Park green space is an important part of the green infrastructure in a city, and urban park space accessibility is an important indicator for measuring the city’s comprehensive strength, living environment, and resident happiness, which greatly affects the sustainable development and construction of the city. The spatial syntax method can discuss the accessibility of urban parks from the perspective of topology, which inherits the objective stability of the topological relationship. There are few research studies on the accessibility of urban parks. Therefore, with the support of space syntax theory and the spatial statistics method, this paper combined the data of park green space and road network to complete the accessibility evaluation of urban parks in the Changsha City urban area. This paper evaluates the accessibility of urban parks in the study area from four aspects, namely global accessibility, perceptual accessibility, local accessibility, and psychological accessibility, by using five quantitative indexes of space syntax, namely connectivity, depth, integration, selection, and synergy. The conclusions are as follows: The spatial layout area of the park is roughly consistent with the areas that have good global and local accessibility of the road network, and the global accessibility and local accessibility of the park in the study area are relatively high. The global spatial structure can be better perceived by the local space at a radius scale greater than or equal to 3000 m, and the perceptual accessibility of the park is high. Most of the urban parks in the Changsha urban area are located in sections with high space efficiency. The park space penetration is good, and nearly 70% of the parks have high psychological accessibility. Based on the overall spatial layout of urban parks, the space syntax method quantitatively and comprehensively evaluates the accessibility of urban parks from the perspective of topology. The conclusion is reliable and has important application value in the evaluation of park accessibility. It can be used as an important supplement to improve the evaluation model of accessibility.

With the rapid development of information technology and the increasing diversity in the education field, personalized teaching has become the key to educational innovation. However, existing methods of customizing and distributing teaching contents often fail to effectively cope with complex teaching environments and resource constraints. To solve this problem, this study proposed a novel intelligent content distribution system, i.e., a teaching content customization method based on machine learning. First, an inverse optimization model of teaching content customization targeted at content combinations was constructed, which minimized the adjustment of configuration parameters and customized resource constraints. This model generated more reasonable and effective teaching content configuration plans by comprehensively considering content diversity, students’ needs, and resource constraints. Second, to further improve the efficiency and effect of content distribution, an intelligent content distribution algorithm based on a hierarchical reinforcement learning network was developed, which allowed the system to automatically learn and adjust content distribution strategies based on students’ needs and preferences, and optimized the teaching content configuration while meeting resource constraints. The method proposed in this study not only significantly improved the teaching effect, but also provided strong technical support for the rational allocation of educational resources, thereby bringing profound impacts to modern education. This study is of great significance for intelligent content distribution and personalized teaching in the education field.

Background: Practical implementation of radiomics research faces significant data accessibility challenges due to privacy and ethical restrictions on multicenter data aggregation. Federated Learning (FL) provides a secure distributed framework that preserves data privacy through cryptographic techniques. Its adoption in radiomics is an emerging trend, enabling collaborative training without sharing sensitive imaging data. However, the inherently Non-IID data distribution across clients in FL often leads to class imbalance, which can substantially degrade global model performance. Purpose: To develop a privacy-preserving, multicenter collaborative CT-radiomics model for evaluating neoadjuvant chemotherapy efficacy in non‑small cell lung cancer (NSCLC). Methods: To mitigate FL performance degradation caused by data imbalance, we propose a parameter‑sharing federated aggregation algorithm (FedPS), where model parameters are sequentially shared via the server. Results: On an imbalanced NSCLC NAC efficacy dataset, centralized learning achieved an AUC of 0.92. FedPS attained competitive performance (AUC = 0.88), approaching the centralized benchmark while preserving privacy. Common FL algorithms performed lower: FedAvg (AUC = 0.84), FedSGD (0.85), and FedProx (0.85). On extremely imbalanced data, FedPS maintained good performance (AUC = 0.86), compared to FedAvg (0.80), FedSGD (0.83), and FedProx (0.85). Conclusions: The proposed FedPS algorithm demonstrates promising classification and generalization performance in imbalanced federated learning scenarios.