Journal: Molecules

Article Title: Multifunctional Isosteric Pyridine Analogs-Based 2-Aminothiazole: Design, Synthesis, and Potential Phosphodiesterase-5 Inhibitory Activity

doi: 10.3390/molecules26040902

Figure Lengend Snippet: PDE5 inhibitors.

Article Snippet: The designed and synthesized compounds were docked into PDE5 (PDB ID: 2H42) [ ] by an OpenEye-applications-2020-Spring released software.

Techniques:

Journal: Molecules

Article Title: Multifunctional Isosteric Pyridine Analogs-Based 2-Aminothiazole: Design, Synthesis, and Potential Phosphodiesterase-5 Inhibitory Activity

doi: 10.3390/molecules26040902

Figure Lengend Snippet: Effect of tested compounds on PDE5 (10 4 nM) and MABP.

Article Snippet: The designed and synthesized compounds were docked into PDE5 (PDB ID: 2H42) [ ] by an OpenEye-applications-2020-Spring released software.

Techniques: Inhibition, Control

Journal: Sensors (Basel, Switzerland)

Article Title: PDeT: A Progressive Deformable Transformer for Photovoltaic Panel Defect Segmentation

doi: 10.3390/s24216908

Figure Lengend Snippet: Overall architecture of the proposed PDeT for photovoltaic defect segmentation.

Article Snippet: To validate the application potential of the PDeT photovoltaic defect detection model in other industrial scenarios, we selected four typical scenes from the MVTec-AD [ ] anomaly detection dataset for experimentation.

Techniques:

Journal: Sensors (Basel, Switzerland)

Article Title: PDeT: A Progressive Deformable Transformer for Photovoltaic Panel Defect Segmentation

doi: 10.3390/s24216908

Figure Lengend Snippet: A comparison of the experimental results with other Decoder heads.

Article Snippet: To validate the application potential of the PDeT photovoltaic defect detection model in other industrial scenarios, we selected four typical scenes from the MVTec-AD [ ] anomaly detection dataset for experimentation.

Techniques: Comparison

Journal: Sensors (Basel, Switzerland)

Article Title: PDeT: A Progressive Deformable Transformer for Photovoltaic Panel Defect Segmentation

doi: 10.3390/s24216908

Figure Lengend Snippet: The training process of the PDeT is assessed using three metrics: loss, mIoU, and mAcc. These metrics offer valuable insights into the model’s performance and effectiveness during training. The left panel displays the loss at each iteration, while the right panel presents the validation results throughout the training process.

Article Snippet: To validate the application potential of the PDeT photovoltaic defect detection model in other industrial scenarios, we selected four typical scenes from the MVTec-AD [ ] anomaly detection dataset for experimentation.

Techniques: Biomarker Discovery

Journal: Sensors (Basel, Switzerland)

Article Title: PDeT: A Progressive Deformable Transformer for Photovoltaic Panel Defect Segmentation

doi: 10.3390/s24216908

Figure Lengend Snippet: Comparison of experimental results of various indicators with other segmentation networks.

Article Snippet: To validate the application potential of the PDeT photovoltaic defect detection model in other industrial scenarios, we selected four typical scenes from the MVTec-AD [ ] anomaly detection dataset for experimentation.

Techniques: Comparison

Journal: Sensors (Basel, Switzerland)

Article Title: PDeT: A Progressive Deformable Transformer for Photovoltaic Panel Defect Segmentation

doi: 10.3390/s24216908

Figure Lengend Snippet: Comparative experimental results of the model across the four scenes: Hazelnut, Metal Nut, Tile, and Wood. All values shown in the table represent the mIoU for assessing the model’s recognition performance in each scene.

Article Snippet: To validate the application potential of the PDeT photovoltaic defect detection model in other industrial scenarios, we selected four typical scenes from the MVTec-AD [ ] anomaly detection dataset for experimentation.

Techniques: