Effects of MC treatment on symptoms and histological changes in DNBS-induced colitis rats. by Jin-Hwa Kim (101817)

KO of iPLA₂γ attenuates development of albuminuria in STZ-induced diabetic nephropathy. by Andrey V. Cybulsky (4007012)

The performance of eigenvectors of the covariance matrix in a model with more complex population structure. by Joshua G. Schraiber (8027060)

Impact of including phylogenetic eigenvectors on detection of coevolution of gene-expression levels in fungi. by Joshua G. Schraiber (8027060)

Performance of different methods for controlling confounding in Felsenstein’s worst case. by Joshua G. Schraiber (8027060)

Complexity comparison of different models. by Li Yuan (102305)

“…Therefore, the study proposes a signal automatic modulation classification model based on fixed K-mean algorithm and denoising autoencoder. The model uses fixed K-mean algorithm for feature classification and optimizes median filtering algorithm using dynamic thresholding. …”

Dynamic window based median filtering algorithm. by Li Yuan (102305)

“…Therefore, the study proposes a signal automatic modulation classification model based on fixed K-mean algorithm and denoising autoencoder. The model uses fixed K-mean algorithm for feature classification and optimizes median filtering algorithm using dynamic thresholding. …”

Flow of operation of improved KMA. by Li Yuan (102305)

“…Therefore, the study proposes a signal automatic modulation classification model based on fixed K-mean algorithm and denoising autoencoder. The model uses fixed K-mean algorithm for feature classification and optimizes median filtering algorithm using dynamic thresholding. …”

Improved DAE based on LSTM. by Li Yuan (102305)

“…Therefore, the study proposes a signal automatic modulation classification model based on fixed K-mean algorithm and denoising autoencoder. The model uses fixed K-mean algorithm for feature classification and optimizes median filtering algorithm using dynamic thresholding. …”

Autoencoder structure. by Li Yuan (102305)

“…Therefore, the study proposes a signal automatic modulation classification model based on fixed K-mean algorithm and denoising autoencoder. The model uses fixed K-mean algorithm for feature classification and optimizes median filtering algorithm using dynamic thresholding. …”

Podocyte numbers in control and iPLA₂γ KO mice (WT1-positive cells). by Andrey V. Cybulsky (4007012)

Trends of the temperature, precipitation, and TVDI in the Santun River Irrigation Area, Xinjiang, during 2005–2023. by Yuxin Wei (11510974)

Pan-cancer analyses of GSRS. by Yu Zhang (12946)

IRE1 depletion increases chromosome instability. by Iratxe Zuazo-Gaztelu (21071939)

The sequences of si-RNAs used in this study. by Changji Li (4806930)

“…This reduction inhibits cell division, promotes cell death, and decreases cell invasion and migration. CRNN overexpression has been found to enhance cell growth and prevent cells from undergoing natural cell death, and the cancer-promoting effects of CRNN are linked to AKT activation. …”

Schematic overview of the study workflow. by Yu Zhang (12946)

Structure diagram of ensemble model. by Hongqi Wang (2208238)

“…Comparative analysis highlights the significant enhancement in prediction accuracy achieved by the proposed ensemble model over single machine learning models, with root mean square error (RMSE) values below 0.05 and mean absolute percentage error (MAPE) values remaining under 2.5% in both frozen and unfrozen states. …”

Fitting formula parameter table. by Hongqi Wang (2208238)

“…Comparative analysis highlights the significant enhancement in prediction accuracy achieved by the proposed ensemble model over single machine learning models, with root mean square error (RMSE) values below 0.05 and mean absolute percentage error (MAPE) values remaining under 2.5% in both frozen and unfrozen states. …”

Test plan. by Hongqi Wang (2208238)

“…Comparative analysis highlights the significant enhancement in prediction accuracy achieved by the proposed ensemble model over single machine learning models, with root mean square error (RMSE) values below 0.05 and mean absolute percentage error (MAPE) values remaining under 2.5% in both frozen and unfrozen states. …”

Fitting surface parameters. by Hongqi Wang (2208238)

“…Comparative analysis highlights the significant enhancement in prediction accuracy achieved by the proposed ensemble model over single machine learning models, with root mean square error (RMSE) values below 0.05 and mean absolute percentage error (MAPE) values remaining under 2.5% in both frozen and unfrozen states. …”