Showing 1 - 20 results of 4,690 for search '(( models ((set decrease) OR (we decrease)) ) OR ( ai ((larger decrease) OR (marked decrease)) ))', query time: 0.60s Refine Results
  1. 1
  2. 2
  3. 3

    Classification model parameter settings. by Chao Tang (10925)

    Published 2025
    “…Experiments demonstrate that PCA-CGAN not only achieves stable convergence on a large-scale heterogeneous dataset comprising 43 patients for the first time but also resolves the “dilution effect” problem in data augmentation, avoiding the asymmetric phenomenon where Precision increases while Recall decreases. After data augmentation, the ResNet model’s average F1 score improved significantly, with particularly outstanding performance on rare categories such as atrial premature beats, far surpassing traditional methods like SigCWGAN and TD-GAN. …”
  4. 4

    Minimal data set. by Jingru Zhou (766195)

    Published 2025
    “…This study focuses on YRD region and analyzes the characteristics of land use changes in the area using land use data from 2000 to 2020, with a 10-year interval. Utilizing InVEST Model’s Carbon Storage module in combination with PLUS model (patch-generating land use simulation), we simulated and projected future land use patterns and carbon storage across YRD region under five scenarios including natural development (ND), urban development (UD), ecological protection (EP), cropland protection (CP), and balanced development (BD). …”
  5. 5

    Raw data files for IMC data sets. by Kafayat Yusuf (22104155)

    Published 2025
    “…Elevated DCLK1-S levels corresponded with MMP13 staining and activity, promoting collagen degradation and fibrosis. We confirmed the DCLK1-S/MMP13 axis in a knock- in mouse model overexpressing DCLK1-S, in conjunction with dextran sulfate sodium (DSS)- induced colitis. …”
  6. 6

    PCA-CGAN model parameter settings. by Chao Tang (10925)

    Published 2025
    “…Experiments demonstrate that PCA-CGAN not only achieves stable convergence on a large-scale heterogeneous dataset comprising 43 patients for the first time but also resolves the “dilution effect” problem in data augmentation, avoiding the asymmetric phenomenon where Precision increases while Recall decreases. After data augmentation, the ResNet model’s average F1 score improved significantly, with particularly outstanding performance on rare categories such as atrial premature beats, far surpassing traditional methods like SigCWGAN and TD-GAN. …”
  7. 7
  8. 8

    Minimum data set. by Zhongxing Wang (7354205)

    Published 2025
    “…Using the particle flow software PFC2D, we conducted direct shear test simulations on joints with various inclinations and five different roughness levels to examine the models’ crack extension penetration paths, damage modes, and strength characteristics. …”
  9. 9
  10. 10
  11. 11
  12. 12
  13. 13
  14. 14
  15. 15
  16. 16
  17. 17
  18. 18
  19. 19
  20. 20