Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay di...Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.展开更多
Pre-stack seismic inversion is an effective way to investigate the characteristics of hydrocarbon-bearing reservoirs.Multi-parameter application is the key to identifying reservoir lithology and fluid in pre-stack inv...Pre-stack seismic inversion is an effective way to investigate the characteristics of hydrocarbon-bearing reservoirs.Multi-parameter application is the key to identifying reservoir lithology and fluid in pre-stack inversion.However,multi-parameter inversion may bring coupling effects on the parameters and destabilize the inversion.In addition,the lateral recognition accuracy of geological structures receives great attention.To address these challenges,a multi-task learning network considering the angle-gather difference is proposed in this work.The deep learning network is usually assumed as a black box and it is unclear what it can learn.However,the introduction of angle-gather difference can force the deep learning network to focus on the lateral differences,thus improving the lateral accuracy of the prediction profile.The proposed deep learning network includes input and output blocks.First,angle gathers and the angle-gather difference are fed into two separate input blocks with Res Net architecture and Unet architecture,respectively.Then,three elastic parameters,including P-and S-wave velocities and density,are simultaneously predicted based on the idea of multi-task learning by using three separate output blocks with the same convolutional network layers.Experimental and field data tests demonstrate the effectiveness of the proposed method in improving the prediction accuracy of seismic elastic parameters.展开更多
Cooperative multi-agent reinforcement learning(MARL)is a key technology for enabling cooperation in complex multi-agent systems.It has achieved remarkable progress in areas such as gaming,autonomous driving,and multi-...Cooperative multi-agent reinforcement learning(MARL)is a key technology for enabling cooperation in complex multi-agent systems.It has achieved remarkable progress in areas such as gaming,autonomous driving,and multi-robot control.Empowering cooperative MARL with multi-task decision-making capabilities is expected to further broaden its application scope.In multi-task scenarios,cooperative MARL algorithms need to address 3 types of multi-task problems:reward-related multi-task,arising from different reward functions;multi-domain multi-task,caused by differences in state and action spaces,state transition functions;and scalability-related multi-task,resulting from the dynamic variation in the number of agents.Most existing studies focus on scalability-related multitask problems.However,with the increasing integration between large language models(LLMs)and multi-agent systems,a growing number of LLM-based multi-agent systems have emerged,enabling more complex multi-task cooperation.This paper provides a comprehensive review of the latest advances in this field.By combining multi-task reinforcement learning with cooperative MARL,we categorize and analyze the 3 major types of multi-task problems under multi-agent settings,offering more fine-grained classifications and summarizing key insights for each.In addition,we summarize commonly used benchmarks and discuss future directions of research in this area,which hold promise for further enhancing the multi-task cooperation capabilities of multi-agent systems and expanding their practical applications in the real world.展开更多
The accurate prediction of drug absorption,distribution,metabolism,excretion,and toxicity(ADMET)properties represents a crucial step in early drug development for reducing failure risk.Current deep learning approaches...The accurate prediction of drug absorption,distribution,metabolism,excretion,and toxicity(ADMET)properties represents a crucial step in early drug development for reducing failure risk.Current deep learning approaches face challenges with data sparsity and information loss due to single-molecule representation limitations and isolated predictive tasks.This research proposes molecular properties prediction with parallel-view and collaborative learning(MolP-PC),a multi-view fusion and multi-task deep learning framework that integrates 1D molecular fingerprints(MFs),2D molecular graphs,and 3D geometric representations,incorporating an attention-gated fusion mechanism and multi-task adaptive learning strategy for precise ADMET property predictions.Experimental results demonstrate that MolP-PC achieves optimal performance in 27 of 54 tasks,with its multi-task learning(MTL)mechanism significantly enhancing predictive performance on small-scale datasets and surpassing single-task models in 41 of 54 tasks.Additional ablation studies and interpretability analyses confirm the significance of multi-view fusion in capturing multi-dimensional molecular information and enhancing model generalization.A case study examining the anticancer compound Oroxylin A demonstrates MolP-PC’s effective generalization in predicting key pharmacokinetic parameters such as half-life(T0.5)and clearance(CL),indicating its practical utility in drug modeling.However,the model exhibits a tendency to underestimate volume of distribution(VD),indicating potential for improvement in analyzing compounds with high tissue distribution.This study presents an efficient and interpretable approach for ADMET property prediction,establishing a novel framework for molecular optimization and risk assessment in drug development.展开更多
As a key node of modern transportation network,the informationization management of road tunnels is crucial to ensure the operation safety and traffic efficiency.However,the existing tunnel vehicle modeling methods ge...As a key node of modern transportation network,the informationization management of road tunnels is crucial to ensure the operation safety and traffic efficiency.However,the existing tunnel vehicle modeling methods generally have problems such as insufficient 3D scene description capability and low dynamic update efficiency,which are difficult to meet the demand of real-time accurate management.For this reason,this paper proposes a vehicle twin modeling method for road tunnels.This approach starts from the actual management needs,and supports multi-level dynamic modeling from vehicle type,size to color by constructing a vehicle model library that can be flexibly invoked;at the same time,semantic constraint rules with geometric layout,behavioral attributes,and spatial relationships are designed to ensure that the virtual model matches with the real model with a high degree of similarity;ultimately,the prototype system is constructed and the case region is selected for the case study,and the dynamic vehicle status in the tunnel is realized by integrating real-time monitoring data with semantic constraints for precise virtual-real mapping.Finally,the prototype system is constructed and case experiments are conducted in selected case areas,which are combined with real-time monitoring data to realize dynamic updating and three-dimensional visualization of vehicle states in tunnels.The experiments show that the proposed method can run smoothly with an average rendering efficiency of 17.70 ms while guaranteeing the modeling accuracy(composite similarity of 0.867),which significantly improves the real-time and intuitive tunnel management.The research results provide reliable technical support for intelligent operation and emergency response of road tunnels,and offer new ideas for digital twin modeling of complex scenes.展开更多
Learning from demonstration is widely regarded as a promising paradigm for robots to acquire diverse skills.Other than the artificial learning from observation-action pairs for machines,humans can learn to imitate in ...Learning from demonstration is widely regarded as a promising paradigm for robots to acquire diverse skills.Other than the artificial learning from observation-action pairs for machines,humans can learn to imitate in a more versatile and effective manner:acquiring skills through mere“observation”.Video to Command task is widely perceived as a promising approach for task-based learning,which yet faces two key challenges:(1)High redundancy and low frame rate of fine-grained action sequences make it difficult to manipulate objects robustly and accurately.(2)Video to Command models often prioritize accuracy and richness of output commands over physical capabilities,leading to impractical or unsafe instructions for robots.This article presents a novel Video to Command framework that employs multiple data associations and physical constraints.First,we introduce an object-level appearancecontrasting multiple data association strategy to effectively associate manipulated objects in visually complex environments,capturing dynamic changes in video content.Then,we propose a multi-task Video to Command model that utilizes object-level video content changes to compile expert demonstrations into manipulation commands.Finally,a multi-task hybrid loss function is proposed to train a Video to Command model that adheres to the constraints of the physical world and manipulation tasks.Our method achieved over 10%on BLEU_N,METEOR,ROUGE_L,and CIDEr compared to the up-to-date methods.The dual-arm robot prototype was established to demonstrate the whole process of learning from an expert demonstration of multiple skills and then executing the tasks by a robot.展开更多
Tropical cyclones(TCs)are one of the most serious types of natural disasters,and accurate TC activity predictions are key to disaster prevention and mitigation.Recently,TC track predictions have made significant progr...Tropical cyclones(TCs)are one of the most serious types of natural disasters,and accurate TC activity predictions are key to disaster prevention and mitigation.Recently,TC track predictions have made significant progress,but the ability to predict their intensity is obviously lagging behind.At present,research on TC intensity prediction takes atmospheric reanalysis data as the research object and mines the relationship between TC-related environmental factors and intensity through deep learning.However,reanalysis data are non-real-time in nature,which does not meet the requirements for operational forecasting applications.Therefore,a TC intensity prediction model named TC-Rolling is proposed,which can simultaneously extract the degree of symmetry for strong TC convective cloud and convection intensity,and fuse the deviation-angle variance with satellite images to construct the correlation between TC convection structure and intensity.For TCs'complex dynamic processes,a convolutional neural network(CNN)is used to learn their temporal and spatial features.For real-time intensity estimation,multi-task learning acts as an implicit time-series enhancement.The model is designed with a rolling strategy that aims to moderate the long-term dependent decay problem and improve accuracy for short-term intensity predictions.Since multiple tasks are correlated,the loss function of 12 h and 24 h are corrected.After testing on a sample of TCs in the Northwest Pacific,with a 4.48 kt root-mean-square error(RMSE)of 6 h intensity prediction,5.78 kt for 12 h,and 13.94 kt for 24 h,TC records from official agencies are used to assess the validity of TC-Rolling.展开更多
Predicting the health status of stroke patients at different stages of the disease is a critical clinical task.The onset and development of stroke are affected by an array of factors,encompassing genetic predispositio...Predicting the health status of stroke patients at different stages of the disease is a critical clinical task.The onset and development of stroke are affected by an array of factors,encompassing genetic predisposition,environmental exposure,unhealthy lifestyle habits,and existing medical conditions.Although existing machine learning-based methods for predicting stroke patients’health status have made significant progress,limitations remain in terms of prediction accuracy,model explainability,and system optimization.This paper proposes a multi-task learning approach based on Explainable Artificial Intelligence(XAI)for predicting the health status of stroke patients.First,we design a comprehensive multi-task learning framework that utilizes the task correlation of predicting various health status indicators in patients,enabling the parallel prediction of multiple health indicators.Second,we develop a multi-task Area Under Curve(AUC)optimization algorithm based on adaptive low-rank representation,which removes irrelevant information from the model structure to enhance the performance of multi-task AUC optimization.Additionally,the model’s explainability is analyzed through the stability analysis of SHAP values.Experimental results demonstrate that our approach outperforms comparison algorithms in key prognostic metrics F1 score and Efficiency.展开更多
Traditional deconvolution methods based on single-channel inversion do not consider the spatial structural relation between channels,and hence,they yield high-resolution results with the existing transverse inconsiste...Traditional deconvolution methods based on single-channel inversion do not consider the spatial structural relation between channels,and hence,they yield high-resolution results with the existing transverse inconsistency or discontinuity.Therefore,in this study,the local dip angle was used to obtain the structural information and construct the spatial structurally constraint operator.This operator is then introduced into multichannel deconvolution as a regularization operator to improve the resolution and maintain the transverse continuity of seismic data.Model tests and actual seismic data processing have demonstrated the effectiveness and practicability of this method.展开更多
This paper begins with a discussion of the trust issues that agricultural supply chain finance faces.It then examines the constraints of using blockchain technology to enhance trust in agricultural supply chain financ...This paper begins with a discussion of the trust issues that agricultural supply chain finance faces.It then examines the constraints of using blockchain technology to enhance trust in agricultural supply chain finance in accordance with the technological and institutional logic of combining blockchain with supply chains.This study then proposes the creation of an agricultural“blockchain+supply chain”information service platform and a financing trust mechanism that can effectively ensure the authenticity of the initial information input on the blockchain,consistency between on-chain transaction data and off-chain physical transactions,the controllability of risks in the set up and execution of smart contracts,and the removal of information constraints,resource allocation constraints,and institutional constraints in the agricultural supply chain financing.This aims to improve the efficiency of financing in agricultural supply chains and contribute to the industrial development of rural areas and rural revitalization.展开更多
As the group-buying model shows significant progress in attracting new users,enhancing user engagement,and increasing platform profitability,providing personalized recommendations for group-buying users has emerged as...As the group-buying model shows significant progress in attracting new users,enhancing user engagement,and increasing platform profitability,providing personalized recommendations for group-buying users has emerged as a new challenge in the field of recommendation systems.This paper introduces a group-buying recommendation model based on multi-head attention mechanisms and multi-task learning,termed the Multi-head Attention Mechanisms and Multi-task Learning Group-Buying Recommendation(MAMGBR)model,specifically designed to optimize group-buying recommendations on e-commerce platforms.The core dataset of this study comes from the Chinese maternal and infant e-commerce platform“Beibei,”encompassing approximately 430,000 successful groupbuying actions and over 120,000 users.Themodel focuses on twomain tasks:recommending items for group organizers(Task Ⅰ)and recommending participants for a given group-buying event(Task Ⅱ).In model evaluation,MAMGBR achieves an MRR@10 of 0.7696 for Task I,marking a 20.23%improvement over baseline models.Furthermore,in Task II,where complex interaction patterns prevail,MAMGBR utilizes auxiliary loss functions to effectively model the multifaceted roles of users,items,and participants,leading to a 24.08%increase in MRR@100 under a 1:99 sample ratio.Experimental results show that compared to benchmark models,such as NGCF and EATNN,MAMGBR’s integration ofmulti-head attentionmechanisms,expert networks,and gating mechanisms enables more accurate modeling of user preferences and social associations within group-buying scenarios,significantly enhancing recommendation accuracy and platform group-buying success rates.展开更多
Aerosol optical depth(AOD)and fine particulate matter with a diameter of less than or equal to 2.5μm(PM_(2.5))play crucial roles in air quality,human health,and climate change.However,the complex correlation of AOD–...Aerosol optical depth(AOD)and fine particulate matter with a diameter of less than or equal to 2.5μm(PM_(2.5))play crucial roles in air quality,human health,and climate change.However,the complex correlation of AOD–PM_(2.5)and the limitations of existing algorithms pose a significant challenge in realizing the accurate joint retrieval of these two parameters at the same location.On this point,a multi-task learning(MTL)model,which enables the joint retrieval of PM_(2.5)concentration and AOD,is proposed and applied on the top-of-the-atmosphere reflectance data gathered by the Fengyun-4A Advanced Geosynchronous Radiation Imager(FY-4A AGRI),and compared to that of two single-task learning models—namely,Random Forest(RF)and Deep Neural Network(DNN).Specifically,MTL achieves a coefficient of determination(R^(2))of 0.88 and a root-mean-square error(RMSE)of 0.10 in AOD retrieval.In comparison to RF,the R^(2)increases by 0.04,the RMSE decreases by 0.02,and the percentage of retrieval results falling within the expected error range(Within-EE)rises by 5.55%.The R^(2)and RMSE of PM_(2.5)retrieval by MTL are 0.84 and 13.76μg m~(-3)respectively.Compared with RF,the R^(2)increases by 0.06,the RMSE decreases by 4.55μg m~(-3),and the Within-EE increases by 7.28%.Additionally,compared to DNN,MTL shows an increase of 0.01 in R^(2)and a decrease of 0.02 in RMSE in AOD retrieval,with a corresponding increase of 2.89%in Within-EE.For PM_(2.5)retrieval,MTL exhibits an increase of 0.05 in R^(2),a decrease of 1.76μg m~(-3)in RMSE,and an increase of 6.83%in Within-EE.The evaluation suggests that MTL is able to provide simultaneously improved AOD and PM_(2.5)retrievals,demonstrating a significant advantage in efficiently capturing the spatial distribution of PM_(2.5)concentration and AOD.展开更多
Accurate short-term forecast of offshore wind fields is still challenging for numerical weather prediction models.Based on three years of 48-hour forecast data from the European Centre for Medium-Range Weather Forecas...Accurate short-term forecast of offshore wind fields is still challenging for numerical weather prediction models.Based on three years of 48-hour forecast data from the European Centre for Medium-Range Weather Forecasts Integrated Forecasting System global model(ECMWF-IFS)over 14 offshore weather stations along the coast of Shandong Province,this study introduces a multi-task learning(MTL)model(TabNet-MTL),which significantly improves the forecast bias of near-surface wind direction and speed simultaneously.TabNet-MTL adopts the feature engineering method,utilizes mean square error as the loss function,and employs the 5-fold cross validation method to ensure the generalization ability of the trained model.It demonstrates superior skills in wind field correction across different forecast lead times over all stations compared to its single-task version(TabNet-STL)and three other popular single-task learning models(Random Forest,LightGBM,and XGBoost).Results show that it significantly reduces root mean square error of the ECMWF-IFS wind speed forecast from 2.20 to 1.25 m s−1,and increases the forecast accuracy of wind direction from 50%to 65%.As an explainable deep learning model,the weather stations and long-term temporal statistics of near-surface wind speed are identified as the most influential variables for TabNet-MTL in constructing its feature engineering.展开更多
Staple crops are the cornerstone of the food supply but are frequently threatened by plant diseases.Effective disease management,including disease identification and severity assessment,helps to better address these c...Staple crops are the cornerstone of the food supply but are frequently threatened by plant diseases.Effective disease management,including disease identification and severity assessment,helps to better address these challenges.Currently,methods for disease severity assessment typically rely on calculating the area proportion of disease segmentation regions or using classification networks for severity assessment.However,these methods require large amounts of labeled data and fail to quantify lesion proportions when using classification networks,leading to inaccurate evaluations.To address these issues,we propose an automated framework for disease severity assessment that combines multi-task learning and knowledge-driven large-model segmentation techniques.This framework includes an image information processor,a lesion and leaf segmentation module,and a disease severity assessment module.First,the image information processor utilizes a multi-task learning strategy to analyze input images comprehensively,ensuring a deep understanding of disease characteristics.Second,the lesion and leaf segmentation module employ prompt-driven large-model technology to accurately segment diseased areas and entire leaves,providing detailed visual analysis.Finally,the disease severity assessment module objectively evaluates the severity of the disease based on professional grading standards by calculating lesion area proportions.Additionally,we have developed a comprehensive database of diseased leaf images from major crops,including several task-specific datasets.Experimental results demonstrate that our framework can accurately identify and assess the types and severity of crop diseases,even without extensive labeled data.Codes and data are available at http://dkp-ads.samlab.cn/.展开更多
Satellite communication technology has emerged as a key solution to address the challenges of data transmission in remote areas.By overcoming the limitations of traditional terrestrial communication networks,it enable...Satellite communication technology has emerged as a key solution to address the challenges of data transmission in remote areas.By overcoming the limitations of traditional terrestrial communication networks,it enables long-distance data transmission anytime and anywhere,ensuring the timely and accurate delivery of water level data,which is particularly crucial for fishway water level monitoring.To enhance the effectiveness of fishway water level monitoring,this study proposes a multi-task learning model,AS-SOMTF,designed for real-time and comprehensive prediction.The model integrates auxiliary sequences with primary input sequences to capture complex relationships and dependencies,thereby improving representational capacity.In addition,a novel timeseries embedding algorithm,AS-SOM,is introduced,which combines generative inference and pooling operations to optimize prediction efficiency for long sequences.This innovation not only ensures the timely transmission of water level data but also enhances the accuracy of real-time monitoring.Compared with traditional models such as Transformer and Long Short-Term Memory(LSTM)networks,the proposed model achieves improvements of 3.8%and 1.4%in prediction accuracy,respectively.These advancements provide more precise technical support for water level forecasting and resource management in the Diqing Tibetan Autonomous Prefecture of the Lancang River,contributing to ecosystem protection and improved operational safety.展开更多
Recent experiments have found that a liquid crystal elastomer(LCE)rod supported in the middle can rotate continuously under horizontal illumination due to the combined impacts of gravity and light-fueled lateral bend-...Recent experiments have found that a liquid crystal elastomer(LCE)rod supported in the middle can rotate continuously under horizontal illumination due to the combined impacts of gravity and light-fueled lateral bend-ing deformation.Similar to traditional gravity-driven systems,it is constrained by the direction of gravity and cannot be applied in microgravity environments.This study introduces a lateral constraint to a liquid crystal elastomer rod system,enabling self-rotation under lighting from any direction,including horizontal and vertical illumination.Through theoretical modeling,the results indicate that the system can steadily rotate under the combined impacts of lateral forces and vertical illumination.Factors like thermal energy flux,thermal conduc-tivity coefficient,the LCE rod length,contraction coefficient,and friction coefficient affect the angular velocity of the self-rotation.The numerical computations align closely with the experimental data.Our proposed steadily self-rotating system features a simple structure with constant self-rotation.It operates independently of gravity direction,making it an excellent choice for special environments,such as the microgravity conditions on the Moon.The lateral constraint strategy presented in this study offers a general approach to expanding the applica-tions of gravity-driven self-sustained motion,with promising potential,especially in microgravity settings,where its versatility under varying lighting conditions could yield valuable insights.展开更多
Constraint satisfaction problems(CSPs)are a class of problems that are ubiquitous in science and engineering.They feature a collection of constraints specified over subsets of variables.A CSP can be solved either dire...Constraint satisfaction problems(CSPs)are a class of problems that are ubiquitous in science and engineering.They feature a collection of constraints specified over subsets of variables.A CSP can be solved either directly or by reducing it to other problems.This paper introduces the Julia ecosystem for solving and analyzing CSPs with a focus on the programming practices.We introduce some important CSPs and show how these problems are reduced to each other.We also show how to transform CSPs into tensor networks,how to optimize the tensor network contraction orders,and how to extract the solution space properties by contracting the tensor networks with generic element types.Examples are given,which include computing the entropy constant,analyzing the overlap gap property,and the reduction between CSPs.展开更多
In machine vision,elliptical targets frequently appear within the camera's region of interest(ROI).Ellipse detection is essential for shape detection and geometric measurements in machine vision.However,existing e...In machine vision,elliptical targets frequently appear within the camera's region of interest(ROI).Ellipse detection is essential for shape detection and geometric measurements in machine vision.However,existing ellipse detection algorithms often face issues such as high computational complexity,strong dependence on initial conditions,sensitivity to noise,and lack of robustness to occlusions.In this paper,we propose a fast and robust ellipse detection method to address these challenges.This method first utilizes edge gradient and curvature information to segment the curve into circular arcs.Next,based on the convexity of the arcs,it divides them into different quadrants of the ellipse,groups and fits the arcs according to multiple geometric constraints at a low computational cost.Finally,it reduces the parameter space for hierarchical clustering and then segments the complete ellipse into several sectors for verification.We compare our method across seven datasets,including five public image datasets and two from industrial camera scenes.Experimental results show that our method achieves a precision ranging from 67.1%to 98.9%,a recall ranging from 48.1%to 92.9%,and an F-measure ranging from 58.0%to 95.8%.The average execution time per image ranges from 25 ms to 192 ms,demonstrating both high accuracy and efficiency.展开更多
Seasonal precipitation has always been a key focus of climate prediction.As a dynamic-statistical combined method,the existing observational constraint correction establishes a regression relationship between the nume...Seasonal precipitation has always been a key focus of climate prediction.As a dynamic-statistical combined method,the existing observational constraint correction establishes a regression relationship between the numerical model outputs and historical observations,which can partly predict seasonal precipitation.However,solving a nonlinear problem through linear regression is significantly biased.This study implements a nonlinear optimization of an existing observational constrained correction model using a Light Gradient Boosting Machine(LightGBM)machine learning algorithm based on output from the Beijing National Climate Center Climate System Model(BCC-CSM)and station observations to improve the prediction of summer precipitation in China.The model was trained using a rolling approach,and LightGBM outperformed Linear Regression(LR),Extreme Gradient Boosting(XGBoost),and Categorical Boosting(CatBoost).Using parameter tuning to optimize the machine learning model and predict future summer precipitation using eight different predictors in BCC-CSM,the mean Anomaly Correlation Coefficient(ACC)score in the 2019–22 summer precipitation predictions was 0.17,and the mean Prediction Score(PS)reached 74.The PS score was improved by 7.87%and 6.63%compared with the BCC-CSM and the linear observational constraint approach,respectively.The observational constraint correction prediction strategy with LightGBM significantly and stably improved the prediction of summer precipitation in China compared to the previous linear observational constraint solution,providing a reference for flood control and drought relief during the flood season(summer)in China.展开更多
Background As visual simultaneous localization and mapping(SLAM)is primarily based on the assumption of a static scene,the presence of dynamic objects in the frame causes problems such as a deterioration of system rob...Background As visual simultaneous localization and mapping(SLAM)is primarily based on the assumption of a static scene,the presence of dynamic objects in the frame causes problems such as a deterioration of system robustness and inaccurate position estimation.In this study,we propose a YGC-SLAM for indoor dynamic environments based on the ORB-SLAM2 framework combined with semantic and geometric constraints to improve the positioning accuracy and robustness of the system.Methods First,the recognition accuracy of YOLOv5 was improved by introducing the convolution block attention model and the improved EIOU loss function,whereby the prediction frame converges quickly for better detection.The improved YOLOv5 was then added to the tracking thread for dynamic target detection to eliminate dynamic points.Subsequently,multi-view geometric constraints were used for re-judging to further eliminate dynamic points while enabling more useful feature points to be retained and preventing the semantic approach from over-eliminating feature points,causing a failure of map building.The K-means clustering algorithm was used to accelerate this process and quickly calculate and determine the motion state of each cluster of pixel points.Finally,a strategy for drawing keyframes with de-redundancy was implemented to construct a clear 3D dense static point-cloud map.Results Through testing on TUM dataset and a real environment,the experimental results show that our algorithm reduces the absolute trajectory error by 98.22%and the relative trajectory error by 97.98%compared with the original ORBSLAM2,which is more accurate and has better real-time performance than similar algorithms,such as DynaSLAM and DS-SLAM.Conclusions The YGC-SLAM proposed in this study can effectively eliminate the adverse effects of dynamic objects,and the system can better complete positioning and map building tasks in complex environments.展开更多
文摘Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.
基金financially supported by the National Natural Science Foundation of China(Grant Nos.42130810,42204135,42174170,and 42074165)the Natural Science Foundation of Hunan Province(Grant No.2023JJ40716)。
文摘Pre-stack seismic inversion is an effective way to investigate the characteristics of hydrocarbon-bearing reservoirs.Multi-parameter application is the key to identifying reservoir lithology and fluid in pre-stack inversion.However,multi-parameter inversion may bring coupling effects on the parameters and destabilize the inversion.In addition,the lateral recognition accuracy of geological structures receives great attention.To address these challenges,a multi-task learning network considering the angle-gather difference is proposed in this work.The deep learning network is usually assumed as a black box and it is unclear what it can learn.However,the introduction of angle-gather difference can force the deep learning network to focus on the lateral differences,thus improving the lateral accuracy of the prediction profile.The proposed deep learning network includes input and output blocks.First,angle gathers and the angle-gather difference are fed into two separate input blocks with Res Net architecture and Unet architecture,respectively.Then,three elastic parameters,including P-and S-wave velocities and density,are simultaneously predicted based on the idea of multi-task learning by using three separate output blocks with the same convolutional network layers.Experimental and field data tests demonstrate the effectiveness of the proposed method in improving the prediction accuracy of seismic elastic parameters.
基金The National Natural Science Foundation of China(62136008,62293541)The Beijing Natural Science Foundation(4232056)The Beijing Nova Program(20240484514).
文摘Cooperative multi-agent reinforcement learning(MARL)is a key technology for enabling cooperation in complex multi-agent systems.It has achieved remarkable progress in areas such as gaming,autonomous driving,and multi-robot control.Empowering cooperative MARL with multi-task decision-making capabilities is expected to further broaden its application scope.In multi-task scenarios,cooperative MARL algorithms need to address 3 types of multi-task problems:reward-related multi-task,arising from different reward functions;multi-domain multi-task,caused by differences in state and action spaces,state transition functions;and scalability-related multi-task,resulting from the dynamic variation in the number of agents.Most existing studies focus on scalability-related multitask problems.However,with the increasing integration between large language models(LLMs)and multi-agent systems,a growing number of LLM-based multi-agent systems have emerged,enabling more complex multi-task cooperation.This paper provides a comprehensive review of the latest advances in this field.By combining multi-task reinforcement learning with cooperative MARL,we categorize and analyze the 3 major types of multi-task problems under multi-agent settings,offering more fine-grained classifications and summarizing key insights for each.In addition,we summarize commonly used benchmarks and discuss future directions of research in this area,which hold promise for further enhancing the multi-task cooperation capabilities of multi-agent systems and expanding their practical applications in the real world.
基金supported by the research on key technologies for monitoring and identifying drug abuse of anesthetic drugs and psychotropic drugs,and intervention for addiction(No.2023YFC3304200)the program of a study on the diagnosis of addiction to synthetic cannabinoids and methods of assessing the risk of abuse(No.2022YFC3300905)+1 种基金the program of Ab initio design and generation of AI models for small molecule ligands based on target structures(No.2022PE0AC03)ZHIJIANG LAB.
文摘The accurate prediction of drug absorption,distribution,metabolism,excretion,and toxicity(ADMET)properties represents a crucial step in early drug development for reducing failure risk.Current deep learning approaches face challenges with data sparsity and information loss due to single-molecule representation limitations and isolated predictive tasks.This research proposes molecular properties prediction with parallel-view and collaborative learning(MolP-PC),a multi-view fusion and multi-task deep learning framework that integrates 1D molecular fingerprints(MFs),2D molecular graphs,and 3D geometric representations,incorporating an attention-gated fusion mechanism and multi-task adaptive learning strategy for precise ADMET property predictions.Experimental results demonstrate that MolP-PC achieves optimal performance in 27 of 54 tasks,with its multi-task learning(MTL)mechanism significantly enhancing predictive performance on small-scale datasets and surpassing single-task models in 41 of 54 tasks.Additional ablation studies and interpretability analyses confirm the significance of multi-view fusion in capturing multi-dimensional molecular information and enhancing model generalization.A case study examining the anticancer compound Oroxylin A demonstrates MolP-PC’s effective generalization in predicting key pharmacokinetic parameters such as half-life(T0.5)and clearance(CL),indicating its practical utility in drug modeling.However,the model exhibits a tendency to underestimate volume of distribution(VD),indicating potential for improvement in analyzing compounds with high tissue distribution.This study presents an efficient and interpretable approach for ADMET property prediction,establishing a novel framework for molecular optimization and risk assessment in drug development.
基金National Natural Science Foundation of China(Nos.42301473,42271424,42171397)Chinese Postdoctoral Innovation Talents Support Program(No.BX20230299)+2 种基金China Postdoctoral Science Foundation(No.2023M742884)Natural Science Foundation of Sichuan Province(Nos.24NSFSC2264,2025ZNSFSC0322)Key Research and Development Project of Sichuan Province(No.24ZDYF0633).
文摘As a key node of modern transportation network,the informationization management of road tunnels is crucial to ensure the operation safety and traffic efficiency.However,the existing tunnel vehicle modeling methods generally have problems such as insufficient 3D scene description capability and low dynamic update efficiency,which are difficult to meet the demand of real-time accurate management.For this reason,this paper proposes a vehicle twin modeling method for road tunnels.This approach starts from the actual management needs,and supports multi-level dynamic modeling from vehicle type,size to color by constructing a vehicle model library that can be flexibly invoked;at the same time,semantic constraint rules with geometric layout,behavioral attributes,and spatial relationships are designed to ensure that the virtual model matches with the real model with a high degree of similarity;ultimately,the prototype system is constructed and the case region is selected for the case study,and the dynamic vehicle status in the tunnel is realized by integrating real-time monitoring data with semantic constraints for precise virtual-real mapping.Finally,the prototype system is constructed and case experiments are conducted in selected case areas,which are combined with real-time monitoring data to realize dynamic updating and three-dimensional visualization of vehicle states in tunnels.The experiments show that the proposed method can run smoothly with an average rendering efficiency of 17.70 ms while guaranteeing the modeling accuracy(composite similarity of 0.867),which significantly improves the real-time and intuitive tunnel management.The research results provide reliable technical support for intelligent operation and emergency response of road tunnels,and offer new ideas for digital twin modeling of complex scenes.
基金Supported by Zhejiang Provincial Key Research and Development Program(Grant No.2021C04015)。
文摘Learning from demonstration is widely regarded as a promising paradigm for robots to acquire diverse skills.Other than the artificial learning from observation-action pairs for machines,humans can learn to imitate in a more versatile and effective manner:acquiring skills through mere“observation”.Video to Command task is widely perceived as a promising approach for task-based learning,which yet faces two key challenges:(1)High redundancy and low frame rate of fine-grained action sequences make it difficult to manipulate objects robustly and accurately.(2)Video to Command models often prioritize accuracy and richness of output commands over physical capabilities,leading to impractical or unsafe instructions for robots.This article presents a novel Video to Command framework that employs multiple data associations and physical constraints.First,we introduce an object-level appearancecontrasting multiple data association strategy to effectively associate manipulated objects in visually complex environments,capturing dynamic changes in video content.Then,we propose a multi-task Video to Command model that utilizes object-level video content changes to compile expert demonstrations into manipulation commands.Finally,a multi-task hybrid loss function is proposed to train a Video to Command model that adheres to the constraints of the physical world and manipulation tasks.Our method achieved over 10%on BLEU_N,METEOR,ROUGE_L,and CIDEr compared to the up-to-date methods.The dual-arm robot prototype was established to demonstrate the whole process of learning from an expert demonstration of multiple skills and then executing the tasks by a robot.
基金jointly supported by the National Natural Science Foundation of China(Grant Nos.42075138 and 42375147)the Program on Key Basic Research Project of Jiangsu(Grant No.BE2023829)。
文摘Tropical cyclones(TCs)are one of the most serious types of natural disasters,and accurate TC activity predictions are key to disaster prevention and mitigation.Recently,TC track predictions have made significant progress,but the ability to predict their intensity is obviously lagging behind.At present,research on TC intensity prediction takes atmospheric reanalysis data as the research object and mines the relationship between TC-related environmental factors and intensity through deep learning.However,reanalysis data are non-real-time in nature,which does not meet the requirements for operational forecasting applications.Therefore,a TC intensity prediction model named TC-Rolling is proposed,which can simultaneously extract the degree of symmetry for strong TC convective cloud and convection intensity,and fuse the deviation-angle variance with satellite images to construct the correlation between TC convection structure and intensity.For TCs'complex dynamic processes,a convolutional neural network(CNN)is used to learn their temporal and spatial features.For real-time intensity estimation,multi-task learning acts as an implicit time-series enhancement.The model is designed with a rolling strategy that aims to moderate the long-term dependent decay problem and improve accuracy for short-term intensity predictions.Since multiple tasks are correlated,the loss function of 12 h and 24 h are corrected.After testing on a sample of TCs in the Northwest Pacific,with a 4.48 kt root-mean-square error(RMSE)of 6 h intensity prediction,5.78 kt for 12 h,and 13.94 kt for 24 h,TC records from official agencies are used to assess the validity of TC-Rolling.
基金funded by the Excellent Talent Training Funding Project in Dongcheng District,Beijing,with project number 2024-dchrcpyzz-9.
文摘Predicting the health status of stroke patients at different stages of the disease is a critical clinical task.The onset and development of stroke are affected by an array of factors,encompassing genetic predisposition,environmental exposure,unhealthy lifestyle habits,and existing medical conditions.Although existing machine learning-based methods for predicting stroke patients’health status have made significant progress,limitations remain in terms of prediction accuracy,model explainability,and system optimization.This paper proposes a multi-task learning approach based on Explainable Artificial Intelligence(XAI)for predicting the health status of stroke patients.First,we design a comprehensive multi-task learning framework that utilizes the task correlation of predicting various health status indicators in patients,enabling the parallel prediction of multiple health indicators.Second,we develop a multi-task Area Under Curve(AUC)optimization algorithm based on adaptive low-rank representation,which removes irrelevant information from the model structure to enhance the performance of multi-task AUC optimization.Additionally,the model’s explainability is analyzed through the stability analysis of SHAP values.Experimental results demonstrate that our approach outperforms comparison algorithms in key prognostic metrics F1 score and Efficiency.
基金supported by the basic and forward-looking project(No.2023YQX302)。
文摘Traditional deconvolution methods based on single-channel inversion do not consider the spatial structural relation between channels,and hence,they yield high-resolution results with the existing transverse inconsistency or discontinuity.Therefore,in this study,the local dip angle was used to obtain the structural information and construct the spatial structurally constraint operator.This operator is then introduced into multichannel deconvolution as a regularization operator to improve the resolution and maintain the transverse continuity of seismic data.Model tests and actual seismic data processing have demonstrated the effectiveness and practicability of this method.
基金an initial outcome of the Research on the Trust Mechanism of Agricultural Supply Chain Financing in the Context of “Blockchain+Supply Chain” Integrated Governance (Project No:20AGL021)a key project under the National Social Science Fund of China (NSSFC)+3 种基金the Research on the Trust Mechanism of Online Bank Lending System Based on Online Social Capital of Long-tail Rural Households (Project No:19BGL155)a project under the NSSFCthe Research on the Cost Formation Mechanism of Data Factor Transactions and the Design of Transaction Mechanism (Project No:23CJY068)a youth project under the NSSFC
文摘This paper begins with a discussion of the trust issues that agricultural supply chain finance faces.It then examines the constraints of using blockchain technology to enhance trust in agricultural supply chain finance in accordance with the technological and institutional logic of combining blockchain with supply chains.This study then proposes the creation of an agricultural“blockchain+supply chain”information service platform and a financing trust mechanism that can effectively ensure the authenticity of the initial information input on the blockchain,consistency between on-chain transaction data and off-chain physical transactions,the controllability of risks in the set up and execution of smart contracts,and the removal of information constraints,resource allocation constraints,and institutional constraints in the agricultural supply chain financing.This aims to improve the efficiency of financing in agricultural supply chains and contribute to the industrial development of rural areas and rural revitalization.
基金supported by the Key Research and Development Program of Heilongjiang Province(No.2022ZX01A35).
文摘As the group-buying model shows significant progress in attracting new users,enhancing user engagement,and increasing platform profitability,providing personalized recommendations for group-buying users has emerged as a new challenge in the field of recommendation systems.This paper introduces a group-buying recommendation model based on multi-head attention mechanisms and multi-task learning,termed the Multi-head Attention Mechanisms and Multi-task Learning Group-Buying Recommendation(MAMGBR)model,specifically designed to optimize group-buying recommendations on e-commerce platforms.The core dataset of this study comes from the Chinese maternal and infant e-commerce platform“Beibei,”encompassing approximately 430,000 successful groupbuying actions and over 120,000 users.Themodel focuses on twomain tasks:recommending items for group organizers(Task Ⅰ)and recommending participants for a given group-buying event(Task Ⅱ).In model evaluation,MAMGBR achieves an MRR@10 of 0.7696 for Task I,marking a 20.23%improvement over baseline models.Furthermore,in Task II,where complex interaction patterns prevail,MAMGBR utilizes auxiliary loss functions to effectively model the multifaceted roles of users,items,and participants,leading to a 24.08%increase in MRR@100 under a 1:99 sample ratio.Experimental results show that compared to benchmark models,such as NGCF and EATNN,MAMGBR’s integration ofmulti-head attentionmechanisms,expert networks,and gating mechanisms enables more accurate modeling of user preferences and social associations within group-buying scenarios,significantly enhancing recommendation accuracy and platform group-buying success rates.
基金supported by the National Natural Science Foundation of China(Grant Nos.42030708,42375138,42030608,42105128,42075079)the Opening Foundation of Key Laboratory of Atmospheric Sounding,China Meteorological Administration(CMA),and the CMA Research Center on Meteorological Observation Engineering Technology(Grant No.U2021Z03),and the Opening Foundation of the Key Laboratory of Atmospheric Chemistry,CMA(Grant No.2022B02)。
文摘Aerosol optical depth(AOD)and fine particulate matter with a diameter of less than or equal to 2.5μm(PM_(2.5))play crucial roles in air quality,human health,and climate change.However,the complex correlation of AOD–PM_(2.5)and the limitations of existing algorithms pose a significant challenge in realizing the accurate joint retrieval of these two parameters at the same location.On this point,a multi-task learning(MTL)model,which enables the joint retrieval of PM_(2.5)concentration and AOD,is proposed and applied on the top-of-the-atmosphere reflectance data gathered by the Fengyun-4A Advanced Geosynchronous Radiation Imager(FY-4A AGRI),and compared to that of two single-task learning models—namely,Random Forest(RF)and Deep Neural Network(DNN).Specifically,MTL achieves a coefficient of determination(R^(2))of 0.88 and a root-mean-square error(RMSE)of 0.10 in AOD retrieval.In comparison to RF,the R^(2)increases by 0.04,the RMSE decreases by 0.02,and the percentage of retrieval results falling within the expected error range(Within-EE)rises by 5.55%.The R^(2)and RMSE of PM_(2.5)retrieval by MTL are 0.84 and 13.76μg m~(-3)respectively.Compared with RF,the R^(2)increases by 0.06,the RMSE decreases by 4.55μg m~(-3),and the Within-EE increases by 7.28%.Additionally,compared to DNN,MTL shows an increase of 0.01 in R^(2)and a decrease of 0.02 in RMSE in AOD retrieval,with a corresponding increase of 2.89%in Within-EE.For PM_(2.5)retrieval,MTL exhibits an increase of 0.05 in R^(2),a decrease of 1.76μg m~(-3)in RMSE,and an increase of 6.83%in Within-EE.The evaluation suggests that MTL is able to provide simultaneously improved AOD and PM_(2.5)retrievals,demonstrating a significant advantage in efficiently capturing the spatial distribution of PM_(2.5)concentration and AOD.
基金the National Key Research and Development Plan of China[Grant No.2023YFB3002400]the Shanghai 2021 Natural Science Foundation[Grant Nos.21ZR1420400 and 21ZR1419800]+1 种基金the Shanghai 2023 Natural Science Foundation[Grant No.23ZR1463000]the Shandong Provincial Meteorological Bureau Scientific Research Project[Grant No.2023SDBD05].
文摘Accurate short-term forecast of offshore wind fields is still challenging for numerical weather prediction models.Based on three years of 48-hour forecast data from the European Centre for Medium-Range Weather Forecasts Integrated Forecasting System global model(ECMWF-IFS)over 14 offshore weather stations along the coast of Shandong Province,this study introduces a multi-task learning(MTL)model(TabNet-MTL),which significantly improves the forecast bias of near-surface wind direction and speed simultaneously.TabNet-MTL adopts the feature engineering method,utilizes mean square error as the loss function,and employs the 5-fold cross validation method to ensure the generalization ability of the trained model.It demonstrates superior skills in wind field correction across different forecast lead times over all stations compared to its single-task version(TabNet-STL)and three other popular single-task learning models(Random Forest,LightGBM,and XGBoost).Results show that it significantly reduces root mean square error of the ECMWF-IFS wind speed forecast from 2.20 to 1.25 m s−1,and increases the forecast accuracy of wind direction from 50%to 65%.As an explainable deep learning model,the weather stations and long-term temporal statistics of near-surface wind speed are identified as the most influential variables for TabNet-MTL in constructing its feature engineering.
基金supported by the National Key Research and Development Program of China (2024YFD2001100,2024YFE0214300)the National Natural Science Foundation of China (62162008)+3 种基金Guizhou Provincial Science and Technology Projects ([2024]002, CXTD[2023]027)Guizhou Province Youth Science and Technology Talent Project ([2024]317)Guiyang Guian Science and Technology Talent Training Project ([2024]2-15)the Guizhou Province Graduate Education Innovation Program Project (2024YJSKYJJ096)
文摘Staple crops are the cornerstone of the food supply but are frequently threatened by plant diseases.Effective disease management,including disease identification and severity assessment,helps to better address these challenges.Currently,methods for disease severity assessment typically rely on calculating the area proportion of disease segmentation regions or using classification networks for severity assessment.However,these methods require large amounts of labeled data and fail to quantify lesion proportions when using classification networks,leading to inaccurate evaluations.To address these issues,we propose an automated framework for disease severity assessment that combines multi-task learning and knowledge-driven large-model segmentation techniques.This framework includes an image information processor,a lesion and leaf segmentation module,and a disease severity assessment module.First,the image information processor utilizes a multi-task learning strategy to analyze input images comprehensively,ensuring a deep understanding of disease characteristics.Second,the lesion and leaf segmentation module employ prompt-driven large-model technology to accurately segment diseased areas and entire leaves,providing detailed visual analysis.Finally,the disease severity assessment module objectively evaluates the severity of the disease based on professional grading standards by calculating lesion area proportions.Additionally,we have developed a comprehensive database of diseased leaf images from major crops,including several task-specific datasets.Experimental results demonstrate that our framework can accurately identify and assess the types and severity of crop diseases,even without extensive labeled data.Codes and data are available at http://dkp-ads.samlab.cn/.
基金supported in part by the National Natural Science Foundation of China under Grant 62371181in part by the Changzhou Science and Technology International Cooperation Program under Grant CZ20230029The Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.RS-2024-00396797,Development of core technology for intelligent O-RAN security platform).
文摘Satellite communication technology has emerged as a key solution to address the challenges of data transmission in remote areas.By overcoming the limitations of traditional terrestrial communication networks,it enables long-distance data transmission anytime and anywhere,ensuring the timely and accurate delivery of water level data,which is particularly crucial for fishway water level monitoring.To enhance the effectiveness of fishway water level monitoring,this study proposes a multi-task learning model,AS-SOMTF,designed for real-time and comprehensive prediction.The model integrates auxiliary sequences with primary input sequences to capture complex relationships and dependencies,thereby improving representational capacity.In addition,a novel timeseries embedding algorithm,AS-SOM,is introduced,which combines generative inference and pooling operations to optimize prediction efficiency for long sequences.This innovation not only ensures the timely transmission of water level data but also enhances the accuracy of real-time monitoring.Compared with traditional models such as Transformer and Long Short-Term Memory(LSTM)networks,the proposed model achieves improvements of 3.8%and 1.4%in prediction accuracy,respectively.These advancements provide more precise technical support for water level forecasting and resource management in the Diqing Tibetan Autonomous Prefecture of the Lancang River,contributing to ecosystem protection and improved operational safety.
基金supported by the University Natural Science Research Project of Anhui Province(Grant Nos.2022AH040042 and 2022AH020029)the National Natural Science Foundation of China(Grant No.12172001)+1 种基金Anhui Provincial Natural Science Foundation(Grant No.2208085Y01)the Housing and Urban-Rural Development Science and Technology Project of Anhui Province(Grant No.2022-YF069).
文摘Recent experiments have found that a liquid crystal elastomer(LCE)rod supported in the middle can rotate continuously under horizontal illumination due to the combined impacts of gravity and light-fueled lateral bend-ing deformation.Similar to traditional gravity-driven systems,it is constrained by the direction of gravity and cannot be applied in microgravity environments.This study introduces a lateral constraint to a liquid crystal elastomer rod system,enabling self-rotation under lighting from any direction,including horizontal and vertical illumination.Through theoretical modeling,the results indicate that the system can steadily rotate under the combined impacts of lateral forces and vertical illumination.Factors like thermal energy flux,thermal conduc-tivity coefficient,the LCE rod length,contraction coefficient,and friction coefficient affect the angular velocity of the self-rotation.The numerical computations align closely with the experimental data.Our proposed steadily self-rotating system features a simple structure with constant self-rotation.It operates independently of gravity direction,making it an excellent choice for special environments,such as the microgravity conditions on the Moon.The lateral constraint strategy presented in this study offers a general approach to expanding the applica-tions of gravity-driven self-sustained motion,with promising potential,especially in microgravity settings,where its versatility under varying lighting conditions could yield valuable insights.
基金funded by the National Key R&D Program of China(Grant No.2024YFE0102500)the National Natural Science Foundation of China(Grant No.12404568)+1 种基金the Guangzhou Municipal Science and Technology Project(Grant No.2023A03J00904)the Quantum Science Center of Guangdong-Hong Kong-Macao Greater Bay Area,China and the Undergraduate Research Project from HKUST(Guangzhou).
文摘Constraint satisfaction problems(CSPs)are a class of problems that are ubiquitous in science and engineering.They feature a collection of constraints specified over subsets of variables.A CSP can be solved either directly or by reducing it to other problems.This paper introduces the Julia ecosystem for solving and analyzing CSPs with a focus on the programming practices.We introduce some important CSPs and show how these problems are reduced to each other.We also show how to transform CSPs into tensor networks,how to optimize the tensor network contraction orders,and how to extract the solution space properties by contracting the tensor networks with generic element types.Examples are given,which include computing the entropy constant,analyzing the overlap gap property,and the reduction between CSPs.
基金supported by National Major Scientific Research Instrument Development Project of China(No.51927804)Science Fund for Shaanxi Provincial Department of Education's Youth Innovation Team Research Plan under Grant(No.23JP169).
文摘In machine vision,elliptical targets frequently appear within the camera's region of interest(ROI).Ellipse detection is essential for shape detection and geometric measurements in machine vision.However,existing ellipse detection algorithms often face issues such as high computational complexity,strong dependence on initial conditions,sensitivity to noise,and lack of robustness to occlusions.In this paper,we propose a fast and robust ellipse detection method to address these challenges.This method first utilizes edge gradient and curvature information to segment the curve into circular arcs.Next,based on the convexity of the arcs,it divides them into different quadrants of the ellipse,groups and fits the arcs according to multiple geometric constraints at a low computational cost.Finally,it reduces the parameter space for hierarchical clustering and then segments the complete ellipse into several sectors for verification.We compare our method across seven datasets,including five public image datasets and two from industrial camera scenes.Experimental results show that our method achieves a precision ranging from 67.1%to 98.9%,a recall ranging from 48.1%to 92.9%,and an F-measure ranging from 58.0%to 95.8%.The average execution time per image ranges from 25 ms to 192 ms,demonstrating both high accuracy and efficiency.
基金jointly supported by the National Natural Science Foundation of China(Grant Nos.42122034,42075043,42330609)the Second Tibetan Plateau Scientific Expedition and Research program(2019QZKK0103)+2 种基金Key Talent Project in Gansu and Central Guidance Fund for Local Science and Technology Development Projects in Gansu(No.24ZYQA031)the Youth Innovation Promotion Association of Chinese Academy of Sciences(2021427)West Light Foundation of the Chinese Academy of Sciences(xbzg-zdsys-202215)。
文摘Seasonal precipitation has always been a key focus of climate prediction.As a dynamic-statistical combined method,the existing observational constraint correction establishes a regression relationship between the numerical model outputs and historical observations,which can partly predict seasonal precipitation.However,solving a nonlinear problem through linear regression is significantly biased.This study implements a nonlinear optimization of an existing observational constrained correction model using a Light Gradient Boosting Machine(LightGBM)machine learning algorithm based on output from the Beijing National Climate Center Climate System Model(BCC-CSM)and station observations to improve the prediction of summer precipitation in China.The model was trained using a rolling approach,and LightGBM outperformed Linear Regression(LR),Extreme Gradient Boosting(XGBoost),and Categorical Boosting(CatBoost).Using parameter tuning to optimize the machine learning model and predict future summer precipitation using eight different predictors in BCC-CSM,the mean Anomaly Correlation Coefficient(ACC)score in the 2019–22 summer precipitation predictions was 0.17,and the mean Prediction Score(PS)reached 74.The PS score was improved by 7.87%and 6.63%compared with the BCC-CSM and the linear observational constraint approach,respectively.The observational constraint correction prediction strategy with LightGBM significantly and stably improved the prediction of summer precipitation in China compared to the previous linear observational constraint solution,providing a reference for flood control and drought relief during the flood season(summer)in China.
基金Supported by Jiangsu Key R&D Program(BE2021622)Jiangsu Postgraduate Practice and Innovation Program(SJCX23_0395).
文摘Background As visual simultaneous localization and mapping(SLAM)is primarily based on the assumption of a static scene,the presence of dynamic objects in the frame causes problems such as a deterioration of system robustness and inaccurate position estimation.In this study,we propose a YGC-SLAM for indoor dynamic environments based on the ORB-SLAM2 framework combined with semantic and geometric constraints to improve the positioning accuracy and robustness of the system.Methods First,the recognition accuracy of YOLOv5 was improved by introducing the convolution block attention model and the improved EIOU loss function,whereby the prediction frame converges quickly for better detection.The improved YOLOv5 was then added to the tracking thread for dynamic target detection to eliminate dynamic points.Subsequently,multi-view geometric constraints were used for re-judging to further eliminate dynamic points while enabling more useful feature points to be retained and preventing the semantic approach from over-eliminating feature points,causing a failure of map building.The K-means clustering algorithm was used to accelerate this process and quickly calculate and determine the motion state of each cluster of pixel points.Finally,a strategy for drawing keyframes with de-redundancy was implemented to construct a clear 3D dense static point-cloud map.Results Through testing on TUM dataset and a real environment,the experimental results show that our algorithm reduces the absolute trajectory error by 98.22%and the relative trajectory error by 97.98%compared with the original ORBSLAM2,which is more accurate and has better real-time performance than similar algorithms,such as DynaSLAM and DS-SLAM.Conclusions The YGC-SLAM proposed in this study can effectively eliminate the adverse effects of dynamic objects,and the system can better complete positioning and map building tasks in complex environments.
