Search

Due to insufficient information and feature extraction in existing face-detection methods, as well as limited computing power, designing high-precision and efficient face-detection algorithms is an open challenge. Based on this, we propose an improved face detection algorithm. First, through 1 × 1’s common convolution block (CBL) expands the channel for feature extraction, introduces a depthwise separable residual network into the YOLO-v4 network to further reduce the amount of model computation, and uses CBL to reduce the dimension, so as to improve the efficiency of the subsequent network. Second, the improved attention mechanism is used to splice the high-level features, and the high-level features and the shallow features are fused to obtain the feature vectors containing more information, so as to improve the richness and representativeness of the feature vectors. Finally, the experimental results show that compared with other comparative methods, our method achieves the best results on public face datasets, and our performance in personal face detection is significantly better than other methods.

Image steganography is the art of concealing secret information within images to prevent detection. In deep‐learning‐based image steganography, a common practice is to fuse the secret image with the cover image to directly generate the stego image. However, not all features are equally critical for data hiding, and some insignificant ones may lead to the appearance of residual artifacts in the stego image. In this article, a novel network architecture for image steganography with hybrid attention mechanism based on generative adversarial network is introduced. This model consists of three subnetworks: a generator for generate stego images, an extractor for extracting the secret images, and a discriminator to simulate the detection process, which aids the generator in producing more realistic stego images. A specific hybrid attention mechanism (HAM) module is designed that effectively fuses information across channel and spatial domains, facilitating adaptive feature refinement within deep image representations. The experimental results suggest that the HAM module not only enhances the image quality during both the steganography and extraction processes but also improves the model's undetectability. Stego images are mixed with varying levels of noise in the training process, which can further improve robustness. Finally, it is verified that the model outperforms current steganography approaches on three datasets and exhibits good undetectability. [ABSTRACT FROM AUTHOR]

Image hiding is a task that hides secret images into cover images. The purposes of image hiding are to ensure the secret images are invisible to the human and the secret images can be recovered. The current state‐of‐the‐art steganography methods run the risk of secret information leakage. A safe image hiding network (SIHNet) is presented to reduce the leakage of secret information. Based on some phenomena of image hiding methods which use invertible neural network, a reversible secret image processing (SIP) module is proposed to make the secret images suitable for hiding and make the stego images leak less secret information. Besides, a reversible lost information hiding (LIH) module is used to hide the lost information into the cover images, thus the method can recover the secret images better than the method that uses random noise to replace the lost information. Experimental results show that SIHNet outperforms other state‐of‐the‐art methods on the PSNR and SSIM values of the recovered secret images and the stego images. Besides, residual images of other state‐of‐the‐art methods all contain information about secret images while residual images of SIHNet leak almost no secret information. Thus the method can prevent the listener of transmission channel from obtaining the information of the secret image through the residual image, which means SIHNet performs better in security than other state‐of‐the‐art methods. [ABSTRACT FROM AUTHOR]

In the rapidly evolving domain of mobile edge–cloud computing (MECC), the proliferation of Internet of Things (IoT) devices and mobile applications poses significant challenges, particularly in dynamically managing computational demands and user mobility. Current research has partially addressed aspects of service migration and resource allocation, yet it often falls short in thoroughly examining the nuanced interdependencies between migration strategies and resource allocation, the consequential impacts of migration delays, and the intricacies of handling incomplete tasks during migration. This study advances the discourse by introducing a sophisticated framework optimized through a deep reinforcement learning (DRL) strategy, underpinned by a Markov decision process (MDP) that dynamically adapts service migration and resource allocation strategies. This refined approach facilitates continuous system monitoring, adept decision making, and iterative policy refinement, significantly enhancing operational efficiency and reducing response times in MECC environments. By meticulously addressing these previously overlooked complexities, our research not only fills critical gaps in the literature but also enhances the practical deployment of edge computing technologies, contributing profoundly to both theoretical insights and practical implementations in contemporary digital ecosystems. [ABSTRACT FROM AUTHOR]

Elucidating the mechanism of soil erosion caused by extreme rainstorms could improve agroecosystems' resilience to the extreme climate. However, less attention has been paid to the regional difference of soil erosion during extreme rainstorms through multiple field investigations. Using six field surveys of extreme rainstorms, soil erosion and its driving mechanism were investigated on farmland in the Loess area and the Rocky mountain area. Conclusions are as follows: (1) Farmland was severely eroded in comparison with abandoned land and forest–grass land. The erosion modulus of farmland in the Loess area (51 606.51 t/km2) was greater than that in the Rocky mountain area (2582.75 t/km2). (2) In both the Loess area and the Rocky mountain area, the main erosion types on sloped cropland and terraced land were rills/gullies and embankment failure, respectively. Terracing is an appropriate measure that can effectively control farmland erosion in rainstorm events. (3) Concentrated flow is a major driver of soil erosion, with nearly all rills/gullies occurring in the flow paths. Drainage measures can prevent the formation of concentrated flow, weakening rills/gullies erosion in farmland. (4) Building bio‐embankment, planting high‐coverage crops, and implementing local protection measures could reduce the farmland erosion influenced by extremely heavy rainfall. Combining drainage and agronomic measures is the common strategy to combat extreme rainstorm events for reducing farmland erosion in the two regions. These results can be applied to improve the ability of agricultural systems to cope with extreme rainstorms. [ABSTRACT FROM AUTHOR]

Image preprocessing models are usually employed as the preceding operations of high‐level vision tasks to improve the performance. The adversarial attack technology makes both these models face severe challenges. Prior research is focused solely on attacking single object detection models, without considering the impact of the preprocessing models (multifocus image fusion) on adversarial perturbations within the object detection system. Multifocus image fusion models work in conjunction with the object detection models to enhance the quality of the images and improve the capability of object detection system. Herein, the problem of attacking object detection system that utilizes multifocus image fusion as its preprocessing models is addressed. To retain the attack capabilities of adversarial samples against as many perturbations as possible, new attack method called adaptive retention attack (ARA) is proposed. Additionally, adversarial perturbations concentration mechanism and image selection mechanism, which, respectively, enhance the transferability and attack capability of ARA‐generated adversarial samples. Extensive experiments have demonstrated the feasibility of the ARA. The results confirm that the ARA method can successfully bypass multifocus image fusion models to attack the object detection model. [ABSTRACT FROM AUTHOR]

Honeycomb lung is a radiological manifestation of various lung diseases, seriously threatening patients' lives worldwide. In clinical practice, the precise localization of lesions and assessment of their severity are crucial. However, accurate segmentation and grading are challenging for physicians due to the heavy annotation burden and diversity of honeycomb lungs. In this paper, we propose a multitask learning architecture for semi-supervised segmentation and grading diagnosis to achieve automatic localization and assessment of lesions. To the best of our knowledge, this is the first method that integrates a grading diagnosis task into honeycomb lung semi-supervised segmentation. Firstly, we adapt cross-learning to capture local features and long-range dependencies from the CNN and transformer. Secondly, considering the diversity of honeycomb lung lesions, the shape-edge aware constraint is designed to assist the model in locating lesions. Then, in order to better understand the different levels of information in the images, we develop global contrast and local contrast learning to enhance the model's learning of semantic-level and pixel-level features. Lastly, aiming to improve the diagnostic accuracy, we propose a gradient thresholding algorithm to integrate the segmentation predictions into the grading diagnosis network. The experiment's results based on the in-house honeycomb lung dataset demonstrate the superiority of our method. Compared to other methods, our approach achieves a state-of-the-art performance. In particular, in external data testing, our predictions are consistent with physicians in the majority of cases. In addition, the segmentation results based on the public Kvasir-SEG dataset also indicate that our method has good generalization ability. [ABSTRACT FROM AUTHOR]

Metalloviologens, as emerging electron-transfer photochromic compounds, have shown intriguing properties such as radiochromism, photochromism and photoconductance. However, only a limited number of them have been reported so far. Exploration of new metalloviologens is strongly desired. Herein, we report a new solvothermally synthesized metalloviologen complex [CdCl2(ND)2]n (1, ND = 1,5-naphthalenes) that exhibits photochromic and intrinsic white light emission properties. Density functional theory calculation results reveal that the photochromism could be assigned to photoinduced electron transfer from chlorine atoms to ND molecules. The photoinduced charge-separated states are heat/air stable, attributed to the delocalization of ND and strong intermolecular π–π interactions. Besides, complex 1 consistently emits intrinsic white light when excited with 340–370 nm UV light, achieving high color rendering index (CRI) values (82.54–94.04). By adjusting the excitation wavelength, both "warm" and "cold" white light emission can be produced, making it suitable for the application of a white light emitting diode (WLED). Thus, this work demonstrates that the ND-based metalloviologen is not only helpful in producing photochromism, but also beneficial for creating white-light emission. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicles (UAVs) have gained considerable attention in the research community due to their exceptional agility, maneuverability, and potential applications in fields like surveillance, multi-access edge computing (MEC), and various other domains. However, efficiently providing computation offloading services for concurrent Internet of Things devices (IOTDs) remains a significant challenge for UAVs due to their limited computing and communication capabilities. Consequently, optimizing and managing the constrained computing, communication, and energy resources of UAVs are essential for establishing an efficient aerial network infrastructure. To address this challenge, we investigate the collaborative computation offloading optimization problem in a UAV-assisted MEC environment comprising multiple UAVs and multiple IODTs. Our primary objective is to obtain efficient offloading strategies within a multi-heterogeneous UAV environment characterized by limited computing and communication capabilities. In this context, we model the problem as a multi-agent markov decision process (MAMDP) to account for environmental dynamics. We employ a multi-agent deep deterministic policy gradient (MADDPG) approach for task offloading. Subsequently, we conduct simulations to evaluate the efficiency of our proposed offloading scheme. The results highlight significant improvements achieved by the proposed offloading strategy, including a notable increase in the system completion rate and a significant reduction in the average energy consumption of the system. [ABSTRACT FROM AUTHOR]

Feature matching is a core step in multi-source remote sensing image registration approaches based on feature. However, for existing methods, whether traditional classical SIFT algorithm or deep learning-based methods, they essentially rely on generating descriptors from local regions of feature points, which can lead to low matching success rates due to various challenges, including gray-scale changes, content changes, local similarity, and occlusions between images. Inspired by the human approach of finding rough corresponding regions globally and then carefully comparing local regions, and the excellent global attention property of transformers, the proposed feature matching network adopts a coarse-to-fine matching strategy that utilizes both global and local information between images to predict corresponding feature points. Importantly, the network has great flexibility of matching corresponding points for any feature points and can be effectively trained without strong supervised signals of corresponding feature points and only require the true geometric transformation between images. The qualitative experiment illustrate the effectiveness of the proposed network by matching feature points extracted by SIFT or sampled uniformly. In the quantitative experiments, we used feature points extracted by SIFT, SuperPoint, and LoFTR as the keypoints to be matched. We then calculated the mean match success ratio (MSR) and mean reprojection error (MRE) of each method at different thresholds in the test dataset. Additionally, boxplot graphs were plotted to visualize the distributions. By comparing the MSR and MRE values as well as their distributions with other methods, we can conclude that the proposed method consistently outperforms the comparison methods in terms of MSR at different thresholds. Moreover, the MSR of the proposed method remains within a reasonable range compared to the MRE of other methods. [ABSTRACT FROM AUTHOR]

There is a large amount of out-of-distribution (OOD) data in remote sensing, which hinders high-accuracy segmentation models under the assumption of independent identical distribution (i.i.d.) from stable and reliable performance in real-world remote sensing applications. And domain adaptation (DA) is presented to seamlessly extend classifiers to the label-scarce target domain in the presence of the label-sufficient source domain with different data distributions. However, given that the domain shift, i.e., the distribution difference between the two domains, is more serious in remote sensing images, the current DA methods for image segmentation in computer vision (CV) typically perform unsatisfactorily in remote sensing, even suffering from the negative domain alignment. To this end, this letter proposes the self-training adversarial DA (STADA) method for remote sensing image segmentation, which not only performs adversarial learning to extract domain-invariant features but also implements self-training using pseudo-labels in the target domain denoised by the conditional adversarial loss for classifier adaptation. The International Society for Photogrammetry and Remote Sensing (ISPRS) and Wuhan University (WHU) datasets are employed to conduct extensive experiments to investigate the effectiveness of STADA and the specific effect of each DA component. And the experimental results demonstrate that STADA outperforms other state-of-the-art DA methods in the remote sensing image segmentation task. [ABSTRACT FROM AUTHOR]

Adversarial examples in which imperceptible perturbations to the input can easily subvert a well-trained model's prediction pose huge potential security threats to deep neural networks (DNNs). As an effective way to resist adversarial samples, input reconstruction can eliminate the antagonism of adversarial examples in the inference process without involving modifications to the target model's structure and parameters. However, preprocessing inputs often results in some loss of the protected model's prediction accuracy. In this paper, we introduce a new input reconstruction method that adopts the high-level representation difference constraint and the relative reconstruction constraint on a dual autoencoder to advance the prediction accuracy of the protected model. The high-level representation difference constraint utilizes the gap between the protected model's high-level representations, activated by clean images, and their adversarial examples to guide the training of the dual autoencoder. Additionally, the relative reconstruction constraint is imposed on latent representations and their noisy versions to advance the robustness of the dual autoencoder to tiny perturbations. The extensive empirical experiments on two real datasets, CIFAR-10 and ImageNet, show that the presented approach demonstrates exceptional performance in resisting different types of attacks. [ABSTRACT FROM AUTHOR]

Electrochemical carbon dioxide reduction reaction (CO2RR) using clean electric energy provides a sustainable route to generate highly‐valuable chemicals and fuels, which is beneficial for realizing the carbon‐neutral cycle. Up to now, achieving a narrow product distribution and highly targeted product selectivity over Cu‐based electrocatalysts is still a big challenge. Herein, sulfur modification on different crystal planes of cuprous oxide (Cu2O) is demonstrated, results in an improvement for formate generation to different degrees. Experimental results and density functional theory (DFT) calculations reveal that sulfur species modified on the surface of Cu2O (100) facet effectively lower the formation energy of key intermediate *OCOH for formate generation compared with Cu2O (111) facet. As a consequence, the modification of p‐Block elements over Cu‐based electrocatalysts is an effective strategy to optimize the adsorption energy of key intermediate during CO2RR, leading to a highly selective product. [ABSTRACT FROM AUTHOR]

Based on iterated Crank–Nicolson (CN) procedure, an alternative algorithm with perfectly matched layer (PML) formulation is proposed in the body‐of‐revolution (BOR) finite‐difference time‐domain (FDTD) lattice for the simulation of rotational symmetric geometrics. For the nonuniform domain simulation, an alternative subgridding method is employed to during the simulation. The iterated CN procedure improves the efficiency through preventing the calculation of tri‐diagonal matrices. The alternative subgridding method enhances the accuracy in nonuniform domains by the calculation of subregions. Numerical example is carried out for the demonstration of effectiveness including efficiency, accuracy and absorption. Through the results, the proposed scheme shows considerable absorption and accuracy improvement in nonuniform domains. Compared with the other CN schemes, the iterated CN procedure can significantly increase the efficiency with small time steps. In conclusion, the advantages and novelty of the proposed algorithm can be described as follows: (1) The iterated CN procedure is proposed for rotational symmetric geometrics. (2) Absorption boundary condition for iterated CN is proposed in BOR‐FDTD. (3) An alternative subgridding method for iterated CN procedure is proposed in BOR‐FDTD lattice. Thus, the proposed algorithm shows potential in nonuniform rotational symmetric geometrics open region simulation. [ABSTRACT FROM AUTHOR]

In the process of open-roller conveying, magnesium alloy plates easily produce temperature drops and uneven temperatures. Ignoring the heat dissipation caused by the contact between the plate and the roller table, the process can be described as a process of air cooling. The present study aimed to investigate the temperature distribution and evolution of a magnesium alloy plate during the process. The air-cooling process of the AZ31B magnesium alloy plate was investigated and analyzed in detail under different initial temperatures and plate thicknesses, with a specific focus on the temperature distribution along both the width and thickness directions. The results show that the temperature-difference curves between the end face and the center under different air-cooling conditions appeared to have four stages: rapid increase, slow increase, basic stable and slow decline. To facilitate the establishment of the temperature model, the whole air-cooling process was approximately divided into two independent one-dimensional heat-conduction processes in the thickness direction and the width direction. Subsequently, one-dimensional steady-state heat-conduction models were developed in various directions, based on the fundamental principles of heat transfer and assuming that the adjacent temperature-drop layer satisfied the quadratic function distribution. Through the superposition of cooling with time in two directions, the temperature evolution at different positions in the process of air cooling can be solved accurately. [ABSTRACT FROM AUTHOR]

To improve the spatial density and quality of measurement points in multitemporal interferometric synthetic aperture radar, distributed scatterers (DSs) should be processed. An essential procedure in DS interferometry is phase estimation, which reconstructs a consistent phase series from all available interferograms. Influenced by the well-known suboptimality of coherence estimation, the performance of the state-of-the-art phase estimation algorithms is severely degraded. Previous research has addressed this problem by introducing the coherence bias correction technique. However, the precision of phase estimation is still insufficient because of the limited correction capabilities. In this paper, a modified phase estimation approach is proposed. Particularly, by incorporating the information on both interferometric coherence and the number of looks, a significant bias correction to each element of the coherence magnitude matrix is achieved. The bias-corrected coherence matrix is combined with advanced statistically homogeneous pixel selection and time series phase optimization algorithms to obtain the optimal phase series. Both the simulated and Sentinel-1 real data sets are used to demonstrate the superiority of this proposed approach over the traditional phase estimation algorithms. Specifically, the coherence bias can be corrected with considerable accuracy by the proposed scheme. The mean bias of coherence magnitude is reduced by more than 29%, and the standard deviation is reduced by more than 18% over the existing bias correction method. The proposed approach achieves higher accuracy than the current methods over the reconstructed phase series, including smoother interferometric phases and fewer outliers. [ABSTRACT FROM AUTHOR]

Epidermal growth factor receptor (EGFR) and Kirsten rat sarcoma (KRAS) are the most common driver genes in non-small cell lung cancer patients. However, frequent gene mutation testing raises a potential risk of cancer metastasis. In our paper, a Mut-SeResNet model based on the ResNet network that incorporated a residual block and attention mechanism was proposed to solve the performance degradation problem caused by a deepening of the network. We introduced a residual structure and extracted small differences between different levels to enhance the feature learning ability. The squeeze and excitation attention mechanism was adapted to fully extract the dependence between different channels of the feature image, and it calibrated the channel feature information. We used the dataset of 363 patients that were collected from collaborating hospitals to train our Mut-SeResNet model. The prediction accuracy for EGFR and KRAS mutations was 89.7% and 88.3%, respectively, with a loss accuracy of 6.4% and 9.2%, respectively. The results showed that the model provided a non-invasive and easy-to-use method to improve the accuracy and stability of clinical diagnosis. [ABSTRACT FROM AUTHOR]

Massive and diverse remote sensing data provide opportunities for data-driven tasks in the real world, but also present challenges in terms of data processing and analysis, especially pixel-level image interpretation. However, the existing shallow-learning and deep-learning segmentation methods, bounded by their technical bottlenecks, cannot properly balance accuracy and efficiency, and are thus hardly scalable to the practice scenarios of remote sensing in a successful way. Instead of following the time-consuming deep stacks of local operations as most state-of-the-art segmentation networks, we propose a novel segmentation model with the encoder–decoder structure, dubbed XANet, which leverages the more computationally economical attention mechanism to boost performance. Two novel attention modules in XANet are proposed to strengthen the encoder and decoder, respectively, namely the Attention Recalibration Module (ARM) and Attention Fusion Module (AFM). Unlike current attention modules, which only focus on elevating the feature representation power, and regard the spatial and channel enhancement of a feature map as two independent steps, ARM gathers element-wise semantic descriptors coupling spatial and channel information to directly generate a 3D attention map for feature enhancement, and AFM innovatively utilizes the cross-attention mechanism for the sufficient spatial and channel fusion of multi-scale features. Extensive experiments were conducted on ISPRS and GID datasets to comprehensively analyze XANet and explore the effects of ARM and AFM. Furthermore, the results demonstrate that XANet surpasses other state-of-the-art segmentation methods in both model performance and efficiency, as ARM yields a superior improvement versus existing attention modules with a competitive computational overhead, and AFM achieves the complementary advantages of multi-level features under the sufficient consideration of efficiency. [ABSTRACT FROM AUTHOR]