Aiming at the problem of insufficient details of retinal blood vessel segmentation in current research methods, this paper proposes a multiscale feature fusion residual network based on dual attention. Specifically, a feature fusion residual module with adaptive calibration weight features is designed, which avoids gradient dispersion and network degradation while effectively extracting image details. The SA module and ECA module are used many times in the backbone feature extraction network to adaptively select the focus position to generate more discriminative feature representations; at the same time, the information of different levels of the network is fused, and long-range and short-range features are used. This method aggregates low-level and high-level feature information, which effectively improves the segmentation performance. The experimental results show that the method in this paper achieves the classification accuracy of 0.9795 and 0.9785 on the STARE and DRIVE datasets, respectively, and the classification performance is better than the current mainstream methods.

To solve the energy hole problem in wireless sensor networks with double sinks, a double sink energy hole avoidance strategy is proposed. The main idea is that two data sinks are set at fixed positions on both sides of the rectangular network to collect nodes data in the corresponding area of the network. In the network, sensor nodes are organized in non-uniform clusters. Clusters close to sink have a smaller cluster radius, and clusters far from sink have a larger cluster radius. According to the results of threshold training, monitoring area of double sink is dynamically adjusted based on the difference of energy consumption and load of nodes in the double sink monitoring area, so that the energy consumption load of nodes in the double sink monitoring area tends to be the same, so as to avoid the premature occurrence of energy hole phenomenon in the area with large load, leading to network failure. The experimental results demonstrate that the strategy proposed in this paper can efficiently balance the energy dissipation of double sink and prolong the network energy utilization efficiency and network lifetime.

Grain storage temperature prediction is crucial for silo safety and can effectively prevent mold and mildew caused by increasing grain temperature and condensation due to decreasing grain temperature. However, current prediction methods lead to information redundancy when capturing temporal and spatial dependencies, which diminishes prediction accuracy. To tackle this issue, this paper introduces an adaptive multi-scale feature fusion transformer model (AMSformer). Firstly, the model utilizes the adaptive channel attention (ACA) mechanism to adjust the weights of different channels according to the input data characteristics and suppress irrelevant or redundant channels. Secondly, AMSformer employs the multi-scale attention mechanism (MSA) to more accurately capture dependencies at different time scales. Finally, the ACA and MSA layers are integrated by a hierarchical encoder (HED) to efficiently utilize adaptive multi-scale information, enhancing prediction accuracy. In this study, actual grain temperature data and six publicly available datasets are used for validation and performance comparison with nine existing models. The results demonstrate that AMSformer outperforms in 36 out of the 58 test cases, highlighting its significant advantages in prediction accuracy and efficiency.

Hybrid excitation synchronous motor (HESM) offers the advantages of a convenient flux regulation and a wide range of available speeds. As such, it may be conveniently employed in the fields of electric vehicle and aerospace. In this paper, based on a suitable control strategy for vector and speed partition, we put forward a speed control method for HESM which shows optimal efficiency. On the one hand, our method aims at minimizing the copper loss by an optimal configuration of theq-axis current, thed-axis current, and the excitation current under the constraint voltage at the armature end. On the other hand, we conduct a comprehensive analysis of the effects of the flux-weakening speed coefficient on the operating performance of the motors and suggest a self-adaptive control method to regulate that coefficient and further improve the overall performance of the motors, including their speed-range regulation, their efficiency, and their dynamical properties. The proposed flux-weakening control method has been assessed by simulations and HESM-driven experiments. Results have confirmed the feasibility and optimality of our method.

With the continuous development and progress of wireless self-organizing network communication technology, how to carry out long-distance cooperative control of multiple intelligences under the framework of an air–ground integrated wireless high-mobility self-organizing network has become a hot and difficult topic that needs to be solved urgently. This paper takes the air–ground integrated wireless high-mobility self-organizing network system as the basic framework and focuses on solving the long-distance cooperative fault-tolerant control of multi-intelligent bodies and the topological stability of a wireless mobile self-organizing network. To solve the above problems, a direct neural network with a robust adaptive fault-tolerant controller is designed in this paper. By constructing a symmetric population neural network model and combining it with the Lyapunov stabilization criterion, the system feedback matrix K has the ability of autonomous adaptive learning, and symmetrically distorts, rotates, or scales the training data to instantly adjust the system’s fault-tolerant corrections and adaptive adjusting factors to resist the unknown disturbances and faults, to achieve the goals of multi-intelligent body stable control and the stable operation of a wireless high-mobility self-organizing network topology. Simulation results show that with the feedback adjustment of the multi-system under the designed controller, the multi-system as a whole has good fault-tolerant performance and autonomous learning approximation performance, and the tracking error asymptotically converges to zero. The experimental results show that the multi-flight subsystems fly stably, the air–ground integrated wireless high-mobility self-organizing network topology has good stability performance, and the maximum relative improvement of the topology stability performance is 50%.