Semantic segmentation by using remote sensing images is an efficient method for agricultural crop classification. Recent solutions in crop segmentation are mainly deep-learning-based methods, including two mainstream architectures: Convolutional Neural Networks (CNNs) and Transformer. However, these two architectures are not sufficiently good for the crop segmentation task due to the following three reasons. First, the ultra-high-resolution images need to be cut into small patches before processing, which leads to the incomplete structure of different categories’ edges. Second, because of the deficiency of global information, categories inside the crop field may be wrongly classified. Third, to restore complete images, the patches need to be spliced together, causing the edge artifacts and small misclassified objects and holes. Therefore, we proposed a novel architecture named the Coupled CNN and Transformer Network (CCTNet), which combines the local details (e.g., edge and texture) by the CNN and global context by Transformer to cope with the aforementioned problems. In particular, two modules, namely the Light Adaptive Fusion Module (LAFM) and the Coupled Attention Fusion Module (CAFM), are also designed to efficiently fuse these advantages. Meanwhile, three effective methods named Overlapping Sliding Window (OSW), Testing Time Augmentation (TTA), and Post-Processing (PP) are proposed to remove small objects and holes embedded in the inference stage and restore complete images. The experimental results evaluated on the Barley Remote Sensing Dataset present that the CCTNet outperformed the single CNN or Transformer methods, achieving 72.97% mean Intersection over Union (mIoU) scores. As a consequence, it is believed that the proposed CCTNet can be a competitive method for crop segmentation by remote sensing images.

This article presents a novel reduced order average model for dual-active-bridge converter which can be applied to all modulation methods, such as single-phase-shift modulation, dual-phase-shift modulation, extended-phase-shift modulation and triple-phase-shift modulation. This model considers conduction, inductance, and transformer power losses. Furthermore, the input-output filters are suitable for system performance analysis. Based on the large-signal average model, the small-signal model and the output transfer function are derived. The detailed model for predicting the large-signal transient is established and the small signal analysis in frequency domain is carried out. This model can accurately predict the steady-state and transient-state response of the system. The experimental results agreed well with the simulation results which proved the accuracy and correctness of the model.

Accurately capturing the burden surface information of a blast furnace (BF) is helpful to adjust the burden distribution matrix and improve the gas flow distribution, which is essential in the steel smelting industry. However, it is difficult to detect the burden surface because of the high temperature, high pressure, high dust and flame combustion environment condition inside the BF, in addition to the fluidization characteristics of the burden surface. With the fusion of high-temperature metallurgy, radar detection and image processing, a new BF surface deep-learning detection system based on energy weight was developed in this study to visualize the smelting status of a BF and digitize the information of the burden surface. First, the original burden surface echo spectrogram was captured using a frequency-modulated continuous wave radar with a high-temperature-resistant sensor. Second, the point cloud distribution map was constructed based on the principle of synthetic aperture radar (SAR) imaging. The coordinate transformation and matrix compensation were completed by the entropy weight method and Gamma correction to convert point cloud map to the burden surface grayscale image, constructing datasets for the network. Third, with a 3rd-order hourglass feature extraction network, a BF surface detection network based on the principle of YOLOv3 was designed and trained to predict the position of the burden surface in the grayscale image and track the changing trend of the burden line. The proposed method, which is tested on two steel plant datasets, achieved an average prediction precision of 99.74%. Finally, compared with the traditional burden line extraction algorithm, burden line oscillations and local outliers can be avoided by the proposed method. The continuous detection of the BF surface information was realized.

The Hegselmann-Krause (HK) model is a typical self-organizing system with local rule dynamics. In spite of its widespread use and numerous extensions, the underlying theory of its synchronization induced by noise still needs to be developed. In its original formulation, as a model first proposed to address opinion dynamics, its state-space was assumed to be bounded, and the theoretical analysis of noise-induced synchronization for this particular situation has been well established. However, when system states are allowed to exist in an unbounded space, mathematical difficulties arise, whose theoretical analysis becomes nontrivial and is as such still lacking. In this paper, we completely resolve this problem by exploring the topological properties of HK dynamics and employing the theory of independent stopping time. The associated result in full state-space provides a solid interpretation of the randomness-induced synchronization of self-organizing systems.

Designing feasible control strategies for opinion dynamics in complex social systems has never been an easy task. It requires a control protocol, which 1) is not enforced on all individuals in the society, and 2) does not exclusively rely on specific opinion values shared by the social system. Thanks to the recent studies on noise-induced consensus in opinion dynamics, the noise-based intervention strategy has emerged as the only one meeting both of the above requirements, yet its underlying general theory is still lacking. In this article, we perform rigorous theoretical analysis and simulations of a noise-based control strategy for opinion formation, in which only a fraction of individuals is affected by randomly generated noise. We develop a new approach to prove the existence of a feasible noise protocol when it is difficult to be explicitly constructed and prove that irrespective of the number of noise-driven individuals, including the case of only one single noise-affected individual, the system can be controlled to achieve quasi-consensus in finite time, and the critical noise strength can be obtained. Our results highlight the efficiency of noise-driven mechanisms for the control of complex social dynamics.

Accurate Burden Surface Profile (BSP) detection is important for the operation of Blast Furnace (BF). The signal-to-noise ratio of radar signals changes greatly during both the charging period of BF and the long maintenance period of the radar device, which increases the difficulty of radar BSP detection. The traditional radar BSP detection method based on signal energy relies on manually selected detection thresholds according to the noise intensity. Hence, the accuracy of the traditional radar BSP detection method is not reliable in the long term. To address this problem, we propose a novel learning-based Key Points estimation (KP-BSP) method to detect the key points of radar reconstructed BSP image, and a new Key Points-based Connected Region Noise Reduction (KP-CRNR) algorithm to remove the noise-affected regions. The prediction deviation at detected key points (at the positions of the mechanical probes) is then used to correct the radar detection results, leading to the improvement of radar detection accuracy. The experimental data were collected from Wuhan Iron Steel Company No.7 BF. The results show that the proposed methods can achieve an average RMSE of 0.0156m, which is improved by more than 50% compared with previous methods. The long-term reliability of the proposed method is also demonstrated in this dataset.