Accurate drone and bird identification is vital for airspace safety and ecological protection. However, their similar appearance and behavior at long distances and small scales, combined with challenges like lighting, weather, and target size, limit single-sensor (visible or infrared) recognition performance in complex scenarios. To address these challenges, this paper proposes YOLOv10-PRD, an enhanced recognition method based on YOLOv10 with multi-source data fusion (visible, infrared, radar, and audio). By leveraging complementary information and enhancing feature extraction, the model achieves higher robustness and accuracy. The improvements include the integration of the PSContextAggregation module to more effectively capture features of distant or blurry targets. To enhance the model’s focus on critical features in complex scenarios, RFAConv is integrated at the tail end of the head network, replacing standard convolutions. Additionally, DWConv effectively preserves local features within each channel while reducing model complexity and inference time. The YOLOv10-PRD model was evaluated on multi-modal datasets including visible light, infrared, radar droppler, audio spectrum, optical fusion, and COCO. It achieved a mAP0.50 of 82.5% on the visible dataset (6.9% improvement over YOLOv10), 84.4% on infrared (2.6% improvement), 66.3% on radar droppler (1.9% improvement), and an 11.1% gain on the audio spectrum dataset. It also significantly outperformed YOLOv11, Gold-YOLO, EfficientDet, DAMO YOLO, and other mainstream models on COCO and optical mixed datasets. In video detection of small and medium targets such as birds and drones, it improved mAP0.50 by 9% and 4.4%, respectively. Deployed on low-power devices, the model maintained 41 FPS with high detection precision, meeting real-time requirements for medium- and long-range scenarios. Overall, YOLOv10-PRD balances mAP, efficiency, and adaptability, showing strong potential for practical deployment.

This study aimed to scrutinize the procedural mechanisms underlying the accurate selection of financial budget items in reimbursement forms, to reinforce adherence to predefined expenditure guidelines, enhance the standardization of form completion procedures, and augment work efficiency. The 7,959 reimbursement dataset was collected from a medical vocational college in Yunnan Province of China in 2022 and partitioned into training (80%) and testing (20%). Leveraging Random Forest (RF) complemented by Recursive Feature Elimination (RFE), we selected pertinent attributes. Further, utilizing Grid Search CV, we trained a K-Nearest Neighbors (KNN) predictive model for budget item classification and contrasted its performance with a Decision Tree (DT) and GBDT. Our outcomes illuminated that the prediction accuracy of KNN (81%) is higher than both GBDT (42%) and DT (59%). These insights offer fresh perspectives on the procedural dynamics of financial budgeting, potentially informing strategies for improving financial management practices and form processing efficiency.