Yanying Shang

This paper investigates the issue of pre-site selection for drone stations with the aim of enhancing the rapid assessment capability of urban road traffic accidents. Firstly, the influence of traffic accidents on urban traffic is analyzed, and the potential application of drones in rapid response at the accident scene is explored. A minimization model is constructed with the goal of minimizing the cost of accident handling and reducing traffic congestion. To solve this problem, we improved the simulated annealing algorithm by combining the multi-neighborhood strategy, adaptive neighborhood size, and adding a taboo list, and verified the effectiveness of the algorithm. The validity of the model is tested through simulation examples, and the impact of the drone coverage radius and the distribution of accident points on the model performance is explored through sensitivity analysis, providing management insights for the pre-site selection of drone stations.

Musculoskeletal diseases affect over 100 million people globally and are a leading cause of severe, prolonged pain, and disability. Recognized as a clinical emergency, prompt and accurate diagnosis of musculoskeletal disorders is crucial, as delayed identification poses the risk of amputation for patients, and in severe cases, can result in life-threatening conditions such as bone cancer. In this paper, a hybrid model HRD (Human-Resnet50-Densenet121) based on deep learning and human participation is proposed to efficiently identify disease features by classifying X-ray images. Feasibility testing of the model was conducted using the MURA dataset, with metrics such as accuracy, recall rate, F1-score, ROC curve, Cohen’s kappa, and AUC values employed for evaluation. Experimental results indicate that, in terms of model accuracy, the hybrid model constructed through a combination strategy surpassed the accuracy of any individual model by more than 4%. The model achieved a peak accuracy of 88.81%, a maximum recall rate of 94%, and the highest F1-score value of 87%, all surpassing those of any single model. The hybrid model demonstrates excellent generalization performance and classification accuracy.

With the increasing frequency of emergencies in recent years, the emergency response capacity of the emergency management system needs to be improved. Based on safety stock strategy, this paper proposes a multilevel siting model on the topic of mobile emergency response. We modeled the emergency response needs during emergencies by incorporating the population distribution of each region. The uncertainty of emergencies is modeled by aggregating the frequency of crises in each region over the past 20 years. The site selection model minimizes contingency logistics costs that include transshipment, deployment, inventory, and safety stock costs. In this paper, the IA (Immune Algorithm) is optimized to solve the constructed emergency site selection model. The experiments on the model were carried out with data from the area of Chongqing, Sichuan Province. The number of logistics centers and distribution storage warehouses was tested. The influence of safety stock strategy on the total cost of emergency logistics was analyzed. The research results found that the cost of safety stock is negatively related to the cost of transshipment. In addition, the total cost of emergency logistics has a lower bound. Adding distribution and storage warehouses does not further reduce the total emergency logistics cost.