Search

Abstract Tumour medical image segmentation plays a crucial role in clinical imaging diagnosis. Existing research has achieved good results, enabling the segmentation of three tumour regions in MRI brain tumour images. Existing models have limited focus on the brain tumour areas, and the long‐term dependency of features is weakened as the network depth increases, resulting in blurred edge segmentation of the targets. Additionally, considering the excellent segmentation performance of the Swin Transformer(Swin‐T) network, its network structure and parameters are relatively large. To address these limitations, this paper proposes a brain tumour segmentation framework with deep nuanced reasoning and Swin‐T. It is mainly composed of the backbone hybrid network (BHN) and the deep micro texture extraction module (DMTE). The BHN combines the Swin‐T stage with a new downsampling transition module called dual path feature reasoning (DPFR). The entire network framework is designed to extract global and local features from multi‐modal data, enabling it to capture and analyze deep texture features in multi‐modal images. It provides significant optimization over the Swin‐T network structure. Experimental results on the BraTS dataset demonstrate that the proposed method outperforms other state‐of‐the‐art models in terms of segmentation performance. The corresponding source codes are available at https://github.com/CurbUni/Brain‐Tumor‐Segmentation‐Framework‐with‐Deep‐Nuanced‐Reasoning‐and‐Swin‐T.

Abstract As a necessary process of modern drug development, finding a drug compound that can selectively bind to a specific protein is highly challenging and costly. Exploring drug‐target interaction strength in terms of drug‐target affinity (DTA) is an emerging and effective research approach for drug development. However, it is challenging to model drug‐target interactions in a deep learning manner, and few studies provide interpretable analysis of models. This paper proposes a DTA prediction method (mutual transformer‐drug target affinity [MT‐DTA]) with interactive learning and an autoencoder mechanism. The proposed MT‐DTA builds a variational autoencoders system with a cascade structure of the attention model and convolutional neural networks. It not only enhances the ability to capture the characteristic information of a single molecular sequence but also establishes the characteristic expression relationship for each substructure in a single molecular sequence. On this basis, a molecular information interaction module is constructed, which adds information interaction paths between molecular sequence pairs and complements the expression of correlations between molecular substructures. The performance of the proposed model was verified on two public benchmark datasets, KIBA and Davis, and the results confirm that the proposed model structure is effective in predicting DTA. Additionally, attention transformer models with different configurations can improve the feature expression of drug/protein molecules. The model performs better in correctly predicting interaction strengths compared with state‐of‐the‐art baselines. In addition, the diversity of drug/protein molecules can be better expressed than existing methods such as SeqGAN and Co‐VAE to generate more effective new drugs. The DTA value prediction module fuses the drug‐target pair interaction information to output the predicted value of DTA. Additionally, this paper theoretically proves that the proposed method maximises evidence lower bound for the joint distribution of the DTA prediction model, which enhances the consistency of the probability distribution between actual and predicted values. The source code of proposed method is available at https://github.com/Lamouryz/Code/tree/main/MT‐DTA.

Its reliance on energy from individual countries has seriously affected its energy security and foreign policy. Therefore, reducing dependence on energy from specific countries and decomposing energy import channels have become crucial goals in China’s efforts to resolve its energy crisis and ensure its national energy security. This study aims to analyze the impact of energy factors on the location determinants of China’s energy OFDI to help reduce energy dependence and improve China’s energy security. Simultaneous equation models and panel data from 162 target countries for the period 2005–2020 are used to examine the coincidental relationship between volatile and non-volatile energy and intermediary factors in investment target countries and China’s energy OFDI. The simultaneous equation model, comprising a system of equations, constitutes a multifaceted modeling approach that allows examination of two or more dependent variables. This study provides insights into energy investment in China through simultaneous equation modelling, it guides the implementation strategies for home and target countries of energy investment.

Real-time and efficient driver distraction detection is of great importance for road traffic safety and assisted driving. The design of a real-time lightweight model is crucial for in-vehicle edge devices that have limited computational resources. However, most existing approaches focus on lighter and more efficient architectures, ignoring the cost of losing tiny target detection performance that comes with lightweighting. In this paper, we present MTNet, a lightweight detector for driver distraction detection scenarios. MTNet consists of a multidimensional adaptive feature extraction block, a lightweight feature fusion block and utilizes the IoU-NWD weighted loss function, all while considering the accuracy gain of tiny target detection. In the feature extraction component, a lightweight backbone network is employed in conjunction with four attention mechanisms strategically integrated across the kernel space. This approach enhances the performance limits of the lightweight network. The lightweight feature fusion module is designed to reduce computational complexity and memory access. The interaction of channel information is improved through the use of lightweight arithmetic techniques. Additionally, CFSM module and EPIEM module are employed to minimize redundant feature map computations and strike a better balance between model weights and accuracy. Finally, the IoU-NWD weighted loss function is formulated to enable more effective detection of tiny targets. We assess the performance of the proposed method on the LDDB benchmark. The experimental results demonstrate that our proposed method outperforms multiple advanced detection models.

With the rapid advancement of technology, satellite and drone technologies have had significant impacts on various fields, creating both opportunities and challenges. In areas like the military, urban planning, and environmental monitoring, the application of remote sensing technology is paramount. However, due to the unique characteristics of remote sensing images, such as high resolution, large-scale scenes, and small, densely packed targets, remote sensing object detection faces numerous technical challenges. Traditional detection methods are inadequate for effectively detecting small targets, rendering the accurate and efficient detection of objects in complex remote sensing images a pressing issue. Current detection techniques fall short in accurately detecting small targets compared to medium and large ones, primarily due to limited feature information, insufficient contextual data, and poor localization capabilities for small targets. In response, we propose an innovative detection method. Unlike previous approaches that often focused solely on either local or contextual information, we introduce a novel Global and Local Attention Mechanism (GAL), providing an in-depth modeling method for input images. Our method integrates fine-grained local feature analysis with global contextual information processing. The local attention concentrates on details and spatial relationships within local windows, enabling the model to recognize intricate details in complex images. Meanwhile, the global attention addresses the entire image’s global information, capturing overarching patterns and structures, thus enhancing the model’s high-level semantic understanding. Ultimately, a specific mechanism fuses local details with global context, allowing the model to consider both aspects for a more precise and comprehensive interpretation of images. Furthermore, we have developed a multi-head prediction module that leverages semantic information at various scales to capture the multi-scale characteristics of remote sensing targets. Adding decoupled prediction heads aims to improve the accuracy and robustness of target detection. Additionally, we have innovatively designed the Ziou loss function, an advanced loss calculation, to enhance the model’s precision in small target localization, thereby boosting its overall performance in small target detection. Experimental results on the Visdrone2019 and DOTA datasets demonstrate that our method significantly surpasses traditional methods in detecting small targets in remote sensing imagery.

The participation of incentive demand response (IDR) can improve power grid flexibility, and reduce peak shaving pressure. However, the further development of incentive demand response services will be limited by the uncertainty of user response behavior. To tackle this problem, this paper proposes a data-driven load forecasting method for IDR, which considers consumer behavior. Firstly, we describe the power market auxiliary service operation mechanism for load aggregators, through which the ability of demand-side resources to respond to auxiliary services is improved. Then, add an attention layer to improve the traditional long and short memory (LSTM) model, and propose an IDR load forecasting method based on this model, which considers the model’s learning of historical data of user behavior. Finally, establish a simulation model to verify the effectiveness of the improved LSTM model forecasting. The proposed method is simulated and compared with the traditional LSTM method and k-nearest neighbor prediction method. The results show that compared with the other two methods, the mean error, root means square error, and mean absolute percentage error in the improved LSTM method are reduced by 7.31 MW, 8.32 MW, 2.06% and 10.62 MW, 13.46 MW and 3.09%, respectively, which effectively improves the accuracy of forecasting and increase the participation of demand-side resources in the power auxiliary service market.

As a type of biometric recognition, palmprint recognition uses unique discriminative features on the palm of a person to identify his/her identity. It has attracted much attention because of its advantages of contactlessness, stability, and security. Recently, many palmprint recognition methods based on convolutional neural networks (CNN) have been proposed in academia. Convolutional neural networks are limited by the size of the convolutional kernel and lack the ability to extract global information of palmprints. This paper proposes a framework based on the integration of CNN and Transformer-GLGAnet for palmprint recognition, which can take advantage of CNN's local information extraction and Transformer's global modeling capabilities. A gating mechanism and an adaptive feature fusion module are also designed for palmprint feature extraction. The gating mechanism filters features by a feature selection algorithm and the adaptive feature fusion module fuses them with the features extracted by the backbone network. Through extensive experiments on two datasets, the experimental results show that the recognition accuracy is 98.5% for 12,000 palmprints in the Tongji University dataset and 99.5% for 600 palmprints in the Hong Kong Polytechnic University dataset. This demonstrates that the proposed method outperforms existing methods in the correctness of both palmprint recognition tasks. The source codes will be available on https://github.com/Ywatery/GLnet.git.

Distracted behavior detection is an important task in computer-assisted driving. Although deep learning has made significant progress in this area, it is still difficult to meet the requirements of the real-time analysis and processing of massive data by relying solely on local computing power. To overcome these problems, this paper proposes a driving distraction detection method based on cloud–fog computing architecture, which introduces scalable modules and a model-driven optimization based on greedy pruning. Specifically, the proposed method makes full use of cloud–fog computing to process complex driving scene data, solves the problem of local computing resource limitations, and achieves the goal of detecting distracted driving behavior in real time. In terms of feature extraction, scalable modules are used to adapt to different levels of feature extraction to effectively capture the diversity of driving behaviors. Additionally, in order to improve the performance of the model, a model-driven optimization method based on greedy pruning is introduced to optimize the model structure to obtain a lighter and more efficient model. Through verification experiments on multiple driving scene datasets such as LDDB and Statefarm, the effectiveness of the proposed driving distraction detection method is proved.

As a key factor, the availability of large-scale training samples determines the improvement of visual performance. However, the size of Fine-Grained Visual Categorization (FGVC) datasets is always limited. Therefore, overfitting as an issue in FGVC-related training needs to be solved. Data mixing augmentation is a widely-used data augmentation method. In most of the recently proposed data mixing augmentation methods, random patch selection may generate meaningless training samples and result in model instability during the training process. This paper proposes a data mixing augmentation strategy termed Semantic and Attentive Data Mixing (SADMix) to select semantic patches for the generation of new training samples. In SADMix, a certain number of critical regions are localized according to convolutional activations. An image patch is selected from these localized regions for the generation of new training samples. The size, aspect ratio, and center location of these image patches are changed according to the random values from a beta distribution. These image patches with semantic information are used to mix two training images. According to the class activation map (CAM), training images and their labels are mixed proportionally to generate new mixed training samples and the corresponding labels. The proposed SADMix is tested on three fine-grained datasets, which are CUB-200-2011, FGVC Aircraft, and Stanford Cars, respectively. The experimental results confirm the effectiveness of the proposed SADMix.

With the large-scale deployment of smart meters and wide application of various machine learning algorithms, non-intrusive load monitoring (NILM) has attracted the attention of academia and industry. However, machine learning algorithms often suffer from high variability in load identification performance due to different features. In view of the poor generalization ability and low accuracy of load identification using an individual feature or classifier model, this paper proposes a novel NILM method that accomplishes deep feature fusion and classifier model fusion by an improved Dempster–Shafer (D–S) evidence theory. Firstly, we extract the power features, current harmonic features, and voltage–current (V–I) trajectory features from the input signals. Then, K-nearest neighbor (KNN), random forest (RF), and convolutional neural networks (CNN) are employed to identify load appliances using three individual features. Finally, the probability estimates of each classifier are transmitted to the aggregator for aggregation to obtain the final identification results by the improved D–S evidence theory. The experimental results on the PLAID dataset show that the proposed method can significantly improve identification performances.

Medical image segmentation has important auxiliary significance for clinical diagnosis and treatment. Most of existing medical image segmentation solutions adopt convolutional neural networks (CNNs). Althought these existing solutions can achieve good image segmentation performance, CNNs focus on local information and ignore global image information. Since Transformer can encode the whole image, it has good global modeling ability and is effective for the extraction of global information. Therefore, this paper proposes a hybrid feature extraction network, into which CNNs and Transformer are integrated to utilize their advantages in feature extraction. To enhance low-dimensional texture features, this paper also proposes a multi-dimensional statistical feature extraction module to fully fuse the features extracted by CNNs and Transformer and enhance the segmentation performance of medical images. The experimental results confirm that the proposed method achieves better results in brain tumor segmentation and ventricle segmentation than state-of-the-art solutions.

AbstractThis study investigates China’s international research collaboration with the United States through a bibliometric analysis of coauthorship over time using historical research publication data. We investigate from three perspectives: overall, high-impact, and high-technology research collaborations using data from Web of Science (WoS), Nature Index, and Technology Alert List maintained by the U.S. Department of State. The results show that the United States is China’s largest research collaborator and that in all three aspects, China and the United States are each other’s primary collaborators much of the time. From China’s perspective, we have found weakening collaboration with the United States over the past 2 years. In terms of high-impact research collaboration, China has historically shared a higher percentage of its research with the United States than vice versa. In terms of high-technology research, the situation is reversed, with the United States sharing more. The percentage of the United States’ high-technology research shared with China has been continuously increasing over the past 10 years, while in China the percentage has been relatively stable.

In recent years, deep-learning-based single image super-resolution reconstruction has achieved good performance. However, most existing methods pursue a high peak signal-to-noise ratio (PSNR), while ignoring the quality of the structure and texture details, resulting in unsatisfactory performance of the reconstruction results in terms of human subjective perception. To solve this issue, this paper proposes a structure- and texture-preserving image super-resolution reconstruction method. Specifically, two different network branches are used to extract features for image structure and texture details. A dual-coordinate direction perception attention (DCDPA) mechanism is designed to highlight structure and texture features. The attention mechanism fully considers the complementarity and directionality of multi-scale image features and effectively avoids information loss and possible distortion of image structure and texture details during image reconstruction. Additionally, a cross-fusion mechanism is designed to comprehensively utilize structure and texture information for super-resolution image reconstruction, which effectively integrates the structure and texture details extracted by the two branch networks. Extensive experiments verify the effectiveness of the proposed method and its superiority over existing methods.

Multi-modality image fusion provides more comprehensive and sophisticated information in modern medical diagnosis, remote sensing, video surveillance, and so on. This paper presents a novel multi-modality medical image fusion method based on phase congruency and local Laplacian energy. In the proposed method, the non-subsampled contourlet transform is performed on medical image pairs to decompose the source images into high-pass and low-pass subbands. The high-pass subbands are integrated by a phase congruency-based fusion rule that can enhance the detailed features of the fused image for medical diagnosis. A local Laplacian energy-based fusion rule is proposed for low-pass subbands. The local Laplacian energy consists of weighted local energy and the weighted sum of Laplacian coefficients that describe the structured information and the detailed features of source image pairs, respectively. Thus, the proposed fusion rule can simultaneously integrate two key components for the fusion of low-pass subbands. The fused high-pass and low-pass subbands are inversely transformed to obtain the fused image. In the comparative experiments, three categories of multi-modality medical image pairs are used to verify the effectiveness of the proposed method. The experiment results show that the proposed method achieves competitive performance in both the image quantity and computational costs.

Image fusion techniques are applied to the synthesis of two or more images captured in the same scene to obtain a high-quality image. However, most of the existing fusion algorithms are aimed at single-mode images. To improve the fusion quality of multi-modal images, a novel multi-sensor image fusion framework based on non-subsampled shearlet transform (NSST) is proposed. First, the proposed solution uses NSST to decompose source images into high- and low-frequency components. Then, an improved pulse coupled neural network (PCNN) is proposed to process high-frequency components. Thus, the feature extraction effect of the high-frequency component is meliorated. After that, a sparse representation (SR) based measure, including compact dictionary learning and Max-L1 fusion rule, is designed to enhance the detailed features of the low-frequency component. Finally, the final image is obtained by the reconstruction of high- and low-frequency components via NSST inverse transformation. The proposed method is compared with several existing fusion methods. The experiment results show that the proposed algorithm outperforms other algorithms in both subjective and objective evaluation.

Near-infrared (NIR) spectroscopy has been widely used in agricultural operations to obtain various crop parameters, such as water content, sugar content, and different indicators of ripeness, as well as other potential information concerning crops that cannot be directly obtained by human observation. The chemical compositions of tobacco play an important role in the quality of cigarettes. The NIR spectroscopy-based chemical composition analysis has recently become one of the most effective methods in tobacco quality analysis. Existing NIR spectroscopy-related solutions either have relatively low analysis accuracy, or are only able to analyze one or two chemical components. Thus, a precise prediction model is needed to improve the analysis accuracy of NIR data. This paper proposes a tobacco chemical component analysis method based on a neural network (TCCANN) to quantitatively analyze the chemical components of tobacco leaves by using NIR spectroscopy, including nicotine, total sugar, reducing sugar, total nitrogen, potassium, chlorine, and pH value. The proposed TCCANN consists of both residual network (ResNet) and long short-term memory (LSTM) neural network. ResNet is applied to the feature extraction of high-dimension NIR spectroscopy, which can effectively avoid the gradient-disappearance issue caused by the increase of network depth. LSTM is used to quantitatively analyze the multiple chemical compositions of tobacco leaves in a simultaneous manner. LSTM selectively allows information to pass through by a gated unit, thereby comprehensively analyzing the correlation between multiple chemical components and corresponding spectroscopy. The experimental results confirm that the proposed TCCANN not only predicts the corresponding values of seven chemical components simultaneously, but also achieves better prediction performance than other existing machine learning methods.

Although deep learning approaches are able to generate generic image features from massive labeled data, discriminative handcrafted features still have advantages in providing explicit domain knowledge and reflecting intuitive visual understanding. Much of the existing research focuses on integrating both handcrafted features and deep networks to leverage the benefits. However, the issues of parameter quality have not been effectively solved in existing applications of handcrafted features in deep networks. In this research, we propose a method that enriches deep network features by utilizing the injected discriminative shape features (generic edge tokens and curve partitioning points) to adjust the network’s internal parameter update process. Thus, the modified neural networks are trained under the guidance of specific domain knowledge, and they are able to generate image representations that incorporate the benefits from both handcrafted and deep learned features. The comparative experiments were performed on several benchmark datasets. The experimental results confirmed our method works well on both large and small training datasets. Additionally, compared with existing models using either handcrafted features or deep network representations, our method not only improves the corresponding performance, but also reduces the computational costs.

As one type of object detection, small object detection has been widely used in daily-life-related applications with many real-time requirements, such as autopilot and navigation. Although deep-learning-based object detection methods have achieved great success in recent years, they are not effective in small object detection and most of them cannot achieve real-time processing. Therefore, this paper proposes a single-stage small object detection network (SODNet) that integrates the specialized feature extraction and information fusion techniques. An adaptively spatial parallel convolution module (ASPConv) is proposed to alleviate the lack of spatial information for target objects and adaptively obtain the corresponding spatial information through multi-scale receptive fields, thereby improving the feature extraction ability. Additionally, a split-fusion sub-module (SF) is proposed to effectively reduce the time complexity of ASPConv. A fast multi-scale fusion module (FMF) is proposed to alleviate the insufficient fusion of both semantic and spatial information. FMF uses two fast upsampling operators to first unify the resolution of the multi-scale feature maps extracted by the network and then fuse them, thereby effectively improving the small object detection ability. Comparative experimental results prove that the proposed method considerably improves the accuracy of small object detection on multiple benchmark datasets and achieves a high real-time performance.

With the increase in the complexity and informatization of power grids, new challenges, such as access to a large number of distributed energy sources and cyber attacks on power grid control systems, are brought to load-frequency control. As load-frequency control methods, both aggregated distributed energy sources (ADES) and artificial intelligence techniques provide flexible solution strategies to mitigate the frequency deviation of power grids. This paper proposes a load-frequency control strategy of ADES-based reinforcement learning under the consideration of reducing the impact of denial of service (DoS) attacks. Reinforcement learning is used to evaluate the pros and cons of the proposed frequency control strategy. The entire evaluation process is realized by the approximation of convex neural networks. Convex neural networks are used to convert the nonlinear optimization problems of reinforcement learning for long-term performance into the corresponding convex optimization problems. Thus, the local optimum is avoided, the optimization process of the strategy utility function is accelerated, and the response ability of controllers is improved. The stability of power grids and the convergence of convex neural networks under the proposed frequency control strategy are studied by constructing Lyapunov functions to obtain the sufficient conditions for the steady states of ADES and the weight convergence of actor–critic networks. The article uses the IEEE14, IEEE57, and IEEE118 bus testing systems to verify the proposed strategy. Our experimental results confirm that the proposed frequency control strategy can effectively reduce the frequency deviation of power grids under DoS attacks.

Due to the variation in the image capturing process, the difference between source and target sets causes a challenge in unsupervised domain adaptation (UDA) on person re-identification (re-ID). Given a labeled source training set and an unlabeled target training set, this paper focuses on improving the generalization ability of the re-ID model on the target testing set. The proposed method enforces two properties at the same time: (1) camera invariance is achieved through the positive learning formed by unlabeled target images and their camera style transfer counterparts; and (2) the robustness of the backbone network feature extraction is improved, and the accuracy of feature extraction is enhanced by adding a position-channel dual attention mechanism. The proposed network model uses a classic dual-stream network. Comparative experimental results on three public benchmarks prove the superiority of the proposed method.

Multi-modality image fusion applied to improve image quality has drawn great attention from researchers in recent years. However, noise is actually generated in images captured by different types of imaging sensors, which can seriously affect the performance of multi-modality image fusion. As the fundamental method of noisy image fusion, source images are denoised first, and then the denoised images are fused. However, image denoising can decrease the sharpness of source images to affect the fusion performance. Additionally, denoising and fusion are processed in separate processing modes, which causes an increase in computation cost. To fuse noisy multi-modality image pairs accurately and efficiently, a multi-modality image simultaneous fusion and denoising method is proposed. In the proposed method, noisy source images are decomposed into cartoon and texture components. Cartoon-texture decomposition not only decomposes source images into detail and structure components for different image fusion schemes, but also isolates image noise from texture components. A Gaussian scale mixture (GSM) based sparse representation model is presented for the denoising and fusion of texture components. A spatial domain fusion rule is applied to cartoon components. The comparative experimental results confirm the proposed simultaneous image denoising and fusion method is superior to the state-of-the-art methods in terms of visual and quantitative evaluations.

Remote sensing images have been widely used in military, national defense, disaster emergency response, ecological environment monitoring, among other applications. However, fog always causes definition of remote sensing images to decrease. The performance of traditional image defogging methods relies on the fog-related prior knowledge, but they cannot always accurately obtain the scene depth information used in the defogging process. Existing deep learning-based image defogging methods often perform well, but they mainly focus on defogging ordinary outdoor foggy images rather than remote sensing images. Due to the different imaging mechanisms used in ordinary outdoor images and remote sensing images, fog residue may exist in the defogged remote sensing images obtained by existing deep learning-based image defogging methods. Therefore, this paper proposes remote sensing image defogging networks based on dual self-attention boost residual octave convolution (DOC). Residual octave convolution (residual OctConv) is used to decompose a source image into high- and low-frequency components. During the extraction of feature maps, high- and low-frequency components are processed by convolution operations, respectively. The entire network structure is mainly composed of encoding and decoding stages. The feature maps of each network layer in the encoding stage are passed to the corresponding network layer in the decoding stage. The dual self-attention module is applied to the feature enhancement of the output feature maps of the encoding stage, thereby obtaining the refined feature maps. The strengthen-operate-subtract (SOS) boosted module is used to fuse the refined feature maps of each network layer with the upsampling feature maps from the corresponding decoding stage. Compared with existing image defogging methods, comparative experimental results confirm the proposed method improves both visual effects and objective indicators to varying degrees and effectively enhances the definition of foggy remote sensing images.

Remote sensing images are widely used in object detection and tracking, military security, and other computer vision tasks. However, remote sensing images are often degraded by suspended aerosol in the air, especially under poor weather conditions, such as fog, haze, and mist. The quality of remote sensing images directly affect the normal operations of computer vision systems. As such, haze removal is a crucial and indispensable pre-processing step in remote sensing image processing. Additionally, most of the existing image dehazing methods are not applicable to all scenes, so the corresponding dehazed images may have varying degrees of color distortion. This paper proposes a novel atmospheric light estimation based dehazing algorithm to obtain high visual-quality remote sensing images. First, a differentiable function is used to train the parameters of a linear scene depth model for the scene depth map generation of remote sensing images. Second, the atmospheric light of each hazy remote sensing image is estimated by the corresponding scene depth map. Then, the corresponding transmission map is estimated on the basis of the estimated atmospheric light by a haze-lines model. Finally, according to the estimated atmospheric light and transmission map, an atmospheric scattering model is applied to remove haze from remote sensing images. The colors of the images dehazed by the proposed method are in line with the perception of human eyes in different scenes. A dataset with 100 remote sensing images from hazy scenes was built for testing. The performance of the proposed image dehazing method is confirmed by theoretical analysis and comparative experiments.

Precise real-time obstacle recognition is both vital to vehicle automation and extremely resource intensive. Current deep-learning based recognition techniques generally reach high recognition accuracy, but require extensive processing power. This study proposes a region of interest extraction method based on the maximum difference method and morphology, and a target recognition solution created with a deep convolutional neural network. In the proposed solution, the central processing unit and graphics processing unit work collaboratively. Compared with traditional deep learning solutions, the proposed solution decreases the complexity of algorithm, and improves both calculation efficiency and recognition accuracy. Overall it achieves a good balance between accuracy and computation.

As a crucial task in surveillance and security, person re-identification (re-ID) aims to identify the targeted pedestrians across multiple images captured by non-overlapping cameras. However, existing person re-ID solutions have two main challenges: the lack of pedestrian identification labels in the captured images, and domain shift issue between different domains. A generative adversarial networks (GAN)-based self-training framework with progressive augmentation (SPA) is proposed to obtain the robust features of the unlabeled data from the target domain, according to the preknowledge of the labeled data from the source domain. Specifically, the proposed framework consists of two stages: the style transfer stage (STrans), and self-training stage (STrain). First, the targeted data is complemented by a camera style transfer algorithm in the STrans stage, in which CycleGAN and Siamese Network are integrated to preserve the unsupervised self-similarity (the similarity of the same image between before and after transformation) and domain dissimilarity (the dissimilarity between a transferred source image and the targeted image). Second, clustering and classification are alternately applied to enhance the model performance progressively in the STrain stage, in which both global and local features of the target-domain images are obtained. Compared with the state-of-the-art methods, the proposed method achieves the competitive accuracy on two existing datasets.

Person re-identification (Re-ID) is challenging due to host of factors: the variety of human positions, difficulties in aligning bounding boxes, and complex backgrounds, among other factors. This paper proposes a new framework called EXAM (EXtreme And Moderate feature embeddings) for Re-ID tasks. This is done using discriminative feature learning, requiring attention-based guidance during training. Here “Extreme” refers to salient human features and “Moderate” refers to common human features. In this framework, these types of embeddings are calculated by global max-pooling and average-pooling operations respectively; and then, jointly supervised by multiple triplet and cross-entropy loss functions. The processes of deducing attention from learned embeddings and discriminative feature learning are incorporated, and benefit from each other in this end-to-end framework. From the comparative experiments and ablation studies, it is shown that the proposed EXAM is effective, and its learned feature representation reaches state-of-the-art performance.

This paper examines the relationship between transport connectivity and regional economic development in China. It develops measurements appropriate for transport connectivity based on a set of evaluation models. This model is used to analyze the logistic connectivity of China’s 31 provinces by focusing on 11 variables, including some new factors (Density of road network, Density of railway network, Number of Internet Users) not used in previous studies, over the 13-year period from 2002 to 2014. Using panel data regression analysis, the empirical results show a statistically significant and positive impact of transport connectivity (factors like Density of road network, Density of railway network and Number of Internet Users) on economic development in China. In particular, the Number of internet users is a key factor reflecting information connectivity in all the variables. Comparative analysis regarding economic development is conducted to benchmark between coastal provinces and interior provinces. Like most previous research, this study yields the same finding of higher impact of transport connectivity on economic development in eastern provinces than in western provinces. This study suggests that decentralized decision-making will be significantly more efficient for analyzing regional infrastructure development. It also shows that the influence of transport connectivity on economic development is dependent on a certain developmental stage. This suggests that an economic region should adopt different development strategies for transport connectivity during different stages of development.

Medical image fusion techniques can fuse medical images from different morphologies to make the medical diagnosis more reliable and accurate, which play an increasingly important role in many clinical applications. To obtain a fused image with high visual quality and clear structure details, this paper proposes a convolutional neural network (CNN) based medical image fusion algorithm. The proposed algorithm uses the trained Siamese convolutional network to fuse the pixel activity information of source images to realize the generation of weight map. Meanwhile, a contrast pyramid is implemented to decompose the source image. According to different spatial frequency bands and a weighted fusion operator, source images are integrated. The results of comparative experiments show that the proposed fusion algorithm can effectively preserve the detailed structure information of source images and achieve good human visual effects.

Multi exposure image fusion (MEF) provides a concise way to generate high-dynamic-range (HDR) images. Although the precise fusion can be achieved by existing MEF methods in different static scenes, the corresponding performance of ghost removal varies in different dynamic scenes. This paper proposes a precise MEF method based on feature patches (FPM) to improve the robustness of ghost removal in a dynamic scene. A reference image is selected by a priori exposure quality first and then used in the structure consistency test to solve the image ghosting issues existing in the dynamic scene MEF. Source images are decomposed into spatial-domain structures by a guided filter. Both the base and detail layer of the decomposed images are fused to achieve the MEF. The structure decomposition of the image patch and the appropriate exposure evaluation are integrated into the proposed solution. Both global and local exposures are optimized to improve the fusion performance. Compared with six existing MEF methods, the proposed FPM not only improves the robustness of ghost removal in a dynamic scene, but also performs well in color saturation, image sharpness, and local detail processing.

In multi-modality image fusion, source image decomposition, such as multi-scale transform (MST), is a necessary step and also widely used. However, when MST is directly used to decompose source images into high- and low-frequency components, the corresponding decomposed components are not precise enough for the following infrared-visible fusion operations. This paper proposes a non-subsampled contourlet transform (NSCT) based decomposition method for image fusion, by which source images are decomposed to obtain corresponding high- and low-frequency sub-bands. Unlike MST, the obtained high-frequency sub-bands have different decomposition layers, and each layer contains different information. In order to obtain a more informative fused high-frequency component, maximum absolute value and pulse coupled neural network (PCNN) fusion rules are applied to different sub-bands of high-frequency components. Activity measures, such as phase congruency (PC), local measure of sharpness change (LSCM), and local signal strength (LSS), are designed to enhance the detailed features of fused low-frequency components. The fused high- and low-frequency components are integrated to form a fused image. The experiment results show that the fused images obtained by the proposed method achieve good performance in clarity, contrast, and image information entropy.

Sparse representation has been widely applied to multi-focus image fusion in recent years. As a key step, the construction of an informative dictionary directly decides the performance of sparsity-based image fusion. To obtain sufficient bases for dictionary learning, different geometric information of source images is extracted and analysed. The classified image bases are used to build corresponding subdictionaries by principle component analysis. All built subdictionaries are merged into one informative dictionary. Based on constructed dictionary, compressive sampling matched pursuit algorithm is used to extract corresponding sparse coefficients for the representation of source images. The obtained sparse coefficients are fused by Max-L1 fusion rule first, and then inverted to form the final fused image. Multiple comparative experiments demonstrate that the proposed method is competitive with other the state-of-the-art fusion methods.

With the rapid growth of distributed energy sources, power grid has become a flexible and complex networked control system. However, it increases the chances of being a denial-of-service attack, which degrades the performance of the power grid, even causing cascading failures. To mitigate negative effects from denial-of-service attack and enhance the reliability of the power grid, we propose a networked control system structure based optimization scheme that is derived from a Stackelberg game model for the frequency regulation of a power grid with distributed energy sources. In the proposed game model, both denial-of-service attacker and control system designer as a defender are considered without using any analytical model. For defenders, we propose a sparse neural network based DES control and system structure design scheme. The neural network is used to approximate the desired control output and reinforce signals for the improvements of short- and long-term performance. It also introduces the sparse regulation of column grouping in the neural network learning process to explore the structure of control system that involves the placement of sensor, distributed energy sources actuator, and communication topology. For denial-of-service attackers, the related attack constraints and attack rewards are established. The solution of game equilibrium is considered as an optimal solution for both denial-of-service attack strategy and control structure. An offline optimization algorithm is proposed to solve the game equilibrium. The effectiveness of proposed scheme is verified by two cases, which illustrate the optimal solutions of both control structure and denial-of-service attack strategy.

Multi-exposure image fusion methods are often applied to the fusion of low-dynamic images that are taken from the same scene at different exposure levels. The fused images not only contain more color and detailed information, but also demonstrate the same real visual effects as the observation by the human eye. This paper proposes a novel multi-exposure image fusion (MEF) method based on adaptive patch structure. The proposed algorithm combines image cartoon-texture decomposition, image patch structure decomposition, and the structural similarity index to improve the local contrast of the image. Moreover, the proposed method can capture more detailed information of source images and produce more vivid high-dynamic-range (HDR) images. Specifically, image texture entropy values are used to evaluate image local information for adaptive selection of image patch size. The intermediate fused image is obtained by the proposed structure patch decomposition algorithm. Finally, the intermediate fused image is optimized by using the structural similarity index to obtain the final fused HDR image. The results of comparative experiments show that the proposed method can obtain high-quality HDR images with better visual effects and more detailed information.

Multi-modality image fusion provides more comprehensive and sophisticated information in modern medical diagnosis, remote sensing, video surveillance, etc. Traditional multi-scale transform (MST) based image fusion solutions have difficulties in the selection of decomposition level, and the contrast loss in fused image. At the same time, traditional sparse-representation based image fusion methods suffer the weak representation ability of fixed dictionary. In order to overcome these deficiencies of MST- and SR-based methods, this paper proposes an image fusion framework which integrates nonsubsampled contour transformation (NSCT) into sparse representation (SR). In this fusion framework, NSCT is applied to source images decomposition for obtaining corresponding low- and high-pass coefficients. It fuses low- and high-pass coefficients by using SR and Sum Modified-laplacian (SML) respectively. NSCT inversely transforms the fused coefficients to obtain the final fused image. In this framework, a principal component analysis (PCA) is implemented in dictionary training to reduce the dimension of learned dictionary and computation costs. A novel high-pass fusion rule based on SML is applied to suppress pseudo-Gibbs phenomena around singularities of fused image. Compared to three mainstream image fusion solutions, the proposed solution achieves better performance on structural similarity and detail preservation in fused images.

Image fusion is widely used in different areas and can integrate complementary and relevant information of source images captured by multiple sensors into a unitary synthetic image. Medical image fusion, as an important image fusion application, can extract the details of multiple images from different imaging modalities and combine them into an image that contains complete and non-redundant information for increasing the accuracy of medical diagnosis and assessment. The quality of the fused image directly affects medical diagnosis and assessment. However, existing solutions have some drawbacks in contrast, sharpness, brightness, blur and details. This paper proposes an integrated dictionary-learning and entropy-based medical image-fusion framework that consists of three steps. First, the input image information is decomposed into low-frequency and high-frequency components by using a Gaussian filter. Second, low-frequency components are fused by weighted average algorithm and high-frequency components are fused by the dictionary-learning based algorithm. In the dictionary-learning process of high-frequency components, an entropy-based algorithm is used for informative blocks selection. Third, the fused low-frequency and high-frequency components are combined to obtain the final fusion results. The results and analyses of comparative experiments demonstrate that the proposed medical image fusion framework has better performance than existing solutions.

In control systems of power grids, conveying observations to controllers and obtaining control outputs depend greatly on communication and computation resources. Particularly for large-scale systems, the costs of computation and communication (cyber costs) should not be neglected. This paper proposes a self-triggered frequency control system for a power grid to reduce communication costs. An equation for obtaining the triggering time is derived, and an approximation method is proposed to reduce the computation cost of triggering time. In addition, the communication cost of frequency triggering is measured quantitatively and proportionally. The defined cost function considers both physical cost (electricity transmission cost) and communication cost (control signal transmission cost). The upper bound of cost is estimated. According to the estimated upper bound of cost, parameters of the controller are investigated by using the proposed optimization algorithm to guarantee the high performance of the system. Finally, the proposed self-triggered power system is simulated to verify its efficiency and effectiveness.

In recent years, sparse representation approaches have been integrated into multi-focus image fusion methods. The fused images of sparse-representation-based image fusion methods show great performance. Constructing an informative dictionary is a key step for sparsity-based image fusion method. In order to ensure sufficient number of useful bases for sparse representation in the process of informative dictionary construction, image patches from all source images are classified into different groups based on geometric similarities. The key information of each image-patch group is extracted by principle component analysis (PCA) to build dictionary. According to the constructed dictionary, image patches are converted to sparse coefficients by simultaneous orthogonal matching pursuit (SOMP) algorithm for representing the source multi-focus images. At last the sparse coefficients are fused by Max-L1 fusion rule and inverted to fused image. Due to the limitation of microscope, the fluorescence image cannot be fully focused. The proposed multi-focus image fusion solution is applied to fluorescence imaging area for generating all-in-focus images. The comparison experimentation results confirm the feasibility and effectiveness of the proposed multi-focus image fusion solution.

The multi-focus image fusion method is used in image processing to generate all-focus images that have large depth of field (DOF) based on original multi-focus images. Different approaches have been used in the spatial and transform domain to fuse multi-focus images. As one of the most popular image processing methods, dictionary-learning-based spare representation achieves great performance in multi-focus image fusion. Most of the existing dictionary-learning-based multi-focus image fusion methods directly use the whole source images for dictionary learning. However, it incurs a high error rate and high computation cost in dictionary learning process by using the whole source images. This paper proposes a novel stochastic coordinate coding-based image fusion framework integrated with local density peaks. The proposed multi-focus image fusion method consists of three steps. First, source images are split into small image patches, then the split image patches are classified into a few groups by local density peaks clustering. Next, the grouped image patches are used for sub-dictionary learning by stochastic coordinate coding. The trained sub-dictionaries are combined into a dictionary for sparse representation. Finally, the simultaneous orthogonal matching pursuit (SOMP) algorithm is used to carry out sparse representation. After the three steps, the obtained sparse coefficients are fused following the max L1-norm rule. The fused coefficients are inversely transformed to an image by using the learned dictionary. The results and analyses of comparison experiments demonstrate that fused images of the proposed method have higher qualities than existing state-of-the-art methods.