Search

ABSTRACT: Mycoplasma gallisepticum (MG) is a highly contagious avian respiratory pathogen characterized by rapid spread, widespread distribution, and long-term persistence of infection. Previous studies have shown that chicken macrophage HD11 cells play a critical role in the replication and immunomodulation of MG. Macrophages are multifunctional immunomodulatory cells that polarize into different functions and morphologies in response to exogenous stimuli. However, the effect of MG infection on HD11 polarization is not well understood. In this study, we observed a time-dependent increase in both the expression of the MG-related virulence protein pMGA1.2 and the copy number of MG upon MG infection. Polarization studies revealed an upregulation of M1-type marker genes in MG-infected HD11 cells, suggesting that MG mainly induces HD11 macrophages towards M1-type polarization. Furthermore, MG activated the inflammatory vesicle NLRP3 signaling pathway, and NLRP3 inhibitors affected the expression of M1 and M2 marker genes, indicating the crucial regulatory role of the NLRP3 signaling pathway in MG-induced polarization of HD11 macrophages. Our findings reveal a novel mechanism of MG infection, namely the polarization of MG-infected HD11 macrophages. This discovery suggests that altering the macrophage phenotype to inhibit MG infection may be an effective control strategy. These findings provide new perspectives on the pathogenic mechanism and control measures of MG.

Abstract The main advantage of DDIM is that it guarantees the quality of the generated images while increasing the efficiency of the generation by modifying the sampling strategy in the diffusion process. DiffusionRig, which addresses the problem of maintaining identity consistency by learning the person-specific facial prior in a tiny personalized dataset, is a successful representation of the DDIM strategy. Based on DiffusionRig, in this article, we propose an improved face attributes editing method based on DDIM to improve naturalness and accuracy of editing results in complex face attribute editing tasks and the generalization ability. Our method combines DDIM and DECA together and use two-stage training strategy. To reduce DiffusionRig’s limitations in handling face attribute editing tasks that require nonlinear understanding and fine-tuning, our method also introduces a channel attention mechanism and a depth-separable convolution technique in the training model. In the first stage we trained our model on the open FFHQ dataset, which consists of 30,000 high-resolution face image. In the second stage, the model was refined by using a tiny personalized dataset. Face attribute editing experiments,comparative experiment with DiffusionRig, and a series of ablation experiments have been performed. Then, the validity of our improved method is verified by qualitative and quantitative analysis.

Ground-based solar telescopes often encounter cloud interference during observations, leading to varying degrees of cloud cover in solar images. Existing cloud removal methods face several challenges, including incomplete cloud removal, insufficient restoration of solar features, and ineffectiveness against severe cloud cover. This paper proposes a novel deep learning-based approach for cloud removal and feature restoration in H α full-disk solar images. First, to create a high-quality data set of cloud-covered images, we developed a method for detecting and classifying cloudiness in H α full-disk solar images. This method correlates average intensity profiles in log-polar coordinates and utilizes the median pixel intensity in the images. Using this approach, we constructed a data set with three levels of cloudiness: mild, moderate, and severe, utilizing high-cadence H α full-disk solar images from different sites within the Global Oscillation Network Group. Second, our cloud removal network employs an encoder–decoder structure, integrating the Res2Net module into the encoder to capture comprehensive solar image features. The decoder enhances the model's ability to extract semantic information about cloud-covered areas through a residual multiscale attention mechanism. Quantitative and qualitative experimental results demonstrate that the proposed method effectively removes complex cloud interference while preserving solar features, significantly improving the quality of observed data and outperforming existing solar image cloud removal methods. Additionally, the model serves as a valuable reference for removing clouds from other ground-based telescope data. The data and code are available on GitHub ( https://github.com/dupeng24/full-disk-cloud-removal ) under a CC0 1.0 License, and version 2.0 is archived in Zenodo (10.5281/zenodo.14184221).

Image restoration is a crucial task in computer vision, aiming to fill in missing areas within an image to restore its integrity. Traditional methods fall short when dealing with intricate facial image restoration, often failing to produce high-quality results. Denoising Diffusion Probabilistic Models(DDPM), characterized by its diversity and stability, plays a significant role in the domain of facial image restoration. This study aims to explore a facial image restoration method based on DDPM, utilizing a pre-trained unconditional DDPM model to achieve more flexible facial image restoration. At the same time, this study found that when the total number of iterations in the resampling process is relatively low, the quality of the restored image is poor. Therefore, we propose a method to optimize the inversion process by combining progressive sampling with sample scheduling to improve the quality of the restored images, and conduct extensive experiments on the CelebA-HQ and FFHQ datasets. Comparisons with other methods demonstrate that our approach yields higher-quality results in facial image restoration. Our method achieved the best results in terms of PSNR and LPIPS metrics. For random masks, the accuracy of face recognition increased by 15.7% after the restoration of facial images. For central masks, the accuracy improved by 26%.

Walnuts possess significant nutritional and economic value. Fast and accurate sorting of shells and kernels will enhance the efficiency of automated production. Therefore, we propose a FastQAFPN-YOLOv8s object detection network to achieve rapid and precise detection of unsorted materials. The method uses lightweight Pconv (Partial Convolution) operators to build the FasterNextBlock structure, which serves as the backbone feature extractor for the Fasternet feature extraction network. The ECIoU loss function, combining EIoU (Efficient-IoU) and CIoU (Complete-IoU), speeds up the adjustment of the prediction frame and the network regression. In the Neck section of the network, the QAFPN feature fusion extraction network is proposed to replace the PAN-FPN (Path Aggregation Network—Feature Pyramid Network) in YOLOv8s with a Rep-PAN structure based on the QARepNext reparameterization framework for feature fusion extraction to strike a balance between network performance and inference speed. To validate the method, we built a three-axis mobile sorting device and created a dataset of 3000 images of walnuts after shell removal for experiments. The results show that the improved network contains 6071008 parameters, a training time of 2.49 h, a model size of 12.3 MB, an mAP (Mean Average Precision) of 94.5%, and a frame rate of 52.1 FPS. Compared with the original model, the number of parameters decreased by 45.5%, with training time reduced by 32.7%, the model size shrunk by 45.3%, and frame rate improved by 40.8%. However, some accuracy is sacrificed due to the lightweight design, resulting in a 1.2% decrease in mAP. The network reduces the model size by 59.7 MB and 23.9 MB compared to YOLOv7 and YOLOv6, respectively, and improves the frame rate by 15.67 fps and 22.55 fps, respectively. The average confidence and mAP show minimal changes compared to YOLOv7 and improved by 4.2% and 2.4% compared to YOLOv6, respectively. The FastQAFPN-YOLOv8s detection method effectively reduces model size while maintaining recognition accuracy.

Accurate coffee plant counting is a crucial metric for yield estimation and a key component of precision agriculture. While multispectral UAV technology provides more accurate crop growth data, the varying spectral characteristics of coffee plants across different phenological stages complicate automatic plant counting. This study compared the performance of mainstream YOLO models for coffee detection and segmentation, identifying YOLOv9 as the best-performing model, with it achieving high precision in both detection (P = 89.3%, mAP50 = 94.6%) and segmentation performance (P = 88.9%, mAP50 = 94.8%). Furthermore, we studied various spectral combinations from UAV data and found that RGB was most effective during the flowering stage, while RGN (Red, Green, Near-infrared) was more suitable for non-flowering periods. Based on these findings, we proposed an innovative dual-channel non-maximum suppression method (dual-channel NMS), which merges YOLOv9 detection results from both RGB and RGN data, leveraging the strengths of each spectral combination to enhance detection accuracy and achieving a final counting accuracy of 98.4%. This study highlights the importance of integrating UAV multispectral technology with deep learning for coffee detection and offers new insights for the implementation of precision agriculture.

In recent years, the estimation of tobacco field areas has become a critical component of precision tobacco cultivation. However, traditional satellite remote sensing methods face challenges such as high costs, low accuracy, and susceptibility to noise, making it difficult to meet the demand for high precision. Additionally, optical remote sensing methods perform poorly in regions with complex terrain. Therefore, Unmanned Aerial Vehicle multispectral remote sensing technology has emerged as a viable solution due to its high resolution and rich spectral information. This study employed a DJI Mavic 3M equipped with high-resolution RGB and multispectral cameras to collect tobacco field data covering five bands: RGB, RED, RED EDGE, NIR, and GREEN in Agang Town, Luoping County, Yunnan Province, China. To ensure the accuracy of the experiment, we used 337, 242, and 215 segmented tobacco field images for model training, targeting both RGB channels and seven-channel data. We developed a tobacco field semantic segmentation method based on PP-LiteSeg and deeply customized the model to adapt to the characteristics of multispectral images. The input layer’s channel number was adjusted to multiple channels to fully utilize the information from the multispectral images. The model structure included an encoder, decoder, and SPPM module, which used a multi-layer convolution structure to achieve feature extraction and segmentation of multispectral images. The results indicated that compared to traditional RGB images, multispectral images offered significant advantages in handling edges and complex terrain for semantic segmentation. Specifically, the predicted area using the seven-channel data was 11.43 m² larger than that obtained with RGB channels. Additionally, the seven-channel model achieved a prediction accuracy of 98.84%. This study provides an efficient and feasible solution for estimating tobacco field areas based on multispectral images, offering robust support for modern agricultural management.

Tobacco is a valuable crop, but its disease identification is rarely involved in existing works. In this work, we use few-shot learning (FSL) to identify abnormalities in tobacco. FSL is a solution for the data deficiency that has been an obstacle to using deep learning. However, weak feature representation caused by limited data is still a challenging issue in FSL. The weak feature representation leads to weak generalization and troubles in cross-domain. In this work, we propose a feature representation enhancement network (FREN) that enhances the feature representation through instance embedding and task adaptation. For instance embedding, global max pooling, and global average pooling are used together for adding more features, and Gaussian-like calibration is used for normalizing the feature distribution. For task adaptation, self-attention is adopted for task contextualization. Given the absence of publicly available data on tobacco, we created a tobacco leaf abnormality dataset (TLA), which includes 16 categories, two settings, and 1,430 images in total. In experiments, we use PlantVillage, which is the benchmark dataset for plant disease identification, to validate the superiority of FREN first. Subsequently, we use the proposed method and TLA to analyze and discuss the abnormality identification of tobacco. For the multi-symptom diseases that always have low accuracy, we propose a solution by dividing the samples into subcategories created by symptom. For the 10 categories of tomato in PlantVillage, the accuracy achieves 66.04% in 5-way, 1-shot tasks. For the two settings of the tobacco leaf abnormality dataset, the accuracies were achieved at 45.5% and 56.5%. By using the multisymptom solution, the best accuracy can be lifted to 60.7% in 16-way, 1-shot tasks and achieved at 81.8% in 16-way, 10-shot tasks. The results show that our method improves the performance greatly by enhancing feature representation, especially for tasks that contain categories with high similarity. The desensitization of data when crossing domains also validates that the FREN has a strong generalization ability.

Abstract Vehicular edge computing (VEC) is emerging as a new computing paradigm to improve the quality of vehicular services and enhance the capabilities of vehicles. It enables performing tasks with low latency by deploying computing and storage resources close to vehicles. However, the traditional task offloading schemes only focus on one-shot offloading, taking less into consideration task dependency. Furthermore, the continuous action space problem during task offloading should be considered. In this paper, an efficient dependency-aware task offloading scheme for VEC with vehicle-edge-cloud collaborative computation is proposed, where subtasks can be processed locally or can be offloaded to an edge server, or a cloud server for execution. Specifically, first, the directed acyclic graph (DAG) is utilized to model the dependency of subtasks. Second, a task offloading algorithm based on Deep Deterministic Policy Gradient (DDPG) was proposed to obtain the optimal offloading strategy in a vehicle-edge-cloud environment, which efficiently solves the continuous control problem and helps reach fast convergence. Finally, extensive simulation experiments have been conducted, and the experimental results show that the proposed scheme can improve performance by about 13.62% on average against three baselines.

The optical flow algorithm (OF) is one the main methods for calculating image velocity field and has many applications in space weather. Most OF calculations are applied to the motion of labeled rigid objects and are not suitable for velocity detection of high-energy particles, such as in a coronal mass ejection (CME). Fluctuations in exposure time and the influence of space weather will lead to inconsistent brightness of the same feature point at different times. To address this problem, we propose an unsupervised multiscale optical flow network based on Vision Transformer, named UTFlowNet. The network comprises a multiscale feature extraction module and a coarse-to-fine global optical flow calculation module. The movement of high-energy particles emitted during a CME eruption follows certain physical rules. Therefore, we apply fluid motion–based loss functions to analyze the motion of high-energy particles more effectively, addressing the problem of CME motion field extraction. Our method can be applied to the real-time automatic extraction of a CME’s velocity field and performs well with inconsistent brightness, large-scale motion, and strong CME noise. Additionally, we can estimate subpixel level fine-grained velocity. Our model may be affected by overfitting during cross–data set inference, so we encourage performing a small amount of transfer learning on new data sets to mitigate this issue. In order to verify the accuracy of our method, we conducted experiments and verification on the Solar and Heliospheric Observatory LASCO C2 data and the High Altitude Observatory MLSO data. We constructed a large-scale displacement simulation data set based on LASCO C2 data and tested on it, achieving the best results.

Plant counting is an important part in precision agriculture (PA). The Unmanned Aerial Vehicle (UAV) becomes popular in agriculture because it can capture data with higher spatiotemporal resolution. When it is equipped with multispectral sensors, more meaningful multispectral data is obtained for plants’ analysis. After tobacco seedlings are raised, they are transplanted into the field. The counting of tobacco plant stands in the field is important for monitoring the transplant survival rate, growth situation, and yield estimation. In this work, we adopt the object detection (OD) method of deep learning to automatically count the plants with multispectral images. For utilizing the advanced YOLOv8 network, we modified the architecture of the network to adapt to the different band combinations and conducted extensive data pre-processing work. The Red + Green + NIR combination obtains the best detection results, which reveal that using a specific band or band combinations can obtain better results than using the traditional RGB images. For making our method more practical, we designed an algorithm that can handling the image of a whole plot, which is required to be watched. The counting accuracy is as high as 99.53%. The UAV, multispectral data combined with the powerful deep learning methods show promising prospective in PA.

A novel deep eutectic solvent (DES) is proposed as a multifunctional porogen to simultaneously improve the permeability and selectivity of the polysulfate (PSE) ultrafiltration (UF) membrane. The effects of DES on the formation process of PSE membrane were explored by the viscosity, cloud point, and phase inversion properties. The molecular weight cutoff (MWCO) of the prepared membranes decreased as the DES content increased to 3.0 wt%, reaching as small as 18.5 kDa, with an improved porosity of 81.9%. In addition, the water flux improved to 212.3 L/m2*h, which was 2.3-fold larger than that of the pristine PSE membrane, and the rejection efficiency for natural organic matter (NOM) was simultaneously enhanced. Considering the easy and cheap preparation of the DESs, the proposed method offers a new possibility for high-performance UF membranes preparation.

We propose an improved BM3D algorithm for block-matching based on UNet denoising network feature maps and structural similarity (SSIM). In response to the traditional BM3D algorithm that directly performs block-matching on a noisy image, without considering the deep-level features of the image, we propose a method that performs block-matching on the feature maps of the noisy image. In this method, we perform block-matching on multiple depth feature maps of a noisy image, and then determine the positions of the corresponding similar blocks in the noisy image based on the block-matching results, to obtain the set of similar blocks that take into account the deep-level features of the noisy image. In addition, we improve the similarity measure criterion for block-matching based on the Structural Similarity Index, which takes into account the pixel-by-pixel value differences in the image blocks while fully considering the structure, brightness, and contrast information of the image blocks. To verify the effectiveness of the proposed method, we conduct extensive comparative experiments. The experimental results demonstrate that the proposed method not only effectively enhances the denoising performance of the image, but also preserves the detailed features of the image and improves the visual quality of the denoised image.

Choreography-driven microservice composition has provided a better way to integrate components in the Cyber-physical-Social System (CPSS). Choreography is a global contract that specifies interactions among microservices participating in a composite service. After modeling a choreography, a problem arises here is whether the choreography specification at design time can be implemented correctly by generated microservices that interact with each other via exchanging messages. In this paper, we propose a novel approach for choreography analysis. Specifically, a choreography is specified using a Labeled Transition Systems (LTSs); then, the microservices participating in a composite service can be generated from the given choreography via projection and ε-remove; finally, the analysis of the choreography can be checked for both synchronous and asynchronous compositions using refinement checking. Our approach is completely automated under the support of our developed tool and the Process Analysis Toolkit (PAT) tool.

Few-shot learning (FSL) is suitable for plant-disease recognition due to the shortage of data. However, the limitations of feature representation and the demanding generalization requirements are still pressing issues that need to be addressed. The recent studies reveal that the frequency representation contains rich patterns for image understanding. Given that most existing studies based on image classification have been conducted in the spatial domain, we introduce frequency representation into the FSL paradigm for plant-disease recognition. A discrete cosine transform module is designed for converting RGB color images to the frequency domain, and a learning-based frequency selection method is proposed to select informative frequencies. As a post-processing of feature vectors, a Gaussian-like calibration module is proposed to improve the generalization by aligning a skewed distribution with a Gaussian-like distribution. The two modules can be independent components ported to other networks. Extensive experiments are carried out to explore the configurations of the two modules. Our results show that the performance is much better in the frequency domain than in the spatial domain, and the Gaussian-like calibrator further improves the performance. The disease identification of the same plant and the cross-domain problem, which are critical to bring FSL to agricultural industry, are the research directions in the future.

Interactions in microservice systems are complex due to three dimensions: numerous asynchronous interactions, the diversity of asynchronous communication, and unbounded buffers. Analyzing such complex interactions is challenging. In this paper, we propose an approach for interaction analysis using model checking techniques, which is supported by the Process Analysis Toolkit (PAT) tool. First, we use Labeled Transition Systems (LTSs) to model interaction behaviors in microservice systems as sequences of send actions under synchronous and asynchronous communications. Second, we introduce a notion of correctness called “interaction soundness” which is considered as a minimal requirement for microservice systems. Third, we propose an encoding of LTSs into the CSP# process algebra for automatic verification of the property interaction soundness. The experimental results show that our approach can automatically and effectively identify interaction faults in microservice systems.

Semantic face inpainting from corrupted images is a challenging problem in computer vision and has many practical applications. Different from well-studied nature image inpainting, the face inpainting task often needs to fill pixels semantically into a missing region based on the available visual data. In this paper, we propose a new face inpainting algorithm based on deep generative models, which increases the structural loss constraint in the image generation model to ensure that the generated image has a structure as similar as possible to the face image to be repaired. At the same time, different weights are calculated in the corrupted image to enforce edge consistency at the repair boundary. Experiments on different face data sets and qualitative and quantitative analyses demonstrate that our algorithm is capable of generating visually pleasing face completions.

In this paper, we describe a technique, which uses an adaptive background learning method to detect the CME (coronal mass ejections) automatically from SOHO/LASCO C2 image sequences. The method consists of several modules: adaptive background module, candidate CME area detection module, and CME detection module. The core of the method is based on adaptive background learning, where CMEs are assumed to be a foreground moving object outward as observed in running-difference time series. Using the static and dynamic features to model the corona observation scene can more accurately describe the complex background. Moreover, the method can detect the subtle changes in the corona sequences while filtering their noise effectively. We applied this method to a month of continuous corona images, compared the result with CDAW, CACTus, SEEDS, and CORIMP catalogs and found a good detection rate in the automatic methods. It detected about 73% of the CMEs listed in the CDAW CME catalog, which is identified by human visual inspection. Currently, the derived parameters are position angle, angular width, linear velocity, minimum velocity, and maximum velocity of CMES. Other parameters could also easily be added if needed.

In this work, the positively or negatively charged anatase TiO2 nanoparticles were synthesized via a low temperature precipitation-peptization process (LTPPP) in the presence of poly(ethyleneimine) (PEI) and poly(sodium4- styrenesulfonate) (PSS). X-ray diffraction (XRD) pattern and high-resolution transmission electron microscope (HRTEM) confirmed the anatase crystalline phase. The charges of the prepared TiO2, PEI-TiO2 and PSS-TiO2 nanoparticles were investigated by zeta potentials. The results showed that the zeta potentials of PEI-TiO2 nanoparticles can be tuned from +39.47 mV to +95.46 mV, and that of PSS-TiO2 nanoparticles can be adjusted from -56.63 mV to -119.32 mV. In comparison with TiO2, PSS-TiO2 exhibited dramatic adsorption and degradation of dye molecules, while the PEI modified TiO2 nanoparticles showed lower photocatalytic activity. The photocatalytic performances of these charged nanoparticles were elucidated by the results of UV-vis diffuse reflectance spectra (DRS) and the photoluminescence (PL) spectra, which indicated that the PSS-TiO2 nanoparticles showed a lower recombination rate of electron-hole pairs than TiO2 and PEI-TiO2.