SEAwise Report on improved predictive models of recruitment under different habitat scenarios and incorporating experimental results by Paco Melià (162862)

“…Projections show no relevant changes in herring recruitment under RCP4.5 and a decreasing trend under RCP8.5. Plaice recruitment would decline slightly under RCP8.5 and increase under RCP4.5, but from a lower level than RCP8.5. …”

Data Sheet 1_The role of lycopene in alleviating soybean meal-induced intestinal injury in an early-weaned piglet model.docx by Shugui Zheng (18151898)

“…</p>Conclusion<p>These findings demonstrated that lycopene supplementation in SBM-based diets significantly enhanced antioxidant capacity, decreased apoptosis in small intestinal cells, improved intestinal barrier function and morphology, and optimized gut microbiota composition. …”

DataSheet1_Shenshuaikang enema restores the intestinal barrier and microbiota-gut-kidney axis balance to alleviate chronic kidney disease via NF-κB pathway.docx by Yan Ye (549400)

“…It has become a significant public health problem, posing a threat to human health worldwide. …”

Supplementary file 1_Spatial-temporal evolution characteristics and driving factors of carbon emission prediction in China-research on ARIMA-BP neural network algorithm.pdf by Sanglin Zhao (20915732)

“…The results show that: (1) From 2000 to 2035, China’s total carbon emissions increased year by year, but the growth rate of carbon emissions gradually decreased; The carbon emission structure is “secondary industry > residents’ life > tertiary industry > primary industry”, and the growth rate of carbon in secondary industry and residents’ life is faster, while the change trend of primary industry and tertiary industry is smaller; (2) The spatial distribution of carbon emissions in China’s provinces presents a typical pattern of “eastern > central > western” and “northern > southern”, and the carbon emission centers tend to move to the northwest; (3) The regions with high level of digital economy, advanced industrial structure and new quality productivity have relatively less carbon emissions, which has significant group difference effect; (4) The intensity effect of energy consumption is the main factor driving the continuous growth of carbon emissions, while the per capita GDP and the structure effect of energy consumption are the main factors restraining carbon emissions, while the effects of industrial structure and population size are relatively small. …”

Data Sheet 1_Impact of artificial intelligence on electronic health record-related burnouts among healthcare professionals: systematic review.pdf by Berna Sarraf (21651629)

“…Nevertheless, EHR-related workload has been considered as a significant contributor to healthcare professionals’ burnout, a syndrome associated with emotional exhaustion, depersonalization, and reduced personal accomplishment. …”

Image 1_Effect of hypoxia-induced mIL15 expression on expansion and memory progenitor stem-like TILs in vitro.tif by Zhen Sun (269397)

“…RNA-Seq data revealed that in TIL-mIL15-IL2 cells, the expression of genes related to T cell differentiation and effector function, including PRDM1, ID2, EOMES, IFNG, GZMB, and TNF, were significantly decreased, whereas the expression of the memory stem-like T cell marker TCF7 was significantly increased. …”

Presentation 1_Anti-PD1 therapies induce an early expansion of Ki67+CD8+ T cells in metastatic non-oncogene addicted NSCLC patients.pptx by Alain Gelibter (6409364)

“…Concurrently, 14 soluble immune checkpoints were analyzed by Luminex assay. Immunotherapy significantly increased the levels of Ki67⁺(total and CD8⁺) T cells, PMN(Lox1⁺)-MDSCs, non-suppressive Tregs (nsTregs), and soluble PD1 from T0 to T1 in the entire NSCLC population, while decreased active Tregs. …”

Dataset visualization diagram. by Yaojun Zhang (389482)

“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”

Dataset sample images. by Yaojun Zhang (389482)

“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”

Performance comparison of different models. by Yaojun Zhang (389482)

“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”

SEAwise synthetic summary report of the findings of WP4 on changes to the ecosystem impacts of fishing in response to spatial management for online tool by Anna Rindorf (6217391)

“…Almost all management strategies except current management led to overall decreases in effort and as a result, the general ecosystem impact to a level where GES was attained (habitats and foodwebs) or the impact was decreased by at least 20% (bycatch). …”

C2f and BC2f module structure diagrams. by Yaojun Zhang (389482)

“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”

YOLOv8n detection results diagram. by Yaojun Zhang (389482)

“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”

YOLOv8n-BWG model structure diagram. by Yaojun Zhang (389482)

“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”

BiFormer structure diagram. by Yaojun Zhang (389482)

“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”

YOLOv8n-BWG detection results diagram. by Yaojun Zhang (389482)

“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”

GSConv module structure diagram. by Yaojun Zhang (389482)

“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”

Performance comparison of three loss functions. by Yaojun Zhang (389482)

“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”

mAP0.5 Curves of various models. by Yaojun Zhang (389482)

“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”

Network loss function change diagram. by Yaojun Zhang (389482)

“…Results on a specialized dataset reveal that YOLOv8n-BWG outperforms YOLOv8n by increasing the mean Average Precision (mAP) by 4.2%, boosting recognition speed by 21.3% per second, and decreasing both the number of floating-point operations (FLOPs) by 28.9% and model size by 26.3%. …”