Two-dimensional endoscopic images are susceptible to interferences such as specular reflections and monotonous texture illumination,hindering accurate three-dimensional lesion reconstruction by surgical robots.This st...Two-dimensional endoscopic images are susceptible to interferences such as specular reflections and monotonous texture illumination,hindering accurate three-dimensional lesion reconstruction by surgical robots.This study proposes a novel end-to-end disparity estimation model to address these challenges.Our approach combines a Pseudo-Siamese neural network architecture with pyramid dilated convolutions,integrating multi-scale image information to enhance robustness against lighting interferences.This study introduces a Pseudo-Siamese structure-based disparity regression model that simplifies left-right image comparison,improving accuracy and efficiency.The model was evaluated using a dataset of stereo endoscopic videos captured by the Da Vinci surgical robot,comprising simulated silicone heart sequences and real heart video data.Experimental results demonstrate significant improvement in the network’s resistance to lighting interference without substantially increasing parameters.Moreover,the model exhibited faster convergence during training,contributing to overall performance enhancement.This study advances endoscopic image processing accuracy and has potential implications for surgical robot applications in complex environments.展开更多
This study constructs a reflective feedback model based on a pedagogical agent(PA)and explores its impact on students’problem-solving ability and cognitive load.A quasi-experimental design was used in the study,with ...This study constructs a reflective feedback model based on a pedagogical agent(PA)and explores its impact on students’problem-solving ability and cognitive load.A quasi-experimental design was used in the study,with 84 students from a middle school selected as the research subjects(44 in the experimental group and 40 in the control group).The experimental group used the reflective feedback model,while the control group used the factual feedback model.The results show that,compared with factual feedback,the reflective feedback model based on the pedagogical agent significantly improves students’problem-solving ability,especially at the action and thinking levels.In addition,this model effectively reduces students’cognitive load,especially in terms of internal and external load.展开更多
【Objectives】Si and microbial application could relieve the crop replanting problems(CRPs).We further studied the change of key microorganisms that are related to the beneficial effects,aiming at provide reference fo...【Objectives】Si and microbial application could relieve the crop replanting problems(CRPs).We further studied the change of key microorganisms that are related to the beneficial effects,aiming at provide reference for the manufacture and application of both microbial agents and Si fertilizer in food lily production.【Methods】A field experiment was conducted over a three-year period,from March 2019 to March 2022.The experimental field had been continuously cultivated with lily for 9 years.Three treatments were established:silicon fertilizer(SF),microbial agents(“Special 8^(TM)”,MF),and combined application of silicon fertilizer and microbial agents(SMF).A control group with blank soil(CK)was also included.At seedling stage of Lanzhou lilies in 2020 and 2021,the shoot and bulb dry weight,and the plant height and stem diameter of Lanzhou lilies were investigated for calculation of seedling index.In July 2020,20 plants were selected in each plot,and root zone soils were sampled at a depth of 20 cm,10 cm away from the roots,and then mixed to form a composite sample.The soil available Si and organic matter content were analyzed,and the fungal community structure and some specific microbial groups in soils were determined with high-throughput sequencing of ITS.【Results】All the three treatments significantly enhanced the lily plant growth and the seedling index,compared to CK.Besides,SF and MF treatments increased the relative abundances(RA)and diversity of fungal communities,and altered the community structures.The RA of some specific groups were found to be significantly correlated with the seedling index and/or soil available Si.Of them,the RA of the genera Fusarium,Dactylonectria,Humicola,Stilbella,and the species Humicola_grisea showed a positive correlation,while that of the genera Mortierella,Stilbella,Holtermanniella,and the species Mortierella_fatshederae showed a negative correlation with seedling index.The genera Fusarium,Stilbella,the species Humicola_grisea,and Dactylonectria_estremocensis showed a positive correlation,while the genura Stilbella,and the species Mortierella fatshederae showed a negative correlation with available Si content.In the co-occurence network of top twenty fungal genera and top sixteen bacterial genera(RA>0.2%),Holtermanniella was the only genus that interacted with the bacteria and negatively correlated with bacterial genus Blastococcus.Holtermanniella was also the most densely connected genera,followed by the genus Fusarium,Didymella and Humicola.In addition,the genus Holtermanniella was the key species connecting fungal and bacterial community in soil.Fungal functional prediction revealed that SF,MF and SMF treatments decreased plant pathogens guilds and increased the beneficial guilds Ectomycorrhizal,plant saprophyte,leaf saprophyte,and arbuscular mycorrhizal compared to CK.【Conclusions】Combined application of silicon fertilizer and microbial agents can alleviate continuous replanting problems of Lanzhou lilies through restoring the fungal community diversity,and promoting plant residue depredation,thus reducing soil born disease incidence.The beneficial genus Humicola and its one species H.grisea acts as bioconversion,and the genus Acremonium acts as plant pathogen inhibitor.展开更多
Seismic data denoising is a critical process usually applied at various stages of the seismic processing workflow,as our ability to mitigate noise in seismic data affects the quality of our subsequent analyses.However...Seismic data denoising is a critical process usually applied at various stages of the seismic processing workflow,as our ability to mitigate noise in seismic data affects the quality of our subsequent analyses.However,finding an optimal balance between preserving seismic signals and effectively reducing seismic noise presents a substantial challenge.In this study,we introduce a multi-stage deep learning model,trained in a self-supervised manner,designed specifically to suppress seismic noise while minimizing signal leakage.This model operates as a patch-based approach,extracting overlapping patches from the noisy data and converting them into 1D vectors for input.It consists of two identical sub-networks,each configured differently.Inspired by the transformer architecture,each sub-network features an embedded block that comprises two fully connected layers,which are utilized for feature extraction from the input patches.After reshaping,a multi-head attention module enhances the model’s focus on significant features by assigning higher attention weights to them.The key difference between the two sub-networks lies in the number of neurons within their fully connected layers.The first sub-network serves as a strong denoiser with a small number of neurons,effectively attenuating seismic noise;in contrast,the second sub-network functions as a signal-add-back model,using a larger number of neurons to retrieve some of the signal that was not preserved in the output of the first sub-network.The proposed model produces two outputs,each corresponding to one of the sub-networks,and both sub-networks are optimized simultaneously using the noisy data as the label for both outputs.Evaluations conducted on both synthetic and field data demonstrate the model’s effectiveness in suppressing seismic noise with minimal signal leakage,outperforming some benchmark methods.展开更多
Computed Tomography(CT)reconstruction is essential inmedical imaging and other engineering fields.However,blurring of the projection during CT imaging can lead to artifacts in the reconstructed images.Projection blur ...Computed Tomography(CT)reconstruction is essential inmedical imaging and other engineering fields.However,blurring of the projection during CT imaging can lead to artifacts in the reconstructed images.Projection blur combines factors such as larger ray sources,scattering and imaging system vibration.To address the problem,we propose DeblurTomo,a novel self-supervised learning-based deblurring and reconstruction algorithm that efficiently reconstructs sharp CT images from blurry input without needing external data and blur measurement.Specifically,we constructed a coordinate-based implicit neural representation reconstruction network,which can map the coordinates to the attenuation coefficient in the reconstructed space formore convenient ray representation.Then,wemodel the blur as aweighted sumof offset rays and design the RayCorrectionNetwork(RCN)andWeight ProposalNetwork(WPN)to fit these rays and their weights bymulti-view consistency and geometric information,thereby extending 2D deblurring to 3D space.In the training phase,we use the blurry input as the supervision signal to optimize the reconstruction network,the RCN,and the WPN simultaneously.Extensive experiments on the widely used synthetic dataset show that DeblurTomo performs superiorly on the limited-angle and sparse-view in the simulated blurred scenarios.Further experiments on real datasets demonstrate the superiority of our method in practical scenarios.展开更多
Blended acquisition offers efficiency improvements over conventional seismic data acquisition, at the cost of introducing blending noise effects. Besides, seismic data often suffers from irregularly missing shots caus...Blended acquisition offers efficiency improvements over conventional seismic data acquisition, at the cost of introducing blending noise effects. Besides, seismic data often suffers from irregularly missing shots caused by artificial or natural effects during blended acquisition. Therefore, blending noise attenuation and missing shots reconstruction are essential for providing high-quality seismic data for further seismic processing and interpretation. The iterative shrinkage thresholding algorithm can help obtain deblended data based on sparsity assumptions of complete unblended data, and it characterizes seismic data linearly. Supervised learning algorithms can effectively capture the nonlinear relationship between incomplete pseudo-deblended data and complete unblended data. However, the dependence on complete unblended labels limits their practicality in field applications. Consequently, a self-supervised algorithm is presented for simultaneous deblending and interpolation of incomplete blended data, which minimizes the difference between simulated and observed incomplete pseudo-deblended data. The used blind-trace U-Net (BTU-Net) prevents identity mapping during complete unblended data estimation. Furthermore, a multistep process with blending noise simulation-subtraction and missing traces reconstruction-insertion is used in each step to improve the deblending and interpolation performance. Experiments with synthetic and field incomplete blended data demonstrate the effectiveness of the multistep self-supervised BTU-Net algorithm.展开更多
Nanolipid carriers and traditional emulsion containing chemical sunscreens were prepared using emulsification combined with ultrasonic technology.The nanolipid carriers showed superior performance in sunscreen encapsu...Nanolipid carriers and traditional emulsion containing chemical sunscreens were prepared using emulsification combined with ultrasonic technology.The nanolipid carriers showed superior performance in sunscreen encapsulation,slow release and skin impermeability,and provided an excellent nanolipid slow-release encapsulation system for sunscreens.As observed by transmission electron microscopy,the nanolipid carriers were spherical shape,with smooth surface and uniform distribution,and the particle sizes were mainly concentrated in the range of 230 to 250 nm without agglomeration.The nanolipid carriers significantly improved the sunscreen performance through the synergistic effect of scattering and chemical absorption,and showed better UV stability than traditional sunscreen,indicating their photoprotective function.In vitro release experiments showed that the nano-lipidic carriers exhibited better release control when loaded with octyl methoxycinnamate(OMC)and butylmethoxydibenzoylmethane(BDFM)sunscreens than traditional traditional emulsions,with the cumulative release rate of OMC in the nano-lipidic carriers decreasing by 17.17% to 30.24% within 12 hours,and that of BDFM decreasing by 26.67% to 44.67%.26.67% to 44.16%.The results of the in vitro permeation experiment further confirmed that the nanolipid carriers could effectively encapsulate the sunscreens and prevent them from penetrating the skin barrier,thus reducing the skin irritation.Compared with traditional traditional emulsion,the cumulative penetration of OMC in nanostructured lipid carriers was 2.24μg/cm^(2)in 4 hours,while the cumulative penetration was reduced by 68.05%.The cumulative penetration of BDFM in the nanostructured lipid carrier was 3.24μg/cm^(2),with a 64.04%reduction in cumulative penetration.展开更多
Given that the citrus psyllid is the primary vector of citrus Huanglongbing(HLB),there is an urgent need to control this pest to mitigate the spread of the disease.This paper reviews the current research on two predom...Given that the citrus psyllid is the primary vector of citrus Huanglongbing(HLB),there is an urgent need to control this pest to mitigate the spread of the disease.This paper reviews the current research on two predominant control strategies:chemical control and biological control agents,in managing the citrus psyllid.It emphasizes the mechanisms of action,efficacy,and application advancements of these control methods.Finally,the paper analyzes the principal challenges associated with the sustainable management of citrus psyllids and offers perspectives for future research.展开更多
Artificial intelligence(AI)is reshaping financial systems and services,as intelligent AI agents increasingly form the foundation of autonomous,goal-driven systems capable of reasoning,learning,and action.This review s...Artificial intelligence(AI)is reshaping financial systems and services,as intelligent AI agents increasingly form the foundation of autonomous,goal-driven systems capable of reasoning,learning,and action.This review synthesizes recent research and developments in the application of AI agents across core financial domains.Specifically,it covers the deployment of agent-based AI in algorithmic trading,fraud detection,credit risk assessment,roboadvisory,and regulatory compliance(RegTech).The review focuses on advanced agent-based methodologies,including reinforcement learning,multi-agent systems,and autonomous decision-making frameworks,particularly those leveraging large language models(LLMs),contrasting these with traditional AI or purely statistical models.Our primary goals are to consolidate current knowledge,identify significant trends and architectural approaches,review the practical efficiency and impact of current applications,and delineate key challenges and promising future research directions.The increasing sophistication of AI agents offers unprecedented opportunities for innovation in finance,yet presents complex technical,ethical,and regulatory challenges that demand careful consideration and proactive strategies.This review aims to provide a comprehensive understanding of this rapidly evolving landscape,highlighting the role of agent-based AI in the ongoing transformation of the financial industry,and is intended to serve financial institutions,regulators,investors,analysts,researchers,and other key stakeholders in the financial ecosystem.展开更多
Feature fusion is an important technique in medical image classification that can improve diagnostic accuracy by integrating complementary information from multiple sources.Recently,Deep Learning(DL)has been widely us...Feature fusion is an important technique in medical image classification that can improve diagnostic accuracy by integrating complementary information from multiple sources.Recently,Deep Learning(DL)has been widely used in pulmonary disease diagnosis,such as pneumonia and tuberculosis.However,traditional feature fusion methods often suffer from feature disparity,information loss,redundancy,and increased complexity,hindering the further extension of DL algorithms.To solve this problem,we propose a Graph-Convolution Fusion Network with Self-Supervised Feature Alignment(Self-FAGCFN)to address the limitations of traditional feature fusion methods in deep learning-based medical image classification for respiratory diseases such as pneumonia and tuberculosis.The network integrates Convolutional Neural Networks(CNNs)for robust feature extraction from two-dimensional grid structures and Graph Convolutional Networks(GCNs)within a Graph Neural Network branch to capture features based on graph structure,focusing on significant node representations.Additionally,an Attention-Embedding Ensemble Block is included to capture critical features from GCN outputs.To ensure effective feature alignment between pre-and post-fusion stages,we introduce a feature alignment loss that minimizes disparities.Moreover,to address the limitations of proposed methods,such as inappropriate centroid discrepancies during feature alignment and class imbalance in the dataset,we develop a Feature-Centroid Fusion(FCF)strategy and a Multi-Level Feature-Centroid Update(MLFCU)algorithm,respectively.Extensive experiments on public datasets LungVision and Chest-Xray demonstrate that the Self-FAGCFN model significantly outperforms existing methods in diagnosing pneumonia and tuberculosis,highlighting its potential for practical medical applications.展开更多
Self-supervised monocular depth estimation has emerged as a major research focus in recent years,primarily due to the elimination of ground-truth depth dependence.However,the prevailing architectures in this domain su...Self-supervised monocular depth estimation has emerged as a major research focus in recent years,primarily due to the elimination of ground-truth depth dependence.However,the prevailing architectures in this domain suffer from inherent limitations:existing pose network branches infer camera ego-motion exclusively under static-scene and Lambertian-surface assumptions.These assumptions are often violated in real-world scenarios due to dynamic objects,non-Lambertian reflectance,and unstructured background elements,leading to pervasive artifacts such as depth discontinuities(“holes”),structural collapse,and ambiguous reconstruction.To address these challenges,we propose a novel framework that integrates scene dynamic pose estimation into the conventional self-supervised depth network,enhancing its ability to model complex scene dynamics.Our contributions are threefold:(1)a pixel-wise dynamic pose estimation module that jointly resolves the pose transformations of moving objects and localized scene perturbations;(2)a physically-informed loss function that couples dynamic pose and depth predictions,designed to mitigate depth errors arising from high-speed distant objects and geometrically inconsistent motion profiles;(3)an efficient SE(3)transformation parameterization that streamlines network complexity and temporal pre-processing.Extensive experiments on the KITTI and NYU-V2 benchmarks show that our framework achieves state-of-the-art performance in both quantitative metrics and qualitative visual fidelity,significantly improving the robustness and generalization of monocular depth estimation under dynamic conditions.展开更多
Domain randomization is a widely adopted technique in deep reinforcement learning(DRL)to improve agent generalization by exposing policies to diverse environmental conditions.This paper investigates the impact of diff...Domain randomization is a widely adopted technique in deep reinforcement learning(DRL)to improve agent generalization by exposing policies to diverse environmental conditions.This paper investigates the impact of different reset strategies,normal,non-randomized,and randomized,on agent performance using the Deep Deterministic Policy Gradient(DDPG)and Twin Delayed DDPG(TD3)algorithms within the CarRacing-v2 environment.Two experimental setups were conducted:an extended training regime with DDPG for 1000 steps per episode across 1000 episodes,and a fast execution setup comparing DDPG and TD3 for 30 episodes with 50 steps per episode under constrained computational resources.A step-based reward scaling mechanism was applied under the randomized reset condition to promote broader state exploration.Experimental results showthat randomized resets significantly enhance learning efficiency and generalization,with DDPG demonstrating superior performance across all reset strategies.In particular,DDPG combined with randomized resets achieves the highest smoothed rewards(reaching approximately 15),best stability,and fastest convergence.These differences are statistically significant,as confirmed by t-tests:DDPG outperforms TD3 under randomized(t=−101.91,p<0.0001),normal(t=−21.59,p<0.0001),and non-randomized(t=−62.46,p<0.0001)reset conditions.The findings underscore the critical role of reset strategy and reward shaping in enhancing the robustness and adaptability of DRL agents in continuous control tasks,particularly in environments where computational efficiency and training stability are crucial.展开更多
Clinical pharmacy is on the cusp of exponential change powered by artificial intelligence agents,automation,data analytics,and robotics.Blockchain will enhance data integrity and transparency,and Augmented and Virtual...Clinical pharmacy is on the cusp of exponential change powered by artificial intelligence agents,automation,data analytics,and robotics.Blockchain will enhance data integrity and transparency,and Augmented and Virtual Reality technologies will revolutionise training,patient education,and simulation-based care planning.Clinical pharmacists need to be ready and upskill to prepare for emerging technologies.The ethical,regulatory,and educational frameworks surrounding artificial intelligence and precision medicine will require constant attention,but the potential benefits for patient outcomes are unprecedented.Clinical pharmacists are in a prime position to design a new era in precision medicine,where technology works hand in hand with humans to transform healthcare.展开更多
Steganography is a technology that discreetly embeds secret information into the redundant space of a carrier,enabling covert communication.As generative models continue to advance,steganography has evolved from tradi...Steganography is a technology that discreetly embeds secret information into the redundant space of a carrier,enabling covert communication.As generative models continue to advance,steganography has evolved from traditional modification-based methods to generative steganography,which includes generative linguistic and image based forms.However,while large model agents are rapidly emerging,no method has exploited the stable redundant space in their action processes.Inspired by this insightful observation,we propose a steganographic method leveraging large model agents,employing their actions to conceal secret messages.In this paper,we introduce StegoAgent,a generative steganography framework based on graphical user interface(GUI)agents,which effectively demonstrates the remarkable potential and effectiveness of large model agent-based steganographic methods.展开更多
All maritime industries are plagued by marine biofouling pollution,which causes large economic and environmental costs.Therefore,there is an urgent need for ecofriendly alternatives that can effectively reduce the neg...All maritime industries are plagued by marine biofouling pollution,which causes large economic and environmental costs.Therefore,there is an urgent need for ecofriendly alternatives that can effectively reduce the negative consequences of biofouling pollution.This study aimed to produce novel capsaicin-inspired amide derivatives(CIADs)with multifunctional antifouling features by introducing amide compounds to aromatic compounds via a Friedel-Crafts alkylation reaction.The structure of the CIADs was characterized using FTIR,1H NMR,13C NMR,and HRMS,and the comprehensive antifouling capacity was determined by thermal stability,anti-ultraviolet,antibacterial,anti-algal,and marine field experiments.CIADs showed good thermal stability and did not show obvious weight loss before 226°C.2,4-dihydroxy-3,5-diphenylimidemet-hylbenzophenone(DDB)had an excellent ultraviolet absorption effect,which was even better than that of 2-hydroxy-4-(octyloxy)benzophenone.The antibacterial and anti-algal rates of N-(2,4-dimethyl-3-chloro-5-benzamide-methyl-6-hydroxybenzyl)benzamide(NDCBHB)were more than 99.5%and 64.0%,respectively,and the surface of antifouling coating with NDCBHB(NDCBHB-AC)was covered with only a small amount of sludge and biofilm,its antifouling effect was better than that of chlorothalonil.The above work provides a reference for preparing green and multifunctional antifouling agents.展开更多
Few-shot learning has emerged as a crucial technique for coral species classification,addressing the challenge of limited labeled data in underwater environments.This study introduces an optimized few-shot learning mo...Few-shot learning has emerged as a crucial technique for coral species classification,addressing the challenge of limited labeled data in underwater environments.This study introduces an optimized few-shot learning model that enhances classification accuracy while minimizing reliance on extensive data collection.The proposed model integrates a hybrid similarity measure combining Euclidean distance and cosine similarity,effectively capturing both feature magnitude and directional relationships.This approach achieves a notable accuracy of 71.8%under a 5-way 5-shot evaluation,outperforming state-of-the-art models such as Prototypical Networks,FEAT,and ESPT by up to 10%.Notably,the model demonstrates high precision in classifying Siderastreidae(87.52%)and Fungiidae(88.95%),underscoring its effectiveness in distinguishing subtle morphological differences.To further enhance performance,we incorporate a self-supervised learning mechanism based on contrastive learning,enabling the model to extract robust representations by leveraging local structural patterns in corals.This enhancement significantly improves classification accuracy,particularly for species with high intra-class variation,leading to an overall accuracy of 76.52%under a 5-way 10-shot evaluation.Additionally,the model exploits the repetitive structures inherent in corals,introducing a local feature aggregation strategy that refines classification through spatial information integration.Beyond its technical contributions,this study presents a scalable and efficient approach for automated coral reef monitoring,reducing annotation costs while maintaining high classification accuracy.By improving few-shot learning performance in underwater environments,our model enhances monitoring accuracy by up to 15%compared to traditional methods,offering a practical solution for large-scale coral conservation efforts.展开更多
This paper discusses the importance of standards in the fire extinguishing agent industry,and highlights the vital role of the standards in promoting technological innovation.China’s standards for fire extinguishing ...This paper discusses the importance of standards in the fire extinguishing agent industry,and highlights the vital role of the standards in promoting technological innovation.China’s standards for fire extinguishing agent products have evolved significantly,aligning with industrial development,market demands,regulatory requirements,to respond to the great impact of international competition in the industry.The paper analyzes the current state of China’s standards,including their composition and integration with industry growth,green development strategies,and international harmonization.Future development strategies for the standards framework should focus on valid period estimation,fire test model development,and raw material selection guidelines.By implementing these strategies,China’s fire protection industry can enhance product quality,contribute to public safety,and maintain a competitive edge in the global market.展开更多
基金Supported by Sichuan Science and Technology Program(2023YFSY0026,2023YFH0004)Supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korean government(MSIT)(No.RS-2022-00155885,Artificial Intelligence Convergence Innovation Human Resources Development(Hanyang University ERICA)).
文摘Two-dimensional endoscopic images are susceptible to interferences such as specular reflections and monotonous texture illumination,hindering accurate three-dimensional lesion reconstruction by surgical robots.This study proposes a novel end-to-end disparity estimation model to address these challenges.Our approach combines a Pseudo-Siamese neural network architecture with pyramid dilated convolutions,integrating multi-scale image information to enhance robustness against lighting interferences.This study introduces a Pseudo-Siamese structure-based disparity regression model that simplifies left-right image comparison,improving accuracy and efficiency.The model was evaluated using a dataset of stereo endoscopic videos captured by the Da Vinci surgical robot,comprising simulated silicone heart sequences and real heart video data.Experimental results demonstrate significant improvement in the network’s resistance to lighting interference without substantially increasing parameters.Moreover,the model exhibited faster convergence during training,contributing to overall performance enhancement.This study advances endoscopic image processing accuracy and has potential implications for surgical robot applications in complex environments.
基金023 Zhejiang Provincial Department of Education General Project:Research on an interdisciplinary teaching model to promote the development of computational thinking in the context of the new curriculum standards[Grant NO:Y202351596]Key Project of Zhejiang Provincial Education Science Planning:Research on an interdisciplinary teaching model to promote students’computational thinking from multiple analytical perspectives[Grant NO:2025SB103].
文摘This study constructs a reflective feedback model based on a pedagogical agent(PA)and explores its impact on students’problem-solving ability and cognitive load.A quasi-experimental design was used in the study,with 84 students from a middle school selected as the research subjects(44 in the experimental group and 40 in the control group).The experimental group used the reflective feedback model,while the control group used the factual feedback model.The results show that,compared with factual feedback,the reflective feedback model based on the pedagogical agent significantly improves students’problem-solving ability,especially at the action and thinking levels.In addition,this model effectively reduces students’cognitive load,especially in terms of internal and external load.
基金Key Research project of Gansu Province of China(22YF7NA108)National Natural Science Foundation of China(31860549)+1 种基金Industry Supporting Project from Education Department of Gansu Province(2023CYZC-49)Major Science and Technology project of Gansu province(24ZDNA006)。
文摘【Objectives】Si and microbial application could relieve the crop replanting problems(CRPs).We further studied the change of key microorganisms that are related to the beneficial effects,aiming at provide reference for the manufacture and application of both microbial agents and Si fertilizer in food lily production.【Methods】A field experiment was conducted over a three-year period,from March 2019 to March 2022.The experimental field had been continuously cultivated with lily for 9 years.Three treatments were established:silicon fertilizer(SF),microbial agents(“Special 8^(TM)”,MF),and combined application of silicon fertilizer and microbial agents(SMF).A control group with blank soil(CK)was also included.At seedling stage of Lanzhou lilies in 2020 and 2021,the shoot and bulb dry weight,and the plant height and stem diameter of Lanzhou lilies were investigated for calculation of seedling index.In July 2020,20 plants were selected in each plot,and root zone soils were sampled at a depth of 20 cm,10 cm away from the roots,and then mixed to form a composite sample.The soil available Si and organic matter content were analyzed,and the fungal community structure and some specific microbial groups in soils were determined with high-throughput sequencing of ITS.【Results】All the three treatments significantly enhanced the lily plant growth and the seedling index,compared to CK.Besides,SF and MF treatments increased the relative abundances(RA)and diversity of fungal communities,and altered the community structures.The RA of some specific groups were found to be significantly correlated with the seedling index and/or soil available Si.Of them,the RA of the genera Fusarium,Dactylonectria,Humicola,Stilbella,and the species Humicola_grisea showed a positive correlation,while that of the genera Mortierella,Stilbella,Holtermanniella,and the species Mortierella_fatshederae showed a negative correlation with seedling index.The genera Fusarium,Stilbella,the species Humicola_grisea,and Dactylonectria_estremocensis showed a positive correlation,while the genura Stilbella,and the species Mortierella fatshederae showed a negative correlation with available Si content.In the co-occurence network of top twenty fungal genera and top sixteen bacterial genera(RA>0.2%),Holtermanniella was the only genus that interacted with the bacteria and negatively correlated with bacterial genus Blastococcus.Holtermanniella was also the most densely connected genera,followed by the genus Fusarium,Didymella and Humicola.In addition,the genus Holtermanniella was the key species connecting fungal and bacterial community in soil.Fungal functional prediction revealed that SF,MF and SMF treatments decreased plant pathogens guilds and increased the beneficial guilds Ectomycorrhizal,plant saprophyte,leaf saprophyte,and arbuscular mycorrhizal compared to CK.【Conclusions】Combined application of silicon fertilizer and microbial agents can alleviate continuous replanting problems of Lanzhou lilies through restoring the fungal community diversity,and promoting plant residue depredation,thus reducing soil born disease incidence.The beneficial genus Humicola and its one species H.grisea acts as bioconversion,and the genus Acremonium acts as plant pathogen inhibitor.
基金supported by the King Abdullah University of Science and Technology(KAUST)。
文摘Seismic data denoising is a critical process usually applied at various stages of the seismic processing workflow,as our ability to mitigate noise in seismic data affects the quality of our subsequent analyses.However,finding an optimal balance between preserving seismic signals and effectively reducing seismic noise presents a substantial challenge.In this study,we introduce a multi-stage deep learning model,trained in a self-supervised manner,designed specifically to suppress seismic noise while minimizing signal leakage.This model operates as a patch-based approach,extracting overlapping patches from the noisy data and converting them into 1D vectors for input.It consists of two identical sub-networks,each configured differently.Inspired by the transformer architecture,each sub-network features an embedded block that comprises two fully connected layers,which are utilized for feature extraction from the input patches.After reshaping,a multi-head attention module enhances the model’s focus on significant features by assigning higher attention weights to them.The key difference between the two sub-networks lies in the number of neurons within their fully connected layers.The first sub-network serves as a strong denoiser with a small number of neurons,effectively attenuating seismic noise;in contrast,the second sub-network functions as a signal-add-back model,using a larger number of neurons to retrieve some of the signal that was not preserved in the output of the first sub-network.The proposed model produces two outputs,each corresponding to one of the sub-networks,and both sub-networks are optimized simultaneously using the noisy data as the label for both outputs.Evaluations conducted on both synthetic and field data demonstrate the model’s effectiveness in suppressing seismic noise with minimal signal leakage,outperforming some benchmark methods.
基金supported in part by the National Natural Science Foundation of China under Grants 62472434 and 62402171in part by the National Key Research and Development Program of China under Grant 2022YFF1203001+1 种基金in part by the Science and Technology Innovation Program of Hunan Province under Grant 2022RC3061in part by the Sci-Tech Innovation 2030 Agenda under Grant 2023ZD0508600.
文摘Computed Tomography(CT)reconstruction is essential inmedical imaging and other engineering fields.However,blurring of the projection during CT imaging can lead to artifacts in the reconstructed images.Projection blur combines factors such as larger ray sources,scattering and imaging system vibration.To address the problem,we propose DeblurTomo,a novel self-supervised learning-based deblurring and reconstruction algorithm that efficiently reconstructs sharp CT images from blurry input without needing external data and blur measurement.Specifically,we constructed a coordinate-based implicit neural representation reconstruction network,which can map the coordinates to the attenuation coefficient in the reconstructed space formore convenient ray representation.Then,wemodel the blur as aweighted sumof offset rays and design the RayCorrectionNetwork(RCN)andWeight ProposalNetwork(WPN)to fit these rays and their weights bymulti-view consistency and geometric information,thereby extending 2D deblurring to 3D space.In the training phase,we use the blurry input as the supervision signal to optimize the reconstruction network,the RCN,and the WPN simultaneously.Extensive experiments on the widely used synthetic dataset show that DeblurTomo performs superiorly on the limited-angle and sparse-view in the simulated blurred scenarios.Further experiments on real datasets demonstrate the superiority of our method in practical scenarios.
基金supported by the National Natural Science Foundation of China(42374134,42304125,U20B6005)the Science and Technology Commission of Shanghai Municipality(23JC1400502)the Fundamental Research Funds for the Central Universities.
文摘Blended acquisition offers efficiency improvements over conventional seismic data acquisition, at the cost of introducing blending noise effects. Besides, seismic data often suffers from irregularly missing shots caused by artificial or natural effects during blended acquisition. Therefore, blending noise attenuation and missing shots reconstruction are essential for providing high-quality seismic data for further seismic processing and interpretation. The iterative shrinkage thresholding algorithm can help obtain deblended data based on sparsity assumptions of complete unblended data, and it characterizes seismic data linearly. Supervised learning algorithms can effectively capture the nonlinear relationship between incomplete pseudo-deblended data and complete unblended data. However, the dependence on complete unblended labels limits their practicality in field applications. Consequently, a self-supervised algorithm is presented for simultaneous deblending and interpolation of incomplete blended data, which minimizes the difference between simulated and observed incomplete pseudo-deblended data. The used blind-trace U-Net (BTU-Net) prevents identity mapping during complete unblended data estimation. Furthermore, a multistep process with blending noise simulation-subtraction and missing traces reconstruction-insertion is used in each step to improve the deblending and interpolation performance. Experiments with synthetic and field incomplete blended data demonstrate the effectiveness of the multistep self-supervised BTU-Net algorithm.
文摘Nanolipid carriers and traditional emulsion containing chemical sunscreens were prepared using emulsification combined with ultrasonic technology.The nanolipid carriers showed superior performance in sunscreen encapsulation,slow release and skin impermeability,and provided an excellent nanolipid slow-release encapsulation system for sunscreens.As observed by transmission electron microscopy,the nanolipid carriers were spherical shape,with smooth surface and uniform distribution,and the particle sizes were mainly concentrated in the range of 230 to 250 nm without agglomeration.The nanolipid carriers significantly improved the sunscreen performance through the synergistic effect of scattering and chemical absorption,and showed better UV stability than traditional sunscreen,indicating their photoprotective function.In vitro release experiments showed that the nano-lipidic carriers exhibited better release control when loaded with octyl methoxycinnamate(OMC)and butylmethoxydibenzoylmethane(BDFM)sunscreens than traditional traditional emulsions,with the cumulative release rate of OMC in the nano-lipidic carriers decreasing by 17.17% to 30.24% within 12 hours,and that of BDFM decreasing by 26.67% to 44.67%.26.67% to 44.16%.The results of the in vitro permeation experiment further confirmed that the nanolipid carriers could effectively encapsulate the sunscreens and prevent them from penetrating the skin barrier,thus reducing the skin irritation.Compared with traditional traditional emulsion,the cumulative penetration of OMC in nanostructured lipid carriers was 2.24μg/cm^(2)in 4 hours,while the cumulative penetration was reduced by 68.05%.The cumulative penetration of BDFM in the nanostructured lipid carrier was 3.24μg/cm^(2),with a 64.04%reduction in cumulative penetration.
基金Supported by National Undergraduate Training Programs for Innovation and Entrepreneurship(202510580009)Special Project for Promoting the Coordinated Development of Urban and Rural Areas and Regions by Introducing Scientific and Technological Achievements of Guangdong Province into Counties and Towns(2025B0202010051)Project of High-quality Development in Hundred Counties,Thousands Towns and Ten Thousand Villages of Guangdong Provincial Department of Science and Technology:Key Dispatch Project for Rural Science and Technology Commissioners(KTP20240704).
文摘Given that the citrus psyllid is the primary vector of citrus Huanglongbing(HLB),there is an urgent need to control this pest to mitigate the spread of the disease.This paper reviews the current research on two predominant control strategies:chemical control and biological control agents,in managing the citrus psyllid.It emphasizes the mechanisms of action,efficacy,and application advancements of these control methods.Finally,the paper analyzes the principal challenges associated with the sustainable management of citrus psyllids and offers perspectives for future research.
基金supported by the Ministry of Education and Science of the Republic of North Macedonia through the project“Utilizing AI and National Large Language Models to Advance Macedonian Language Capabilties”。
文摘Artificial intelligence(AI)is reshaping financial systems and services,as intelligent AI agents increasingly form the foundation of autonomous,goal-driven systems capable of reasoning,learning,and action.This review synthesizes recent research and developments in the application of AI agents across core financial domains.Specifically,it covers the deployment of agent-based AI in algorithmic trading,fraud detection,credit risk assessment,roboadvisory,and regulatory compliance(RegTech).The review focuses on advanced agent-based methodologies,including reinforcement learning,multi-agent systems,and autonomous decision-making frameworks,particularly those leveraging large language models(LLMs),contrasting these with traditional AI or purely statistical models.Our primary goals are to consolidate current knowledge,identify significant trends and architectural approaches,review the practical efficiency and impact of current applications,and delineate key challenges and promising future research directions.The increasing sophistication of AI agents offers unprecedented opportunities for innovation in finance,yet presents complex technical,ethical,and regulatory challenges that demand careful consideration and proactive strategies.This review aims to provide a comprehensive understanding of this rapidly evolving landscape,highlighting the role of agent-based AI in the ongoing transformation of the financial industry,and is intended to serve financial institutions,regulators,investors,analysts,researchers,and other key stakeholders in the financial ecosystem.
基金supported by the National Natural Science Foundation of China(62276092,62303167)the Postdoctoral Fellowship Program(Grade C)of China Postdoctoral Science Foundation(GZC20230707)+3 种基金the Key Science and Technology Program of Henan Province,China(242102211051,242102211042,212102310084)Key Scientiffc Research Projects of Colleges and Universities in Henan Province,China(25A520009)the China Postdoctoral Science Foundation(2024M760808)the Henan Province medical science and technology research plan joint construction project(LHGJ2024069).
文摘Feature fusion is an important technique in medical image classification that can improve diagnostic accuracy by integrating complementary information from multiple sources.Recently,Deep Learning(DL)has been widely used in pulmonary disease diagnosis,such as pneumonia and tuberculosis.However,traditional feature fusion methods often suffer from feature disparity,information loss,redundancy,and increased complexity,hindering the further extension of DL algorithms.To solve this problem,we propose a Graph-Convolution Fusion Network with Self-Supervised Feature Alignment(Self-FAGCFN)to address the limitations of traditional feature fusion methods in deep learning-based medical image classification for respiratory diseases such as pneumonia and tuberculosis.The network integrates Convolutional Neural Networks(CNNs)for robust feature extraction from two-dimensional grid structures and Graph Convolutional Networks(GCNs)within a Graph Neural Network branch to capture features based on graph structure,focusing on significant node representations.Additionally,an Attention-Embedding Ensemble Block is included to capture critical features from GCN outputs.To ensure effective feature alignment between pre-and post-fusion stages,we introduce a feature alignment loss that minimizes disparities.Moreover,to address the limitations of proposed methods,such as inappropriate centroid discrepancies during feature alignment and class imbalance in the dataset,we develop a Feature-Centroid Fusion(FCF)strategy and a Multi-Level Feature-Centroid Update(MLFCU)algorithm,respectively.Extensive experiments on public datasets LungVision and Chest-Xray demonstrate that the Self-FAGCFN model significantly outperforms existing methods in diagnosing pneumonia and tuberculosis,highlighting its potential for practical medical applications.
基金supported in part by the National Natural Science Foundation of China under Grants 62071345。
文摘Self-supervised monocular depth estimation has emerged as a major research focus in recent years,primarily due to the elimination of ground-truth depth dependence.However,the prevailing architectures in this domain suffer from inherent limitations:existing pose network branches infer camera ego-motion exclusively under static-scene and Lambertian-surface assumptions.These assumptions are often violated in real-world scenarios due to dynamic objects,non-Lambertian reflectance,and unstructured background elements,leading to pervasive artifacts such as depth discontinuities(“holes”),structural collapse,and ambiguous reconstruction.To address these challenges,we propose a novel framework that integrates scene dynamic pose estimation into the conventional self-supervised depth network,enhancing its ability to model complex scene dynamics.Our contributions are threefold:(1)a pixel-wise dynamic pose estimation module that jointly resolves the pose transformations of moving objects and localized scene perturbations;(2)a physically-informed loss function that couples dynamic pose and depth predictions,designed to mitigate depth errors arising from high-speed distant objects and geometrically inconsistent motion profiles;(3)an efficient SE(3)transformation parameterization that streamlines network complexity and temporal pre-processing.Extensive experiments on the KITTI and NYU-V2 benchmarks show that our framework achieves state-of-the-art performance in both quantitative metrics and qualitative visual fidelity,significantly improving the robustness and generalization of monocular depth estimation under dynamic conditions.
基金supported by the Deputyship for Research&Innovation,Ministry of Education in Saudi Arabia(Project No.MoE-IF-UJ-R2-22-04220773-1).
文摘Domain randomization is a widely adopted technique in deep reinforcement learning(DRL)to improve agent generalization by exposing policies to diverse environmental conditions.This paper investigates the impact of different reset strategies,normal,non-randomized,and randomized,on agent performance using the Deep Deterministic Policy Gradient(DDPG)and Twin Delayed DDPG(TD3)algorithms within the CarRacing-v2 environment.Two experimental setups were conducted:an extended training regime with DDPG for 1000 steps per episode across 1000 episodes,and a fast execution setup comparing DDPG and TD3 for 30 episodes with 50 steps per episode under constrained computational resources.A step-based reward scaling mechanism was applied under the randomized reset condition to promote broader state exploration.Experimental results showthat randomized resets significantly enhance learning efficiency and generalization,with DDPG demonstrating superior performance across all reset strategies.In particular,DDPG combined with randomized resets achieves the highest smoothed rewards(reaching approximately 15),best stability,and fastest convergence.These differences are statistically significant,as confirmed by t-tests:DDPG outperforms TD3 under randomized(t=−101.91,p<0.0001),normal(t=−21.59,p<0.0001),and non-randomized(t=−62.46,p<0.0001)reset conditions.The findings underscore the critical role of reset strategy and reward shaping in enhancing the robustness and adaptability of DRL agents in continuous control tasks,particularly in environments where computational efficiency and training stability are crucial.
文摘Clinical pharmacy is on the cusp of exponential change powered by artificial intelligence agents,automation,data analytics,and robotics.Blockchain will enhance data integrity and transparency,and Augmented and Virtual Reality technologies will revolutionise training,patient education,and simulation-based care planning.Clinical pharmacists need to be ready and upskill to prepare for emerging technologies.The ethical,regulatory,and educational frameworks surrounding artificial intelligence and precision medicine will require constant attention,but the potential benefits for patient outcomes are unprecedented.Clinical pharmacists are in a prime position to design a new era in precision medicine,where technology works hand in hand with humans to transform healthcare.
基金supported in part by the National Natural Science Foundation of China under Grant Nos.62472398 and U2336206.
文摘Steganography is a technology that discreetly embeds secret information into the redundant space of a carrier,enabling covert communication.As generative models continue to advance,steganography has evolved from traditional modification-based methods to generative steganography,which includes generative linguistic and image based forms.However,while large model agents are rapidly emerging,no method has exploited the stable redundant space in their action processes.Inspired by this insightful observation,we propose a steganographic method leveraging large model agents,employing their actions to conceal secret messages.In this paper,we introduce StegoAgent,a generative steganography framework based on graphical user interface(GUI)agents,which effectively demonstrates the remarkable potential and effectiveness of large model agent-based steganographic methods.
基金supported by the Scientific Research Project funded by the Qingdao Postdoctoral Science Foundation(No.QDBSH20230102075)the China Postdoctoral Science Foundation(No.2023M733337)the National Natural Science Foundation of China(No.U2141251).
文摘All maritime industries are plagued by marine biofouling pollution,which causes large economic and environmental costs.Therefore,there is an urgent need for ecofriendly alternatives that can effectively reduce the negative consequences of biofouling pollution.This study aimed to produce novel capsaicin-inspired amide derivatives(CIADs)with multifunctional antifouling features by introducing amide compounds to aromatic compounds via a Friedel-Crafts alkylation reaction.The structure of the CIADs was characterized using FTIR,1H NMR,13C NMR,and HRMS,and the comprehensive antifouling capacity was determined by thermal stability,anti-ultraviolet,antibacterial,anti-algal,and marine field experiments.CIADs showed good thermal stability and did not show obvious weight loss before 226°C.2,4-dihydroxy-3,5-diphenylimidemet-hylbenzophenone(DDB)had an excellent ultraviolet absorption effect,which was even better than that of 2-hydroxy-4-(octyloxy)benzophenone.The antibacterial and anti-algal rates of N-(2,4-dimethyl-3-chloro-5-benzamide-methyl-6-hydroxybenzyl)benzamide(NDCBHB)were more than 99.5%and 64.0%,respectively,and the surface of antifouling coating with NDCBHB(NDCBHB-AC)was covered with only a small amount of sludge and biofilm,its antifouling effect was better than that of chlorothalonil.The above work provides a reference for preparing green and multifunctional antifouling agents.
基金funded by theNational Science and TechnologyCouncil(NSTC),Taiwan,under grant numbers NSTC 112-2634-F-019-001 and NSTC 113-2634-F-A49-007.
文摘Few-shot learning has emerged as a crucial technique for coral species classification,addressing the challenge of limited labeled data in underwater environments.This study introduces an optimized few-shot learning model that enhances classification accuracy while minimizing reliance on extensive data collection.The proposed model integrates a hybrid similarity measure combining Euclidean distance and cosine similarity,effectively capturing both feature magnitude and directional relationships.This approach achieves a notable accuracy of 71.8%under a 5-way 5-shot evaluation,outperforming state-of-the-art models such as Prototypical Networks,FEAT,and ESPT by up to 10%.Notably,the model demonstrates high precision in classifying Siderastreidae(87.52%)and Fungiidae(88.95%),underscoring its effectiveness in distinguishing subtle morphological differences.To further enhance performance,we incorporate a self-supervised learning mechanism based on contrastive learning,enabling the model to extract robust representations by leveraging local structural patterns in corals.This enhancement significantly improves classification accuracy,particularly for species with high intra-class variation,leading to an overall accuracy of 76.52%under a 5-way 10-shot evaluation.Additionally,the model exploits the repetitive structures inherent in corals,introducing a local feature aggregation strategy that refines classification through spatial information integration.Beyond its technical contributions,this study presents a scalable and efficient approach for automated coral reef monitoring,reducing annotation costs while maintaining high classification accuracy.By improving few-shot learning performance in underwater environments,our model enhances monitoring accuracy by up to 15%compared to traditional methods,offering a practical solution for large-scale coral conservation efforts.
基金supported by the specialized fund project for the fundamental research operation of central-level public welfare scientific research institutes,titled“Research on the International Standards System Construction and Updates in the Field of Fire Protection(Project No.2023SJ09)”.
文摘This paper discusses the importance of standards in the fire extinguishing agent industry,and highlights the vital role of the standards in promoting technological innovation.China’s standards for fire extinguishing agent products have evolved significantly,aligning with industrial development,market demands,regulatory requirements,to respond to the great impact of international competition in the industry.The paper analyzes the current state of China’s standards,including their composition and integration with industry growth,green development strategies,and international harmonization.Future development strategies for the standards framework should focus on valid period estimation,fire test model development,and raw material selection guidelines.By implementing these strategies,China’s fire protection industry can enhance product quality,contribute to public safety,and maintain a competitive edge in the global market.
