To address multi-UAV task allocation and dynamic obstacle avoidance in post-disaster scenarios, this paper proposes a hierarchical GOAPF-MARL (Goal-Oriented Artificial Potential Field Guided Multi-Agent Reinforcement Learning) framework. In the perception layer, a task model is built to couple casualty level and disaster scale, forming a unified task weight W and enabling more accurate demand representation under varying conditions. For upper-layer allocation, an improved SADCK-Medoid method is used with the Balanced Residual Capacity (BRC) metric to enable nonuniform UAV deployment across five rescue regions. In the execution layer, a Goal-Oriented Artificial Potential Field (GOAPF) is embedded into multi-agent reinforcement learning (MARL), improving navigation around buildings, debris, and expanding fire zones while enhancing coordination and decision stability in complex scenes. Simulation results demonstrate improved efficiency and robustness compared with baseline methods under both ideal and challenging settings.
Lipeng Zhang, Junjie Liu, Yuehui Ji et al.· 2026 IEEE 27th China Confere...· 0 citations
Cardiovascular disease, as a highly prevalent chronic condition, has shown a continuously rising incidence in China and now ranks as the leading cause of death among both urban and rural residents. Mainstream Cardiovascular disease risk prediction models have mostly been developed based on European and American populations, which do not align well with the physical characteristics and disease patterns of the Chinese population. Moreover, traditional statistical methods have inherent limitations, further restricting the clinical applicability of these models. To address this, the present study constructed a Cardiovascular disease risk prediction model tailored to the Chinese population using machine learning algorithms based on the China Health and Retirement Longitudinal Study database. The dataset was split into a training set and a test set at a ratio of 7:3. Seven algorithms were employed for parallel modeling, and multi-dimensional performance comparisons were conducted. The study found that, in addition to traditional risk factors such as blood pressure and blood glucose, sleep indicators—including nap duration and nighttime sleep duration—were also important influencing factors for Cardiovascular disease. The comparative results demonstrated that the LightGBM model achieved the best predictive performance, with an AUC of 0.828, a recall of 0.717, and an F1 score of 0.568. The integration of SHapley Additive exPlanations further validated the internal logic and rationality of the model. This model can assist clinicians in risk assessment, thereby effectively improving the accuracy and efficiency of cardiovascular disease prediction.
Longfa Chu, Jing Lin, Zekai Li et al.· 2026 IEEE 27th China Confere...· 0 citations