Repeat the detection experiment. by Yingying Liu (360782)

“…The actual accuracy and mean latency time of the model were 92.43% and 260ms, respectively. …”

Detection network structure with IRAU [34]. by Yingying Liu (360782)

“…The actual accuracy and mean latency time of the model were 92.43% and 260ms, respectively. …”

Ablation experiments of various block. by Yingying Liu (360782)

“…The actual accuracy and mean latency time of the model were 92.43% and 260ms, respectively. …”

Kappa coefficients for different algorithms. by Yingying Liu (360782)

“…The actual accuracy and mean latency time of the model were 92.43% and 260ms, respectively. …”

The structure of ASPP+ block. by Yingying Liu (360782)

“…The actual accuracy and mean latency time of the model were 92.43% and 260ms, respectively. …”

The structure of attention gate block [31]. by Yingying Liu (360782)

“…The actual accuracy and mean latency time of the model were 92.43% and 260ms, respectively. …”

DSC block and its application network structure. by Yingying Liu (360782)

“…The actual accuracy and mean latency time of the model were 92.43% and 260ms, respectively. …”

The structure of multi-scale residual block [30]. by Yingying Liu (360782)

“…The actual accuracy and mean latency time of the model were 92.43% and 260ms, respectively. …”

The structure of IRAU and Res2Net+ block [22]. by Yingying Liu (360782)

“…The actual accuracy and mean latency time of the model were 92.43% and 260ms, respectively. …”

The effect of CEP and PDS treatment on recombinant CCHFV. by Yutong Sui (11151669)

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%. …”

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%. …”