Data-Driven Tool for Cross-Run Ion Selection and Peak-Picking in Quantitative Proteomics with Data-Independent Acquisition LC–MS/MS by Binjun Yan (17310633)

“…The advantages of assimilating DIA data in multiple runs for quantitative proteomics were demonstrated, which can significantly improve the quantification accuracy.…”

Accuracy and loss values of each model. by Hongwei Bai (1447999)

“…Experimental results demonstrate that the proposed model achieves superior performance in fault diagnosis, attaining an accuracy of 99.62%, significantly outperforming traditional CNNs and other benchmark methods.…”

MGPC module. by Bo Tong (2138632)

“…The DCNV2(Deformable Convolutional Networks v2) module was incorporated to handle geometric scale transformations by generating spatial offsets and feature masks from interactive features, thereby improving localization accuracy and dynamically selecting weights to enhance classification precision.The improved model incorporates rich multi-level and multi-scale features, allowing it to better adapt to tasks involving geometric transformations and aligning with the image data distribution in construction scenarios. …”

Comparative experiment. by Bo Tong (2138632)

“…The DCNV2(Deformable Convolutional Networks v2) module was incorporated to handle geometric scale transformations by generating spatial offsets and feature masks from interactive features, thereby improving localization accuracy and dynamically selecting weights to enhance classification precision.The improved model incorporates rich multi-level and multi-scale features, allowing it to better adapt to tasks involving geometric transformations and aligning with the image data distribution in construction scenarios. …”

Pruning experiment. by Bo Tong (2138632)

“…The DCNV2(Deformable Convolutional Networks v2) module was incorporated to handle geometric scale transformations by generating spatial offsets and feature masks from interactive features, thereby improving localization accuracy and dynamically selecting weights to enhance classification precision.The improved model incorporates rich multi-level and multi-scale features, allowing it to better adapt to tasks involving geometric transformations and aligning with the image data distribution in construction scenarios. …”

Parameter setting table. by Bo Tong (2138632)

“…The DCNV2(Deformable Convolutional Networks v2) module was incorporated to handle geometric scale transformations by generating spatial offsets and feature masks from interactive features, thereby improving localization accuracy and dynamically selecting weights to enhance classification precision.The improved model incorporates rich multi-level and multi-scale features, allowing it to better adapt to tasks involving geometric transformations and aligning with the image data distribution in construction scenarios. …”

DTADH module. by Bo Tong (2138632)

“…The DCNV2(Deformable Convolutional Networks v2) module was incorporated to handle geometric scale transformations by generating spatial offsets and feature masks from interactive features, thereby improving localization accuracy and dynamically selecting weights to enhance classification precision.The improved model incorporates rich multi-level and multi-scale features, allowing it to better adapt to tasks involving geometric transformations and aligning with the image data distribution in construction scenarios. …”

Ablation experiment. by Bo Tong (2138632)

“…The DCNV2(Deformable Convolutional Networks v2) module was incorporated to handle geometric scale transformations by generating spatial offsets and feature masks from interactive features, thereby improving localization accuracy and dynamically selecting weights to enhance classification precision.The improved model incorporates rich multi-level and multi-scale features, allowing it to better adapt to tasks involving geometric transformations and aligning with the image data distribution in construction scenarios. …”

Multi scale detection. by Bo Tong (2138632)

“…The DCNV2(Deformable Convolutional Networks v2) module was incorporated to handle geometric scale transformations by generating spatial offsets and feature masks from interactive features, thereby improving localization accuracy and dynamically selecting weights to enhance classification precision.The improved model incorporates rich multi-level and multi-scale features, allowing it to better adapt to tasks involving geometric transformations and aligning with the image data distribution in construction scenarios. …”

MFDPN module. by Bo Tong (2138632)

“…The DCNV2(Deformable Convolutional Networks v2) module was incorporated to handle geometric scale transformations by generating spatial offsets and feature masks from interactive features, thereby improving localization accuracy and dynamically selecting weights to enhance classification precision.The improved model incorporates rich multi-level and multi-scale features, allowing it to better adapt to tasks involving geometric transformations and aligning with the image data distribution in construction scenarios. …”

Detection effect of different sizes. by Bo Tong (2138632)

“…The DCNV2(Deformable Convolutional Networks v2) module was incorporated to handle geometric scale transformations by generating spatial offsets and feature masks from interactive features, thereby improving localization accuracy and dynamically selecting weights to enhance classification precision.The improved model incorporates rich multi-level and multi-scale features, allowing it to better adapt to tasks involving geometric transformations and aligning with the image data distribution in construction scenarios. …”

Radar chart comparing indicators. by Bo Tong (2138632)

“…The DCNV2(Deformable Convolutional Networks v2) module was incorporated to handle geometric scale transformations by generating spatial offsets and feature masks from interactive features, thereby improving localization accuracy and dynamically selecting weights to enhance classification precision.The improved model incorporates rich multi-level and multi-scale features, allowing it to better adapt to tasks involving geometric transformations and aligning with the image data distribution in construction scenarios. …”

MFD-YOLO structure. by Bo Tong (2138632)

“…The DCNV2(Deformable Convolutional Networks v2) module was incorporated to handle geometric scale transformations by generating spatial offsets and feature masks from interactive features, thereby improving localization accuracy and dynamically selecting weights to enhance classification precision.The improved model incorporates rich multi-level and multi-scale features, allowing it to better adapt to tasks involving geometric transformations and aligning with the image data distribution in construction scenarios. …”

Detection results of each category. by Bo Tong (2138632)

“…The DCNV2(Deformable Convolutional Networks v2) module was incorporated to handle geometric scale transformations by generating spatial offsets and feature masks from interactive features, thereby improving localization accuracy and dynamically selecting weights to enhance classification precision.The improved model incorporates rich multi-level and multi-scale features, allowing it to better adapt to tasks involving geometric transformations and aligning with the image data distribution in construction scenarios. …”

Select metabolites that are significantly altered in the <i>cop</i>^- strain when cultured in presence of 5 μM Cu(II)^b'*'. by Javiera Norambuena (137228)

Architecture of Swin-T model. by Wen-Qing Huang (5258126)

“…Experimental results demonstrate that compared to the baseline model, the proposed enhanced model achieves a reduction of 2.5G Flops computational complexity and a 16% speed improvement on a private pavement disease dataset, with only a 1.2 percentage point decrease in AUC accuracy. Moreover, compared to other mainstream image classification models, this model exhibits more balanced performance on a public dataset, with improved accuracy and speed that better align with the practical requirements of pavement inspection. …”

Model the experimental results curve. by Wen-Qing Huang (5258126)

“…Experimental results demonstrate that compared to the baseline model, the proposed enhanced model achieves a reduction of 2.5G Flops computational complexity and a 16% speed improvement on a private pavement disease dataset, with only a 1.2 percentage point decrease in AUC accuracy. Moreover, compared to other mainstream image classification models, this model exhibits more balanced performance on a public dataset, with improved accuracy and speed that better align with the practical requirements of pavement inspection. …”

Results of comparison experiments. by Wen-Qing Huang (5258126)

“…Experimental results demonstrate that compared to the baseline model, the proposed enhanced model achieves a reduction of 2.5G Flops computational complexity and a 16% speed improvement on a private pavement disease dataset, with only a 1.2 percentage point decrease in AUC accuracy. Moreover, compared to other mainstream image classification models, this model exhibits more balanced performance on a public dataset, with improved accuracy and speed that better align with the practical requirements of pavement inspection. …”

Architecture of Swin Transformer Block. by Wen-Qing Huang (5258126)

“…Experimental results demonstrate that compared to the baseline model, the proposed enhanced model achieves a reduction of 2.5G Flops computational complexity and a 16% speed improvement on a private pavement disease dataset, with only a 1.2 percentage point decrease in AUC accuracy. Moreover, compared to other mainstream image classification models, this model exhibits more balanced performance on a public dataset, with improved accuracy and speed that better align with the practical requirements of pavement inspection. …”

Disease distribution map of the GZDL-BD. by Wen-Qing Huang (5258126)

“…Experimental results demonstrate that compared to the baseline model, the proposed enhanced model achieves a reduction of 2.5G Flops computational complexity and a 16% speed improvement on a private pavement disease dataset, with only a 1.2 percentage point decrease in AUC accuracy. Moreover, compared to other mainstream image classification models, this model exhibits more balanced performance on a public dataset, with improved accuracy and speed that better align with the practical requirements of pavement inspection. …”