Search Results (1,263)

In the field of hyperspectral image classification, deep learning technology, especially convolutional neural networks, has achieved remarkable progress. However, convolutional neural network models encounter challenges in hyperspectral image classification due to limitations in their receptive fields. Conversely, the global modeling capability of Transformers has garnered attention in hyperspectral image classification. Nevertheless, the high computational cost and inadequate local feature extraction hinder its widespread application. In this study, we propose a novel fusion model of convolutional neural networks and Transformers to enhance performance in hyperspectral image classification, namely the dual-branch multi-granularity convolutional cross-substitution Transformer (DMCCT). The proposed model adopts a dual-branch structure to separately extract spatial and spectral features, thereby mitigating mutual interference and information loss between spectral and spatial data during feature extraction. Moreover, a multi-granularity embedding module is introduced to facilitate multi-scale and multi-level local feature extraction for spatial and spectral information. In particular, the improved convolutional cross-substitution Transformer module effectively integrates convolution and Transformer, reducing the complexity of attention operations and enhancing the accuracy of hyperspectral image classification tasks. Subsequently, the proposed method is evaluated against existing approaches using three classical datasets, namely Pavia University, Kennedy Space Center, and Indian Pines. Experimental results demonstrate the efficacy of the proposed method, achieving significant classification results on these datasets with overall classification accuracies of 98.57%, 97.96%, and 96.59%, respectively. These results establish the superiority of the proposed method in the context of hyperspectral image classification under similar experimental conditions. Full article

Deep learning is becoming the most widely used technology for multi-sensor data fusion. Semantic correspondence has recently emerged as a foundational task, enabling a range of downstream applications, such as style or appearance transfer, robot manipulation, and pose estimation, through its ability to provide robust correspondence in RGB images with semantic information. However, current representations generated by self-supervised learning and generative models are often limited in their ability to capture and understand the geometric structure of objects, which is significant for matching the correct details in applications of semantic correspondence. Furthermore, efficiently fusing these two types of features presents an interesting challenge. Achieving harmonious integration of these features is crucial for improving the expressive power of models in various tasks. To tackle these issues, our key idea is to integrate depth information from depth estimation or depth sensors into feature maps and leverage learnable weights for feature fusion. First, depth information is used to model pixel-wise depth distributions, assigning relative depth weights to feature maps for perceiving an object’s structural information. Then, based on a contrastive learning optimization objective, a series of weights are optimized to leverage feature maps from self-supervised learning and generative models. Depth features are naturally embedded into feature maps, guiding the network to learn geometric structure information about objects and alleviating depth ambiguity issues. Experiments on the SPair-71K and AP-10K datasets show that the proposed method achieves scores of 81.8 and 83.3 on the percentage of correct keypoints (PCK) at the 0.1 level, respectively. Our approach not only demonstrates significant advantages in experimental results but also introduces the depth awareness module and a learnable feature fusion module, which enhances the understanding of object structures through depth information and fully utilizes features from various pre-trained models, offering new possibilities for the application of deep learning in RGB and depth data fusion technologies. We will also continue to focus on accelerating model inference and optimizing model lightweighting, enabling our model to operate at a faster speed. Full article

With the advent of the 6G era, the number of IoT devices has experienced explosive growth, leading to the generation of massive amounts of data at the network edge. Semantic communication, as an innovative solution to handling this data deluge, can significantly enhance communication efficiency. However, the limited storage and computational resources of terminal devices constrain the widespread application of semantic communication in 6G networks. To address this issue, we propose a terminal-side-computing-driven intelligent semantic communication solution. Specifically, we introduce a semantic communication model based on Kolmogorov–Arnold Networks (KANs), named K-DeepSC. Using image-reconstruction tasks as an example, the proposed K-DeepSC reduces the number of model parameters by 44% compared to semantic communication models based on Multi-Layer Perceptrons (MLPs), while maintaining similar performance. Furthermore, to fully leverage idle terminal computing power for semantic tasks, we explore computation offloading in dynamic Terminal-Side Computing Power Networks. By optimizing task delay minimization, a deep reinforcement learning algorithm is employed to determine the optimal offloading strategy. Simulation results demonstrate that our proposed solution effectively reduces semantic task processing delay. Full article

This paper introduces a novel approach to pavement material crack detection, classification, and segmentation using advanced deep learning techniques, including multi-scale feature aggregation and transformer-based attention mechanisms. The proposed methodology significantly enhances the model’s ability to handle varying crack sizes, shapes, and complex pavement textures. Trained on a dataset of 10,000 images, the model achieved substantial performance improvements across all tasks after integrating transformer-based attention. Detection precision increased from 88.7% to 94.3%, and IoU improved from 78.8% to 93.2%. In classification, precision rose from 88.3% to 94.8%, and recall improved from 86.8% to 94.2%. For segmentation, the Dice Coefficient increased from 80.3% to 94.7%, and IoU for segmentation advanced from 74.2% to 92.3%. These results underscore the model’s robustness and accuracy in identifying pavement cracks in challenging real-world scenarios. This framework not only advances automated pavement maintenance but also provides a foundation for future research focused on optimizing real-time processing and extending the model’s applicability to more diverse pavement conditions. Full article

Human–robot collaboration will play an important role in the fourth industrial revolution in applications related to hostile environments, mining, industry, forestry, education, natural disaster and defense. Effective collaboration requires robots to understand human intentions and tasks, which involves advanced user profiling. Voice-based communication, rich in complex information, is key to this. Beamforming, a technology that enhances speech signals, can help robots extract semantic, emotional, or health-related information from speech. This paper describes the implementation of a system that provides substantially improved signal-to-noise ratio (SNR) and speech recognition accuracy to a moving robotic platform for use in human–robot interaction (HRI) applications in static and dynamic contexts. This study focuses on training deep learning-based beamformers using acoustic model-based multi-style training with measured room impulse responses (RIRs). The results show that this approach outperforms training with simulated RIRs or matched measured RIRs, especially in dynamic conditions involving robot motion. The findings suggest that training with a broad range of measured RIRs is sufficient for effective HRI in various environments, making additional data recording or augmentation unnecessary. This research demonstrates that deep learning-based beamforming can significantly improve HRI performance, particularly in challenging acoustic environments, surpassing traditional beamforming methods. Full article

Radar emitter signal deinterleaving based on pulse description words (PDWs) is a challenging task in the field of electronic warfare because of the parameter sparsity and uncertainty of PDWs. In this paper, a modulation-hypothesis-augmented Transformer model is proposed to identify emitters from a single PDW with an end-to-end manner. Firstly, the pulse features are enriched by the modulation hypothesis mechanism to generate I/Q complex signals from PDWs. Secondly, a multiple-parameter embedding method is proposed to expand the signal discriminative features and to enhance the identification capability of emitters. Moreover, a novel Transformer deep learning model, named PulseFormer and composed of spectral convolution, multi-layer perceptron, and self-attention based basic blocks, is proposed for discriminative feature extraction, emitter identification, and signal deinterleaving. Experimental results on synthesized PDW dataset show that the proposed method performs better on emitter signal deinterleaving in complex environments without relying on the pulse repetition interval (PRI). Compared with other deep learning methods, the PulseFormer performs better in noisy environments. Full article

Adversarial attack methods can significantly improve the classification accuracy of deep learning models, but research has found that although most deep learning models with defense methods still show good classification accuracy in the face of various adversarial attack attacks, the improved robust models have a significantly lower classification accuracy when facing clean samples compared to themselves without using defense methods. This means that while improving the model’s adversarial robustness, it is necessary to find a defense method to balance the accuracy of clean samples (clean accuracy) and the accuracy of adversarial samples (robust accuracy). Therefore, in this work, we propose an Adaptive Asynchronous Generalized Adversarial Training (A3GT) method, which is an improvement over the existing Generalist method. It employs an adaptive update strategy without the need for extensive experiments to determine the optimal starting iteration for global updates. The experimental results show that compared with other advanced methods, A3GT can achieve a balance between clean sample classification accuracy and robust classification accuracy while improving the model’s adversarial robustness. Full article

In this paper, a deep learning-based device modeling framework for design-technology co-optimization (DTCO) is proposed. A ResNet surrogate model is utilized as an alternative to traditional compact models, demonstrating high accuracy in both single-task (I–V or C–V) and multi-task (I–V and C–V) device modeling. Moreover, transfer learning is applied to the ResNet model, using the BSIM-CMG compact model for a 12 nm FinFET SPICE model as the pre-trained source. Through this approach, superior modeling accuracy and faster training speed are achieved compared to a ResNet surrogate model initialized with random weights, thereby meeting the rapid and efficient demands of the DTCO process. The effectiveness of the ResNet surrogate model in circuit simulation for 12 nm FinFET devices is demonstrated. Full article

Current deep learning models for time series often face challenges with generalizability in scenarios characterized by limited samples or inadequately labeled data. By tapping into the robust generative capabilities of diffusion models, which have shown success in computer vision and natural language processing, we see potential for improving the adaptability of deep learning models. However, the specific application of diffusion models in generating samples for time series classification tasks remains underexplored. To bridge this gap, we introduce the MDGPS model, which incorporates multi-task diffusion learning and gradient-free patch search (MDGPS). Our methodology aims to bolster the generalizability of time series classification models confronted with restricted labeled samples. The multi-task diffusion learning module integrates frequency-domain classification with random masked patches diffusion learning, leveraging frequency-domain feature representations and patch observation distributions to improve the discriminative properties of generated samples. Furthermore, a gradient-free patch search module, utilizing the particle swarm optimization algorithm, refines time series for specific samples through a pre-trained multi-task diffusion model. This process aims to reduce classification errors caused by random patch masking. The experimental results on four time series datasets show that the proposed MDGPS model consistently surpasses other methods, achieving the highest classification accuracy and F1-score across all datasets: 95.81%, 87.64%, 82.31%, and 100% in accuracy; and 95.21%, 82.32%, 78.57%, and 100% in F1-Score for Epilepsy, FD-B, Gesture, and EMG, respectively. In addition, evaluations in a reinforcement learning scenario confirm MDGPS’s superior performance. Ablation and visualization experiments further validate the effectiveness of its individual components. Full article

High-resolution optical images will provide planetary geology researchers with finer and more microscopic image data information. In order to maximize scientific output, it is necessary to further increase the resolution of acquired images, so image super-resolution (SR) reconstruction techniques have become the best choice. Aiming at the problems of large parameter quantity and high computational complexity in current deep learning-based image SR reconstruction methods, we propose a novel Recursive Swin Transformer Super-Resolution Network (RSTSRN) for SR applied to images. The RSTSRN improves upon the LapSRN, which we use as our backbone architecture. A Residual Swin Transformer Block (RSTB) is used for more efficient residual learning, which consists of stacked Swin Transformer Blocks (STBs) with a residual connection. Moreover, the idea of parameter sharing was introduced to reduce the number of parameters, and a multi-scale training strategy was designed to accelerate convergence speed. Experimental results show that the proposed RSTSRN achieves superior performance on 2×, 4× and 8×SR tasks to state-of-the-art methods with similar parameters. Especially on high-magnification SR tasks, the RSTSRN has great performance superiority. Compared to the LapSRN network, for 2×, 4× and 8× Mars image SR tasks, the RSTSRN network has increased PSNR values by 0.35 dB, 0.88 dB and 1.22 dB, and SSIM values by 0.0048, 0.0114 and 0.0311, respectively. Full article

Recently, developing multi-UAVs to cooperatively pursue a fast-moving target has become a research hotspot in the current world. Although deep reinforcement learning (DRL) has made a lot of achievements in the UAV pursuit game, there are still some problems such as high-dimensional parameter space, the ease of falling into local optimization, the long training time, and the low task success rate. To solve the above-mentioned issues, we propose an improved twin delayed deep deterministic policy gradient algorithm combining the genetic algorithm and maximum mean discrepancy method (GM-TD3) for multi-UAV cooperative pursuit of high-speed targets. Firstly, this paper combines GA-based evolutionary strategies with TD3 to generate action networks. Then, in order to avoid local optimization in the algorithm training process, the maximum mean difference (MMD) method is used to increase the diversity of the policy population in the updating process of the population parameters. Finally, by setting the sensitivity weights of the genetic memory buffer of UAV individuals, the mutation operator is improved to enhance the stability of the algorithm. In addition, this paper designs a hybrid reward function to accelerate the convergence speed of training. Through simulation experiments, we have verified that the training efficiency of the improved algorithm has been greatly improved, which can achieve faster convergence; the successful rate of the task has reached 95%, and further validated UAVs can better cooperate to complete the pursuit game task. Full article

The correct diagnosis and early treatment of respiratory diseases can significantly improve the health status of patients, reduce healthcare expenses, and enhance quality of life. Therefore, there has been extensive interest in developing automatic respiratory disease detection systems. Most recent methods for detecting respiratory disease use machine and deep learning algorithms. The success of these machine learning methods depends heavily on the selection of proper features to be used in the classifier. Although metaheuristic-based feature selection methods have been successful in addressing difficulties presented by high-dimensional medical data in various biomedical classification tasks, there is not much research on the utilization of metaheuristic methods in respiratory disease classification. This paper aims to conduct a detailed and comparative analysis of six widely used metaheuristic optimization methods using eight different transfer functions in respiratory disease classification. For this purpose, two different classification cases were examined: binary and multi-class. The findings demonstrate that metaheuristic algorithms using correct transfer functions could effectively reduce data dimensionality while enhancing classification accuracy. Full article

Wind turbine rolling bearings are crucial components for ensuring the reliability and stability of wind power systems. Their failure can lead to significant economic losses and equipment downtime. Therefore, the accurate diagnosis of bearing faults is of great importance. Although existing deep learning fault diagnosis methods have achieved certain results, they still face limitations such as inadequate feature extraction capabilities, insufficient generalization to complex working conditions, and ineffective multi-scale feature capture. To address these issues, this paper proposes an advanced fault diagnosis method named the two-stream feature fusion convolutional neural network (TSFFResNet-Net). Firstly, the proposed method combines the advantages of one-dimensional convolutional neural networks (1D-ResNet) and two-dimensional convolutional neural networks (2D-ResNet). It transforms one-dimensional vibration signals into two-dimensional images through the empirical wavelet transform (EWT) method. Then, parallel convolutional kernels in 1D-ResNet and 2D-ResNet are used to extract multi-scale features, respectively. Next, the Convolutional Block Attention Module (CBAM) is introduced to enhance the network’s ability to capture key features by focusing on important features in specific channels or spatial areas. After feature fusion, CBAM is introduced again to further enhance the effect of feature fusion, ensuring that the features extracted by different network branches can be effectively integrated, ultimately providing more accurate input features for the classification task of the fully connected layer. The experimental results demonstrate that the proposed method outperforms other traditional methods and advanced convolutional neural network models on different datasets. Compared with convolutional neural network models such as LeNet-5, AlexNet, and ResNet, the proposed method achieves a significantly higher accuracy on the test set, with a stable accuracy of over 99%. Compared with other models, it shows better generalization and stability, effectively improving the overall performance of rolling bearing vibration signal fault diagnosis. The method provides an effective solution for the intelligent fault diagnosis of wind turbine rolling bearings. Full article

The advancement of deep learning techniques has significantly propelled the development of the continuous sign language recognition (cSLR) task. However, the spatial feature extraction of sign language videos in the RGB space tends to focus on the overall image information while neglecting the perception of traits at different granularities, such as eye gaze and lip shape, which are more detailed, or posture and gestures, which are more macroscopic. Exploring the efficient fusion of visual information of different granularities is crucial for accurate sign language recognition. In addition, applying a vanilla Transformer to sequence modeling in cSLR exhibits weak performance because specific video frames could interfere with the attention mechanism. These limitations constrain the capability to understand potential semantic characteristics. We introduce a feature fusion method for integrating visual features of disparate granularities and refine the metric of attention to enhance the Transformer’s comprehension of video content. Specifically, we extract CNN feature maps with varying receptive fields and employ a self-attention mechanism to fuse feature maps of different granularities, thereby obtaining multi-scale spatial features of the sign language framework. As for video modeling, we first analyze why the vanilla Transformer failed in cSLR and observe that the magnitude of the feature vectors of video frames could interfere with the distribution of attention weights. Therefore, we utilize the Euclidean distance among vectors to measure the attention weights instead of scaled-dot to enhance dynamic temporal modeling capabilities. Finally, we integrate the two components to construct the model MSF-ET (Multi-Scaled feature Fusion–Euclidean Transformer) for cSLR and train the model end-to-end. We perform experiments on large-scale cSLR benchmarks—PHOENIX-2014 and Chinese Sign Language (CSL)—to validate the effectiveness. Full article

The accurate segmentation of cracks in structural materials is crucial for assessing the safety and durability of infrastructure. Although conventional segmentation models based on deep learning techniques have shown impressive detection capabilities in these tasks, their performance can be restricted by small amounts of training data. Data augmentation techniques have been proposed to mitigate the data availability issue; however, these systems often have limitations in texture diversity, scalability over multiple physical structures, and the need for manual annotation. In this paper, a novel generative artificial intelligence (GAI)-driven data augmentation framework is proposed to overcome these limitations by integrating a projected generative adversarial network (ProjectedGAN) and a multi-crack texture transfer generative adversarial network (MCT2GAN). Additionally, a novel metric is proposed to evaluate the quality of the generated data. The proposed method is evaluated using three datasets: the bridge crack library (BCL), DeepCrack, and Volker. From the simulation results, it is confirmed that the segmentation performance can be improved by the proposed method in terms of intersection over union (IoU) and Dice scores across three datasets. Full article