Lin Song

Background: Equitable distribution of medical facilities is a foundational element of urban health policy, particularly in rapidly urbanizing settings where spatial mismatches between healthcare supply and population demand can exacerbate health inequities. In China, despite national efforts to strengthen primary healthcare, the planning and distribution of medical facilities remain uneven, raising concerns about fairness, efficiency, and social justice in public service provision. Methods: We conducted a multi-city geospatial assessment across four major cities in Shandong Province (Jinan, Qingdao, Yantai, and Weihai) using an integrated framework that combines healthcare Points of Interest (POIs), 100-meter resolution census-based population grids, OpenStreetMap road networks, and official land use records. To evaluate spatial equity, we applied the Gini coefficient, global and local indicators of spatial autocorrelation (Moran’s I and LISA), and geographically weighted regression (GWR) to identify disparities and context-specific drivers of medical facility distribution. Results: Our analysis reveals significant over-concentration of medical resources in central urban districts, while peripheral and county-level areas face systemic under-provision. Gini coefficients ranged from 0.59 to 0.73 indicating high levels of intra-urban inequity. GWR results further show that in core areas, facility location aligns with population density and economic activity, whereas in outlying regions, inadequate transport infrastructure and inflexible land-use regulations constrain equitable access. Notably, Qixia, Liuhe, and Rongcheng emerged as critical underserved zones requiring targeted policy intervention. Conclusion: This study provides actionable, spatially explicit evidence for urban health policymakers seeking to advance equity in medical resource allocation. By linking fine-grained geospatial analytics with principles of spatial justice, our findings support the redesign of medical facility planning guidelines, the integration of accessibility metrics into smart city governance, and the prioritization of underserved areas in future health infrastructure investment. The methodological approach offers a scalable model for evidence-informed public health policy in other emerging urban contexts.

To more effectively capture the periodic and dynamic changes in urban traffic flow and the spatiotemporal correlation of complex road networks, a new traffic flow prediction method, the Enhanced Spatiotemporal Graph Convolutional Network Encoder-Decoder Model (ESGCN-EDM), is proposed. The model achieves a significant enhancement in prediction accuracy through the introduction of the attention-based Personalized-enhanced Fusion Graph Convolutional Network (aPFGCN) and the Temporal Convolutional Bidirectional Long Short-Term Memory (TCBiL) module. The aPFGCN module effectively reduces the dimensionality of features and decreases model complexity to obtain the final node feature representation by personalizing the adjustment of node influence coefficients and applying Fourier transform and inverse transform techniques. Additionally, by incorporating an attention mechanism, it enhances the model’s ability to focus on important information and effectively captures the spatial topological relationships within the traffic network. The TCBiL module integrates 1D convolution with BiLSTM to form a unified temporal feature extraction module. The 1D convolution is utilized to extract local features from the time series, while the BiLSTM captures long-term dependencies within the time series. This allows for simultaneous feature extraction and temporal modeling, thereby enhancing the model’s efficiency and performance, and strengthening its ability to model time series. In the encoder part of the ESGCN-EDM, the aPFGCN is combined with the TCBiL to handle the spatiotemporal coupling interactions of the road network. The decoder part then performs multi-step predictions based on spatiotemporal sequences using the TCBiL and CNN, generating high-dimensional representations. Extensive experiments conducted on two real-world road traffic datasets demonstrate that the ESGCN-EDM model consistently outperforms other benchmark models in 1-hour, 30-minute, and 15-minute traffic flow predictions. Specifically, on the PeMSD8 dataset, the model achieves reductions in MAE, RMSE, and SMAPE by 7.9%, 2.1%, and 16.9%, respectively, compared to the AMRGCN model for 1-hour predictions. Similarly, on the PeMSD4 dataset, the model reduces MAE, RMSE, and MAPE by 1.8%, 1.1%, and 3.0%, respectively. These results validate the efficacy of the proposed model and its ability to significantly enhance the accuracy of traffic flow forecasting.

Currently, weed control robots that can accurately identify weeds and carry out removal work are gradually replacing traditional chemical weed control techniques. However, the computational and storage resources of the core processing equipment of weeding robots are limited. Aiming at the current problems of high computation and the high number of model parameters in weeding robots, this paper proposes a lightweight weed target detection model based on the improved YOLOv8 (You Only Look Once Version 8), called RVDR-YOLOv8 (Reversible Column Dilation-wise Residual). First, the backbone network is reconstructed based on RevCol (Reversible Column Networks). The unique reversible columnar structure of the new backbone network not only reduces the computational volume but also improves the model generalisation ability. Second, the C2fDWR module is designed using Dilation-wise Residual and integrated with the reconstructed backbone network, which improves the adaptive ability of the new backbone network RVDR and enhances the model’s recognition accuracy for occluded targets. Again, GSConv is introduced at the neck end instead of traditional convolution to reduce the complexity of computation and network structure while ensuring the model recognition accuracy. Finally, InnerMPDIoU is designed by combining MPDIoU with InnerIoU to improve the prediction accuracy of the model. The experimental results show that the computational complexity of the new model is reduced by 35.8%, the number of parameters is reduced by 35.4% and the model size is reduced by 30.2%, while the mAP₅₀ and mAP_50-95 values are improved by 1.7% and 1.1%, respectively, compared to YOLOv8. The overall performance of the new model is improved compared to models such as Faster R-CNN, SSD and RetinaNet. The new model proposed in this paper can achieve the accurate identification of weeds in farmland under the condition of limited hardware resources, which provides theoretical and technical support for the effective control of weeds in farmland.

Simulation environment of the mobile Ad Hoc network is built by applying NS2 simulation software. The simulation data indicates that AODV routing protocol is better than DSDV in throughput, fairness and stability. In the underwater network environment where the nodes are in Low-Speed movement, the data transfer rate of AODV routing protocol is higher than AOMDV. To a certain extent, AODV is more suitable for application in underwater environments.