Quantitative results on WEDU dataset. by Dunlu Lu (19964225)

“…In comparative experiments on four plant datasets, MAR-YOLOv9 improved the mAP@0.5 accuracy by 39.18% compared to seven mainstream object detection algorithms, and by 1.28% compared to the YOLOv9 model. At the same time, the model size was reduced by 9.3%, and the number of model layers was decreased, reducing computational costs and storage requirements. …”

Counting results on DRPD dataset. by Dunlu Lu (19964225)

“…In comparative experiments on four plant datasets, MAR-YOLOv9 improved the mAP@0.5 accuracy by 39.18% compared to seven mainstream object detection algorithms, and by 1.28% compared to the YOLOv9 model. At the same time, the model size was reduced by 9.3%, and the number of model layers was decreased, reducing computational costs and storage requirements. …”

Quantitative results on RFRB dataset. by Dunlu Lu (19964225)

“…In comparative experiments on four plant datasets, MAR-YOLOv9 improved the mAP@0.5 accuracy by 39.18% compared to seven mainstream object detection algorithms, and by 1.28% compared to the YOLOv9 model. At the same time, the model size was reduced by 9.3%, and the number of model layers was decreased, reducing computational costs and storage requirements. …”

Main module structure. by Dunlu Lu (19964225)

“…In comparative experiments on four plant datasets, MAR-YOLOv9 improved the mAP@0.5 accuracy by 39.18% compared to seven mainstream object detection algorithms, and by 1.28% compared to the YOLOv9 model. At the same time, the model size was reduced by 9.3%, and the number of model layers was decreased, reducing computational costs and storage requirements. …”

Counting results on MTDC-UAV dataset. by Dunlu Lu (19964225)

“…In comparative experiments on four plant datasets, MAR-YOLOv9 improved the mAP@0.5 accuracy by 39.18% compared to seven mainstream object detection algorithms, and by 1.28% compared to the YOLOv9 model. At the same time, the model size was reduced by 9.3%, and the number of model layers was decreased, reducing computational costs and storage requirements. …”

Quantitative results on DRPD dataset. by Dunlu Lu (19964225)

“…In comparative experiments on four plant datasets, MAR-YOLOv9 improved the mAP@0.5 accuracy by 39.18% compared to seven mainstream object detection algorithms, and by 1.28% compared to the YOLOv9 model. At the same time, the model size was reduced by 9.3%, and the number of model layers was decreased, reducing computational costs and storage requirements. …”

Architecture of MAR-YOLOv9. by Dunlu Lu (19964225)

“…In comparative experiments on four plant datasets, MAR-YOLOv9 improved the mAP@0.5 accuracy by 39.18% compared to seven mainstream object detection algorithms, and by 1.28% compared to the YOLOv9 model. At the same time, the model size was reduced by 9.3%, and the number of model layers was decreased, reducing computational costs and storage requirements. …”

Quantitative results on MTDC-UAV dataset. by Dunlu Lu (19964225)

“…In comparative experiments on four plant datasets, MAR-YOLOv9 improved the mAP@0.5 accuracy by 39.18% compared to seven mainstream object detection algorithms, and by 1.28% compared to the YOLOv9 model. At the same time, the model size was reduced by 9.3%, and the number of model layers was decreased, reducing computational costs and storage requirements. …”

Counting results on WEDU dataset. by Dunlu Lu (19964225)

“…In comparative experiments on four plant datasets, MAR-YOLOv9 improved the mAP@0.5 accuracy by 39.18% compared to seven mainstream object detection algorithms, and by 1.28% compared to the YOLOv9 model. At the same time, the model size was reduced by 9.3%, and the number of model layers was decreased, reducing computational costs and storage requirements. …”

Example images from four plant datasets. by Dunlu Lu (19964225)

“…In comparative experiments on four plant datasets, MAR-YOLOv9 improved the mAP@0.5 accuracy by 39.18% compared to seven mainstream object detection algorithms, and by 1.28% compared to the YOLOv9 model. At the same time, the model size was reduced by 9.3%, and the number of model layers was decreased, reducing computational costs and storage requirements. …”

Counting results on RFRB dataset. by Dunlu Lu (19964225)

“…In comparative experiments on four plant datasets, MAR-YOLOv9 improved the mAP@0.5 accuracy by 39.18% compared to seven mainstream object detection algorithms, and by 1.28% compared to the YOLOv9 model. At the same time, the model size was reduced by 9.3%, and the number of model layers was decreased, reducing computational costs and storage requirements. …”

Detection visualization results on WEDU dataset. by Dunlu Lu (19964225)

“…In comparative experiments on four plant datasets, MAR-YOLOv9 improved the mAP@0.5 accuracy by 39.18% compared to seven mainstream object detection algorithms, and by 1.28% compared to the YOLOv9 model. At the same time, the model size was reduced by 9.3%, and the number of model layers was decreased, reducing computational costs and storage requirements. …”

Table 2_Bioelectrical impedance vector analysis in older adults: reference standards from a cross-sectional study.docx by Francesco Campa (20997323)

“…</p>Results<p>New reference values for older adults were established. Significant differences (p < 0.001) in R/H and phase angle were observed when older adults were grouped by age categories, while R/H, Xc/H, and phase angle showed significant differences among ALSM/H² tertiles. …”

PRMT5 isoforms during zebrafish developmental stages by Zain Zakaria (20354028)

“…NCBI database (version of 2019) was used in the searches. The significance of identification was set to p<0.5, one missed cleavage was allowed, and the expectation value was set to >0.95. …”

Data Sheet 2_Assessing the impact of moxibustion on colonic mucosal integrity and gut microbiota in a rat model of cerebral ischemic stroke: insights from the “brain-gut axis” theo... by Yi-Xia Ding (20792930)

“…The model group demonstrated decreased expression of Occludin and ZO-1 in colonic tissues (p < 0.01) and changes in gut microbiota structure. …”

Data Sheet 2_Rutin ameliorates LPS-induced acute lung injury in mice by inhibiting the cGAS-STING-NLRP3 signaling pathway.docx by Xin Zhou (54275)

“…Mechanistically, rutin demonstrated dual suppression: 1) inhibiting cGAS-STING activation through decreased expression of cGAS, STING, and phosphorylation of TBK1/IRF3 (P<0.05), and 2) attenuating NLRP3-mediated pyroptosis via downregulation of NLRP3-ASC-caspase1-GSDMD signaling (P<0.05). …”

Table 4_Mendelian randomization and bioinformatics unveil potential links between gut microbial genera and colorectal cancer.xlsx by Long Wu (655081)

“…Background<p>Colorectal cancer (CRC) poses a significant global health burden, with high incidence and mortality rates. …”

Table 2_Mendelian randomization and bioinformatics unveil potential links between gut microbial genera and colorectal cancer.xlsx by Long Wu (655081)

“…Background<p>Colorectal cancer (CRC) poses a significant global health burden, with high incidence and mortality rates. …”

Table 3_Mendelian randomization and bioinformatics unveil potential links between gut microbial genera and colorectal cancer.xlsx by Long Wu (655081)

“…Background<p>Colorectal cancer (CRC) poses a significant global health burden, with high incidence and mortality rates. …”

Baseline characteristics of participants. by Mei Zhou (269746)

“…</p><p>Results</p><p>After DRG implementation, the logarithmic mean of total hospitalization expenditures decreased significantly (3.914 ± 0.837 vs. 3.872 ± 1.004), while rates of unplanned readmissions, unplanned reoperations, postoperative complications, and patient complaints within 30 days increased significantly (3.784% vs 4.214%, 0.083% vs 0.166%, 0.207% vs 0.258%, 3.741% vs 5.133%). …”