To effectively solve the problems that most convolutional neural networks cannot be applied to the pixelwise input in remote sensing (RS) classification and cannot adequately represent the spectral sequence information, we propose a new multispectral RS image classification framework called HyFormer based on Transformer. First, a network framework combining a fully connected layer (FC) and convolutional neural network (CNN) is designed, and the 1D pixelwise spectral sequences obtained from the fully connected layers are reshaped into a 3D spectral feature matrix for the input of CNN, which enhances the dimensionality of the features through FC as well as increasing the feature expressiveness, and can solve the problem that 2D CNN cannot achieve pixel-level classification. Secondly, the features of the three levels of CNN are extracted and combined with the linearly transformed spectral information to enhance the information expression capability, and also used as the input of the transformer encoder to improve the features of CNN using the powerful global modelling capability of the Transformer, and finally the skip connection of the adjacent encoders to enhance the fusion between different levels of information. The pixel classification results are obtained by MLP Head. In this paper, we mainly focus on the feature distribution in the eastern part of Changxing County and the central part of Nanxun District, Zhejiang Province, and conduct experiments based on Sentinel-2 multispectral RS images. The experimental results show that the overall accuracy of HyFormer for the study area classification in Changxing County is 95.37% and that of Transformer (ViT) is 94.15%. The experimental results show that the overall accuracy of HyFormer for the study area classification in Nanxun District is 95.4% and that of Transformer (ViT) is 94.69%, and the performance of HyFormer on the Sentinel-2 dataset is better than that of the Transformer.

To address the problem that traditional deep learning algorithms cannot fully utilize the correlation properties between spectral sequence information and the feature differences between different spectra, this paper proposes a parallel network architecture land-use classification based on a combined multi-head attention mechanism and multiscale residual cascade called MARC-Net. This parallel framework is firstly implemented by deeply mining the features generated by grouped spectral embedding for information among spectral features by adding a multi-head attention mechanism, which allows semantic features to have expressions from more subspaces while fully considering all spatial location interrelationships. Secondly, a multiscale residual cascade CNN (convolutional neural network) is designed to fully utilize the fused feature information at different scales, thereby improving the network’s ability to represent different levels of information. Lastly, the features obtained by the multi-head attention mechanism are fused with those obtained by the CNN, and the merged resultant features are downgraded through the fully connected layer to obtain the classification results and achieve pixel-level multispectral image classification. The findings show that the algorithm proposed in this paper has an aggregate precision of 97.22%, compared to that of the Vision Transformer (ViT) with 95.08%; its performance on the Sentinel-2 dataset shows a huge improvement. Moreover, this article mainly focuses on the change rate of forest land in the study area. The Forest land area was 125.1143 km${}^2$ in 2017, 105.6089 km${}^2$ in 2019, and 76.3699 km${}^2$ in 2021, with an increase of $15.59\%$, an decrease of $0.97\%$, and increase of $14.76\%$ in 2017–2019, 2019–2021 and 2017–2021, respectively.

In this paper, we propose a new filtering switch with excellent working performance made using an optimized coupled microstrip line. Upon analyzing the RF (radio frequency) front-end’s system structure, the switching device was simplified to a diode, which was connected to the microstrip circuit we designed to become a filter switch with both filtering and shutdown functions. First, we obtained an equivalent schematic of this filtering switch based on the relevant microstrip line theory. This switch consists of two coupled microstrip circuits, parallel-coupled feed lines and coupled-line stub-load resonators (CLSs), and a PIN diode. Second, the operating principle is described by the switching of the operating states, with ideal shutdown performance in the off state and considerable selectivity and excellent out-of-band rejection performance in the filtered state. Finally, a prototype filtering switch with a center frequency of 0.8 GHz was designed and tested. After subsequent optimization and improvement, the simulation and test performance results were noticeably consistent, consequently verifying the performance requirements of this filtering switch in two operating states in the center frequency band.

It is difficult for traditional algorithms to remove cloud edge contours in multi-cloud scenarios. In order to improve the detection ability of dim and small targets in complex edge contour scenes, this paper proposes a new dim and small target detection algorithm based on local multi-directional gradient information energy perception. Herein, based on the information difference between the target area and the background area in the four direction neighborhood blocks, an energy enhancement model for multi-directional gray aggregation (EMDGA) is constructed to preliminarily enhance the target signal. Subsequently, a local multi-directional gradient reciprocal background suppression model (LMDGR) was constructed to model the background of the image. Furthermore, this paper proposes a multi-directional gradient scale segmentation model (MDGSS) to obtain candidate target points and then combines the proposed multi-frame energy-sensing (MFESD) detection algorithm to extract the true targets from sequence images. Finally, in order to better illustrate the effect of the algorithm proposed in this paper in detecting small targets in a cloudy background, four sequence images are selected for detection. The experimental results show that the proposed algorithm can effectively suppress the edge contour of complex clouds compared with the traditional algorithm. When the false alarm rate Pf is 0.005%, the detection rate Pd is greater than 95%.

The dependence of electronic products on printed circuit boards (PCBs) is increasing. In recent years, PCB defect detection technology has achieved considerable results, but the defect targets are small, the background is complex, and there are many integrated components, which poses great challenges to product quality control. Therefore, this paper proposes a printed circuit board defect detection network that integrates coordinate attention and multi-level gradient flow optimization, called EP-YOLO, to improve the detection accuracy of printed circuit board defects. Firstly, this paper improves the model’s ability to capture small target details by reconstructing the detection head of the small target. Based on this, a Shallow Context Feature Extraction (SCFE) network is designed to fuse shallow features with multi-scale features, effectively preventing the loss of shallow detail information and texture features. At the same time, in order to suppress background noise, this paper designs a multi-level feature gradient flow optimization module (C2f_CA, abbreviated as CCA) that integrates coordinate attention and a Cross-Stage Partial Frequency-domain Omni-Kernel module (CSPFOK) to enhance feature extraction capability. Finally, the SCYLLA-IoU (SIoU) optimization model training process was introduced. The experimental results showed that EP-YOLO achieved 97.5% mAP50 on the PKU-Market-PCB dataset and 98.5% mAP50 on the DeepPCB dataset, with a parameter reduction of approximately 12.55%, outperforming popular object detection networks. The results highlight the potential capabilities of EP-YOLO, providing a powerful and effective solution for industrial PCB defect detection.