref_primary_10_1115_1_4050778 crossref_primary_10_1007_s00521_021_05790_5 crossref_primary_10_1016_j_jag_2022_103092 crossref_primary_10_1016_j_aei_2019_101030 crossref_primary_10_3390_app13116494 crossref_primary_10_1016_j_corsci_2023_111222 crossref_primary_10_1016_j_mlwa_2023_100505 crossref_primary_10_1016_j_apr_2023_101836 crossref_primary_10_32604_cmes_2023_022699 crossref_primary_10_3390_ijgi13120452 crossref_primary_10_5194_bg_22_117_2025 crossref_primary_10_1016_j_foodres_2022_111998 crossref_primary_10_3390_jsan12050067 crossref_primary_10_1145_3609391 crossref_primary_10_1177_17515831241241947 crossref_primary_10_12720_jait_14_5_980_990 crossref_primary_10_1007_s41060_024_00509_w crossref_primary_10_1002_for_3008 crossref_primary_10_3390_atmos16030238 crossref_primary_10_1155_2021_6053824 crossref_primary_10_3390_drones9030189 crossref_primary_10_1109_TCC_2024_3449884 crossref_primary_10_1088_1755_1315_1109_1_012062 crossref_primary_10_1002_jtr_2476 crossref_primary_10_3390_diagnostics14222482 crossref_primary_10_1002_hsr2_2148 crossref_primary_10_3390_math11020431 crossref_primary_10_3390_math13030411 crossref_primary_10_3389_fdgth_2024_1427845 crossref_primary_10_1098_rsos_230386 crossref_primary_10_1007_s10614_024_10709_y crossref_primary_10_1016_j_foreco_2023_121034 crossref_primary_10_3390_diagnostics11040612 crossref_primary_10_1016_j_ress_2025_111000 crossref_primary_10_3390_covid3090093 crossref_primary_10_1007_s11042_023_15791_2 crossref_primary_10_1109_MNET_001_2100754 crossref_primary_10_1093_comjnl_bxaa006 crossref_primary_10_1002_cem_3536 crossref_primary_10_2478_jses_2023_0007 crossref_primary_10_11922_11_6035_csd_2024_0066_zh crossref_primary_10_1016_j_dajour_2023_100307 crossref_primary_10_1080_23249935_2024_2437477 crossref_primary_10_3390_s23167154 crossref_primary_10_1007_s10853_025_10719_7 crossref_primary_10_1155_2022_2206689 crossref_primary_10_1016_j_scs_2021_103185 crossref_primary_10_3390_app12105106 crossref_primary_10_1111_jace_19518 crossref_primary_10_3390_pr12091900 crossref_primary_10_1007_s11408_024_00451_8 crossref_primary_10_1080_07853890_2025_2474172 crossref_primary_10_1061__ASCE_CO_1943_7862_0002162 crossref_primary_10_1016_j_fcr_2023_109102 crossref_primary_10_1007_s12145_024_01234_5 crossref_primary_10_1016_j_ecolind_2023_111348 crossref_primary_10_1016_j_geoen_2023_212064 crossref_primary_10_3390_bioengineering12020119 crossref_primary_10_1016_j_engfailanal_2024_108724 crossref_primary_10_2139_ssrn_4182917 crossref_primary_10_2478_amns_2024_3065 crossref_primary_10_1002_cem_3522 crossref_primary_10_1016_j_conbuildmat_2023_133860 crossref_primary_10_1016_j_compedu_2024_105093 crossref_primary_10_1016_j_cscm_2024_e03869 |
| Cites_doi | 10.1093/bioinformatics/btq134 10.1186/1471-2105-7-3 10.18637/jss.v036.i11 10.1002/sim.6351 10.1093/bib/bbx124 10.1023/A:1010933404324 10.1016/j.eswa.2016.12.008 10.32614/RJ-2015-018 10.1016/j.csda.2012.09.020 10.1016/j.patcog.2013.05.018 10.1186/1471-2105-5-81 10.1016/j.ijmedinf.2018.05.006 10.1016/j.eswa.2013.05.051 |
| ContentType | Journal Article |
| Copyright | 2019 Elsevier Ltd Copyright Elsevier BV Nov 15, 2019 |
| Copyright_xml | – notice: 2019 Elsevier Ltd – notice: Copyright Elsevier BV Nov 15, 2019 |
| DBID | AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D 7X8 5PM |
| DOI | 10.1016/j.eswa.2019.05.028 |
| DatabaseName | CrossRef Computer and Information Systems Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic PubMed Central (Full Participant titles) |
| DatabaseTitle | CrossRef Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic Computer and Information Systems Abstracts |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1873-6793 |
| EndPage | 101 |
| ExternalDocumentID | PMC7508310 10_1016_j_eswa_2019_05_028 S0957417419303574 |
| GroupedDBID | --K --M .DC .~1 0R~ 13V 1B1 1RT 1~. 1~5 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN 9JO AAAKF AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AARIN AAXUO AAYFN ABBOA ABFNM ABMAC ABMVD ABUCO ABYKQ ACDAQ ACGFS ACHRH ACNTT ACRLP ACZNC ADBBV ADEZE ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGJBL AGUBO AGUMN AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJOXV ALEQD ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD APLSM AXJTR BJAXD BKOJK BLXMC BNSAS CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HAMUX IHE J1W JJJVA KOM LG9 LY1 LY7 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PQQKQ Q38 RIG ROL RPZ SDF SDG SDP SDS SES SPC SPCBC SSB SSD SSL SST SSV SSZ T5K TN5 ~G- 29G AAAKG AAQXK AATTM AAXKI AAYWO AAYXX ABJNI ABKBG ABWVN ABXDB ACNNM ACRPL ACVFH ADCNI ADJOM ADMUD ADNMO AEIPS AEUPX AFJKZ AFPUW AFXIZ AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN BNPGV CITATION FEDTE FGOYB G-2 HLZ HVGLF HZ~ R2- SBC SET SEW SSH WUQ XPP ZMT 7SC 8FD EFKBS JQ2 L7M L~C L~D 7X8 5PM |
| ID | FETCH-LOGICAL-c513t-2783599bf20dc64f54b48e66319bf6b4069496bbc26481011d98617121ffd5e93 |
| IEDL.DBID | .~1 |
| ISSN | 0957-4174 |
| IngestDate | Thu Aug 21 18:18:04 EDT 2025 Fri Jul 11 01:38:18 EDT 2025 Mon Jul 14 07:43:06 EDT 2025 Thu Apr 24 22:55:12 EDT 2025 Tue Jul 01 04:05:46 EDT 2025 Fri Feb 23 02:24:26 EST 2024 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Random forest Feature reduction Classification Variable selection |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c513t-2783599bf20dc64f54b48e66319bf6b4069496bbc26481011d98617121ffd5e93 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 MEM: Funding acquisition, methodology, editing draft JT: Funding acquisition, methodology, editing draft EI: Funding acquisition, methodology, editing draft Author contributions JLS: Conceptualization, analysis, funding acquisition, methodology, writing original draft |
| OpenAccessLink | https://www.ncbi.nlm.nih.gov/pmc/articles/7508310 |
| PMID | 32968335 |
| PQID | 2264151110 |
| PQPubID | 2045477 |
| PageCount | 9 |
| ParticipantIDs | pubmedcentral_primary_oai_pubmedcentral_nih_gov_7508310 proquest_miscellaneous_2445973307 proquest_journals_2264151110 crossref_citationtrail_10_1016_j_eswa_2019_05_028 crossref_primary_10_1016_j_eswa_2019_05_028 elsevier_sciencedirect_doi_10_1016_j_eswa_2019_05_028 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2019-11-15 |
| PublicationDateYYYYMMDD | 2019-11-15 |
| PublicationDate_xml | – month: 11 year: 2019 text: 2019-11-15 day: 15 |
| PublicationDecade | 2010 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | Expert systems with applications |
| PublicationYear | 2019 |
| Publisher | Elsevier Ltd Elsevier BV |
| Publisher_xml | – name: Elsevier Ltd – name: Elsevier BV |
| References | Kursa, Rudnicki (bib0019) 2010; 36 Degenhardt, Seifert, Szymczak (bib0008) 2017; 20 Altmann, Toloşi, Sander, Lengauer (bib0001) 2010; 26 Deng, Runger (bib0009) 2013; 46 Fernández-Delgado, Cernadas, Barro, Amorim (bib0011) 2014; 15 Hapfelmeier, Ulm (bib0013) 2013; 60 Jiang, Deng, Chen, Tao, Sha, Chen (bib0017) 2004; 5 Ishwaran, Kogalur (bib0015) 2014 Hothorn, T., Hornik, K., Strobl, C., & Zeileis, A. (2010). Genuer, Poggi, Tuleau-Malot (bib0012) 2015; 7 Breiman, Friedman, Olshen, Stone (bib0003) 1984 Sanchez-Pinto, Venable, Fahrenbach, Churpek (bib0021) 2018; 116 Breiman (bib0002) 2001; 45 Cadenas, Garrido, MartíNez (bib0004) 2013; 40 Conn, Ngun, Li, Ramirez (bib0007) 2015 Cano, Garcia-Rodriguez, Garcia-Garcia, Perez-Sanchez, Benediktsson, Thapa (bib0005) 2017; 72 Svetnik, Liaw, Tong, Wang (bib0023) 2004 Speiser, Durkalski, Lee (bib0022) 2015; 34 Casalicchio, Bossek, Lang, Kirchhoff, Kerschke, Hofner (bib0006) 2017 Díaz-Uriarte, De Andres (bib0010) 2006; 7 Kuhn (bib0018) 2008; 28 Liaw, Weiner (bib0020) 2002; 2 Wei, Wang, Jia (bib0026) 2019 Janitza, Celik, Boulesteix (bib0016) 2015 Urrea, Calle (bib0024) 2012 Deng (10.1016/j.eswa.2019.05.028_bib0009) 2013; 46 Kursa (10.1016/j.eswa.2019.05.028_bib0019) 2010; 36 Genuer (10.1016/j.eswa.2019.05.028_bib0012) 2015; 7 Conn (10.1016/j.eswa.2019.05.028_bib0007) 2015 Breiman (10.1016/j.eswa.2019.05.028_bib0002) 2001; 45 Wei (10.1016/j.eswa.2019.05.028_bib0026) 2019 Liaw (10.1016/j.eswa.2019.05.028_bib0020) 2002; 2 Hapfelmeier (10.1016/j.eswa.2019.05.028_bib0013) 2013; 60 Breiman (10.1016/j.eswa.2019.05.028_bib0003) 1984 Cadenas (10.1016/j.eswa.2019.05.028_bib0004) 2013; 40 Fernández-Delgado (10.1016/j.eswa.2019.05.028_bib0011) 2014; 15 Janitza (10.1016/j.eswa.2019.05.028_bib0016) 2015 Altmann (10.1016/j.eswa.2019.05.028_bib0001) 2010; 26 Ishwaran (10.1016/j.eswa.2019.05.028_bib0015) 2014 Casalicchio (10.1016/j.eswa.2019.05.028_bib0006) 2017 Díaz-Uriarte (10.1016/j.eswa.2019.05.028_bib0010) 2006; 7 Jiang (10.1016/j.eswa.2019.05.028_bib0017) 2004; 5 Cano (10.1016/j.eswa.2019.05.028_bib0005) 2017; 72 Sanchez-Pinto (10.1016/j.eswa.2019.05.028_bib0021) 2018; 116 Svetnik (10.1016/j.eswa.2019.05.028_bib0023) 2004 Degenhardt (10.1016/j.eswa.2019.05.028_bib0008) 2017; 20 Kuhn (10.1016/j.eswa.2019.05.028_bib0018) 2008; 28 Urrea (10.1016/j.eswa.2019.05.028_bib0024) 2012 Speiser (10.1016/j.eswa.2019.05.028_bib0022) 2015; 34 10.1016/j.eswa.2019.05.028_bib0014 |
| References_xml | – volume: 7 start-page: 19 year: 2015 end-page: 33 ident: bib0012 article-title: VSURF: An R package for variable selection using random forests publication-title: The R Journal – volume: 7 start-page: 3 year: 2006 ident: bib0010 article-title: Gene selection and classification of microarray data using random forest publication-title: BMC Bioinformatics – start-page: 334 year: 2004 end-page: 343 ident: bib0023 article-title: Application of Breiman's random forest to modeling structure-activity relationships of pharmaceutical molecules publication-title: International workshop on multiple classifier systems – reference: Hothorn, T., Hornik, K., Strobl, C., & Zeileis, A. (2010). – year: 2012 ident: bib0024 article-title: AUCRF – volume: 36 start-page: 1 year: 2010 end-page: 13 ident: bib0019 article-title: Feature selection with the Boruta package publication-title: Journal of Statistical Software – volume: 5 start-page: 81 year: 2004 ident: bib0017 article-title: Joint analysis of two microarray gene-expression data sets to select lung adenocarcinoma marker genes publication-title: BMC Bioinformatics – volume: 20 start-page: 492 year: 2017 end-page: 503 ident: bib0008 article-title: Evaluation of variable selection methods for random forests and omics data sets publication-title: Briefings in Bioinformatics – volume: 15 start-page: 3133 year: 2014 end-page: 3181 ident: bib0011 article-title: Do we need hundreds of classifiers to solve real world classification problems publication-title: Journal of Machine Learning Research – volume: 28 start-page: 1 year: 2008 end-page: 26 ident: bib0018 article-title: Caret package publication-title: Journal of Statistical Software – volume: 2 start-page: 18 year: 2002 end-page: 22 ident: bib0020 article-title: Classification and Regression by randomForest publication-title: R News – volume: 40 start-page: 6241 year: 2013 end-page: 6252 ident: bib0004 article-title: Feature subset selection filter–wrapper based on low quality data publication-title: Expert Systems with Applications – volume: 116 start-page: 10 year: 2018 end-page: 17 ident: bib0021 article-title: Comparison of variable selection methods for clinical predictive modeling publication-title: International Journal of Medical Informatics – volume: 46 start-page: 3483 year: 2013 end-page: 3489 ident: bib0009 article-title: Gene selection with guided regularized random forest publication-title: Pattern Recognition – volume: 45 start-page: 5 year: 2001 end-page: 32 ident: bib0002 article-title: Random forests publication-title: Machine Learning – volume: 26 start-page: 1340 year: 2010 end-page: 1347 ident: bib0001 article-title: Permutation importance: A corrected feature importance measure publication-title: Bioinformatics – year: 1984 ident: bib0003 article-title: Classification and regression trees – year: 2019 ident: bib0026 article-title: R package: MultiROC – year: 2014 ident: bib0015 article-title: Random forests for survival, regression and classification (RF-SRC) – start-page: 1 year: 2015 end-page: 31 ident: bib0016 article-title: A computationally fast variable importance test for random forests for high-dimensional data publication-title: Advances in Data Analysis and Classification – start-page: 1 year: 2017 end-page: 15 ident: bib0006 article-title: OpenML: An R package to connect to the machine learning platform OpenML publication-title: Computational Statistics – volume: 34 start-page: 887 year: 2015 end-page: 899 ident: bib0022 article-title: Random forest classification of etiologies for an orphan disease publication-title: Statistics in Medicine – year: 2015 ident: bib0007 article-title: Fuzzy forests: Extending random forests for correlated publication-title: High-Dimensional Data – volume: 60 start-page: 50 year: 2013 end-page: 69 ident: bib0013 article-title: A new variable selection approach using random forests publication-title: Computational Statistics & Data Analysis – volume: 72 start-page: 151 year: 2017 end-page: 159 ident: bib0005 article-title: Automatic selection of molecular descriptors using random forest: Application to drug discovery publication-title: Expert Systems with Applications – ident: 10.1016/j.eswa.2019.05.028_bib0014 – volume: 26 start-page: 1340 issue: 10 year: 2010 ident: 10.1016/j.eswa.2019.05.028_bib0001 article-title: Permutation importance: A corrected feature importance measure publication-title: Bioinformatics doi: 10.1093/bioinformatics/btq134 – volume: 7 start-page: 3 year: 2006 ident: 10.1016/j.eswa.2019.05.028_bib0010 article-title: Gene selection and classification of microarray data using random forest publication-title: BMC Bioinformatics doi: 10.1186/1471-2105-7-3 – volume: 36 start-page: 1 year: 2010 ident: 10.1016/j.eswa.2019.05.028_bib0019 article-title: Feature selection with the Boruta package publication-title: Journal of Statistical Software doi: 10.18637/jss.v036.i11 – volume: 34 start-page: 887 issue: 5 year: 2015 ident: 10.1016/j.eswa.2019.05.028_bib0022 article-title: Random forest classification of etiologies for an orphan disease publication-title: Statistics in Medicine doi: 10.1002/sim.6351 – start-page: 1 year: 2017 ident: 10.1016/j.eswa.2019.05.028_bib0006 article-title: OpenML: An R package to connect to the machine learning platform OpenML publication-title: Computational Statistics – start-page: 334 year: 2004 ident: 10.1016/j.eswa.2019.05.028_bib0023 article-title: Application of Breiman's random forest to modeling structure-activity relationships of pharmaceutical molecules – volume: 15 start-page: 3133 year: 2014 ident: 10.1016/j.eswa.2019.05.028_bib0011 article-title: Do we need hundreds of classifiers to solve real world classification problems publication-title: Journal of Machine Learning Research – volume: 20 start-page: 492 issue: 2 year: 2017 ident: 10.1016/j.eswa.2019.05.028_bib0008 article-title: Evaluation of variable selection methods for random forests and omics data sets publication-title: Briefings in Bioinformatics doi: 10.1093/bib/bbx124 – volume: 45 start-page: 5 issue: 1 year: 2001 ident: 10.1016/j.eswa.2019.05.028_bib0002 article-title: Random forests publication-title: Machine Learning doi: 10.1023/A:1010933404324 – volume: 72 start-page: 151 year: 2017 ident: 10.1016/j.eswa.2019.05.028_bib0005 article-title: Automatic selection of molecular descriptors using random forest: Application to drug discovery publication-title: Expert Systems with Applications doi: 10.1016/j.eswa.2016.12.008 – volume: 7 start-page: 19 issue: 2 year: 2015 ident: 10.1016/j.eswa.2019.05.028_bib0012 article-title: VSURF: An R package for variable selection using random forests publication-title: The R Journal doi: 10.32614/RJ-2015-018 – volume: 60 start-page: 50 year: 2013 ident: 10.1016/j.eswa.2019.05.028_bib0013 article-title: A new variable selection approach using random forests publication-title: Computational Statistics & Data Analysis doi: 10.1016/j.csda.2012.09.020 – year: 2012 ident: 10.1016/j.eswa.2019.05.028_bib0024 – year: 1984 ident: 10.1016/j.eswa.2019.05.028_bib0003 – year: 2015 ident: 10.1016/j.eswa.2019.05.028_bib0007 article-title: Fuzzy forests: Extending random forests for correlated publication-title: High-Dimensional Data – volume: 28 start-page: 1 year: 2008 ident: 10.1016/j.eswa.2019.05.028_bib0018 article-title: Caret package publication-title: Journal of Statistical Software – volume: 46 start-page: 3483 issue: 12 year: 2013 ident: 10.1016/j.eswa.2019.05.028_bib0009 article-title: Gene selection with guided regularized random forest publication-title: Pattern Recognition doi: 10.1016/j.patcog.2013.05.018 – volume: 2 start-page: 18 year: 2002 ident: 10.1016/j.eswa.2019.05.028_bib0020 article-title: Classification and Regression by randomForest publication-title: R News – year: 2014 ident: 10.1016/j.eswa.2019.05.028_bib0015 – volume: 5 start-page: 81 year: 2004 ident: 10.1016/j.eswa.2019.05.028_bib0017 article-title: Joint analysis of two microarray gene-expression data sets to select lung adenocarcinoma marker genes publication-title: BMC Bioinformatics doi: 10.1186/1471-2105-5-81 – year: 2019 ident: 10.1016/j.eswa.2019.05.028_bib0026 – volume: 116 start-page: 10 year: 2018 ident: 10.1016/j.eswa.2019.05.028_bib0021 article-title: Comparison of variable selection methods for clinical predictive modeling publication-title: International Journal of Medical Informatics doi: 10.1016/j.ijmedinf.2018.05.006 – volume: 40 start-page: 6241 issue: 16 year: 2013 ident: 10.1016/j.eswa.2019.05.028_bib0004 article-title: Feature subset selection filter–wrapper based on low quality data publication-title: Expert Systems with Applications doi: 10.1016/j.eswa.2013.05.051 – start-page: 1 year: 2015 ident: 10.1016/j.eswa.2019.05.028_bib0016 article-title: A computationally fast variable importance test for random forests for high-dimensional data publication-title: Advances in Data Analysis and Classification |
| SSID | ssj0017007 |
| Score | 2.71526 |
| SecondaryResourceType | review_article |
| Snippet | •We compare performance for random forest variable selection methods.•VSURF or Jiang's method are preferable for most datasets.•varSelRF or Boruta perform well... Random forest classification is a popular machine learning method for developing prediction models in many research settings. Often in prediction modeling, a... |
| SourceID | pubmedcentral proquest crossref elsevier |
| SourceType | Open Access Repository Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 93 |
| SubjectTerms | Classification Data acquisition Datasets Feature reduction Identification methods Machine learning Methods Random forest Test procedures Variable selection |
| Title | A comparison of random forest variable selection methods for classification prediction modeling |
| URI | https://dx.doi.org/10.1016/j.eswa.2019.05.028 https://www.proquest.com/docview/2264151110 https://www.proquest.com/docview/2445973307 https://pubmed.ncbi.nlm.nih.gov/PMC7508310 |
| Volume | 134 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3fT9swED5V8MILgw20MkCetLcpFBM7Px4rBOpA6wurxJvVxI7WaUsrWsYbfzvfOU7USogHpKpK44tq3dl3n5W7-4i-4XzmYGcbyTh1kSozGU0Rp_DlXKzd1OW-XOznOBlN1M29vu_RZVsLw2mVwfc3Pt1763BnELQ5WMxmgzuAA4RDfHK4YVxyBbtKOa3v7LlL8-D2c2nTby-NWDoUzjQ5Xm75xL2HZO67dzIj--vBaQ18bqZOrsWi6z3aDSBSDJt57lPP1R_pQ0vQIMJ-_URmKMqOZ1DMK4HAZOf_BIAq_kX8xwBXTomlJ8OBhURDKL1kCVEysOZMIm88sXjgdzqNFNPnIOYd0OT66tflKAqMClGpZbyKmFZD53lRXZzbMlGVVoXKHECHxL2k8FWweVIUJee9QUfS5hkgjryQVWW1y-ND2qrntftMAictuILUpojwqopdVllAwSyx2uK6yPokW1WaMrQbZ9aLv6bNK_tjWP2G1W_OtYH6-_S9e2bRNNt4U1q3FjIbS8YgGrz53HFrThM27NJwPTHAD8BQn752w9hq_P5kWrv5I2SUwvErhlfsU7qxDLrZcrPuzZF69ts37U6153Q7euekv9AO_-IqSKmPaWv18OhOAIdWxalf76e0PfxxOxq_AG-mDC0 |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1NT-MwEB1BOcAFlgW05WPxSntDUevGzsexQqCyQC8LEjeriR3R1W5a0QJ_nzeJE1EJcVipqqLYVqwZe-ZZnplH9BPnMwc920CGsQtUnshgAj-FP-dC7SYurdLFbsfR6F79etAPa3Te5MJwWKW3_bVNr6y1f9Pz0uzNp9Peb4ADuEP8UphhPK7TBlenUh3aGF5dj8btZULcr7Om0T_gAT53pg7zcotXLj8k06qAJ5Oyf-yf3uHP1ejJd-7o8gttexwphvVUd2nNlV9pp-FoEH7L7pEZirylGhSzQsA32dk_AayKr4gXNHDylFhUfDhQkqg5pRfcQ-SMrTmYqNKfmD_xtU7dixl04Pb26f7y4u58FHhShSDXMlwGzKyh0zQrBn2bR6rQKlOJA-6QeBdlVSJsGmVZzqFvkJG0aQKUIweyKKx2aXhAnXJWum8kcNiCNYhtDCevitAlhQUaTCKrLZ6zpEuyEaXJfcVxJr74a5rQsj-GxW9Y_KavDcTfpbN2zLyut_Fpb91oyKysGgOH8Om440adxu_ZheGUYuAf4KEu_Wibsdv4CmVSutkz-iiFE1gIw9ileGUZtLPlet2rLeX0sarbHeuK1u3wPyd9Spuju9sbc3M1vj6iLW7hpEipj6mzfHp2J0BHy-y7X_1vkA4O3g |
| 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=A+Comparison+of+Random+Forest+Variable+Selection+Methods+for+Classification+Prediction+Modeling&rft.jtitle=Expert+systems+with+applications&rft.au=Speiser%2C+Jaime+Lynn&rft.au=Miller%2C+Michael+E.&rft.au=Tooze%2C+Janet&rft.au=Ip%2C+Edward&rft.date=2019-11-15&rft.issn=0957-4174&rft.volume=134&rft.spage=93&rft.epage=101&rft_id=info:doi/10.1016%2Fj.eswa.2019.05.028&rft_id=info%3Apmid%2F32968335&rft.externalDocID=PMC7508310 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0957-4174&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0957-4174&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0957-4174&client=summon |