A systematic study of the class imbalance problem in convolutional neural networks
In this study, we systematically investigate the impact of class imbalance on classification performance of convolutional neural networks (CNNs) and compare frequently used methods to address the issue. Class imbalance is a common problem that has been comprehensively studied in classical machine le...
Saved in:
| Published in | Neural networks Vol. 106; pp. 249 - 259 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
Elsevier Ltd
01.10.2018
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | In this study, we systematically investigate the impact of class imbalance on classification performance of convolutional neural networks (CNNs) and compare frequently used methods to address the issue. Class imbalance is a common problem that has been comprehensively studied in classical machine learning, yet very limited systematic research is available in the context of deep learning. In our study, we use three benchmark datasets of increasing complexity, MNIST, CIFAR-10 and ImageNet, to investigate the effects of imbalance on classification and perform an extensive comparison of several methods to address the issue: oversampling, undersampling, two-phase training, and thresholding that compensates for prior class probabilities. Our main evaluation metric is area under the receiver operating characteristic curve (ROC AUC) adjusted to multi-class tasks since overall accuracy metric is associated with notable difficulties in the context of imbalanced data. Based on results from our experiments we conclude that (i) the effect of class imbalance on classification performance is detrimental; (ii) the method of addressing class imbalance that emerged as dominant in almost all analyzed scenarios was oversampling; (iii) oversampling should be applied to the level that completely eliminates the imbalance, whereas the optimal undersampling ratio depends on the extent of imbalance; (iv) as opposed to some classical machine learning models, oversampling does not cause overfitting of CNNs; (v) thresholding should be applied to compensate for prior class probabilities when overall number of properly classified cases is of interest. |
|---|---|
| AbstractList | In this study, we systematically investigate the impact of class imbalance on classification performance of convolutional neural networks (CNNs) and compare frequently used methods to address the issue. Class imbalance is a common problem that has been comprehensively studied in classical machine learning, yet very limited systematic research is available in the context of deep learning. In our study, we use three benchmark datasets of increasing complexity, MNIST, CIFAR-10 and ImageNet, to investigate the effects of imbalance on classification and perform an extensive comparison of several methods to address the issue: oversampling, undersampling, two-phase training, and thresholding that compensates for prior class probabilities. Our main evaluation metric is area under the receiver operating characteristic curve (ROC AUC) adjusted to multi-class tasks since overall accuracy metric is associated with notable difficulties in the context of imbalanced data. Based on results from our experiments we conclude that (i) the effect of class imbalance on classification performance is detrimental; (ii) the method of addressing class imbalance that emerged as dominant in almost all analyzed scenarios was oversampling; (iii) oversampling should be applied to the level that completely eliminates the imbalance, whereas the optimal undersampling ratio depends on the extent of imbalance; (iv) as opposed to some classical machine learning models, oversampling does not cause overfitting of CNNs; (v) thresholding should be applied to compensate for prior class probabilities when overall number of properly classified cases is of interest.In this study, we systematically investigate the impact of class imbalance on classification performance of convolutional neural networks (CNNs) and compare frequently used methods to address the issue. Class imbalance is a common problem that has been comprehensively studied in classical machine learning, yet very limited systematic research is available in the context of deep learning. In our study, we use three benchmark datasets of increasing complexity, MNIST, CIFAR-10 and ImageNet, to investigate the effects of imbalance on classification and perform an extensive comparison of several methods to address the issue: oversampling, undersampling, two-phase training, and thresholding that compensates for prior class probabilities. Our main evaluation metric is area under the receiver operating characteristic curve (ROC AUC) adjusted to multi-class tasks since overall accuracy metric is associated with notable difficulties in the context of imbalanced data. Based on results from our experiments we conclude that (i) the effect of class imbalance on classification performance is detrimental; (ii) the method of addressing class imbalance that emerged as dominant in almost all analyzed scenarios was oversampling; (iii) oversampling should be applied to the level that completely eliminates the imbalance, whereas the optimal undersampling ratio depends on the extent of imbalance; (iv) as opposed to some classical machine learning models, oversampling does not cause overfitting of CNNs; (v) thresholding should be applied to compensate for prior class probabilities when overall number of properly classified cases is of interest. In this study, we systematically investigate the impact of class imbalance on classification performance of convolutional neural networks (CNNs) and compare frequently used methods to address the issue. Class imbalance is a common problem that has been comprehensively studied in classical machine learning, yet very limited systematic research is available in the context of deep learning. In our study, we use three benchmark datasets of increasing complexity, MNIST, CIFAR-10 and ImageNet, to investigate the effects of imbalance on classification and perform an extensive comparison of several methods to address the issue: oversampling, undersampling, two-phase training, and thresholding that compensates for prior class probabilities. Our main evaluation metric is area under the receiver operating characteristic curve (ROC AUC) adjusted to multi-class tasks since overall accuracy metric is associated with notable difficulties in the context of imbalanced data. Based on results from our experiments we conclude that (i) the effect of class imbalance on classification performance is detrimental; (ii) the method of addressing class imbalance that emerged as dominant in almost all analyzed scenarios was oversampling; (iii) oversampling should be applied to the level that completely eliminates the imbalance, whereas the optimal undersampling ratio depends on the extent of imbalance; (iv) as opposed to some classical machine learning models, oversampling does not cause overfitting of CNNs; (v) thresholding should be applied to compensate for prior class probabilities when overall number of properly classified cases is of interest. In this study, we systematically investigate the impact of class imbalance on classification performance of convolutional neural networks (CNNs) and compare frequently used methods to address the issue. Class imbalance is a common problem that has been comprehensively studied in classical machine learning, yet very limited systematic research is available in the context of deep learning. In our study, we use three benchmark datasets of increasing complexity, MNIST, CIFAR-10 and ImageNet, to investigate the effects of imbalance on classification and perform an extensive comparison of several methods to address the issue: oversampling, undersampling, two-phase training, and thresholding that compensates for prior class probabilities. Our main evaluation metric is area under the receiver operating characteristic curve (ROC AUC) adjusted to multi-class tasks since overall accuracy metric is associated with notable difficulties in the context of imbalanced data. Based on results from our experiments we conclude that (i) the effect of class imbalance on classification performance is detrimental; (ii) the method of addressing class imbalance that emerged as dominant in almost all analyzed scenarios was oversampling; (iii) oversampling should be applied to the level that completely eliminates the imbalance, whereas the optimal undersampling ratio depends on the extent of imbalance; (iv) as opposed to some classical machine learning models, oversampling does not cause overfitting of CNNs; (v) thresholding should be applied to compensate for prior class probabilities when overall number of properly classified cases is of interest. |
| Author | Buda, Mateusz Mazurowski, Maciej A. Maki, Atsuto |
| Author_xml | – sequence: 1 givenname: Mateusz orcidid: 0000-0003-3222-0203 surname: Buda fullname: Buda, Mateusz email: buda@kth.se organization: Department of Radiology, Duke University School of Medicine, Durham, NC, USA – sequence: 2 givenname: Atsuto surname: Maki fullname: Maki, Atsuto email: atsuto@kth.se organization: School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden – sequence: 3 givenname: Maciej A. surname: Mazurowski fullname: Mazurowski, Maciej A. email: maciej.mazurowski@duke.edu organization: Department of Radiology, Duke University School of Medicine, Durham, NC, USA |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/30092410$$D View this record in MEDLINE/PubMed https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-235561$$DView record from Swedish Publication Index |
| BookMark | eNqFkUFv1DAUhC1URLeFf4CQj1wSnu3ESTggrQq0SJWQUMXVcpxn6m0SL7bTav89XlJ64ACnuXwzem_mjJzMfkZCXjMoGTD5blfOuMyYSg6sLaEpgbFnZMPapit40_ITsoG2E4WEFk7JWYw7AJBtJV6QUwHQ8YrBhnzb0niICSednKExLcOBekvTLVIz6hipm3o96tkg3QffjzhRN1Pj53s_Lsn5WY803xF-S3rw4S6-JM-tHiO-etRzcvP5083FVXH99fLLxfa6MDXjqagrK2rUrKlML01bSyu7obZCWuACUVcCW4tV01fQGYmcY2PB1gNvJMAwiHNSrLHxAfdLr_bBTToclNdOfXTft8qHH-ou3Sou6lqyzL9d-fzHzwVjUpOLBsf8HPolKg5tU3dCwhF984gu_YTDU_Sf2jJQrYAJPsaA9glhoI7rqJ1a11HHdRQ0Kq-Tbe__shmX9LHFFLQb_2f-sJoxd3rvMKhoHOZhBhfQJDV49--AX20zrkY |
| CitedBy_id | crossref_primary_10_1016_j_knosys_2022_108578 crossref_primary_10_1016_j_eswa_2024_125597 crossref_primary_10_3390_app14031157 crossref_primary_10_1002_agj2_21285 crossref_primary_10_1002_tee_23775 crossref_primary_10_1016_j_artmed_2023_102751 crossref_primary_10_1109_TGRS_2024_3369178 crossref_primary_10_1111_pace_14209 crossref_primary_10_1109_ACCESS_2022_3218463 crossref_primary_10_1016_j_jag_2020_102279 crossref_primary_10_1016_j_jag_2021_102313 crossref_primary_10_3390_app14010454 crossref_primary_10_1080_03081079_2025_2456960 crossref_primary_10_1145_3594669 crossref_primary_10_1134_S1063779620030259 crossref_primary_10_3390_cancers13112779 crossref_primary_10_1111_2041_210X_13436 crossref_primary_10_1016_j_compbiomed_2023_107167 crossref_primary_10_1007_s11334_022_00457_3 crossref_primary_10_1007_s11263_024_02049_z crossref_primary_10_1148_radiol_2019181343 crossref_primary_10_1021_acsestwater_1c00037 crossref_primary_10_1190_geo2021_0318_1 crossref_primary_10_1109_TIV_2022_3145035 crossref_primary_10_3390_agriengineering6040277 crossref_primary_10_3389_fmars_2023_1113224 crossref_primary_10_1080_01431161_2019_1608393 crossref_primary_10_1016_j_eswa_2023_119643 crossref_primary_10_1007_s11831_024_10179_3 crossref_primary_10_1016_j_eswa_2022_118255 crossref_primary_10_1016_j_future_2024_07_032 crossref_primary_10_3390_jimaging9100232 crossref_primary_10_3390_rs10111689 crossref_primary_10_1016_j_neucom_2025_129747 crossref_primary_10_3390_cancers15154007 crossref_primary_10_1080_10618600_2025_2459285 crossref_primary_10_1016_j_compag_2024_109002 crossref_primary_10_1016_j_neucom_2025_129983 crossref_primary_10_3390_a16020065 crossref_primary_10_1109_TNNLS_2022_3177695 crossref_primary_10_1007_s00521_024_10323_x crossref_primary_10_1088_1741_2552_abb5be crossref_primary_10_3390_agriculture12081084 crossref_primary_10_1007_s11280_024_01256_5 crossref_primary_10_1016_j_neuroimage_2023_120253 crossref_primary_10_1016_j_patrec_2024_12_016 crossref_primary_10_1016_j_media_2023_102957 crossref_primary_10_1111_neup_12880 crossref_primary_10_1016_j_eswa_2025_126507 crossref_primary_10_1109_TAI_2022_3160658 crossref_primary_10_1109_ACCESS_2019_2963461 crossref_primary_10_1016_j_autcon_2020_103383 crossref_primary_10_1016_j_chinastron_2021_08_005 crossref_primary_10_1080_19942060_2023_2288235 crossref_primary_10_3390_app11135868 crossref_primary_10_1016_j_ast_2025_110090 crossref_primary_10_1109_TASLP_2020_2966857 crossref_primary_10_1016_j_asoc_2024_112677 crossref_primary_10_1080_19424280_2023_2198987 crossref_primary_10_3390_jpm11121349 crossref_primary_10_3390_rs16081398 crossref_primary_10_1016_j_ijhydene_2023_04_091 crossref_primary_10_3389_fgene_2019_00013 crossref_primary_10_1016_j_patcog_2021_108069 crossref_primary_10_1016_j_ecoinf_2022_101649 crossref_primary_10_1016_j_jhydrol_2024_130950 crossref_primary_10_1016_j_neucom_2023_126921 crossref_primary_10_1016_j_atech_2025_100867 crossref_primary_10_35234_fumbd_1642238 crossref_primary_10_1007_s11263_022_01625_5 crossref_primary_10_1177_09544097221080366 crossref_primary_10_1002_lom3_10591 crossref_primary_10_4316_AECE_2022_01001 crossref_primary_10_1109_TPAMI_2022_3174892 crossref_primary_10_1142_S0129065720500604 crossref_primary_10_1016_j_media_2021_102121 crossref_primary_10_1016_j_solener_2021_05_095 crossref_primary_10_1029_2023MS004145 crossref_primary_10_1016_j_apacoust_2020_107740 crossref_primary_10_1016_j_engappai_2021_104541 crossref_primary_10_3390_app9040746 crossref_primary_10_1016_j_tplants_2022_08_021 crossref_primary_10_3390_rs11141713 crossref_primary_10_1109_TGRS_2021_3134674 crossref_primary_10_1016_j_jag_2021_102510 crossref_primary_10_1109_TCOMM_2022_3157314 crossref_primary_10_1186_s40537_022_00648_6 crossref_primary_10_1109_TIM_2020_2998233 crossref_primary_10_1109_TIP_2024_3425148 crossref_primary_10_1109_TAFFC_2021_3053275 crossref_primary_10_1016_j_cma_2022_115236 crossref_primary_10_1016_j_neurobiolaging_2020_12_005 crossref_primary_10_1016_j_engappai_2022_105080 crossref_primary_10_1109_TII_2024_3413982 crossref_primary_10_1145_3339308 crossref_primary_10_1016_j_jnca_2020_102766 crossref_primary_10_1109_JSTARS_2024_3509712 crossref_primary_10_1016_j_eswa_2021_114885 crossref_primary_10_1016_j_ejrad_2025_111957 crossref_primary_10_1007_s13351_019_8162_6 crossref_primary_10_1109_TGRS_2021_3066802 crossref_primary_10_1186_s13643_022_02082_4 crossref_primary_10_1016_j_jag_2024_103697 crossref_primary_10_1016_j_neucom_2021_04_021 crossref_primary_10_1007_s10278_022_00637_4 crossref_primary_10_3389_fpls_2022_972445 crossref_primary_10_3390_app10030973 crossref_primary_10_1016_j_ecolmodel_2023_110414 crossref_primary_10_1109_TIM_2023_3234095 crossref_primary_10_1016_j_procs_2024_10_319 crossref_primary_10_1111_mice_12495 crossref_primary_10_1016_j_isatra_2020_05_001 crossref_primary_10_1093_bioinformatics_btab547 crossref_primary_10_1007_s13369_021_06377_x crossref_primary_10_1007_s40477_021_00642_3 crossref_primary_10_3390_app13064006 crossref_primary_10_1007_s10462_024_11081_x crossref_primary_10_1016_j_saa_2023_123742 crossref_primary_10_1109_ACCESS_2019_2956725 crossref_primary_10_1002_jbio_201960186 crossref_primary_10_1051_e3sconf_202458307015 crossref_primary_10_1088_1361_6560_acce1c crossref_primary_10_1109_TNNLS_2021_3051721 crossref_primary_10_1017_S0033291720001579 crossref_primary_10_1080_13658816_2021_1931237 crossref_primary_10_1016_j_neunet_2020_06_026 crossref_primary_10_24857_rgsa_v18n10_293 crossref_primary_10_1111_1462_2920_16175 crossref_primary_10_1007_s40194_025_01951_5 crossref_primary_10_1109_MSP_2021_3134629 crossref_primary_10_1177_02670836241308470 crossref_primary_10_1016_j_patcog_2022_109012 crossref_primary_10_1109_JIOT_2022_3218008 crossref_primary_10_1109_JSTARS_2022_3142395 crossref_primary_10_1109_TGRS_2024_3446950 crossref_primary_10_1109_TMI_2020_2995508 crossref_primary_10_1097_j_pain_0000000000003587 crossref_primary_10_3390_agronomy12102363 crossref_primary_10_1038_s41598_022_07174_8 crossref_primary_10_1016_j_isatra_2023_06_016 crossref_primary_10_1109_TIM_2024_3366277 crossref_primary_10_3390_agronomy13061530 crossref_primary_10_3390_rs14164103 crossref_primary_10_1007_s13369_021_06275_2 crossref_primary_10_3390_s18093039 crossref_primary_10_3390_nu15122751 crossref_primary_10_1117_1_JMI_6_2_027501 crossref_primary_10_3390_diagnostics14232646 crossref_primary_10_1016_j_neucom_2023_126762 crossref_primary_10_1039_C9AN01624D crossref_primary_10_1016_j_rineng_2019_100036 crossref_primary_10_1109_ACCESS_2024_3494550 crossref_primary_10_1186_s40537_019_0197_0 crossref_primary_10_1016_j_neunet_2024_106134 crossref_primary_10_1109_TIP_2022_3197931 crossref_primary_10_1109_TIM_2021_3063755 crossref_primary_10_1111_nph_18387 crossref_primary_10_1186_s40537_020_00382_x crossref_primary_10_4018_IJRSDA_2019070103 crossref_primary_10_1007_s10796_020_10022_7 crossref_primary_10_1007_s00428_019_02594_w crossref_primary_10_1007_s13042_022_01575_x crossref_primary_10_1016_j_health_2024_100374 crossref_primary_10_3390_app13031912 crossref_primary_10_1109_TPAMI_2022_3196044 crossref_primary_10_4995_raet_2025_21858 crossref_primary_10_1109_ACCESS_2020_2995567 crossref_primary_10_1002_cyto_a_24829 crossref_primary_10_3389_frai_2024_1446368 crossref_primary_10_1016_j_patcog_2022_109284 crossref_primary_10_1109_ACCESS_2023_3308822 crossref_primary_10_1088_1755_1315_606_1_012025 crossref_primary_10_1039_D0MO00031K crossref_primary_10_1109_TPAMI_2023_3311636 crossref_primary_10_3390_foods13121869 crossref_primary_10_1007_s42979_022_01549_4 crossref_primary_10_1109_ACCESS_2020_3022883 crossref_primary_10_1121_10_0016845 crossref_primary_10_1088_1361_6501_ac6224 crossref_primary_10_3390_rs13030464 crossref_primary_10_1007_s10994_023_06326_9 crossref_primary_10_3390_cancers15041174 crossref_primary_10_1109_TNNLS_2022_3231917 crossref_primary_10_1016_j_patcog_2023_110064 crossref_primary_10_1109_ACCESS_2020_3033531 crossref_primary_10_35453_NEDJR_ASCN_2018_0006 crossref_primary_10_1016_j_autcon_2019_01_017 crossref_primary_10_1007_s11432_021_3489_1 crossref_primary_10_1016_j_ifacol_2023_10_320 crossref_primary_10_1186_s13677_020_00187_6 crossref_primary_10_3389_fcvm_2022_849223 crossref_primary_10_1016_j_petrol_2021_109482 crossref_primary_10_1109_TNNLS_2021_3102514 crossref_primary_10_1016_j_asoc_2022_109588 crossref_primary_10_1109_TKDE_2023_3324510 crossref_primary_10_3390_computers12020045 crossref_primary_10_4103_jmss_jmss_12_22 crossref_primary_10_1007_s00521_024_09641_x crossref_primary_10_1007_s11063_020_10366_w crossref_primary_10_1002_prot_25966 crossref_primary_10_3233_IDA_215735 crossref_primary_10_1016_j_procs_2023_01_239 crossref_primary_10_3390_s22176592 crossref_primary_10_1007_s13753_019_00233_1 crossref_primary_10_1088_2632_2153_acc637 crossref_primary_10_1080_09540091_2023_2227780 crossref_primary_10_1186_s13075_022_02914_7 crossref_primary_10_1002_mp_16875 crossref_primary_10_1016_j_dsp_2023_103951 crossref_primary_10_1016_j_knosys_2020_106631 crossref_primary_10_1109_ACCESS_2022_3233411 crossref_primary_10_46632_cset_1_2_2 crossref_primary_10_1080_09540091_2023_2191893 crossref_primary_10_1145_3603253 crossref_primary_10_1016_j_measurement_2021_110691 crossref_primary_10_1109_TSMC_2022_3151394 crossref_primary_10_1088_2632_2153_ad64a7 crossref_primary_10_1029_2023GL106278 crossref_primary_10_1109_TITS_2024_3386928 crossref_primary_10_3847_1538_4365_ad7730 crossref_primary_10_1109_ACCESS_2024_3413578 crossref_primary_10_3390_app11041691 crossref_primary_10_1016_j_jestch_2024_101818 crossref_primary_10_1109_JSEN_2024_3383887 crossref_primary_10_1109_TSC_2024_3437742 crossref_primary_10_1007_s00521_021_06629_9 crossref_primary_10_1016_j_compbiomed_2022_105339 crossref_primary_10_1109_TEVC_2023_3257230 crossref_primary_10_1371_journal_pone_0235765 crossref_primary_10_1007_s00521_023_08374_7 crossref_primary_10_1038_s41598_020_77875_5 crossref_primary_10_1016_j_scico_2024_103172 crossref_primary_10_1109_ACCESS_2021_3102399 crossref_primary_10_1109_ACCESS_2023_3336289 crossref_primary_10_1109_TNNLS_2021_3071122 crossref_primary_10_3390_app131810182 crossref_primary_10_1109_ACCESS_2019_2924060 crossref_primary_10_1109_TNNLS_2020_3047335 crossref_primary_10_1109_TGRS_2021_3071559 crossref_primary_10_3390_met13111820 crossref_primary_10_1109_TASLP_2023_3265860 crossref_primary_10_1016_j_mattod_2023_05_029 crossref_primary_10_1016_j_infsof_2020_106430 crossref_primary_10_1109_ACCESS_2023_3349132 crossref_primary_10_1016_j_jbi_2022_104171 crossref_primary_10_1111_ggi_14670 crossref_primary_10_1016_j_isatra_2020_08_010 crossref_primary_10_1093_comjnl_bxae017 crossref_primary_10_1007_s00521_023_08363_w crossref_primary_10_1088_1361_6501_ad5b7d crossref_primary_10_1088_1361_6668_ad3d10 crossref_primary_10_3390_a17030097 crossref_primary_10_1109_TIP_2024_3379929 crossref_primary_10_1016_j_cie_2025_111024 crossref_primary_10_1038_s41598_020_65105_x crossref_primary_10_1109_TNSRE_2022_3145515 crossref_primary_10_1038_s41398_024_02876_1 crossref_primary_10_1088_1361_6560_acc9f8 crossref_primary_10_1186_s40537_021_00414_0 crossref_primary_10_1109_TITS_2022_3207798 crossref_primary_10_1016_j_cstp_2023_101093 crossref_primary_10_1007_s10032_024_00492_9 crossref_primary_10_1177_14759217241291143 crossref_primary_10_1109_TSM_2023_3283101 crossref_primary_10_1002_mp_14467 crossref_primary_10_3390_s22176325 crossref_primary_10_1007_s10489_021_02623_9 crossref_primary_10_1007_s40747_024_01370_x crossref_primary_10_3390_s20123504 crossref_primary_10_1016_j_eswa_2023_122678 crossref_primary_10_1016_j_adiac_2023_100722 crossref_primary_10_3390_app142310782 crossref_primary_10_1038_s41746_024_01311_5 crossref_primary_10_1007_s13042_023_01835_4 crossref_primary_10_1177_25138502211063531 crossref_primary_10_1109_ACCESS_2020_3035910 crossref_primary_10_1183_23120541_00579_2021 crossref_primary_10_1016_j_cortex_2022_10_016 crossref_primary_10_3390_rs14163937 crossref_primary_10_1039_D0LC00055H crossref_primary_10_3390_rs12060999 crossref_primary_10_1016_j_cageo_2023_105450 crossref_primary_10_1093_iob_obae036 crossref_primary_10_1038_s41598_024_69109_9 crossref_primary_10_3390_electronics11010002 crossref_primary_10_1016_j_oregeorev_2024_106270 crossref_primary_10_1002_hed_27999 crossref_primary_10_1016_j_neucom_2024_127735 crossref_primary_10_1016_j_ijcard_2024_132191 crossref_primary_10_1109_ACCESS_2023_3240216 crossref_primary_10_1016_j_ins_2022_12_046 crossref_primary_10_3390_sym11010005 crossref_primary_10_1007_s10462_024_10779_2 crossref_primary_10_1109_TR_2024_3356515 crossref_primary_10_1109_ACCESS_2024_3388099 crossref_primary_10_3389_fnins_2021_756536 crossref_primary_10_3390_a16110521 crossref_primary_10_3390_agriculture12020259 crossref_primary_10_1016_j_neunet_2024_106789 crossref_primary_10_1186_s13007_018_0292_9 crossref_primary_10_3390_rs13101933 crossref_primary_10_1016_j_ijpe_2022_108708 crossref_primary_10_1016_j_iswa_2023_200316 crossref_primary_10_1016_j_neucom_2021_07_055 crossref_primary_10_1029_2019PA003612 crossref_primary_10_1016_j_optlastec_2024_110648 crossref_primary_10_1016_j_procs_2022_12_026 crossref_primary_10_3390_ijgi12060245 crossref_primary_10_1002_qre_2983 crossref_primary_10_1111_odi_13825 crossref_primary_10_22144_ctujos_2024_407 crossref_primary_10_1109_ACCESS_2020_2991237 crossref_primary_10_1177_14780771231225697 crossref_primary_10_1016_j_energy_2022_125042 crossref_primary_10_1016_j_aei_2024_102737 crossref_primary_10_1016_j_cviu_2025_104291 crossref_primary_10_1088_2632_2153_ad4768 crossref_primary_10_1142_S0218488522500209 crossref_primary_10_3390_a16110510 crossref_primary_10_1109_TGRS_2020_3043661 crossref_primary_10_1186_s40537_019_0192_5 crossref_primary_10_1038_s44172_023_00066_3 crossref_primary_10_1016_j_neunet_2023_01_015 crossref_primary_10_51130_graphicon_2020_2_4_19 crossref_primary_10_1109_ACCESS_2020_2991231 crossref_primary_10_1007_s10994_023_06344_7 crossref_primary_10_1016_j_patcog_2023_110107 crossref_primary_10_2139_ssrn_4115383 crossref_primary_10_3390_info15100590 crossref_primary_10_1016_j_undsp_2023_01_004 crossref_primary_10_1061__ASCE_IS_1943_555X_0000708 crossref_primary_10_1016_j_seppur_2024_128237 crossref_primary_10_3390_s20082296 crossref_primary_10_1109_JSTARS_2022_3197937 crossref_primary_10_3390_s20082297 crossref_primary_10_1007_s10044_024_01209_8 crossref_primary_10_3389_fdata_2025_1455442 crossref_primary_10_1109_ACCESS_2023_3267964 crossref_primary_10_1007_s13246_025_01526_0 crossref_primary_10_3390_rs12223820 crossref_primary_10_1038_s41598_023_28175_1 crossref_primary_10_1049_ipr2_12410 crossref_primary_10_1109_ACCESS_2019_2946264 crossref_primary_10_1016_j_ijcha_2022_100954 crossref_primary_10_1145_3345318 crossref_primary_10_1016_j_neucom_2024_128617 crossref_primary_10_1038_s41893_019_0246_x crossref_primary_10_1016_j_eswa_2021_115067 crossref_primary_10_1109_TGRS_2022_3177853 crossref_primary_10_1148_ryai_2019180050 crossref_primary_10_1109_TGRS_2024_3390764 crossref_primary_10_1177_24056456241297300 crossref_primary_10_3390_electronics9050731 crossref_primary_10_1109_ACCESS_2022_3205744 crossref_primary_10_1016_j_bas_2025_104208 crossref_primary_10_1109_TSE_2023_3305244 crossref_primary_10_1177_00220345221100169 crossref_primary_10_1049_ipr2_12661 crossref_primary_10_1109_ACCESS_2020_3032580 crossref_primary_10_1016_j_engappai_2022_105741 crossref_primary_10_1016_j_ijdrr_2023_103972 crossref_primary_10_1016_j_rse_2020_112107 crossref_primary_10_1016_j_eswa_2024_124613 crossref_primary_10_1002_smr_2543 crossref_primary_10_2139_ssrn_4197678 crossref_primary_10_1109_TII_2019_2898264 crossref_primary_10_3390_f14081596 crossref_primary_10_1109_ACCESS_2021_3107687 crossref_primary_10_3390_fire8020050 crossref_primary_10_12688_f1000research_20498_1 crossref_primary_10_1007_s00521_021_06139_8 crossref_primary_10_1186_s12911_021_01430_z crossref_primary_10_1109_ACCESS_2024_3522972 crossref_primary_10_1186_s12859_023_05582_9 crossref_primary_10_1109_ACCESS_2018_2884249 crossref_primary_10_12688_f1000research_20498_2 crossref_primary_10_1016_j_iot_2023_100687 crossref_primary_10_1016_j_knosys_2024_111682 crossref_primary_10_1016_j_eujim_2020_101114 crossref_primary_10_1117_1_JMI_9_4_044503 crossref_primary_10_1038_s41746_019_0170_5 crossref_primary_10_1016_j_chemolab_2024_105247 crossref_primary_10_1016_j_patrec_2020_02_007 crossref_primary_10_1016_j_neunet_2019_05_010 crossref_primary_10_1016_j_ecoinf_2020_101137 crossref_primary_10_1016_j_ins_2019_11_004 crossref_primary_10_1016_j_health_2025_100387 crossref_primary_10_3390_app11219783 crossref_primary_10_1021_acs_analchem_2c03020 crossref_primary_10_1109_TAI_2023_3298303 crossref_primary_10_1007_s10462_024_10831_1 crossref_primary_10_1016_j_nucengdes_2020_110699 crossref_primary_10_2196_67967 crossref_primary_10_1016_j_atech_2021_100028 crossref_primary_10_1007_s13349_022_00552_w crossref_primary_10_1016_j_jviromet_2024_115011 crossref_primary_10_1016_j_neunet_2023_07_030 crossref_primary_10_3390_app13052932 crossref_primary_10_1016_j_neucom_2022_01_004 crossref_primary_10_3390_rs14133075 crossref_primary_10_1016_j_jpsychires_2022_06_009 crossref_primary_10_1016_j_cmpb_2021_106281 crossref_primary_10_1016_j_cageo_2021_104968 crossref_primary_10_1016_j_ecoinf_2021_101423 crossref_primary_10_1016_j_jhydrol_2024_132250 crossref_primary_10_1186_s12911_022_01775_z crossref_primary_10_1016_j_cageo_2020_104430 crossref_primary_10_1109_ACCESS_2021_3063461 crossref_primary_10_1109_TCSVT_2021_3122110 crossref_primary_10_3389_fnbot_2021_775688 crossref_primary_10_1007_s10462_020_09820_x crossref_primary_10_1016_j_ijar_2022_08_007 crossref_primary_10_1155_2021_6619088 crossref_primary_10_3390_s21196451 crossref_primary_10_3390_s21238077 crossref_primary_10_1016_j_engappai_2020_103535 crossref_primary_10_1016_j_neucom_2024_128419 crossref_primary_10_1016_j_jdent_2025_105679 crossref_primary_10_1080_19475683_2020_1803402 crossref_primary_10_1109_TCYB_2022_3173356 crossref_primary_10_1016_j_neunet_2024_106932 crossref_primary_10_1016_j_rse_2024_114274 crossref_primary_10_32604_cmc_2024_048307 crossref_primary_10_1007_s10515_021_00319_5 crossref_primary_10_1109_ACCESS_2020_3031908 crossref_primary_10_1177_09544100221107252 crossref_primary_10_3390_jpm11060482 crossref_primary_10_3390_rs11212523 crossref_primary_10_1016_j_isci_2022_105331 crossref_primary_10_1038_s42256_025_01006_w crossref_primary_10_1016_j_compag_2024_109653 crossref_primary_10_1016_j_knosys_2022_109817 crossref_primary_10_1051_shsconf_202214402018 crossref_primary_10_1109_ACCESS_2024_3431534 crossref_primary_10_3390_cancers16234046 crossref_primary_10_1007_s10845_020_01579_w crossref_primary_10_3390_electronics14020280 crossref_primary_10_1145_3715073_3715082 crossref_primary_10_1016_j_jag_2023_103478 crossref_primary_10_1016_j_caeai_2024_100312 crossref_primary_10_1109_MAES_2019_2933972 crossref_primary_10_1016_j_asoc_2024_112050 crossref_primary_10_1016_j_media_2020_101715 crossref_primary_10_1080_17421772_2023_2214600 crossref_primary_10_1007_s11042_022_13617_1 crossref_primary_10_1109_ACCESS_2024_3358275 crossref_primary_10_1016_j_ins_2021_07_033 crossref_primary_10_3390_life14101248 crossref_primary_10_1186_s12984_020_00758_3 crossref_primary_10_1007_s10994_023_06397_8 crossref_primary_10_1155_2023_3018320 crossref_primary_10_3390_machines13010049 crossref_primary_10_1109_TKDE_2024_3443160 crossref_primary_10_3390_rs12060934 crossref_primary_10_1016_j_canrad_2021_06_027 crossref_primary_10_1186_s42492_020_00055_9 crossref_primary_10_3233_IDT_210037 crossref_primary_10_1016_j_neunet_2023_06_036 crossref_primary_10_1111_mice_12578 crossref_primary_10_3390_drones4040075 crossref_primary_10_1016_j_ecoinf_2021_101217 crossref_primary_10_1016_j_eswa_2020_113660 crossref_primary_10_1007_s13755_025_00343_9 crossref_primary_10_1038_s41598_019_44839_3 crossref_primary_10_1007_s00521_024_09483_7 crossref_primary_10_1038_s41576_021_00434_9 crossref_primary_10_3390_rs11070772 crossref_primary_10_1109_JBHI_2018_2885134 crossref_primary_10_1016_j_knosys_2024_112301 crossref_primary_10_3389_fgene_2022_912614 crossref_primary_10_1016_j_compbiomed_2022_106092 crossref_primary_10_3390_diagnostics13010067 crossref_primary_10_3389_frai_2019_00028 crossref_primary_10_3390_s23125485 crossref_primary_10_1016_j_knosys_2024_112306 crossref_primary_10_1002_ima_22465 crossref_primary_10_2147_JMDH_S472170 crossref_primary_10_1186_s12911_025_02900_4 crossref_primary_10_2174_0126662558286875231215054324 crossref_primary_10_1016_j_ascom_2022_100625 crossref_primary_10_3390_computers13110297 crossref_primary_10_1016_j_aei_2020_101131 crossref_primary_10_37391_ijeer_110203 crossref_primary_10_1016_j_neunet_2020_07_019 crossref_primary_10_1029_2024JB029194 crossref_primary_10_1073_pnas_2103091118 crossref_primary_10_1142_S1469026822500158 crossref_primary_10_1007_s11657_020_00802_8 crossref_primary_10_1016_j_neucom_2019_12_091 crossref_primary_10_1016_j_compag_2024_109859 crossref_primary_10_1016_j_eswa_2024_123138 crossref_primary_10_1093_mnras_staa1856 crossref_primary_10_1109_JBHI_2022_3141976 crossref_primary_10_1109_TPAMI_2023_3298433 crossref_primary_10_3390_drones5010006 crossref_primary_10_1109_ACCESS_2023_3255983 crossref_primary_10_1007_s40747_023_01225_x crossref_primary_10_1049_cit2_12152 crossref_primary_10_1007_s11633_023_1487_8 crossref_primary_10_1016_j_joen_2024_05_014 crossref_primary_10_1111_ppa_13988 crossref_primary_10_1109_TNNLS_2021_3106306 crossref_primary_10_1007_s11053_025_10462_5 crossref_primary_10_18048_2019_57_01 crossref_primary_10_1016_j_patcog_2023_109971 crossref_primary_10_1142_S0218001421520108 crossref_primary_10_1016_j_compscitech_2021_109091 crossref_primary_10_1016_j_compag_2025_109909 crossref_primary_10_1145_3630256 crossref_primary_10_1016_j_bspc_2024_106545 crossref_primary_10_3390_info13010009 crossref_primary_10_1016_j_comnet_2020_107315 crossref_primary_10_1016_j_chest_2022_03_044 crossref_primary_10_1080_08839514_2024_2411845 crossref_primary_10_3390_s22020497 crossref_primary_10_1007_s11704_023_3272_9 crossref_primary_10_1109_TSE_2021_3079841 crossref_primary_10_1109_TPWRD_2022_3202958 crossref_primary_10_3390_rs11243056 crossref_primary_10_1142_S1793351X22500040 crossref_primary_10_1038_s41598_021_93889_z crossref_primary_10_1038_s41598_022_26825_4 crossref_primary_10_1186_s12859_020_03914_7 crossref_primary_10_1007_s11063_021_10534_6 crossref_primary_10_1016_j_media_2022_102359 crossref_primary_10_3390_agriengineering6040243 crossref_primary_10_1016_j_chemolab_2025_105366 crossref_primary_10_1016_j_compag_2020_105792 crossref_primary_10_1016_j_neucom_2021_06_012 crossref_primary_10_3390_ijgi11120587 crossref_primary_10_1109_ACCESS_2021_3050548 crossref_primary_10_1109_TPAMI_2023_3275585 crossref_primary_10_1016_j_neucom_2020_11_009 crossref_primary_10_1109_ACCESS_2022_3202295 crossref_primary_10_1111_2041_210X_13099 crossref_primary_10_1016_j_eswa_2024_123153 crossref_primary_10_1109_LSP_2024_3451962 crossref_primary_10_1109_TNNLS_2022_3213522 crossref_primary_10_1190_geo2023_0149_1 crossref_primary_10_1093_llc_fqad046 crossref_primary_10_1109_JIOT_2020_2985694 crossref_primary_10_1016_j_bbe_2021_10_003 crossref_primary_10_1016_j_comcom_2023_04_002 crossref_primary_10_1016_j_jrras_2022_100461 crossref_primary_10_1088_2057_1976_ad4f73 crossref_primary_10_1038_s41598_022_18463_7 crossref_primary_10_1016_j_patcog_2021_108026 crossref_primary_10_1016_j_patcog_2022_108564 crossref_primary_10_1016_j_compbiomed_2021_104644 crossref_primary_10_1016_j_compbiomed_2024_109503 crossref_primary_10_1016_j_isprsjprs_2019_04_014 crossref_primary_10_1061__ASCE_NH_1527_6996_0000561 crossref_primary_10_1080_17538947_2023_2298245 crossref_primary_10_1177_10963480241230957 crossref_primary_10_1109_TGRS_2021_3097148 crossref_primary_10_3389_frai_2024_1299169 crossref_primary_10_1155_2019_7206096 crossref_primary_10_1029_2023SW003524 crossref_primary_10_3390_app112110373 crossref_primary_10_1051_itmconf_20246301025 crossref_primary_10_1016_j_agwat_2024_108692 crossref_primary_10_1109_ACCESS_2019_2899608 crossref_primary_10_3390_diagnostics12061410 crossref_primary_10_1016_j_eswa_2024_124230 crossref_primary_10_1016_j_media_2023_102881 crossref_primary_10_1049_iet_ipr_2019_1690 crossref_primary_10_1109_LRA_2020_2969947 crossref_primary_10_3390_app13063457 crossref_primary_10_1016_j_ophoto_2022_100016 crossref_primary_10_3390_diagnostics12102362 crossref_primary_10_3390_rs11232765 crossref_primary_10_3390_rs14040897 crossref_primary_10_1109_TGRS_2021_3064316 crossref_primary_10_1109_TPAMI_2024_3435937 crossref_primary_10_1016_j_jag_2022_102949 crossref_primary_10_32604_csse_2022_024695 crossref_primary_10_1016_j_bspc_2023_105637 crossref_primary_10_1016_j_imu_2022_100850 crossref_primary_10_1088_2632_2153_ad23fb crossref_primary_10_1109_TBDATA_2024_3352978 crossref_primary_10_1109_TNNLS_2022_3154204 crossref_primary_10_1016_j_neucom_2024_129115 crossref_primary_10_1063_1_5113532 crossref_primary_10_1007_s10664_021_10095_1 crossref_primary_10_1109_TMLCN_2025_3533427 crossref_primary_10_5351_KJAS_2024_37_5_615 crossref_primary_10_1186_s40494_024_01468_y crossref_primary_10_3233_ICA_220676 crossref_primary_10_1016_j_eswa_2020_114463 crossref_primary_10_1093_bib_bbaa272 crossref_primary_10_1109_ACCESS_2019_2955983 crossref_primary_10_1088_1674_4527_19_9_133 crossref_primary_10_1007_s00779_019_01292_3 crossref_primary_10_1007_s13369_021_05674_9 crossref_primary_10_1109_TGRS_2023_3274296 crossref_primary_10_3390_en18010059 crossref_primary_10_1016_j_engstruct_2022_115485 crossref_primary_10_1109_TPAMI_2024_3421300 crossref_primary_10_3847_1538_4357_ac9d91 crossref_primary_10_32604_cmes_2022_020263 crossref_primary_10_3390_s21165317 crossref_primary_10_1002_int_23068 crossref_primary_10_1016_j_measurement_2019_107459 crossref_primary_10_1016_j_health_2022_100060 crossref_primary_10_1186_s12903_023_03751_z crossref_primary_10_1016_j_eswa_2023_121806 crossref_primary_10_1016_j_jss_2023_111650 crossref_primary_10_1038_s41598_023_48751_9 crossref_primary_10_1016_j_ymssp_2021_108271 crossref_primary_10_3390_agronomy12081843 crossref_primary_10_1007_s11760_024_03651_x crossref_primary_10_1111_2041_210X_13335 crossref_primary_10_1016_j_marpetgeo_2020_104687 crossref_primary_10_1007_s10115_023_01975_7 crossref_primary_10_1016_j_eswa_2024_124399 crossref_primary_10_1007_s11227_023_05820_0 crossref_primary_10_1109_ACCESS_2024_3399204 crossref_primary_10_1109_TMI_2020_3046692 crossref_primary_10_1016_j_compag_2021_106059 crossref_primary_10_1016_j_biosystemseng_2019_04_007 crossref_primary_10_1080_2573234X_2021_1978337 crossref_primary_10_1109_TAI_2023_3275133 crossref_primary_10_1109_ACCESS_2020_3041672 crossref_primary_10_1371_journal_pbio_3001544 crossref_primary_10_1007_s10044_024_01387_5 crossref_primary_10_1016_j_ress_2021_107934 crossref_primary_10_3390_s21093169 crossref_primary_10_1016_j_neucom_2025_129606 crossref_primary_10_1016_j_neucom_2023_01_063 crossref_primary_10_1038_s41598_023_45532_2 crossref_primary_10_1007_s10994_022_06241_5 crossref_primary_10_1007_s11227_022_05037_7 crossref_primary_10_1080_07391102_2022_2112976 crossref_primary_10_3390_rs15164098 crossref_primary_10_3390_ijgi9020104 crossref_primary_10_1007_s10462_023_10557_6 crossref_primary_10_1007_s11263_024_02342_x crossref_primary_10_1016_j_isprsjprs_2022_02_013 crossref_primary_10_1155_2022_6805460 crossref_primary_10_1016_j_compag_2021_106065 crossref_primary_10_1109_TCE_2023_3275540 crossref_primary_10_3390_medicina57111230 crossref_primary_10_1093_icesjms_fsad165 crossref_primary_10_1109_ACCESS_2023_3262604 crossref_primary_10_1016_j_eswa_2019_112866 crossref_primary_10_1016_j_neucom_2025_129832 crossref_primary_10_1007_s11676_024_01768_w crossref_primary_10_1177_1088467X241305509 crossref_primary_10_1016_j_compeleceng_2023_108586 crossref_primary_10_1038_s41598_023_42847_y crossref_primary_10_11648_j_ijdsa_20241001_12 crossref_primary_10_1136_bjophthalmol_2021_319470 crossref_primary_10_3390_electronics12071542 crossref_primary_10_1109_TASE_2023_3270202 crossref_primary_10_1155_2021_9954204 crossref_primary_10_1016_j_mtbio_2023_100879 crossref_primary_10_3390_ijms21165710 crossref_primary_10_37394_23205_2020_19_22 crossref_primary_10_1109_ACCESS_2024_3444772 crossref_primary_10_3389_fpubh_2023_1241388 crossref_primary_10_1063_1_5144458 crossref_primary_10_1016_j_compedu_2020_104109 crossref_primary_10_1016_j_heliyon_2024_e37647 crossref_primary_10_1016_j_ipm_2021_102599 crossref_primary_10_1016_j_compbiomed_2019_05_002 crossref_primary_10_1088_1742_6596_1631_1_012046 crossref_primary_10_1007_s11042_024_19303_8 crossref_primary_10_1109_TAI_2022_3149971 crossref_primary_10_3390_app11041387 crossref_primary_10_1080_10618600_2021_1978470 crossref_primary_10_1109_JBHI_2020_3025381 crossref_primary_10_1109_JBHI_2023_3240136 crossref_primary_10_1007_s11432_023_3897_2 crossref_primary_10_1016_j_knosys_2022_109561 crossref_primary_10_1155_2021_6702625 crossref_primary_10_1016_j_imu_2021_100545 crossref_primary_10_26552_com_C_2022_3_D105_D115 crossref_primary_10_1016_j_eswa_2021_114994 crossref_primary_10_1007_s11042_022_12697_3 crossref_primary_10_1109_ACCESS_2021_3132046 crossref_primary_10_1109_TPAMI_2023_3278694 crossref_primary_10_3390_app122010623 crossref_primary_10_7717_peerj_cs_328 crossref_primary_10_1016_j_neucom_2025_129807 crossref_primary_10_1002_adom_202301337 crossref_primary_10_3390_s21020638 crossref_primary_10_1016_j_neunet_2021_07_003 crossref_primary_10_1109_JBHI_2023_3253208 crossref_primary_10_1016_j_compbiomed_2022_105402 crossref_primary_10_1016_j_knosys_2020_105833 crossref_primary_10_1016_j_diii_2019_07_002 crossref_primary_10_1016_j_measurement_2020_107703 crossref_primary_10_3390_rs13030389 crossref_primary_10_3390_app11010202 crossref_primary_10_1109_TCBB_2023_3238001 crossref_primary_10_1109_TMM_2023_3267887 crossref_primary_10_3390_sym12050836 crossref_primary_10_3390_s21237950 crossref_primary_10_1109_JSTSP_2024_3374593 crossref_primary_10_1007_s11390_023_3086_0 crossref_primary_10_4103_jpi_jpi_36_21 crossref_primary_10_3389_fspas_2020_600031 crossref_primary_10_3390_f16030492 crossref_primary_10_1002_ima_22703 crossref_primary_10_1109_THMS_2022_3189576 crossref_primary_10_1007_s11042_021_11747_6 crossref_primary_10_1177_0192623320986423 crossref_primary_10_1111_2041_210X_14239 crossref_primary_10_1007_s10278_024_01221_8 crossref_primary_10_1016_j_jdent_2024_105063 crossref_primary_10_1016_j_eswa_2024_125287 crossref_primary_10_1002_qre_3217 crossref_primary_10_1016_j_neucom_2022_11_020 crossref_primary_10_1016_j_ins_2021_03_001 crossref_primary_10_3390_app12125775 crossref_primary_10_1016_j_imavis_2024_105307 crossref_primary_10_1016_j_compbiomed_2022_106519 crossref_primary_10_1145_3636427 crossref_primary_10_1016_j_knosys_2022_108296 crossref_primary_10_1007_s11356_022_23280_6 crossref_primary_10_1109_TIV_2023_3325343 crossref_primary_10_1109_JBHI_2024_3439568 crossref_primary_10_1016_j_cj_2022_01_009 crossref_primary_10_1016_j_amjcard_2025_02_030 crossref_primary_10_1109_TCSVT_2023_3311142 crossref_primary_10_3390_rs14225793 crossref_primary_10_1016_j_bspc_2023_104704 crossref_primary_10_1111_2041_210X_13953 crossref_primary_10_1007_s10994_022_06296_4 crossref_primary_10_1109_TIM_2022_3232646 crossref_primary_10_1016_j_array_2021_100057 crossref_primary_10_1109_ACCESS_2020_3019336 crossref_primary_10_1007_s12021_020_09477_5 crossref_primary_10_1016_j_media_2024_103102 crossref_primary_10_3390_w14192939 crossref_primary_10_1007_s00521_021_06770_5 crossref_primary_10_1017_S0003055419000285 crossref_primary_10_1016_j_ijleo_2022_169986 crossref_primary_10_1016_j_dsp_2025_105149 crossref_primary_10_1016_j_patrec_2021_01_011 crossref_primary_10_3390_bdcc8090118 crossref_primary_10_1016_j_jcae_2024_100403 crossref_primary_10_1016_j_patrec_2023_05_035 crossref_primary_10_1007_s11263_022_01622_8 crossref_primary_10_1109_JSEN_2021_3131166 crossref_primary_10_1109_TITS_2020_3009725 crossref_primary_10_1016_j_ymeth_2022_11_004 crossref_primary_10_1109_TNSM_2024_3430052 crossref_primary_10_3389_fmicb_2022_886201 crossref_primary_10_1109_ACCESS_2020_3018498 crossref_primary_10_1021_acs_chemrestox_0c00316 crossref_primary_10_1177_25138502221063531 crossref_primary_10_1016_j_hydroa_2025_100201 crossref_primary_10_1109_TMI_2023_3310716 crossref_primary_10_3390_data3030028 crossref_primary_10_1016_j_eswa_2025_126695 crossref_primary_10_1007_s11042_020_10485_5 crossref_primary_10_1007_s42452_020_3128_y crossref_primary_10_1016_j_bspc_2025_107562 crossref_primary_10_1115_1_4044645 crossref_primary_10_1088_1361_6579_aaf34d crossref_primary_10_1071_MF23166 crossref_primary_10_1159_000510992 crossref_primary_10_1007_s11119_022_09959_3 crossref_primary_10_1007_s00530_021_00827_0 crossref_primary_10_1007_s10994_022_06208_6 crossref_primary_10_1016_j_eswa_2022_119054 crossref_primary_10_1016_j_eswa_2023_119578 crossref_primary_10_1109_JBHI_2023_3308697 crossref_primary_10_2174_1574893618666230320103421 crossref_primary_10_1007_s00603_023_03623_6 crossref_primary_10_3389_fenrg_2021_686616 crossref_primary_10_1016_j_acags_2025_100229 crossref_primary_10_1021_acs_iecr_9b06298 crossref_primary_10_1109_ACCESS_2021_3091810 crossref_primary_10_1785_0120230198 crossref_primary_10_1038_s41598_020_66505_9 crossref_primary_10_1186_s12911_021_01623_6 crossref_primary_10_3390_jcp4040040 crossref_primary_10_3390_electronics10050586 crossref_primary_10_1186_s12859_018_2474_x crossref_primary_10_1007_s11227_024_06301_8 crossref_primary_10_1016_j_phycom_2024_102355 crossref_primary_10_3390_app12136645 crossref_primary_10_1038_s41598_022_07111_9 crossref_primary_10_1016_j_jag_2024_104085 crossref_primary_10_32604_iasc_2023_041873 crossref_primary_10_1016_j_neunet_2024_106485 crossref_primary_10_1109_JBHI_2019_2929264 crossref_primary_10_1155_2021_6659022 crossref_primary_10_1109_JTEHM_2022_3180933 crossref_primary_10_1148_radiol_2019191061 crossref_primary_10_1016_j_promfg_2020_07_003 crossref_primary_10_1109_ACCESS_2024_3373001 crossref_primary_10_1371_journal_pgph_0001584 crossref_primary_10_2139_ssrn_4557797 crossref_primary_10_3390_info11040200 crossref_primary_10_1109_TSE_2024_3454605 crossref_primary_10_1128_spectrum_05237_22 crossref_primary_10_1007_s12524_024_01869_3 crossref_primary_10_1111_ddg_15113_g crossref_primary_10_1016_j_engappai_2025_110541 crossref_primary_10_1093_icesjms_fsab140 crossref_primary_10_3390_molecules25061317 crossref_primary_10_35940_ijeat_B3915_1212222 crossref_primary_10_1007_s00170_023_11021_z crossref_primary_10_1016_j_asoc_2024_111841 crossref_primary_10_1016_j_compmedimag_2021_101866 crossref_primary_10_1093_mnras_staa2265 crossref_primary_10_1109_ACCESS_2023_3341755 crossref_primary_10_1038_s41598_022_26180_4 crossref_primary_10_1002_cyto_a_24514 crossref_primary_10_2166_wst_2023_097 crossref_primary_10_3389_fbioe_2024_1465108 crossref_primary_10_3390_geomatics1010004 crossref_primary_10_1109_ACCESS_2024_3417822 crossref_primary_10_1109_ACCESS_2020_2975640 crossref_primary_10_1109_TVT_2020_3003933 crossref_primary_10_2514_1_I011508 crossref_primary_10_1080_08839514_2024_2406712 crossref_primary_10_1177_14759217221139730 crossref_primary_10_1016_j_jag_2024_104029 crossref_primary_10_1002_cpe_8103 crossref_primary_10_1148_ryai_220010 crossref_primary_10_3389_feart_2023_1285138 crossref_primary_10_1001_jamanetworkopen_2021_19100 crossref_primary_10_1088_1757_899X_1099_1_012077 crossref_primary_10_1002_mrm_27166 crossref_primary_10_1016_j_bspc_2021_103010 crossref_primary_10_1021_acs_jcim_4c00159 crossref_primary_10_3390_rs12172839 crossref_primary_10_1109_TBDATA_2023_3313029 crossref_primary_10_1016_j_patrec_2019_07_006 crossref_primary_10_1080_07038992_2021_1910499 crossref_primary_10_3390_app12031600 crossref_primary_10_1002_eng2_12298 crossref_primary_10_1007_s10994_022_06185_w crossref_primary_10_1016_j_artmed_2021_102017 crossref_primary_10_1017_pan_2021_9 crossref_primary_10_1177_15910199221140962 crossref_primary_10_1007_s10278_022_00618_7 crossref_primary_10_1200_CCI_20_00060 crossref_primary_10_1016_j_irbm_2022_09_006 crossref_primary_10_3390_ai5040105 crossref_primary_10_1109_ACCESS_2023_3327463 crossref_primary_10_3390_w17010021 crossref_primary_10_1007_s10278_024_01018_9 crossref_primary_10_2196_14952 crossref_primary_10_1111_adj_12812 crossref_primary_10_1016_j_jag_2024_104272 crossref_primary_10_1371_journal_pcbi_1009257 crossref_primary_10_1148_radiol_2020200334 crossref_primary_10_2139_ssrn_4182236 crossref_primary_10_4018_IJFC_2018070103 crossref_primary_10_1016_j_ecoinf_2023_102262 crossref_primary_10_1002_jrs_5750 crossref_primary_10_1002_acm2_70061 crossref_primary_10_2196_18082 crossref_primary_10_1109_TNNLS_2020_3007943 crossref_primary_10_1007_s10994_021_06087_3 crossref_primary_10_1016_j_eswax_2019_100003 crossref_primary_10_1016_j_media_2021_101997 crossref_primary_10_1093_mnras_stab2041 crossref_primary_10_1115_1_4065754 crossref_primary_10_1080_08839514_2021_1975393 crossref_primary_10_1016_j_engappai_2023_106950 crossref_primary_10_1016_j_isprsjprs_2022_04_012 crossref_primary_10_3390_s22176441 crossref_primary_10_1016_j_ssci_2021_105390 crossref_primary_10_3390_ijerph191912378 crossref_primary_10_3390_math11132996 crossref_primary_10_4018_IJNCR_2020010104 crossref_primary_10_1016_j_bspc_2023_104962 crossref_primary_10_1016_j_eswa_2021_115673 crossref_primary_10_1109_JOE_2022_3221127 crossref_primary_10_1186_s12911_019_0899_4 crossref_primary_10_3390_atmos15060631 crossref_primary_10_1016_j_neunet_2023_09_022 crossref_primary_10_1145_3369798 crossref_primary_10_3390_agronomy12040906 crossref_primary_10_1016_j_jretconser_2021_102573 crossref_primary_10_1109_ACCESS_2020_2975630 crossref_primary_10_1109_JSEN_2024_3360408 crossref_primary_10_1162_neco_a_01470 crossref_primary_10_1111_jiec_13340 crossref_primary_10_1016_j_knosys_2024_111504 crossref_primary_10_1007_s11869_019_00734_4 crossref_primary_10_1016_j_ssci_2024_106677 crossref_primary_10_1016_j_cose_2023_103347 crossref_primary_10_3390_jmse12122203 crossref_primary_10_1109_TGRS_2024_3444045 crossref_primary_10_1109_TITS_2023_3256442 crossref_primary_10_1016_j_mehy_2020_109761 crossref_primary_10_1016_j_neucom_2023_03_020 crossref_primary_10_1109_TIM_2023_3292952 crossref_primary_10_1080_07038992_2023_2247091 crossref_primary_10_3390_app10041276 crossref_primary_10_1007_s10044_022_01103_1 crossref_primary_10_1080_09524622_2020_1835539 crossref_primary_10_1002_ece3_7591 crossref_primary_10_1016_j_artint_2021_103602 crossref_primary_10_1080_02678292_2023_2292635 crossref_primary_10_1007_s00521_023_08290_w crossref_primary_10_1007_s11263_024_01998_9 crossref_primary_10_1177_0192623320973986 crossref_primary_10_1016_j_neunet_2020_10_004 crossref_primary_10_1109_TCSVT_2023_3297842 crossref_primary_10_1016_j_autcon_2022_104342 crossref_primary_10_1117_1_NPh_10_3_035004 crossref_primary_10_3389_fpls_2021_671134 crossref_primary_10_3390_app142311093 crossref_primary_10_1186_s13007_020_0563_0 crossref_primary_10_3390_s21196511 crossref_primary_10_1109_ACCESS_2022_3157316 crossref_primary_10_1016_j_softx_2020_100630 crossref_primary_10_1371_journal_pone_0289613 crossref_primary_10_3390_app11083331 crossref_primary_10_3389_fpls_2019_00941 crossref_primary_10_1109_ACCESS_2021_3116034 crossref_primary_10_1515_itit_2023_0050 crossref_primary_10_1016_j_cmpb_2023_107804 crossref_primary_10_1111_ddg_15113 crossref_primary_10_3390_app13169146 crossref_primary_10_1186_s40537_019_0225_0 crossref_primary_10_1016_j_neucom_2020_12_122 crossref_primary_10_1007_s00330_024_11181_w crossref_primary_10_1186_s41747_025_00557_2 crossref_primary_10_5115_acb_22_205 crossref_primary_10_1109_ACCESS_2020_3022242 crossref_primary_10_1016_j_eplepsyres_2022_106861 crossref_primary_10_1016_j_procs_2022_11_349 crossref_primary_10_1016_j_engappai_2024_108297 crossref_primary_10_1016_j_patter_2022_100464 crossref_primary_10_1051_0004_6361_202142751 crossref_primary_10_1016_j_rse_2021_112751 crossref_primary_10_1007_s13042_019_01001_9 crossref_primary_10_3390_diagnostics12020414 crossref_primary_10_1007_s00138_023_01480_5 crossref_primary_10_1109_TKDE_2021_3061428 crossref_primary_10_1007_s10489_024_05754_x crossref_primary_10_3390_s23125768 crossref_primary_10_1155_2021_1735386 crossref_primary_10_1016_j_compbiomed_2020_103735 crossref_primary_10_1007_s12652_023_04602_z crossref_primary_10_3390_bioengineering9090480 crossref_primary_10_1016_j_ecoinf_2023_102233 crossref_primary_10_1021_acs_jcim_1c00086 crossref_primary_10_1016_j_scico_2024_103156 crossref_primary_10_1088_1361_6579_ad2218 crossref_primary_10_1016_j_iswa_2023_200215 crossref_primary_10_1007_s11042_023_16181_4 crossref_primary_10_1109_TMI_2021_3066295 crossref_primary_10_1145_3689036 crossref_primary_10_1016_j_rsase_2025_101505 crossref_primary_10_1016_j_ijdrr_2019_101243 crossref_primary_10_1111_mice_12832 crossref_primary_10_1007_s10120_019_00992_2 crossref_primary_10_1016_j_scitotenv_2019_134723 crossref_primary_10_1186_s40537_023_00738_z crossref_primary_10_1002_cyto_a_23701 crossref_primary_10_1016_j_ins_2021_12_083 crossref_primary_10_7717_peerj_cs_2286 crossref_primary_10_1109_ACCESS_2019_2923022 crossref_primary_10_3390_ijgi10090600 crossref_primary_10_1016_j_bbcan_2021_188515 crossref_primary_10_1007_s12205_024_1587_1 crossref_primary_10_1029_2022EA002338 crossref_primary_10_3390_life14121602 crossref_primary_10_1109_TIM_2023_3264047 crossref_primary_10_1021_acs_jcim_0c00565 crossref_primary_10_1109_JSTARS_2023_3335891 crossref_primary_10_1145_3636512 crossref_primary_10_1109_ACCESS_2020_3025941 crossref_primary_10_1016_j_aei_2024_102684 crossref_primary_10_3390_s21051906 crossref_primary_10_1109_ACCESS_2022_3167397 crossref_primary_10_1016_j_joen_2019_03_016 crossref_primary_10_1080_2150704X_2023_2270107 crossref_primary_10_1016_j_compbiomed_2025_109772 crossref_primary_10_1109_TKDE_2023_3323401 crossref_primary_10_1038_s41598_022_21017_6 crossref_primary_10_1117_1_OE_63_5_054117 crossref_primary_10_1038_s41598_021_03546_8 crossref_primary_10_1111_raq_12726 crossref_primary_10_1088_1361_6560_ac72f0 crossref_primary_10_1109_TSM_2019_2940334 crossref_primary_10_3390_app13148403 crossref_primary_10_1109_TNNLS_2021_3106484 crossref_primary_10_1016_j_engappai_2020_103878 crossref_primary_10_1007_s11042_023_17583_0 crossref_primary_10_1016_j_compbiomed_2022_106178 crossref_primary_10_1109_ACCESS_2023_3240515 crossref_primary_10_3390_app11083301 crossref_primary_10_1007_s10489_021_02983_2 crossref_primary_10_1016_j_artd_2023_101308 crossref_primary_10_1016_j_engappai_2024_109580 crossref_primary_10_1587_transinf_2021HCK0001 crossref_primary_10_1007_s11633_021_1291_2 crossref_primary_10_1109_TNNLS_2024_3350363 crossref_primary_10_1016_j_ins_2021_11_058 crossref_primary_10_1007_s00521_021_06066_8 crossref_primary_10_1016_j_tust_2022_104399 crossref_primary_10_1109_TCAD_2022_3227815 crossref_primary_10_3390_math10224286 crossref_primary_10_1007_s11760_024_03701_4 crossref_primary_10_3389_fonc_2020_00490 crossref_primary_10_3390_s25051437 crossref_primary_10_1016_j_imu_2022_101139 crossref_primary_10_1007_s00521_021_06138_9 crossref_primary_10_1016_j_patcog_2021_108302 crossref_primary_10_3390_s21103500 crossref_primary_10_1016_j_neucom_2024_128530 crossref_primary_10_1016_j_jenvman_2021_111979 crossref_primary_10_3390_e24070974 crossref_primary_10_3390_rs15071768 crossref_primary_10_1007_s11263_022_01716_3 crossref_primary_10_1016_j_neunet_2020_12_003 crossref_primary_10_3390_rs14071552 crossref_primary_10_1109_ACCESS_2020_2985097 crossref_primary_10_1038_s41598_021_87737_3 crossref_primary_10_3390_agronomy13030887 crossref_primary_10_3390_cancers16193417 crossref_primary_10_1007_s11548_021_02498_8 crossref_primary_10_1007_s13246_020_00952_6 crossref_primary_10_1038_s41598_025_89574_0 crossref_primary_10_1016_j_media_2022_102490 crossref_primary_10_3390_e22091058 crossref_primary_10_3390_rs15184572 crossref_primary_10_1002_smtd_202101619 crossref_primary_10_1016_j_ins_2023_01_074 crossref_primary_10_3390_drones8090484 crossref_primary_10_3390_rs16020390 crossref_primary_10_1016_j_nicl_2023_103482 crossref_primary_10_7717_peerj_cs_2088 crossref_primary_10_1007_s00521_024_09582_5 crossref_primary_10_1007_s13278_024_01328_4 crossref_primary_10_1155_2021_8667868 crossref_primary_10_1136_jcp_2023_209215 crossref_primary_10_1051_0004_6361_202347244 crossref_primary_10_1016_j_jretconser_2024_103865 crossref_primary_10_1371_journal_pone_0274522 crossref_primary_10_1016_j_media_2020_101836 crossref_primary_10_37221_eaef_15_2_47 crossref_primary_10_3390_diagnostics12061318 crossref_primary_10_1371_journal_pone_0271260 crossref_primary_10_1109_ACCESS_2021_3109780 crossref_primary_10_1109_TMRB_2023_3260273 crossref_primary_10_1007_s00530_024_01317_9 crossref_primary_10_1002_rse2_205 crossref_primary_10_1016_j_caeai_2024_100200 crossref_primary_10_1016_j_compbiomed_2025_109971 crossref_primary_10_1007_s13042_024_02241_0 crossref_primary_10_1016_j_compbiomed_2021_104712 crossref_primary_10_1109_ACCESS_2024_3442569 crossref_primary_10_1007_s11263_023_01831_9 crossref_primary_10_1038_s41746_024_01196_4 crossref_primary_10_1109_TMI_2021_3123300 crossref_primary_10_1109_TCSVT_2023_3321733 crossref_primary_10_1108_IJBPA_01_2022_0018 crossref_primary_10_1109_ACCESS_2021_3096822 crossref_primary_10_1109_TBME_2021_3136753 crossref_primary_10_1016_j_engstruct_2022_115291 crossref_primary_10_1145_3624774 crossref_primary_10_1111_2041_210X_14031 crossref_primary_10_1007_s10207_023_00686_y crossref_primary_10_1016_j_compositesa_2022_106973 crossref_primary_10_1007_s11263_024_01996_x crossref_primary_10_1007_s11263_024_02081_z crossref_primary_10_1016_j_autcon_2022_104167 crossref_primary_10_1007_s00146_021_01370_2 crossref_primary_10_1007_s11548_024_03061_x crossref_primary_10_1007_s12652_020_01773_x crossref_primary_10_1016_j_engappai_2022_104959 crossref_primary_10_1515_bmt_2020_0106 crossref_primary_10_3390_app12042158 crossref_primary_10_1007_s10994_022_06268_8 crossref_primary_10_1007_s11548_019_02070_5 crossref_primary_10_1109_TNNLS_2021_3105104 crossref_primary_10_1007_s10489_023_04486_8 crossref_primary_10_1016_j_ecoinf_2024_102927 crossref_primary_10_1007_s11042_021_10612_w crossref_primary_10_1109_TGRS_2022_3211847 crossref_primary_10_1109_TPWRS_2023_3326137 crossref_primary_10_1587_transfun_2021EAP1036 crossref_primary_10_1063_1_5136269 crossref_primary_10_1109_TSMC_2020_2982226 crossref_primary_10_3390_ani12091177 crossref_primary_10_1093_mnras_stac3770 crossref_primary_10_1111_ina_12780 crossref_primary_10_1016_j_artint_2021_103635 crossref_primary_10_1016_j_isprsjprs_2023_09_001 crossref_primary_10_1016_j_oceaneng_2021_110130 crossref_primary_10_1007_s11227_025_06920_9 crossref_primary_10_1109_ACCESS_2019_2921241 crossref_primary_10_1016_j_measen_2024_101080 crossref_primary_10_1080_07038992_2019_1682980 crossref_primary_10_1007_s12008_024_02045_0 crossref_primary_10_1016_j_apenergy_2022_120279 crossref_primary_10_1109_TNNLS_2023_3321753 crossref_primary_10_1088_1361_6579_ad2c13 crossref_primary_10_3390_pharmaceutics11090466 crossref_primary_10_3390_f16030513 crossref_primary_10_1109_TMC_2024_3476340 crossref_primary_10_1016_j_ecoinf_2021_101350 crossref_primary_10_1016_j_eng_2023_07_014 crossref_primary_10_3390_rs16183494 crossref_primary_10_2139_ssrn_4046060 crossref_primary_10_1016_j_jvscit_2022_04_003 crossref_primary_10_3389_fenvs_2022_1044706 crossref_primary_10_1016_j_heliyon_2024_e38448 crossref_primary_10_1016_j_cag_2021_09_007 crossref_primary_10_1111_jep_14041 crossref_primary_10_1016_j_isprsjprs_2021_07_007 crossref_primary_10_3390_app13053287 crossref_primary_10_1016_j_addma_2021_101965 crossref_primary_10_1071_WR23151 crossref_primary_10_1109_TVCG_2022_3189094 crossref_primary_10_1016_j_neucom_2022_08_031 crossref_primary_10_1109_TIM_2023_3246470 crossref_primary_10_1016_j_jss_2024_112077 crossref_primary_10_1109_TIM_2023_3343775 crossref_primary_10_3390_app10010188 crossref_primary_10_1007_s10278_024_01383_5 crossref_primary_10_3390_atmos15101229 crossref_primary_10_1016_j_acra_2023_02_016 crossref_primary_10_1088_2632_2153_acf362 crossref_primary_10_1109_ACCESS_2022_3187140 crossref_primary_10_1109_TIFS_2024_3488527 crossref_primary_10_1109_ACCESS_2019_2954170 crossref_primary_10_1007_s11042_020_09155_3 crossref_primary_10_1109_ACCESS_2021_3122998 crossref_primary_10_3389_feart_2022_1106799 crossref_primary_10_1016_j_ibmed_2021_100034 crossref_primary_10_1007_s10115_022_01772_8 crossref_primary_10_1016_j_yebeh_2024_109732 crossref_primary_10_1007_s00034_019_01249_0 crossref_primary_10_1016_j_ecoinf_2025_103046 crossref_primary_10_54021_seesv5n2_772 crossref_primary_10_1016_j_ymeth_2019_04_008 crossref_primary_10_1002_ima_22558 crossref_primary_10_1016_j_measurement_2020_107785 crossref_primary_10_1109_JSTARS_2022_3184156 crossref_primary_10_1016_j_jbi_2019_103184 crossref_primary_10_1016_j_infrared_2021_103987 crossref_primary_10_1097_ICU_0000000000000695 crossref_primary_10_1016_j_scitotenv_2022_155807 crossref_primary_10_1016_j_neunet_2022_03_027 crossref_primary_10_1016_j_knosys_2020_106087 crossref_primary_10_1021_acs_jcim_8b00350 crossref_primary_10_1016_j_compbiolchem_2023_107929 crossref_primary_10_1186_s12903_024_03898_3 crossref_primary_10_3390_molecules26041111 crossref_primary_10_3390_s18041142 crossref_primary_10_3390_jmse8100770 crossref_primary_10_3390_s21082803 crossref_primary_10_1016_j_neucom_2023_01_023 crossref_primary_10_1111_mice_12667 crossref_primary_10_1016_j_aei_2019_101009 crossref_primary_10_2139_ssrn_4102846 crossref_primary_10_3389_fonc_2024_1335740 crossref_primary_10_1016_j_compbiomed_2021_104527 crossref_primary_10_3390_electronics10243124 crossref_primary_10_1007_s00417_022_05919_9 crossref_primary_10_3389_fonc_2020_01186 crossref_primary_10_3390_healthcare9080938 crossref_primary_10_1016_j_ress_2023_109832 crossref_primary_10_1080_08839514_2025_2468534 crossref_primary_10_1007_s00521_022_07167_8 crossref_primary_10_3390_electronics11091322 crossref_primary_10_1038_s41598_021_94750_z crossref_primary_10_36306_konjes_1078358 |
| Cites_doi | 10.1080/01431161.2013.810825 10.1109/TKDE.2008.239 10.1162/neco.1991.3.4.461 10.1613/jair.953 10.1109/CVPR.2016.90 10.1016/S0933-3657(01)00092-6 10.1016/j.jbi.2004.07.008 10.4103/2153-3539.186902 10.1109/TKDE.2006.17 10.3233/IDA-2002-6504 10.1023/A:1007452223027 10.1109/TSMCB.2008.2007853 10.1016/0031-3203(81)90102-3 10.1145/1007730.1007737 10.1007/s11263-015-0816-y 10.1016/j.asoc.2013.09.014 10.1016/j.neunet.2007.12.031 10.1109/CVPRW.2015.7301352 10.1162/neco.1989.1.4.541 10.1016/S0031-3203(96)00142-2 10.1109/5.726791 10.1023/A:1024099825458 10.1016/S0893-6080(98)00116-6 10.1016/j.media.2016.05.004 10.1145/1007730.1007736 10.1162/089976600300015691 10.1007/11538059_91 |
| ContentType | Journal Article |
| Copyright | 2018 Elsevier Ltd Copyright © 2018 Elsevier Ltd. All rights reserved. |
| Copyright_xml | – notice: 2018 Elsevier Ltd – notice: Copyright © 2018 Elsevier Ltd. All rights reserved. |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 ADTPV AOWAS D8V |
| DOI | 10.1016/j.neunet.2018.07.011 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic SwePub SwePub Articles SWEPUB Kungliga Tekniska Högskolan |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic MEDLINE |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1879-2782 |
| EndPage | 259 |
| ExternalDocumentID | oai_DiVA_org_kth_235561 30092410 10_1016_j_neunet_2018_07_011 S0893608018302107 |
| Genre | Journal Article |
| GroupedDBID | --- --K --M -~X .DC .~1 0R~ 123 186 1B1 1RT 1~. 1~5 29N 4.4 457 4G. 53G 5RE 5VS 6TJ 7-5 71M 8P~ 9JM 9JN AABNK AACTN AADPK AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXLA AAXUO AAYFN ABAOU ABBOA ABCQJ ABEFU ABFNM ABFRF ABHFT ABIVO ABJNI ABLJU ABMAC ABXDB ABYKQ ACAZW ACDAQ ACGFO ACGFS ACIUM ACNNM ACRLP ACZNC ADBBV ADEZE ADGUI ADJOM ADMUD ADRHT AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AFXIZ AGHFR AGUBO AGWIK AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ARUGR ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q G8K GBLVA GBOLZ HLZ HMQ HVGLF HZ~ IHE J1W JJJVA K-O KOM KZ1 LG9 LMP M2V M41 MHUIS MO0 MOBAO MVM N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SCC SDF SDG SDP SES SEW SNS SPC SPCBC SSN SST SSV SSW SSZ T5K TAE UAP UNMZH VOH WUQ XPP ZMT ~G- AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP BNPGV CITATION SSH CGR CUY CVF ECM EIF NPM 7X8 ADTPV AOWAS D8V EFKBS |
| ID | FETCH-LOGICAL-c512t-54f35ea174cb6c856f69d5f36f023eea43e8fe47b409c6e22e7f0f5d27600dd3 |
| IEDL.DBID | .~1 |
| ISSN | 0893-6080 1879-2782 |
| IngestDate | Thu Aug 21 07:29:37 EDT 2025 Fri Jul 11 08:27:24 EDT 2025 Thu Apr 03 07:02:07 EDT 2025 Tue Jul 01 01:24:32 EDT 2025 Thu Apr 24 23:07:37 EDT 2025 Fri Feb 23 02:47:28 EST 2024 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Deep learning Convolutional neural networks Class imbalance Image classification |
| Language | English |
| License | Copyright © 2018 Elsevier Ltd. All rights reserved. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c512t-54f35ea174cb6c856f69d5f36f023eea43e8fe47b409c6e22e7f0f5d27600dd3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0003-3222-0203 |
| OpenAccessLink | http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-219872 |
| PMID | 30092410 |
| PQID | 2087593601 |
| PQPubID | 23479 |
| PageCount | 11 |
| ParticipantIDs | swepub_primary_oai_DiVA_org_kth_235561 proquest_miscellaneous_2087593601 pubmed_primary_30092410 crossref_primary_10_1016_j_neunet_2018_07_011 crossref_citationtrail_10_1016_j_neunet_2018_07_011 elsevier_sciencedirect_doi_10_1016_j_neunet_2018_07_011 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2018-10-01 |
| PublicationDateYYYYMMDD | 2018-10-01 |
| PublicationDate_xml | – month: 10 year: 2018 text: 2018-10-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Neural networks |
| PublicationTitleAlternate | Neural Netw |
| PublicationYear | 2018 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Goodfellow, I. J., Warde-Farley, D., Mirza, M., Courville, A. C., & Bengio, Y. (2013). Maxout networks. In Lawrence, Burns, Back, Tsoi, Giles (b39) 1998 Wang, Makond, Chen, Wang (b64) 2014; 20 Glorot, X., & Bengio, Y. (2010). Understanding the difficulty of training deep feedforward neural networks. In Havaei, Davy, Warde-Farley, Biard, Courville, Bengio (b19) 2017; 35 Van Horn, G., Mac Aodha, O., Song, Y., Shepard, A., Adam, H., & Perona, P. et al., The inaturalist challenge 2017 dataset, arXiv preprint Kubat, Holte, Matwin (b36) 1998; 30 (pp. 179–186), Nashville, USA. Barandela, Rangel, Sánchez, Ferri (b1) 2003 Japkowicz, N., Myers, C., & Gluck, M. et al., (1995). A novelty detection approach to classification. In Chan, P. K., & Stolfo, S. J. (1998). Toward scalable learning with non-uniform class and cost distributions: A case study in credit card fraud detection. In Ling, C. X., & Li, C. (1998). Data mining for direct marketing: Problems and solutions. In Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. Striving for simplicity: The all convolutional net, arXiv preprint Liu, Wu, Zhou (b46) 2009; 39 (pp. 164–168). Mac Namee, Cunningham, Byrne, Corrigan (b47) 2002; 24 Qian (b52) 1999; 12 (pp. 573–580), New York, NY. He, Zhang, Ren, Sun (b21) 2015 Mazurowski, Habas, Zurada, Lo, Baker, Tourassi (b49) 2008; 21 Raj, Magg, Wermter (b54) 2016 Cardie, C., & Howe, N. (1997). Improving minority class prediction using case-specific feature weights. In Janowczyk, Madabhushi (b25) 2016; 7 He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Japkowicz, Stephen (b28) 2002; 6 . (pp. 1–8). Grzymala-Busse, Goodwin, Grzymala-Busse, Zheng (b14) 2004 (pp. 519–524). Elkan (b11) 2001 Xiao, Hays, Ehinger, Oliva, Torralba (b65) 2010 Wang, Liu, Wu, Cao, Meng, Kennedy (b63) 2016 (pp. 518–523). Zhou, Liu (b67) 2006; 18 LeCun, Bottou, Bengio, Haffner (b41) 1998 Zeiler, Fergus (b66) 2014 Beijbom, Edmunds, Kline, Mitchell, Kriegman (b2) 2012 Jia, Shelhamer, Donahue, Karayev, Long, Girshick (b29) 2014 Jo, Japkowicz (b30) 2004; 6 Shen, Lin, Huang (b57) 2016 Ling, C. X., Huang, J., & Zhang, H. (2003). Auc: a statistically consistent and more discriminating measure than accuracy. In Russakovsky, Deng, Su, Krause, Satheesh, Ma (b56) 2015; 115 (pp. 57–65). Chung, Y. A., Lin, H. T., & Yang, S. W. Cost-aware pre-training for multiclass cost-sensitive deep learning, arXiv preprint Bradley (b3) 1997; 30 (pp. 34–42). Johnson, Tateishi, Hoan (b31) 2013; 34 (pp. 1319–1327). Kubat, M., & Matwin, S. et al., (1997). Addressing the curse of imbalanced training sets: one-sided selection. In Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., & Shuai, B. et al., Recent advances in convolutional neural networks, arXiv preprint Ioffe, S., & Szegedy, C. Batch normalization: Accelerating deep network training by reducing internal covariate shift, arXiv preprint Japkowicz, Hanson, Gluck (b26) 2000; 12 (pp. 249–256). (pp. 73–79). Chawla, Bowyer, Hall, Kegelmeyer (b7) 2002; 16 Maloof, M. A. (2003). Learning when data sets are imbalanced and when costs are unequal and unknown. In Pedregosa, Varoquaux, Gramfort, Michel, Thirion, Grisel (b50) 2011; 12 Radivojac, Chawla, Dunker, Obradovic (b53) 2004; 37 Kukar, M., & Kononenko, I. et al., (1998). Cost-sensitive learning with neural networks. In Han, Wang, Mao (b18) 2005 (pp. 770–778). Provost, Domingos (b51) 2003; 52 Krizhevsky, A., & Hinton, G. Learning multiple layers of features from tiny images. Khan, S. H., Bennamoun, M., Sohel, F., & Togneri, R. Cost sensitive learning of deep feature representations from imbalanced data, arXiv preprint Chawla, Lazarevic, Hall, Bowyer (b8) 2003 Guo, Viktor (b16) 2004; 6 Jaccard, Rogers, Morton, Griffin (b24) 2016 LeCun, Boser, Denker, Henderson, Howard, Hubbard (b40) 1989; 1 Koplowitz, Brown (b33) 1981; 13 Simon, M., Rodner, E., & Denzler, J. Imagenet pre-trained models with batch normalization, arXiv preprint Chawla (b6) 2005 Haixiang, Yijing, Shang, Mingyun, Yuanyue, Bing (b17) 2016 Drummond, C., & Holte, R. C. et al., (2009). C4.5, class imbalance, and cost sensitivity: why under-sampling beats over-sampling. In Krizhevsky, Sutskever, Hinton (b35) 2012 Richard, Lippmann (b55) 1991; 3 Lee, Cho (b42) 2006 Simonyan, K., & Zisserman, A. Very deep convolutional networks for large-scale image recognition, arXiv preprint (pp. 445–449). Sohn, H., Worden, K., & Farrar, C. R. (2001). Novelty detection using auto-associative neural network. In He, Garcia (b20) 2009; 21 Levi, G., & Hassner, T. (2015). Age and gender classification using convolutional neural networks. In Russakovsky (10.1016/j.neunet.2018.07.011_b56) 2015; 115 Haixiang (10.1016/j.neunet.2018.07.011_b17) 2016 Radivojac (10.1016/j.neunet.2018.07.011_b53) 2004; 37 10.1016/j.neunet.2018.07.011_b23 10.1016/j.neunet.2018.07.011_b22 Jia (10.1016/j.neunet.2018.07.011_b29) 2014 10.1016/j.neunet.2018.07.011_b61 Jo (10.1016/j.neunet.2018.07.011_b30) 2004; 6 10.1016/j.neunet.2018.07.011_b60 Krizhevsky (10.1016/j.neunet.2018.07.011_b35) 2012 10.1016/j.neunet.2018.07.011_b62 Barandela (10.1016/j.neunet.2018.07.011_b1) 2003 LeCun (10.1016/j.neunet.2018.07.011_b40) 1989; 1 10.1016/j.neunet.2018.07.011_b27 Beijbom (10.1016/j.neunet.2018.07.011_b2) 2012 Janowczyk (10.1016/j.neunet.2018.07.011_b25) 2016; 7 Japkowicz (10.1016/j.neunet.2018.07.011_b26) 2000; 12 Han (10.1016/j.neunet.2018.07.011_b18) 2005 Koplowitz (10.1016/j.neunet.2018.07.011_b33) 1981; 13 Chawla (10.1016/j.neunet.2018.07.011_b7) 2002; 16 10.1016/j.neunet.2018.07.011_b10 10.1016/j.neunet.2018.07.011_b12 Wang (10.1016/j.neunet.2018.07.011_b64) 2014; 20 He (10.1016/j.neunet.2018.07.011_b21) 2015 Kubat (10.1016/j.neunet.2018.07.011_b36) 1998; 30 Japkowicz (10.1016/j.neunet.2018.07.011_b28) 2002; 6 He (10.1016/j.neunet.2018.07.011_b20) 2009; 21 10.1016/j.neunet.2018.07.011_b58 10.1016/j.neunet.2018.07.011_b13 Richard (10.1016/j.neunet.2018.07.011_b55) 1991; 3 Chawla (10.1016/j.neunet.2018.07.011_b6) 2005 10.1016/j.neunet.2018.07.011_b15 10.1016/j.neunet.2018.07.011_b59 Bradley (10.1016/j.neunet.2018.07.011_b3) 1997; 30 Raj (10.1016/j.neunet.2018.07.011_b54) 2016 Jaccard (10.1016/j.neunet.2018.07.011_b24) 2016 Pedregosa (10.1016/j.neunet.2018.07.011_b50) 2011; 12 10.1016/j.neunet.2018.07.011_b43 10.1016/j.neunet.2018.07.011_b45 10.1016/j.neunet.2018.07.011_b44 Elkan (10.1016/j.neunet.2018.07.011_b11) 2001 Mazurowski (10.1016/j.neunet.2018.07.011_b49) 2008; 21 Zeiler (10.1016/j.neunet.2018.07.011_b66) 2014 Mac Namee (10.1016/j.neunet.2018.07.011_b47) 2002; 24 Lawrence (10.1016/j.neunet.2018.07.011_b39) 1998 10.1016/j.neunet.2018.07.011_b48 10.1016/j.neunet.2018.07.011_b9 Wang (10.1016/j.neunet.2018.07.011_b63) 2016 Zhou (10.1016/j.neunet.2018.07.011_b67) 2006; 18 Provost (10.1016/j.neunet.2018.07.011_b51) 2003; 52 Chawla (10.1016/j.neunet.2018.07.011_b8) 2003 Grzymala-Busse (10.1016/j.neunet.2018.07.011_b14) 2004 LeCun (10.1016/j.neunet.2018.07.011_b41) 1998 10.1016/j.neunet.2018.07.011_b32 Guo (10.1016/j.neunet.2018.07.011_b16) 2004; 6 Johnson (10.1016/j.neunet.2018.07.011_b31) 2013; 34 Xiao (10.1016/j.neunet.2018.07.011_b65) 2010 10.1016/j.neunet.2018.07.011_b34 Lee (10.1016/j.neunet.2018.07.011_b42) 2006 Liu (10.1016/j.neunet.2018.07.011_b46) 2009; 39 Havaei (10.1016/j.neunet.2018.07.011_b19) 2017; 35 Qian (10.1016/j.neunet.2018.07.011_b52) 1999; 12 Shen (10.1016/j.neunet.2018.07.011_b57) 2016 10.1016/j.neunet.2018.07.011_b5 10.1016/j.neunet.2018.07.011_b38 10.1016/j.neunet.2018.07.011_b4 10.1016/j.neunet.2018.07.011_b37 |
| References_xml | – reference: He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In – start-page: 3485 year: 2010 end-page: 3492 ident: b65 article-title: Sun database: Large-scale scene recognition from abbey to zoo publication-title: 2010 IEEE conference on computer vision and pattern recognition – reference: (pp. 1319–1327). – reference: (pp. 179–186), Nashville, USA. – reference: (pp. 445–449). – reference: Simonyan, K., & Zisserman, A. Very deep convolutional networks for large-scale image recognition, arXiv preprint – reference: Maloof, M. A. (2003). Learning when data sets are imbalanced and when costs are unequal and unknown. In – volume: 18 start-page: 63 year: 2006 end-page: 77 ident: b67 article-title: Training cost-sensitive neural networks with methods addressing the class imbalance problem publication-title: IEEE Transactions on Knowledge and Data Engineering – reference: (pp. 519–524). – volume: 6 start-page: 429 year: 2002 end-page: 449 ident: b28 article-title: The class imbalance problem: A systematic study publication-title: Intelligent Data Analysis – reference: Kubat, M., & Matwin, S. et al., (1997). Addressing the curse of imbalanced training sets: one-sided selection. In – reference: Krizhevsky, A., & Hinton, G. Learning multiple layers of features from tiny images. – volume: 52 start-page: 199 year: 2003 end-page: 215 ident: b51 article-title: Tree induction for probability-based ranking publication-title: Machine Learning – reference: Khan, S. H., Bennamoun, M., Sohel, F., & Togneri, R. Cost sensitive learning of deep feature representations from imbalanced data, arXiv preprint – volume: 20 start-page: 15 year: 2014 end-page: 24 ident: b64 article-title: A hybrid classifier combining smote with pso to estimate 5-year survivability of breast cancer patients publication-title: Applied Soft Computing – volume: 30 start-page: 195 year: 1998 end-page: 215 ident: b36 article-title: Machine learning for the detection of oil spills in satellite radar images publication-title: Machine Learning – start-page: 467 year: 2016 end-page: 482 ident: b57 article-title: Relay backpropagation for effective learning of deep convolutional neural networks publication-title: European conference on computer vision – reference: (pp. 34–42). – start-page: 853 year: 2005 end-page: 867 ident: b6 article-title: Data mining for imbalanced datasets: An overview publication-title: Data mining and knowledge discovery handbook – start-page: 973 year: 2001 end-page: 978 ident: b11 article-title: The foundations of cost-sensitive learning publication-title: International joint conference on artificial intelligence, Vol. 17 – volume: 37 start-page: 224 year: 2004 end-page: 239 ident: b53 article-title: Classification and knowledge discovery in protein databases publication-title: Journal of Biomedical Informatics – reference: (pp. 249–256). – reference: (pp. 1–8). – reference: Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., & Shuai, B. et al., Recent advances in convolutional neural networks, arXiv preprint – volume: 16 start-page: 321 year: 2002 end-page: 357 ident: b7 article-title: Smote: synthetic minority over-sampling technique publication-title: Journal of Artificial Intelligence Research – reference: Ioffe, S., & Szegedy, C. Batch normalization: Accelerating deep network training by reducing internal covariate shift, arXiv preprint – start-page: 1 year: 2016 end-page: 17 ident: b24 article-title: Detection of concealed cars in complex cargo X-ray imagery using deep learning publication-title: Journal of X-Ray Science and Technology – volume: 12 start-page: 145 year: 1999 end-page: 151 ident: b52 article-title: On the momentum term in gradient descent learning algorithms publication-title: Neural Networks – reference: Ling, C. X., Huang, J., & Zhang, H. (2003). Auc: a statistically consistent and more discriminating measure than accuracy. In – volume: 3 start-page: 461 year: 1991 end-page: 483 ident: b55 article-title: Neural network classifiers estimate Bayesian a posteriori probabilities publication-title: Neural Computation – reference: Cardie, C., & Howe, N. (1997). Improving minority class prediction using case-specific feature weights. In – volume: 1 start-page: 541 year: 1989 end-page: 551 ident: b40 article-title: Backpropagation applied to handwritten zip code recognition publication-title: Neural Computation – reference: Levi, G., & Hassner, T. (2015). Age and gender classification using convolutional neural networks. In – volume: 39 start-page: 539 year: 2009 end-page: 550 ident: b46 article-title: Exploratory undersampling for class-imbalance learning publication-title: IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics) – start-page: 1170 year: 2012 end-page: 1177 ident: b2 article-title: Automated annotation of coral reef survey images publication-title: 2012 IEEE conference on computer vision and pattern recognition – volume: 7 year: 2016 ident: b25 article-title: Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases publication-title: Journal of Pathology Informatics – start-page: 543 year: 2004 end-page: 553 ident: b14 article-title: An approach to imbalanced data sets based on changing rule strength publication-title: Rough-neural computing – reference: Kukar, M., & Kononenko, I. et al., (1998). Cost-sensitive learning with neural networks. In – volume: 13 start-page: 251 year: 1981 end-page: 255 ident: b33 article-title: On the relation of performance to editing in nearest neighbor rules publication-title: Pattern Recognition – volume: 30 start-page: 1145 year: 1997 end-page: 1159 ident: b3 article-title: The use of the area under the roc curve in the evaluation of machine learning algorithms publication-title: Pattern Recognition – volume: 6 start-page: 40 year: 2004 end-page: 49 ident: b30 article-title: Class imbalances versus small disjuncts publication-title: ACM Sigkdd Explorations Newsletter – start-page: 1026 year: 2015 end-page: 1034 ident: b21 article-title: Delving deep into rectifiers: Surpassing human-level performance on imagenet classification publication-title: Proceedings of the IEEE international conference on computer vision – start-page: 107 year: 2003 end-page: 119 ident: b8 article-title: Smoteboost: Improving prediction of the minority class in boosting publication-title: European conference on principles of data mining and knowledge discovery – reference: Sohn, H., Worden, K., & Farrar, C. R. (2001). Novelty detection using auto-associative neural network. In – reference: Japkowicz, N., Myers, C., & Gluck, M. et al., (1995). A novelty detection approach to classification. In – reference: Simon, M., Rodner, E., & Denzler, J. Imagenet pre-trained models with batch normalization, arXiv preprint – start-page: 878 year: 2005 end-page: 887 ident: b18 article-title: Borderline-smote: a new over-sampling method in imbalanced data sets learning publication-title: Advances in Intelligent Computing – start-page: 21 year: 2006 end-page: 30 ident: b42 article-title: The novelty detection approach for different degrees of class imbalance publication-title: Neural information processing – start-page: 4368 year: 2016 end-page: 4374 ident: b63 article-title: Training deep neural networks on imbalanced data sets publication-title: 2016 international joint conference on neural networks – volume: 115 start-page: 211 year: 2015 end-page: 252 ident: b56 article-title: Imagenet large scale visual recognition challenge publication-title: International Journal of Computer Vision – reference: Chung, Y. A., Lin, H. T., & Yang, S. W. Cost-aware pre-training for multiclass cost-sensitive deep learning, arXiv preprint – reference: Glorot, X., & Bengio, Y. (2010). Understanding the difficulty of training deep feedforward neural networks. In – reference: (pp. 518–523). – reference: (pp. 164–168). – volume: 12 start-page: 531 year: 2000 end-page: 545 ident: b26 article-title: Nonlinear autoassociation is not equivalent to pca publication-title: Neural Computation – start-page: 675 year: 2014 end-page: 678 ident: b29 article-title: Caffe: Convolutional architecture for fast feature embedding publication-title: Proceedings of the 22nd ACM international conference on multimedia – reference: (pp. 770–778). – start-page: 299 year: 1998 end-page: 313 ident: b39 article-title: Neural network classification and prior class probabilities publication-title: Neural networks: Tricks of the trade – reference: Ling, C. X., & Li, C. (1998). Data mining for direct marketing: Problems and solutions. In – volume: 21 start-page: 427 year: 2008 end-page: 436 ident: b49 article-title: Training neural network classifiers for medical decision making: The effects of imbalanced datasets on classification performance publication-title: Neural Networks – start-page: 1097 year: 2012 end-page: 1105 ident: b35 article-title: Imagenet classification with deep convolutional neural networks publication-title: Advances in Neural Information Processing Systems – volume: 35 start-page: 18 year: 2017 end-page: 31 ident: b19 article-title: Brain tumor segmentation with deep neural networks publication-title: Medical Image Analysis – start-page: 818 year: 2014 end-page: 833 ident: b66 article-title: Visualizing and understanding convolutional networks publication-title: European conference on computer vision – year: 1998 ident: b41 article-title: Gradient-based learning applied to document recognition publication-title: Proceedings of the IEEE – reference: Chan, P. K., & Stolfo, S. J. (1998). Toward scalable learning with non-uniform class and cost distributions: A case study in credit card fraud detection. In – reference: . – volume: 24 start-page: 51 year: 2002 end-page: 70 ident: b47 article-title: The problem of bias in training data in regression problems in medical decision support publication-title: Artificial Intelligence in Medicine – start-page: 150 year: 2016 end-page: 162 ident: b54 article-title: Towards effective classification of imbalanced data with convolutional neural networks publication-title: IAPR workshop on artificial neural networks in pattern recognition – reference: Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. Striving for simplicity: The all convolutional net, arXiv preprint – reference: (pp. 57–65). – volume: 21 start-page: 1263 year: 2009 end-page: 1284 ident: b20 article-title: Learning from imbalanced data publication-title: The IEEE Transactions on Knowledge and Data Engineering – reference: (pp. 573–580), New York, NY. – start-page: 424 year: 2003 end-page: 431 ident: b1 article-title: Restricted decontamination for the imbalanced training sample problem publication-title: Iberoamerican congress on pattern recognition – volume: 12 start-page: 2825 year: 2011 end-page: 2830 ident: b50 article-title: Scikit-learn: machine learning in python publication-title: Journal of Machine Learning Research – volume: 6 start-page: 30 year: 2004 end-page: 39 ident: b16 article-title: Learning from imbalanced data sets with boosting and data generation: the databoost-im approach publication-title: ACM Sigkdd Explorations Newsletter – reference: Goodfellow, I. J., Warde-Farley, D., Mirza, M., Courville, A. C., & Bengio, Y. (2013). Maxout networks. In – volume: 34 start-page: 6969 year: 2013 end-page: 6982 ident: b31 article-title: A hybrid pansharpening approach and multiscale object-based image analysis for mapping diseased pine and oak trees publication-title: International Journal of Remote Sensing – reference: Van Horn, G., Mac Aodha, O., Song, Y., Shepard, A., Adam, H., & Perona, P. et al., The inaturalist challenge 2017 dataset, arXiv preprint – year: 2016 ident: b17 article-title: Learning from class-imbalanced data: Review of methods and applications publication-title: Expert Systems with Applications – reference: (pp. 73–79). – reference: Drummond, C., & Holte, R. C. et al., (2009). C4.5, class imbalance, and cost sensitivity: why under-sampling beats over-sampling. In – volume: 34 start-page: 6969 issue: 20 year: 2013 ident: 10.1016/j.neunet.2018.07.011_b31 article-title: A hybrid pansharpening approach and multiscale object-based image analysis for mapping diseased pine and oak trees publication-title: International Journal of Remote Sensing doi: 10.1080/01431161.2013.810825 – ident: 10.1016/j.neunet.2018.07.011_b34 – start-page: 107 year: 2003 ident: 10.1016/j.neunet.2018.07.011_b8 article-title: Smoteboost: Improving prediction of the minority class in boosting – volume: 21 start-page: 1263 issue: 9 year: 2009 ident: 10.1016/j.neunet.2018.07.011_b20 article-title: Learning from imbalanced data publication-title: The IEEE Transactions on Knowledge and Data Engineering doi: 10.1109/TKDE.2008.239 – volume: 3 start-page: 461 issue: 4 year: 1991 ident: 10.1016/j.neunet.2018.07.011_b55 article-title: Neural network classifiers estimate Bayesian a posteriori probabilities publication-title: Neural Computation doi: 10.1162/neco.1991.3.4.461 – ident: 10.1016/j.neunet.2018.07.011_b15 – start-page: 1097 year: 2012 ident: 10.1016/j.neunet.2018.07.011_b35 article-title: Imagenet classification with deep convolutional neural networks – start-page: 1 year: 2016 ident: 10.1016/j.neunet.2018.07.011_b24 article-title: Detection of concealed cars in complex cargo X-ray imagery using deep learning publication-title: Journal of X-Ray Science and Technology – start-page: 3485 year: 2010 ident: 10.1016/j.neunet.2018.07.011_b65 article-title: Sun database: Large-scale scene recognition from abbey to zoo – ident: 10.1016/j.neunet.2018.07.011_b38 – volume: 16 start-page: 321 year: 2002 ident: 10.1016/j.neunet.2018.07.011_b7 article-title: Smote: synthetic minority over-sampling technique publication-title: Journal of Artificial Intelligence Research doi: 10.1613/jair.953 – ident: 10.1016/j.neunet.2018.07.011_b22 doi: 10.1109/CVPR.2016.90 – volume: 24 start-page: 51 issue: 1 year: 2002 ident: 10.1016/j.neunet.2018.07.011_b47 article-title: The problem of bias in training data in regression problems in medical decision support publication-title: Artificial Intelligence in Medicine doi: 10.1016/S0933-3657(01)00092-6 – start-page: 424 year: 2003 ident: 10.1016/j.neunet.2018.07.011_b1 article-title: Restricted decontamination for the imbalanced training sample problem – start-page: 21 year: 2006 ident: 10.1016/j.neunet.2018.07.011_b42 article-title: The novelty detection approach for different degrees of class imbalance – ident: 10.1016/j.neunet.2018.07.011_b44 – volume: 37 start-page: 224 issue: 4 year: 2004 ident: 10.1016/j.neunet.2018.07.011_b53 article-title: Classification and knowledge discovery in protein databases publication-title: Journal of Biomedical Informatics doi: 10.1016/j.jbi.2004.07.008 – ident: 10.1016/j.neunet.2018.07.011_b48 – volume: 7 year: 2016 ident: 10.1016/j.neunet.2018.07.011_b25 article-title: Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases publication-title: Journal of Pathology Informatics doi: 10.4103/2153-3539.186902 – volume: 18 start-page: 63 issue: 1 year: 2006 ident: 10.1016/j.neunet.2018.07.011_b67 article-title: Training cost-sensitive neural networks with methods addressing the class imbalance problem publication-title: IEEE Transactions on Knowledge and Data Engineering doi: 10.1109/TKDE.2006.17 – ident: 10.1016/j.neunet.2018.07.011_b9 – start-page: 543 year: 2004 ident: 10.1016/j.neunet.2018.07.011_b14 article-title: An approach to imbalanced data sets based on changing rule strength – volume: 6 start-page: 429 issue: 5 year: 2002 ident: 10.1016/j.neunet.2018.07.011_b28 article-title: The class imbalance problem: A systematic study publication-title: Intelligent Data Analysis doi: 10.3233/IDA-2002-6504 – ident: 10.1016/j.neunet.2018.07.011_b5 – ident: 10.1016/j.neunet.2018.07.011_b58 – start-page: 675 year: 2014 ident: 10.1016/j.neunet.2018.07.011_b29 article-title: Caffe: Convolutional architecture for fast feature embedding – ident: 10.1016/j.neunet.2018.07.011_b60 – start-page: 973 year: 2001 ident: 10.1016/j.neunet.2018.07.011_b11 article-title: The foundations of cost-sensitive learning – volume: 30 start-page: 195 issue: 2–3 year: 1998 ident: 10.1016/j.neunet.2018.07.011_b36 article-title: Machine learning for the detection of oil spills in satellite radar images publication-title: Machine Learning doi: 10.1023/A:1007452223027 – volume: 39 start-page: 539 issue: 2 year: 2009 ident: 10.1016/j.neunet.2018.07.011_b46 article-title: Exploratory undersampling for class-imbalance learning publication-title: IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics) doi: 10.1109/TSMCB.2008.2007853 – volume: 13 start-page: 251 issue: 3 year: 1981 ident: 10.1016/j.neunet.2018.07.011_b33 article-title: On the relation of performance to editing in nearest neighbor rules publication-title: Pattern Recognition doi: 10.1016/0031-3203(81)90102-3 – start-page: 1026 year: 2015 ident: 10.1016/j.neunet.2018.07.011_b21 article-title: Delving deep into rectifiers: Surpassing human-level performance on imagenet classification – volume: 6 start-page: 40 issue: 1 year: 2004 ident: 10.1016/j.neunet.2018.07.011_b30 article-title: Class imbalances versus small disjuncts publication-title: ACM Sigkdd Explorations Newsletter doi: 10.1145/1007730.1007737 – ident: 10.1016/j.neunet.2018.07.011_b37 – ident: 10.1016/j.neunet.2018.07.011_b12 – volume: 115 start-page: 211 issue: 3 year: 2015 ident: 10.1016/j.neunet.2018.07.011_b56 article-title: Imagenet large scale visual recognition challenge publication-title: International Journal of Computer Vision doi: 10.1007/s11263-015-0816-y – volume: 12 start-page: 2825 issue: Oct year: 2011 ident: 10.1016/j.neunet.2018.07.011_b50 article-title: Scikit-learn: machine learning in python publication-title: Journal of Machine Learning Research – start-page: 150 year: 2016 ident: 10.1016/j.neunet.2018.07.011_b54 article-title: Towards effective classification of imbalanced data with convolutional neural networks – ident: 10.1016/j.neunet.2018.07.011_b4 – volume: 20 start-page: 15 year: 2014 ident: 10.1016/j.neunet.2018.07.011_b64 article-title: A hybrid classifier combining smote with pso to estimate 5-year survivability of breast cancer patients publication-title: Applied Soft Computing doi: 10.1016/j.asoc.2013.09.014 – ident: 10.1016/j.neunet.2018.07.011_b59 – volume: 21 start-page: 427 issue: 2 year: 2008 ident: 10.1016/j.neunet.2018.07.011_b49 article-title: Training neural network classifiers for medical decision making: The effects of imbalanced datasets on classification performance publication-title: Neural Networks doi: 10.1016/j.neunet.2007.12.031 – start-page: 4368 year: 2016 ident: 10.1016/j.neunet.2018.07.011_b63 article-title: Training deep neural networks on imbalanced data sets – ident: 10.1016/j.neunet.2018.07.011_b32 – ident: 10.1016/j.neunet.2018.07.011_b43 doi: 10.1109/CVPRW.2015.7301352 – ident: 10.1016/j.neunet.2018.07.011_b13 – year: 2016 ident: 10.1016/j.neunet.2018.07.011_b17 article-title: Learning from class-imbalanced data: Review of methods and applications publication-title: Expert Systems with Applications – volume: 1 start-page: 541 issue: 4 year: 1989 ident: 10.1016/j.neunet.2018.07.011_b40 article-title: Backpropagation applied to handwritten zip code recognition publication-title: Neural Computation doi: 10.1162/neco.1989.1.4.541 – volume: 30 start-page: 1145 issue: 7 year: 1997 ident: 10.1016/j.neunet.2018.07.011_b3 article-title: The use of the area under the roc curve in the evaluation of machine learning algorithms publication-title: Pattern Recognition doi: 10.1016/S0031-3203(96)00142-2 – ident: 10.1016/j.neunet.2018.07.011_b27 – start-page: 299 year: 1998 ident: 10.1016/j.neunet.2018.07.011_b39 article-title: Neural network classification and prior class probabilities – ident: 10.1016/j.neunet.2018.07.011_b61 – ident: 10.1016/j.neunet.2018.07.011_b23 – year: 1998 ident: 10.1016/j.neunet.2018.07.011_b41 article-title: Gradient-based learning applied to document recognition publication-title: Proceedings of the IEEE doi: 10.1109/5.726791 – volume: 52 start-page: 199 issue: 3 year: 2003 ident: 10.1016/j.neunet.2018.07.011_b51 article-title: Tree induction for probability-based ranking publication-title: Machine Learning doi: 10.1023/A:1024099825458 – ident: 10.1016/j.neunet.2018.07.011_b10 – volume: 12 start-page: 145 issue: 1 year: 1999 ident: 10.1016/j.neunet.2018.07.011_b52 article-title: On the momentum term in gradient descent learning algorithms publication-title: Neural Networks doi: 10.1016/S0893-6080(98)00116-6 – start-page: 467 year: 2016 ident: 10.1016/j.neunet.2018.07.011_b57 article-title: Relay backpropagation for effective learning of deep convolutional neural networks – volume: 35 start-page: 18 year: 2017 ident: 10.1016/j.neunet.2018.07.011_b19 article-title: Brain tumor segmentation with deep neural networks publication-title: Medical Image Analysis doi: 10.1016/j.media.2016.05.004 – start-page: 853 year: 2005 ident: 10.1016/j.neunet.2018.07.011_b6 article-title: Data mining for imbalanced datasets: An overview – volume: 6 start-page: 30 issue: 1 year: 2004 ident: 10.1016/j.neunet.2018.07.011_b16 article-title: Learning from imbalanced data sets with boosting and data generation: the databoost-im approach publication-title: ACM Sigkdd Explorations Newsletter doi: 10.1145/1007730.1007736 – ident: 10.1016/j.neunet.2018.07.011_b45 – start-page: 1170 year: 2012 ident: 10.1016/j.neunet.2018.07.011_b2 article-title: Automated annotation of coral reef survey images – volume: 12 start-page: 531 issue: 3 year: 2000 ident: 10.1016/j.neunet.2018.07.011_b26 article-title: Nonlinear autoassociation is not equivalent to pca publication-title: Neural Computation doi: 10.1162/089976600300015691 – start-page: 878 year: 2005 ident: 10.1016/j.neunet.2018.07.011_b18 article-title: Borderline-smote: a new over-sampling method in imbalanced data sets learning publication-title: Advances in Intelligent Computing doi: 10.1007/11538059_91 – start-page: 818 year: 2014 ident: 10.1016/j.neunet.2018.07.011_b66 article-title: Visualizing and understanding convolutional networks – ident: 10.1016/j.neunet.2018.07.011_b62 |
| SSID | ssj0006843 |
| Score | 2.708161 |
| Snippet | In this study, we systematically investigate the impact of class imbalance on classification performance of convolutional neural networks (CNNs) and compare... |
| SourceID | swepub proquest pubmed crossref elsevier |
| SourceType | Open Access Repository Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 249 |
| SubjectTerms | Class imbalance Convolutional neural networks Deep learning Humans Image classification Machine Learning - trends Neural Networks (Computer) Probability ROC Curve |
| Title | A systematic study of the class imbalance problem in convolutional neural networks |
| URI | https://dx.doi.org/10.1016/j.neunet.2018.07.011 https://www.ncbi.nlm.nih.gov/pubmed/30092410 https://www.proquest.com/docview/2087593601 https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-235561 |
| Volume | 106 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwELaqcuEC5b0FKiMhbmad-JU9rgrVAqIHKKg3a21PaHhkq3b3ym9nxnG2AoQqcYqSjBVrPPbMxJ-_Yey5cTKi1zYiJZ2ErmEmQgpJVCHAUppkG6D_He-P7eKTfntqTnfY4XgWhmCVZe0f1vS8Wpcn06LN6XnXTT9KdLUWA56KKKyqfKJca0dW_vLnFczDNgNyDoUFSY_H5zLGq4dND4SorJpM4VlV_3JPf4eff3CLZn90tMdulUCSz4e-3mE70N9lt8ciDbzM2Xvsw5xfsTXzzCbLVy3HuI9Hipx59yMQvDECL8VleNdzAqMXo8SPEOllvmTI-OV9dnL0-uRwIUohBRHRn6-F0a0ysMTkIwYbG2NbO0umVbZFjw2w1AqaFrQLmOxFC3UNrpWtSTXt2qWkHrDdftXDI8adblKSCZM2l_QsyRAVOAwxXaNaC3I2YWpUn4-FZJxqXXz3I5rsqx-U7knpXjqPSp8wsW11PpBsXCPvxpHxvxmLRz9wTctn40B6nEe0ObLsYbW5RCHM3MigUObhMMLbvihiptKVnLAXw5Bv3xA596vu89yvLr74b-szXyuqN7r_3x18zG7S3QAXfMJ21xcbeIphzzocZLs-YDfmb94tjn8BzPcDTg |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9swDBaK9LBd9n5kTw0YdhMi23o4x6Bbka5tDls29CZEEtV5D6dok_8_0pYzbMNQYCcDlgQLJEVS1qePjL3WVgaM2lrEqKJQJUyFjz6KwntYSR1NDfS_43Rh5p_U-zN9tscOhrswBKvMvr_36Z23zm8mWZqTi6aZfJQYag0mPAVRWBV0o3yf2Kn0iO3Pjo7ni51DNnUPnsP-ggYMN-g6mFcL2xYIVFnUHYtnUfwrQv2dgf5BL9qFpMM77FbOJfmsn-5dtgftPXZ7qNPA87K9zz7M-C_CZt4RyvJ14pj68UDJM29-eEI4BuC5vgxvWk549GyX-BHiveweHWr86gFbHr5bHsxFrqUgAob0jdAqVRpWuP8I3oRam2SmUafKJAzaACtVQZ1AWY_7vWCgLMEmmXQs6eAuxuohG7XrFh4zblUdo4y4b7NRTaP0oQKLWaatq2RATsesGsTnQuYZp3IX390AKPvqeqE7ErqT1qHQx0zsRl30PBvX9LeDZtxv9uIwFFwz8tWgSIdLic5HVi2st1fYCTdvZFPY51Gv4d1cKiKnUoUcsze9ynctxM_9tvk8c-vLc_dt88WVFZUcffLfE3zJbsyXpyfu5Ghx_JTdpJYePfiMjTaXW3iOWdDGv8hW_hOm_wX_ |
| 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+systematic+study+of+the+class+imbalance+problem+in+convolutional+neural+networks&rft.jtitle=Neural+networks&rft.au=Buda%2C+Mateusz&rft.au=Maki%2C+Atsuto&rft.au=Mazurowski%2C+Maciej+A.&rft.date=2018-10-01&rft.issn=0893-6080&rft.volume=106&rft.spage=249&rft.epage=259&rft_id=info:doi/10.1016%2Fj.neunet.2018.07.011&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_neunet_2018_07_011 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0893-6080&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0893-6080&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0893-6080&client=summon |