Performance comparison of YOLOv8n adding different loss functions. حسب Wenyuan Xu (2553028)

Algorithm comparison test results. حسب Hang Ren (1312905)

Supplementary file 1_A real-world disproportionality analysis of FDA adverse event reporting system (FAERS) events for lecanemab.docx حسب Linlin Yan (4480570)

"…At the system organ class (SOC) level, the highest signal detection for lecanemab was observed in nervous system disorders among AD and Non-AD patients [ROR for AD: 2.42 (2.2–2.65); ROR for Non-AD: 6.97 (6.12–7.95)]. …"

Network structure diagram of YOLOv8 algorithm. حسب Weiyu Han (3448742)

Spatiotemporal spike sorting on multi-electrode array (MEA) data: Uniform Manifold Approximation and Projection (UMAP) vs. SpyKING CIRCUS (SC). حسب Daniel Suárez-Barrera (22676654)

Aluminum alloy industrial materials defect حسب Ying Han (20349093)

Schematic diagram of MHSA mechanism. حسب Guofeng Qin (11025170)

"…Second, a 160 × 160-pixel Small Object (SO) detection layer is added to the Neck structure. Finally, the Multi-Head Self-Attention (MHSA) mechanism is introduced into the Backbone network to enhance the model’s detection performance. …"

Improved FPN combined with PAN structure. حسب Guofeng Qin (11025170)

"…Second, a 160 × 160-pixel Small Object (SO) detection layer is added to the Neck structure. Finally, the Multi-Head Self-Attention (MHSA) mechanism is introduced into the Backbone network to enhance the model’s detection performance. …"

YOLOv5s network structure. حسب Guofeng Qin (11025170)

"…Second, a 160 × 160-pixel Small Object (SO) detection layer is added to the Neck structure. Finally, the Multi-Head Self-Attention (MHSA) mechanism is introduced into the Backbone network to enhance the model’s detection performance. …"

Improved YOLOv5s network structure. حسب Guofeng Qin (11025170)

"…Second, a 160 × 160-pixel Small Object (SO) detection layer is added to the Neck structure. Finally, the Multi-Head Self-Attention (MHSA) mechanism is introduced into the Backbone network to enhance the model’s detection performance. …"

Improved YOLOv5s-DeepSORT network structure. حسب Guofeng Qin (11025170)

"…Second, a 160 × 160-pixel Small Object (SO) detection layer is added to the Neck structure. Finally, the Multi-Head Self-Attention (MHSA) mechanism is introduced into the Backbone network to enhance the model’s detection performance. …"

Ablation experiments. حسب Weiyu Han (3448742)

Ablation experiments. حسب Weiyu Han (3448742)

Structure of CRU. حسب Weiyu Han (3448742)

Ablation experiments. حسب Weiyu Han (3448742)

Contrasting experiment results. حسب Weiyu Han (3448742)

Structure of SRU. حسب Weiyu Han (3448742)

Experimental hyperparameter setting. حسب Weiyu Han (3448742)

Experimental software and hardware configuration. حسب Weiyu Han (3448742)

Distribution of insulator target data. حسب Weiyu Han (3448742)