This paper establishes a comprehensive and scientifically rigorous evaluation index system specifically designed for high-quality agricultural development. Utilizing methods such as the entropy weight method, comprehensive evaluation index method, and Dagum Gini coefficient, it provides an in-depth analysis of the level and spatiotemporal dynamics of agricultural development in Zhejiang Province. The results indicate that Zhejiang Province has consistently demonstrated an improvement in the overall quality of its agricultural development, evident from a substantial increase in the agricultural development index, particularly after 2018. This upward trend is primarily driven by significant advancements in agricultural production efficiency, coupled with the rapid integration and expansion of mechanization and technology. Additionally, the study highlights notable regional disparities and burgeoning trends in agricultural development within Zhejiang. Specifically, the northern region maintains its leading position, while the eastern region is progressively gaining prominence. To facilitate comprehensive and high-quality agricultural development across Zhejiang Province, the paper suggests strategies including fostering coordinated regional development, optimizing resource allocation, and refining the structure of the agricultural industry.

In recent years, high-dimensional fractional equations have gained prominence as a pivotal focus of interdisciplinary research spanning mathematical physics, fluid mechanics, and related fields. In this paper, we investigate a (4+1)-dimensional time-fractional Kadomtsev-Petviashvili (KP) equation with variable coefficients. We first derive the (4+1)-dimensional time-fractional KP equation with variable coefficients in the sense of the Riemann-Liouville fractional derivative using the semi-inverse and variational methods. The symmetries and conservation laws of this equation are analyzed through Lie symmetry analysis and a new conservation theorem, respectively. Finally, both exact and numerical solutions of the fractional-order equation are obtained using the Hirota bilinear method and the pseudo-spectral method. The effectiveness and reliability of the proposed approach are demonstrated by comparing the numerical solutions of the derived models with exact solutions in cases where such solutions are known.

Accurate segmentation of brain magnetic resonance (MR) images is critical in brain disease research and treatment. While deep learning methods have advanced image segmentation by extracting hierarchical features, they typically require large labeled datasets for precise results. Acquiring annotated medical data remains challenging due to the need for specialized expertise and privacy restrictions. To address this, we propose a semi-supervised model combining dual tasks: segmentation and boundary feature regression. For class imbalance in segmentation, the network employs focal loss to extract common features from annotated data. To handle asymmetric data distributions, a skew Normal Mixture-based Level set loss guides the network to learn individual image characteristics, enhancing class distribution fitting. This dual-feature integration enables strong performance on limited datasets. In regression, Level set signed distance functions focus the model on boundary information, mitigating partial volume effects on focal loss. Experiments on IBSR and MRBrainS18 datasets demonstrate our method’s advantages over current state-of-the-art approaches.

In addressing the tracking control problem for unmanned aerial vehicle (UAV) swarms, we consider several challenges: the unmeasurable state of the swarm system, potential deception attacks on actuators, external random disturbances, and the nonlinear dynamics of each UAV. To tackle these issues, we first introduce a time-varying function and utilize a coordinate transformation method to convert the time tracking problem into an error variable constraint problem. Next, we propose an adaptive time tracking control method employing one-to-one mapping and inversion techniques, aimed at achieving system convergence to a specified accuracy within a designated time frame. To mitigate the impact of possible deception attacks on actuators, we design an attack compensator that removes disturbances caused by time-varying attack gains. Additionally, we implement an observer to estimate the unmeasurable state of the system and utilize a fuzzy logic system to manage unknown functions. Finally, we validate the effectiveness of our control method through simulations.

Inspired by the Fast point Feature Histogram (FPFH) feature extraction algorithm, this paper proposes a new 3D point cloud registration method, MFIPC (Multi-feature Fusion and Interval Pairing Consistency). The method uses feature fusion and interval pairwise consistency to improve the registration accuracy. In the MFIPC framework, the point cloud is first downsampled to optimize computational efficiency and expand the analysis domain. Then, clustering algorithm using local directional centrality (CDC) classification algorithm is used to calculate the DCM (directional centrality measure) value of each point. The Gaussian curvature values of the points are calculated at the same time, and these eigenvalues are fused. To further refine the registration process, the range between the minimum and maximum eigenvalues is divided into several equal intervals and sorted in ascending order. A sorting algorithm is used to assign each eigenvalue to a corresponding interval. For the global point cloud computing step, after the operation is completed, the number of points in each interval and its proportion are calculated. The program processes both point clouds in order to analyze their interval percentage. This algorithm significantly improves the robustness of MFIPC in establishing point correspondence. To verify the effectiveness of MFIPC for 3D point cloud registration, we conducted extensive testing on various datasets, including 3DMatch, RESSO, ModelNet40, Stanford Rabbit, and Dragon. The experimental results show that the algorithm has high efficiency, good consistency of point cloud, significantly reduced registration errors, low error and high registration accuracy