As one of the three major outdoor components of the railroad signal system, the track circuit plays an important role in ensuring the safety and efficiency of train operation. Therefore, when a fault occurs, the cause of the fault needs to be found quickly and accurately and dealt with in a timely manner to avoid affecting the efficiency of train operation and the occurrence of safety accidents. This article proposes a fault diagnosis method based on multi-scale attention network, which uses Gramian Angular Field (GAF) to transform one-dimensional time series into two-dimensional images, making full use of the advantages of convolutional networks in processing image data. A new feature fusion training structure is designed to effectively train the model, fully extract features at different scales, and fusing spatial feature information through spatial attention mechanisms. Finally, experiments are conducted using real track circuit fault datasets, and the accuracy of fault diagnosis reaches 99.36%, and our model demonstrates better performance compared to classical and state-of-the-art models. And the ablation experiments verified that each module in the designed model plays a key role.

In image classification of tomato leaf diseases based on deep learning, models often focus on features such as edges, stems, backgrounds, and shadows of the experimental samples, while ignoring the features of the disease area, resulting in weak generalization ability. In this study, a self-attention mechanism called GD-Attention is proposed, which considers global pixel value distribution information and guide the deep learning model to give more concern on the leaf disease area. Based on data augmentation, the proposed method inputs both the image and its pixel value distribution information to the model. The GD-Attention mechanism guides the model to extract features related to pixel value distribution information, thereby increasing attention towards the disease area. The model is trained and tested on the Plant Village (PV) dataset, and by analyzing the generated attention heatmaps, it is observed that the disease area obtains greater weight. The results achieve an accuracy of 99.97% and 27 MB parameters only. Compared to classical and state-of-the-art models, our model showcases competitive performance. As a next step, we are committed to further research and application, aiming to address real-world, complex scenarios.

In the task of pavement distress recognition and classification, the complexity of the pavement environment, the small proportion of distresses in images, significant variation in distress scales, and the influence of features such as vehicles and traffic signs in the data make distress feature extraction challenging. This paper proposes a spectrum focus transformer (SFT) layer, which processes the signal spectrum and focuses on important frequency components. Initially, by thoroughly analyzing the frequency domain characteristics of image data, frequency value distribution information is obtained to achieve fine-tuning of different frequency components. Subsequently, frequency information and images are learned and weighted in the frequency domain, thereby enhancing the capability to capture pavement distress regions. Experiments conducted on the road pavement distress dataset revealed through heatmap analysis that distress regions received increased attention, achieving an accuracy of 97.73%. This performance demonstrates a higher accuracy compared to other models.

As a commonly used mode of transportation in people’s daily lives, the normal operation of railway transportation is crucial. The track circuit, as a key component of the railway transportation system, is prone to malfunctions due to environmental factors. However, the current method of inspecting track circuit faults still relies on the experience of on-site personnel. In order to improve the efficiency and accuracy of fault diagnosis, we propose to establish an intelligent fault diagnosis system. Considering that the fault data are a one-dimensional time series, this paper presents a fault diagnosis method based on the UNet-LSTM network (ULN). The LSTM network is established on the basis of fault data and used for ZPW-2000A track circuit fault diagnosis. However, the use of a single LSTM network has a high error rate in the common fault diagnosis of track circuits. Therefore, this paper proposes a feature extraction method based on the UNet network. This method is used to extract the features of the original data and then input them into the LSTM network for fault diagnosis. Through experiments with on-site fault data, it has been verified that this method can accurately classify seven common track circuit faults. Finally, the superiority of the method is verified by comparing it with other commonly used fault classification methods.

Drone detection plays a key role in various fields, but from the perspective of drones, factors such as the size of the target, interference from different backgrounds, and lighting affect the detection effect, which can easily lead to missed detections and false detections. To address this problem, this paper proposes a small target detection algorithm. First, the hybrid control of attention mechanism and a convolutional module (HCAC) are used to effectively extract contextual details of targets of different scales, directions, and shapes, while relative position encoding is used to associate targets with position information. Secondly, in view of the small size characteristics of small targets, a high-resolution detection branch is introduced, the large target detection head and its redundant network layers are pruned, and a multi-level weighted feature fusion network (MWFN) is used for multi-dimensional fusion. Finally, the WIoU loss is used as a bounding box regression loss, combined with a dynamic non-monotonic focusing mechanism, to evaluate the quality of anchor boxes so that the detector can handle anchor boxes of different qualities, thus improving the overall performance. Experiments were conducted on the UAV aerial photography data set VisDrone2019. The results showed that the accuracy of P increased by 9.0% and MAP by 9.8%, with higher detection results.

In the recognition of fruit leaf diseases, image recognition technology based on deep learning has received increasing attention. However, deep learning models often perform poorly in complex backgrounds, and in some cases, they even outperform traditional algorithms. To address this issue, this paper proposes a Frequency-Adaptive Attention (FA-attention) mechanism that leverages the significance of frequency-domain features in fruit leaf disease regions. By enhancing the processing of frequency domain features, the recognition performance in complex backgrounds is improved. Specifically, FA-attention combines Fourier transform with the attention mechanism to extract frequency domain features as key features. Then, this mechanism is integrated with the Unet model to obtain feature maps strongly related to frequency domain features. These feature maps are fused with multi-scale convolutional feature maps and then used for classification. Experiments were conducted on the Plant Village (PV) dataset and the Plant Pathology (PP) dataset with complex backgrounds. The results indicate that the proposed FA-attention mechanism achieves significant effects in learning frequency domain features. Our model achieves a recognition accuracy of 99.91% on the PV dataset and 89.59% on the PP dataset. At the same time, the convergence speed is significantly improved, reaching 94% accuracy with only 20 epochs, demonstrating the effectiveness of this method. Compared with classical models and state-of-the-art (SOTA) models, our model performs better on complex background datasets, demonstrating strong generalization capabilities.