Digital Twin(DT)supports real time analysis and provides a reliable simulation platform in the Internet of Things(IoT).The creation and application of DT hinges on amounts of data,which poses pressure on the applicati...Digital Twin(DT)supports real time analysis and provides a reliable simulation platform in the Internet of Things(IoT).The creation and application of DT hinges on amounts of data,which poses pressure on the application of Artificial Intelligence(AI)for DT descriptions and intelligent decision-making.Federated Learning(FL)is a cutting-edge technology that enables geographically dispersed devices to collaboratively train a shared global model locally rather than relying on a data center to perform model training.Therefore,DT can benefit by combining with FL,successfully solving the"data island"problem in traditional AI.However,FL still faces serious challenges,such as enduring single-point failures,suffering from poison attacks,lacking effective incentive mechanisms.Before the successful deployment of DT,we should tackle the issues caused by FL.Researchers from industry and academia have recognized the potential of introducing Blockchain Technology(BT)into FL to overcome the challenges faced by FL,where BT acting as a distributed and immutable ledger,can store data in a secure,traceable,and trusted manner.However,to the best of our knowledge,a comprehensive literature review on this topic is still missing.In this paper,we review existing works about blockchain-enabled FL and visualize their prospects with DT.To this end,we first propose evaluation requirements with respect to security,faulttolerance,fairness,efficiency,cost-saving,profitability,and support for heterogeneity.Then,we classify existing literature according to the functionalities of BT in FL and analyze their advantages and disadvantages based on the proposed evaluation requirements.Finally,we discuss open problems in the existing literature and the future of DT supported by blockchain-enabled FL,based on which we further propose some directions for future research.展开更多
The Autonomous Underwater Glider(AUG)is a kind of prevailing underwater intelligent internet vehicle and occupies a dominant position in industrial applications,in which path planning is an essential problem.Due to th...The Autonomous Underwater Glider(AUG)is a kind of prevailing underwater intelligent internet vehicle and occupies a dominant position in industrial applications,in which path planning is an essential problem.Due to the complexity and variability of the ocean,accurate environment modeling and flexible path planning algorithms are pivotal challenges.The traditional models mainly utilize mathematical functions,which are not complete and reliable.Most existing path planning algorithms depend on the environment and lack flexibility.To overcome these challenges,we propose a path planning system for underwater intelligent internet vehicles.It applies digital twins and sensor data to map the real ocean environment to a virtual digital space,which provides a comprehensive and reliable environment for path simulation.We design a value-based reinforcement learning path planning algorithm and explore the optimal network structure parameters.The path simulation is controlled by a closed-loop model integrated into the terminal vehicle through edge computing.The integration of state input enriches the learning of neural networks and helps to improve generalization and flexibility.The task-related reward function promotes the rapid convergence of the training.The experimental results prove that our reinforcement learning based path planning algorithm has great flexibility and can effectively adapt to a variety of different ocean conditions.展开更多
The rapid development of emerging technologies,such as edge intelligence and digital twins,have added momentum towards the development of the Industrial Internet of Things(IIo T).However,the massive amount of data gen...The rapid development of emerging technologies,such as edge intelligence and digital twins,have added momentum towards the development of the Industrial Internet of Things(IIo T).However,the massive amount of data generated by the IIo T,coupled with heterogeneous computation capacity across IIo T devices,and users’data privacy concerns,have posed challenges towards achieving industrial edge intelligence(IEI).To achieve IEI,in this paper,we propose a semi-federated learning framework where a portion of the data with higher privacy is kept locally and a portion of the less private data can be potentially uploaded to the edge server.In addition,we leverage digital twins to overcome the problem of computation capacity heterogeneity of IIo T devices through the mapping of physical entities.We formulate a synchronization latency minimization problem which jointly optimizes edge association and the proportion of uploaded nonprivate data.As the joint problem is NP-hard and combinatorial and taking into account the reality of largescale device training,we develop a multi-agent hybrid action deep reinforcement learning(DRL)algorithm to find the optimal solution.Simulation results show that our proposed DRL algorithm can reduce latency and have a better convergence performance for semi-federated learning compared to benchmark algorithms.展开更多
Limited by battery and computing re-sources,the computing-intensive tasks generated by Internet of Things(IoT)devices cannot be processed all by themselves.Mobile edge computing(MEC)is a suitable solution for this pro...Limited by battery and computing re-sources,the computing-intensive tasks generated by Internet of Things(IoT)devices cannot be processed all by themselves.Mobile edge computing(MEC)is a suitable solution for this problem,and the gener-ated tasks can be offloaded from IoT devices to MEC.In this paper,we study the problem of dynamic task offloading for digital twin-empowered MEC.Digital twin techniques are applied to provide information of environment and share the training data of agent de-ployed on IoT devices.We formulate the task offload-ing problem with the goal of maximizing the energy efficiency and the workload balance among the ESs.Then,we reformulate the problem as an MDP problem and design DRL-based energy efficient task offloading(DEETO)algorithm to solve it.Comparative experi-ments are carried out which show the superiority of our DEETO algorithm in improving energy efficiency and balancing the workload.展开更多
Over the past two decades,digital microfluidic biochips have been in much demand for safety-critical and biomedical applications and increasingly important in point-of-care analysis,drug discovery,and immunoassays,amo...Over the past two decades,digital microfluidic biochips have been in much demand for safety-critical and biomedical applications and increasingly important in point-of-care analysis,drug discovery,and immunoassays,among other areas.However,for complex bioassays,finding routes for the transportation of droplets in an electrowetting-on-dielectric digital biochip while maintaining their discreteness is a challenging task.In this study,we propose a deep reinforcement learning-based droplet routing technique for digital microfluidic biochips.The technique is implemented on a distributed architecture to optimize the possible paths for predefined source–target pairs of droplets.The actors of the technique calculate the possible routes of the source–target pairs and store the experience in a replay buffer,and the learner fetches the experiences and updates the routing paths.The proposed algorithm was applied to benchmark suitesⅠand Ⅲ as two different test benches,and it achieved significant improvements over state-of-the-art techniques.展开更多
In this paper,to deal with the heterogeneity in federated learning(FL)systems,a knowledge distillation(KD)driven training framework for FL is proposed,where each user can select its neural network model on demand and ...In this paper,to deal with the heterogeneity in federated learning(FL)systems,a knowledge distillation(KD)driven training framework for FL is proposed,where each user can select its neural network model on demand and distill knowledge from a big teacher model using its own private dataset.To overcome the challenge of train the big teacher model in resource limited user devices,the digital twin(DT)is exploit in the way that the teacher model can be trained at DT located in the server with enough computing resources.Then,during model distillation,each user can update the parameters of its model at either the physical entity or the digital agent.The joint problem of model selection and training offloading and resource allocation for users is formulated as a mixed integer programming(MIP)problem.To solve the problem,Q-learning and optimization are jointly used,where Q-learning selects models for users and determines whether to train locally or on the server,and optimization is used to allocate resources for users based on the output of Q-learning.Simulation results show the proposed DT-assisted KD framework and joint optimization method can significantly improve the average accuracy of users while reducing the total delay.展开更多
The connected autonomous vehicle is considered an effective way to improve transport safety and efficiency.To overcome the limited sensing and computing capabilities of individual vehicles,we design a digital twin ass...The connected autonomous vehicle is considered an effective way to improve transport safety and efficiency.To overcome the limited sensing and computing capabilities of individual vehicles,we design a digital twin assisted decision-making framework for Internet of Vehicles,by leveraging the integration of communication,sensing and computing.In this framework,the digital twin entities residing on edge can effectively communicate and cooperate with each other to plan sub-targets for their respective vehicles,while the vehicles only need to achieve the sub-targets by generating a sequence of atomic actions.Furthermore,we propose a hierarchical multiagent reinforcement learning approach to implement the framework,which can be trained in an end-to-end way.In the proposed approach,the communication interval of digital twin entities could adapt to timevarying environment.Extensive experiments on driving decision-making have been performed in traffic junction scenarios of different difficulties.The experimental results show that the proposed approach can largely improve collaboration efficiency while reducing communication overhead.展开更多
Mechanical metamaterials such as auxetic materials have attracted great interest due to their unusual properties that are dictated by their architectures.However,these architected materials usually have low stiffness ...Mechanical metamaterials such as auxetic materials have attracted great interest due to their unusual properties that are dictated by their architectures.However,these architected materials usually have low stiffness because of the bending or rotation deformation mechanisms in the microstructures.In this work,a convolutional neural network(CNN)based self-learning multi-objective optimization is performed to design digital composite materials.The CNN models have undergone rigorous training using randomly generated two-phase digital composite materials,along with their corresponding Poisson's ratios and stiffness values.Then the CNN models are used for designing composite material structures with the minimum Poisson's ratio at a given volume fraction constraint.Furthermore,we have designed composite materials with optimized stiffness while exhibiting a desired Poisson's ratio(negative,zero,or positive).The optimized designs have been successfully and efficiently obtained,and their validity has been confirmed through finite element analysis results.This self-learning multi-objective optimization model offers a promising approach for achieving comprehensive multi-objective optimization.展开更多
With the advent of the“fourth industrial revolution”,the digital trend has become a hot issue in the field of architecture.Colleges and universities are an important part of Chinese society,and the development of di...With the advent of the“fourth industrial revolution”,the digital trend has become a hot issue in the field of architecture.Colleges and universities are an important part of Chinese society,and the development of digital technology has had a profound impact on college life.In order to explore the new campus development path in line with the development trend of the digital society,the old library of North China University of Technology is taken as the research object.The new teaching mode and learning mode under the digital trend are discussed,and the learning space renewal strategy in line with the new era background is explored,with a view to contributing practical experience in space renewal of colleges and universities.展开更多
Deep learning is considered one of the most efficient and reliable methods through which the legitimacy of a digital image can be verified.In the current cyber world where deepfakes have shaken the global community,co...Deep learning is considered one of the most efficient and reliable methods through which the legitimacy of a digital image can be verified.In the current cyber world where deepfakes have shaken the global community,confirming the legitimacy of a digital image is of great importance.With the advancements made in deep learning techniques,now we can efficiently train and develop state-of-the-art digital image forensic models.The most traditional and widely used method by researchers is convolution neural networks(CNN)for verification of image authenticity but it consumes a considerable number of resources and requires a large dataset for training.Therefore,in this study,a transfer learning based deep learning technique for image forgery detection is proposed.The proposed methodology consists of three modules namely;preprocessing module,convolutional module,and the classification module.By using our proposed technique,the training time is drastically reduced by utilizing the pre-trained weights.The performance of the proposed technique is evaluated by using benchmark datasets,i.e.,BOW and BOSSBase that detect five forensic types which include JPEG compression,contrast enhancement(CE),median filtering(MF),additive Gaussian noise,and resampling.We evaluated the performance of our proposed technique by conducting various experiments and case scenarios and achieved an accuracy of 99.92%.The results show the superiority of the proposed system.展开更多
As professors are subjected to teaching their classes online due to the recent COVID-19, our local Hong Kong students find it difficult to consult their teachers, and ultimately would fail to achieve the intended lear...As professors are subjected to teaching their classes online due to the recent COVID-19, our local Hong Kong students find it difficult to consult their teachers, and ultimately would fail to achieve the intended learning outcomes, especially for practical-based subjects. In this research, students having online classes of a practical-based fabric design subject were encouraged to self-study from Open Educational Resource (OER) materials for a further and better understanding of their subject. Additionally, online materials were developed to improve students’ understanding via skill of digital literacy. Their learning progress was evaluated and compared to the face-to-face version. The majority of students found online classes combined with self-studying OER materials, potentially be a substitute for face-to-face classes. Most of the students further opined different OER videos assisted them without any face-to-face instructions in practical works, to develop new fabric samples from the inspiration. Analysis of test results, and comparison of students’ final grades with different learning modes, supported these phenomena.展开更多
Knowledge about the spatial distribution of the soil physical and mechanical properties is crucial for soil management,water yield,and sustainability at the watershed scale;however,the lack of soil data hinders the ap...Knowledge about the spatial distribution of the soil physical and mechanical properties is crucial for soil management,water yield,and sustainability at the watershed scale;however,the lack of soil data hinders the application of this tool,thus urging the need to estimate soil properties and consequently,to perform the spatial distribution.This research attempted to examine the proficiency of three machine learning methods(RF:Random Forest;Cubist:Regression Tree;and SVM:Support Vector Machine)to predict soil physical and mechanical properties,saturated hydraulic conductivity(Ks),Cohesion measured by fall-cone at the saturated(Psat)and dry(Pdry)states,hardness index(HI)and dry shear strength(SS)by integrating environmental variables and soil features in the Zayandeh-Rood dam watershed,central Iran.To determine the best combination of input variables,three scenarios were examined as follows:scenarioⅠ,terrain attributes derivative from a digital elevation model(DEM)+remotely sensed data;scenarioⅡ,covariates of scenarioⅠ+selected climatic data and some thematic maps;scenarioⅢ,covariates in scenarioⅡ+intrinsic soil properties(Clay,Silt,Sand,bulk density(BD),soil organic matter(SOM),calcium carbonate equivalent(CCE),mean weight diameter(MWD)and geometric weight diameter(GWD)).The results showed that for Ks,Psat Pdry and SS,the best performance was found by the RF model in the third scenario,with R2=0.53,0.32,0.31 and 0.41,respectively,while for soil hardness index(HI),Cubist model in the third scenario with R2=0.25 showed the highest performance.For predicting Ks and Psat,soil characteristics(i.e.clay and soil SOM and BD),and land use were the most important variables.For predicting Pdry,HI,and SS,some topographical characteristics(Valley depth,catchment area,mltiresolution of ridge top flatness index),and some soil characteristics(i.e.clay,SOM and MWD)were the most important input variables.The results of this research present moderate accuracy,however,the methodology employed provides quick and costeffective information serving as the scientific basis for decision-making goals.展开更多
Stroke is a leading cause of disability and mortality worldwide,necessitating the development of advanced technologies to improve its diagnosis,treatment,and patient outcomes.In recent years,machine learning technique...Stroke is a leading cause of disability and mortality worldwide,necessitating the development of advanced technologies to improve its diagnosis,treatment,and patient outcomes.In recent years,machine learning techniques have emerged as promising tools in stroke medicine,enabling efficient analysis of large-scale datasets and facilitating personalized and precision medicine approaches.This abstract provides a comprehensive overview of machine learning’s applications,challenges,and future directions in stroke medicine.Recently introduced machine learning algorithms have been extensively employed in all the fields of stroke medicine.Machine learning models have demonstrated remarkable accuracy in imaging analysis,diagnosing stroke subtypes,risk stratifications,guiding medical treatment,and predicting patient prognosis.Despite the tremendous potential of machine learning in stroke medicine,several challenges must be addressed.These include the need for standardized and interoperable data collection,robust model validation and generalization,and the ethical considerations surrounding privacy and bias.In addition,integrating machine learning models into clinical workflows and establishing regulatory frameworks are critical for ensuring their widespread adoption and impact in routine stroke care.Machine learning promises to revolutionize stroke medicine by enabling precise diagnosis,tailored treatment selection,and improved prognostication.Continued research and collaboration among clinicians,researchers,and technologists are essential for overcoming challenges and realizing the full potential of machine learning in stroke care,ultimately leading to enhanced patient outcomes and quality of life.This review aims to summarize all the current implications of machine learning in stroke diagnosis,treatment,and prognostic evaluation.At the same time,another purpose of this paper is to explore all the future perspectives these techniques can provide in combating this disabling disease.展开更多
BACKGROUND Intensive care unit-acquired weakness(ICU-AW)is a common complication that significantly impacts the patient's recovery process,even leading to adverse outcomes.Currently,there is a lack of effective pr...BACKGROUND Intensive care unit-acquired weakness(ICU-AW)is a common complication that significantly impacts the patient's recovery process,even leading to adverse outcomes.Currently,there is a lack of effective preventive measures.AIM To identify significant risk factors for ICU-AW through iterative machine learning techniques and offer recommendations for its prevention and treatment.METHODS Patients were categorized into ICU-AW and non-ICU-AW groups on the 14th day post-ICU admission.Relevant data from the initial 14 d of ICU stay,such as age,comorbidities,sedative dosage,vasopressor dosage,duration of mechanical ventilation,length of ICU stay,and rehabilitation therapy,were gathered.The relationships between these variables and ICU-AW were examined.Utilizing iterative machine learning techniques,a multilayer perceptron neural network model was developed,and its predictive performance for ICU-AW was assessed using the receiver operating characteristic curve.RESULTS Within the ICU-AW group,age,duration of mechanical ventilation,lorazepam dosage,adrenaline dosage,and length of ICU stay were significantly higher than in the non-ICU-AW group.Additionally,sepsis,multiple organ dysfunction syndrome,hypoalbuminemia,acute heart failure,respiratory failure,acute kidney injury,anemia,stress-related gastrointestinal bleeding,shock,hypertension,coronary artery disease,malignant tumors,and rehabilitation therapy ratios were significantly higher in the ICU-AW group,demonstrating statistical significance.The most influential factors contributing to ICU-AW were identified as the length of ICU stay(100.0%)and the duration of mechanical ventilation(54.9%).The neural network model predicted ICU-AW with an area under the curve of 0.941,sensitivity of 92.2%,and specificity of 82.7%.CONCLUSION The main factors influencing ICU-AW are the length of ICU stay and the duration of mechanical ventilation.A primary preventive strategy,when feasible,involves minimizing both ICU stay and mechanical ventilation duration.展开更多
High-efficiency and low-cost knowledge sharing can improve the decision-making ability of autonomous vehicles by mining knowledge from the Internet of Vehicles(IoVs).However,it is challenging to ensure high efficiency...High-efficiency and low-cost knowledge sharing can improve the decision-making ability of autonomous vehicles by mining knowledge from the Internet of Vehicles(IoVs).However,it is challenging to ensure high efficiency of local data learning models while preventing privacy leakage in a high mobility environment.In order to protect data privacy and improve data learning efficiency in knowledge sharing,we propose an asynchronous federated broad learning(FBL)framework that integrates broad learning(BL)into federated learning(FL).In FBL,we design a broad fully connected model(BFCM)as a local model for training client data.To enhance the wireless channel quality for knowledge sharing and reduce the communication and computation cost of participating clients,we construct a joint resource allocation and reconfigurable intelligent surface(RIS)configuration optimization framework for FBL.The problem is decoupled into two convex subproblems.Aiming to improve the resource scheduling efficiency in FBL,a double Davidon–Fletcher–Powell(DDFP)algorithm is presented to solve the time slot allocation and RIS configuration problem.Based on the results of resource scheduling,we design a reward-allocation algorithm based on federated incentive learning(FIL)in FBL to compensate clients for their costs.The simulation results show that the proposed FBL framework achieves better performance than the comparison models in terms of efficiency,accuracy,and cost for knowledge sharing in the IoV.展开更多
Jet grouting is one of the most popular soil improvement techniques,but its design usually involves great uncertainties that can lead to economic cost overruns in construction projects.The high dispersion in the prope...Jet grouting is one of the most popular soil improvement techniques,but its design usually involves great uncertainties that can lead to economic cost overruns in construction projects.The high dispersion in the properties of the improved material leads to designers assuming a conservative,arbitrary and unjustified strength,which is even sometimes subjected to the results of the test fields.The present paper presents an approach for prediction of the uniaxial compressive strength(UCS)of jet grouting columns based on the analysis of several machine learning algorithms on a database of 854 results mainly collected from different research papers.The selected machine learning model(extremely randomized trees)relates the soil type and various parameters of the technique to the value of the compressive strength.Despite the complex mechanism that surrounds the jet grouting process,evidenced by the high dispersion and low correlation of the variables studied,the trained model allows to optimally predict the values of compressive strength with a significant improvement with respect to the existing works.Consequently,this work proposes for the first time a reliable and easily applicable approach for estimation of the compressive strength of jet grouting columns.展开更多
Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metavers...Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metaverses. However, avatar tasks include a multitude of human-to-avatar and avatar-to-avatar interactive applications, e.g., augmented reality navigation,which consumes intensive computing resources. It is inefficient and impractical for vehicles to process avatar tasks locally. Fortunately, migrating avatar tasks to the nearest roadside units(RSU)or unmanned aerial vehicles(UAV) for execution is a promising solution to decrease computation overhead and reduce task processing latency, while the high mobility of vehicles brings challenges for vehicles to independently perform avatar migration decisions depending on current and future vehicle status. To address these challenges, in this paper, we propose a novel avatar task migration system based on multi-agent deep reinforcement learning(MADRL) to execute immersive vehicular avatar tasks dynamically. Specifically, we first formulate the problem of avatar task migration from vehicles to RSUs/UAVs as a partially observable Markov decision process that can be solved by MADRL algorithms. We then design the multi-agent proximal policy optimization(MAPPO) approach as the MADRL algorithm for the avatar task migration problem. To overcome slow convergence resulting from the curse of dimensionality and non-stationary issues caused by shared parameters in MAPPO, we further propose a transformer-based MAPPO approach via sequential decision-making models for the efficient representation of relationships among agents. Finally, to motivate terrestrial or non-terrestrial edge servers(e.g., RSUs or UAVs) to share computation resources and ensure traceability of the sharing records, we apply smart contracts and blockchain technologies to achieve secure sharing management. Numerical results demonstrate that the proposed approach outperforms the MAPPO approach by around 2% and effectively reduces approximately 20% of the latency of avatar task execution in UAV-assisted vehicular Metaverses.展开更多
This work constructed a machine learning(ML)model to predict the atmospheric corrosion rate of low-alloy steels(LAS).The material properties of LAS,environmental factors,and exposure time were used as the input,while ...This work constructed a machine learning(ML)model to predict the atmospheric corrosion rate of low-alloy steels(LAS).The material properties of LAS,environmental factors,and exposure time were used as the input,while the corrosion rate as the output.6 dif-ferent ML algorithms were used to construct the proposed model.Through optimization and filtering,the eXtreme gradient boosting(XG-Boost)model exhibited good corrosion rate prediction accuracy.The features of material properties were then transformed into atomic and physical features using the proposed property transformation approach,and the dominant descriptors that affected the corrosion rate were filtered using the recursive feature elimination(RFE)as well as XGBoost methods.The established ML models exhibited better predic-tion performance and generalization ability via property transformation descriptors.In addition,the SHapley additive exPlanations(SHAP)method was applied to analyze the relationship between the descriptors and corrosion rate.The results showed that the property transformation model could effectively help with analyzing the corrosion behavior,thereby significantly improving the generalization ability of corrosion rate prediction models.展开更多
基金supported in part by the National Natural Science Foundation of China under Grant 62072351in part by the Academy of Finland under Grant 308087,Grant 335262,Grant 345072,and Grant 350464+1 种基金in part by the Open Project of Zhejiang Lab under Grant 2021PD0AB01in part by the 111 Project under Grant B16037.
文摘Digital Twin(DT)supports real time analysis and provides a reliable simulation platform in the Internet of Things(IoT).The creation and application of DT hinges on amounts of data,which poses pressure on the application of Artificial Intelligence(AI)for DT descriptions and intelligent decision-making.Federated Learning(FL)is a cutting-edge technology that enables geographically dispersed devices to collaboratively train a shared global model locally rather than relying on a data center to perform model training.Therefore,DT can benefit by combining with FL,successfully solving the"data island"problem in traditional AI.However,FL still faces serious challenges,such as enduring single-point failures,suffering from poison attacks,lacking effective incentive mechanisms.Before the successful deployment of DT,we should tackle the issues caused by FL.Researchers from industry and academia have recognized the potential of introducing Blockchain Technology(BT)into FL to overcome the challenges faced by FL,where BT acting as a distributed and immutable ledger,can store data in a secure,traceable,and trusted manner.However,to the best of our knowledge,a comprehensive literature review on this topic is still missing.In this paper,we review existing works about blockchain-enabled FL and visualize their prospects with DT.To this end,we first propose evaluation requirements with respect to security,faulttolerance,fairness,efficiency,cost-saving,profitability,and support for heterogeneity.Then,we classify existing literature according to the functionalities of BT in FL and analyze their advantages and disadvantages based on the proposed evaluation requirements.Finally,we discuss open problems in the existing literature and the future of DT supported by blockchain-enabled FL,based on which we further propose some directions for future research.
基金supported by the National Natural Science Foundation of China(No.61871283).
文摘The Autonomous Underwater Glider(AUG)is a kind of prevailing underwater intelligent internet vehicle and occupies a dominant position in industrial applications,in which path planning is an essential problem.Due to the complexity and variability of the ocean,accurate environment modeling and flexible path planning algorithms are pivotal challenges.The traditional models mainly utilize mathematical functions,which are not complete and reliable.Most existing path planning algorithms depend on the environment and lack flexibility.To overcome these challenges,we propose a path planning system for underwater intelligent internet vehicles.It applies digital twins and sensor data to map the real ocean environment to a virtual digital space,which provides a comprehensive and reliable environment for path simulation.We design a value-based reinforcement learning path planning algorithm and explore the optimal network structure parameters.The path simulation is controlled by a closed-loop model integrated into the terminal vehicle through edge computing.The integration of state input enriches the learning of neural networks and helps to improve generalization and flexibility.The task-related reward function promotes the rapid convergence of the training.The experimental results prove that our reinforcement learning based path planning algorithm has great flexibility and can effectively adapt to a variety of different ocean conditions.
基金supported in part by the National Nature Science Foundation of China under Grant 62001168in part by the Foundation and Application Research Grant of Guangzhou under Grant 202102020515。
文摘The rapid development of emerging technologies,such as edge intelligence and digital twins,have added momentum towards the development of the Industrial Internet of Things(IIo T).However,the massive amount of data generated by the IIo T,coupled with heterogeneous computation capacity across IIo T devices,and users’data privacy concerns,have posed challenges towards achieving industrial edge intelligence(IEI).To achieve IEI,in this paper,we propose a semi-federated learning framework where a portion of the data with higher privacy is kept locally and a portion of the less private data can be potentially uploaded to the edge server.In addition,we leverage digital twins to overcome the problem of computation capacity heterogeneity of IIo T devices through the mapping of physical entities.We formulate a synchronization latency minimization problem which jointly optimizes edge association and the proportion of uploaded nonprivate data.As the joint problem is NP-hard and combinatorial and taking into account the reality of largescale device training,we develop a multi-agent hybrid action deep reinforcement learning(DRL)algorithm to find the optimal solution.Simulation results show that our proposed DRL algorithm can reduce latency and have a better convergence performance for semi-federated learning compared to benchmark algorithms.
基金This work was partly supported by the Project of Cultivation for young top-motch Talents of Beijing Municipal Institutions(No BPHR202203225)the Young Elite Scientists Sponsorship Program by BAST(BYESS2023031)the National key research and development program(No 2022YFF0604502).
文摘Limited by battery and computing re-sources,the computing-intensive tasks generated by Internet of Things(IoT)devices cannot be processed all by themselves.Mobile edge computing(MEC)is a suitable solution for this problem,and the gener-ated tasks can be offloaded from IoT devices to MEC.In this paper,we study the problem of dynamic task offloading for digital twin-empowered MEC.Digital twin techniques are applied to provide information of environment and share the training data of agent de-ployed on IoT devices.We formulate the task offload-ing problem with the goal of maximizing the energy efficiency and the workload balance among the ESs.Then,we reformulate the problem as an MDP problem and design DRL-based energy efficient task offloading(DEETO)algorithm to solve it.Comparative experi-ments are carried out which show the superiority of our DEETO algorithm in improving energy efficiency and balancing the workload.
文摘Over the past two decades,digital microfluidic biochips have been in much demand for safety-critical and biomedical applications and increasingly important in point-of-care analysis,drug discovery,and immunoassays,among other areas.However,for complex bioassays,finding routes for the transportation of droplets in an electrowetting-on-dielectric digital biochip while maintaining their discreteness is a challenging task.In this study,we propose a deep reinforcement learning-based droplet routing technique for digital microfluidic biochips.The technique is implemented on a distributed architecture to optimize the possible paths for predefined source–target pairs of droplets.The actors of the technique calculate the possible routes of the source–target pairs and store the experience in a replay buffer,and the learner fetches the experiences and updates the routing paths.The proposed algorithm was applied to benchmark suitesⅠand Ⅲ as two different test benches,and it achieved significant improvements over state-of-the-art techniques.
基金supported by the National Key Research and Development Program of China (2020YFB1807700)the National Natural Science Foundation of China (NSFC)under Grant No.62071356the Chongqing Key Laboratory of Mobile Communications Technology under Grant cqupt-mct202202。
文摘In this paper,to deal with the heterogeneity in federated learning(FL)systems,a knowledge distillation(KD)driven training framework for FL is proposed,where each user can select its neural network model on demand and distill knowledge from a big teacher model using its own private dataset.To overcome the challenge of train the big teacher model in resource limited user devices,the digital twin(DT)is exploit in the way that the teacher model can be trained at DT located in the server with enough computing resources.Then,during model distillation,each user can update the parameters of its model at either the physical entity or the digital agent.The joint problem of model selection and training offloading and resource allocation for users is formulated as a mixed integer programming(MIP)problem.To solve the problem,Q-learning and optimization are jointly used,where Q-learning selects models for users and determines whether to train locally or on the server,and optimization is used to allocate resources for users based on the output of Q-learning.Simulation results show the proposed DT-assisted KD framework and joint optimization method can significantly improve the average accuracy of users while reducing the total delay.
基金supported in part by the Natural Science Foundation of China under Grant 62001054,Grant 62272053 and Grant 61901191in part by the Natural Science Foundation of Shandong Province of China under Grant ZR2020LZH005in part by the Fundamental Research Funds for the Central Universities。
文摘The connected autonomous vehicle is considered an effective way to improve transport safety and efficiency.To overcome the limited sensing and computing capabilities of individual vehicles,we design a digital twin assisted decision-making framework for Internet of Vehicles,by leveraging the integration of communication,sensing and computing.In this framework,the digital twin entities residing on edge can effectively communicate and cooperate with each other to plan sub-targets for their respective vehicles,while the vehicles only need to achieve the sub-targets by generating a sequence of atomic actions.Furthermore,we propose a hierarchical multiagent reinforcement learning approach to implement the framework,which can be trained in an end-to-end way.In the proposed approach,the communication interval of digital twin entities could adapt to timevarying environment.Extensive experiments on driving decision-making have been performed in traffic junction scenarios of different difficulties.The experimental results show that the proposed approach can largely improve collaboration efficiency while reducing communication overhead.
文摘Mechanical metamaterials such as auxetic materials have attracted great interest due to their unusual properties that are dictated by their architectures.However,these architected materials usually have low stiffness because of the bending or rotation deformation mechanisms in the microstructures.In this work,a convolutional neural network(CNN)based self-learning multi-objective optimization is performed to design digital composite materials.The CNN models have undergone rigorous training using randomly generated two-phase digital composite materials,along with their corresponding Poisson's ratios and stiffness values.Then the CNN models are used for designing composite material structures with the minimum Poisson's ratio at a given volume fraction constraint.Furthermore,we have designed composite materials with optimized stiffness while exhibiting a desired Poisson's ratio(negative,zero,or positive).The optimized designs have been successfully and efficiently obtained,and their validity has been confirmed through finite element analysis results.This self-learning multi-objective optimization model offers a promising approach for achieving comprehensive multi-objective optimization.
文摘With the advent of the“fourth industrial revolution”,the digital trend has become a hot issue in the field of architecture.Colleges and universities are an important part of Chinese society,and the development of digital technology has had a profound impact on college life.In order to explore the new campus development path in line with the development trend of the digital society,the old library of North China University of Technology is taken as the research object.The new teaching mode and learning mode under the digital trend are discussed,and the learning space renewal strategy in line with the new era background is explored,with a view to contributing practical experience in space renewal of colleges and universities.
基金supported by Security Research Center at Naif Arab University for Security Sciences(Project No.SRC-PR2-01).
文摘Deep learning is considered one of the most efficient and reliable methods through which the legitimacy of a digital image can be verified.In the current cyber world where deepfakes have shaken the global community,confirming the legitimacy of a digital image is of great importance.With the advancements made in deep learning techniques,now we can efficiently train and develop state-of-the-art digital image forensic models.The most traditional and widely used method by researchers is convolution neural networks(CNN)for verification of image authenticity but it consumes a considerable number of resources and requires a large dataset for training.Therefore,in this study,a transfer learning based deep learning technique for image forgery detection is proposed.The proposed methodology consists of three modules namely;preprocessing module,convolutional module,and the classification module.By using our proposed technique,the training time is drastically reduced by utilizing the pre-trained weights.The performance of the proposed technique is evaluated by using benchmark datasets,i.e.,BOW and BOSSBase that detect five forensic types which include JPEG compression,contrast enhancement(CE),median filtering(MF),additive Gaussian noise,and resampling.We evaluated the performance of our proposed technique by conducting various experiments and case scenarios and achieved an accuracy of 99.92%.The results show the superiority of the proposed system.
文摘As professors are subjected to teaching their classes online due to the recent COVID-19, our local Hong Kong students find it difficult to consult their teachers, and ultimately would fail to achieve the intended learning outcomes, especially for practical-based subjects. In this research, students having online classes of a practical-based fabric design subject were encouraged to self-study from Open Educational Resource (OER) materials for a further and better understanding of their subject. Additionally, online materials were developed to improve students’ understanding via skill of digital literacy. Their learning progress was evaluated and compared to the face-to-face version. The majority of students found online classes combined with self-studying OER materials, potentially be a substitute for face-to-face classes. Most of the students further opined different OER videos assisted them without any face-to-face instructions in practical works, to develop new fabric samples from the inspiration. Analysis of test results, and comparison of students’ final grades with different learning modes, supported these phenomena.
基金the Iranian National Science Foundation(INSF)for the financial support of this research under Project Number 4004169Isfahan University of Technology。
文摘Knowledge about the spatial distribution of the soil physical and mechanical properties is crucial for soil management,water yield,and sustainability at the watershed scale;however,the lack of soil data hinders the application of this tool,thus urging the need to estimate soil properties and consequently,to perform the spatial distribution.This research attempted to examine the proficiency of three machine learning methods(RF:Random Forest;Cubist:Regression Tree;and SVM:Support Vector Machine)to predict soil physical and mechanical properties,saturated hydraulic conductivity(Ks),Cohesion measured by fall-cone at the saturated(Psat)and dry(Pdry)states,hardness index(HI)and dry shear strength(SS)by integrating environmental variables and soil features in the Zayandeh-Rood dam watershed,central Iran.To determine the best combination of input variables,three scenarios were examined as follows:scenarioⅠ,terrain attributes derivative from a digital elevation model(DEM)+remotely sensed data;scenarioⅡ,covariates of scenarioⅠ+selected climatic data and some thematic maps;scenarioⅢ,covariates in scenarioⅡ+intrinsic soil properties(Clay,Silt,Sand,bulk density(BD),soil organic matter(SOM),calcium carbonate equivalent(CCE),mean weight diameter(MWD)and geometric weight diameter(GWD)).The results showed that for Ks,Psat Pdry and SS,the best performance was found by the RF model in the third scenario,with R2=0.53,0.32,0.31 and 0.41,respectively,while for soil hardness index(HI),Cubist model in the third scenario with R2=0.25 showed the highest performance.For predicting Ks and Psat,soil characteristics(i.e.clay and soil SOM and BD),and land use were the most important variables.For predicting Pdry,HI,and SS,some topographical characteristics(Valley depth,catchment area,mltiresolution of ridge top flatness index),and some soil characteristics(i.e.clay,SOM and MWD)were the most important input variables.The results of this research present moderate accuracy,however,the methodology employed provides quick and costeffective information serving as the scientific basis for decision-making goals.
文摘Stroke is a leading cause of disability and mortality worldwide,necessitating the development of advanced technologies to improve its diagnosis,treatment,and patient outcomes.In recent years,machine learning techniques have emerged as promising tools in stroke medicine,enabling efficient analysis of large-scale datasets and facilitating personalized and precision medicine approaches.This abstract provides a comprehensive overview of machine learning’s applications,challenges,and future directions in stroke medicine.Recently introduced machine learning algorithms have been extensively employed in all the fields of stroke medicine.Machine learning models have demonstrated remarkable accuracy in imaging analysis,diagnosing stroke subtypes,risk stratifications,guiding medical treatment,and predicting patient prognosis.Despite the tremendous potential of machine learning in stroke medicine,several challenges must be addressed.These include the need for standardized and interoperable data collection,robust model validation and generalization,and the ethical considerations surrounding privacy and bias.In addition,integrating machine learning models into clinical workflows and establishing regulatory frameworks are critical for ensuring their widespread adoption and impact in routine stroke care.Machine learning promises to revolutionize stroke medicine by enabling precise diagnosis,tailored treatment selection,and improved prognostication.Continued research and collaboration among clinicians,researchers,and technologists are essential for overcoming challenges and realizing the full potential of machine learning in stroke care,ultimately leading to enhanced patient outcomes and quality of life.This review aims to summarize all the current implications of machine learning in stroke diagnosis,treatment,and prognostic evaluation.At the same time,another purpose of this paper is to explore all the future perspectives these techniques can provide in combating this disabling disease.
基金Supported by Science and Technology Support Program of Qiandongnan Prefecture,No.Qiandongnan Sci-Tech Support[2021]12Guizhou Province High-Level Innovative Talent Training Program,No.Qiannan Thousand Talents[2022]201701.
文摘BACKGROUND Intensive care unit-acquired weakness(ICU-AW)is a common complication that significantly impacts the patient's recovery process,even leading to adverse outcomes.Currently,there is a lack of effective preventive measures.AIM To identify significant risk factors for ICU-AW through iterative machine learning techniques and offer recommendations for its prevention and treatment.METHODS Patients were categorized into ICU-AW and non-ICU-AW groups on the 14th day post-ICU admission.Relevant data from the initial 14 d of ICU stay,such as age,comorbidities,sedative dosage,vasopressor dosage,duration of mechanical ventilation,length of ICU stay,and rehabilitation therapy,were gathered.The relationships between these variables and ICU-AW were examined.Utilizing iterative machine learning techniques,a multilayer perceptron neural network model was developed,and its predictive performance for ICU-AW was assessed using the receiver operating characteristic curve.RESULTS Within the ICU-AW group,age,duration of mechanical ventilation,lorazepam dosage,adrenaline dosage,and length of ICU stay were significantly higher than in the non-ICU-AW group.Additionally,sepsis,multiple organ dysfunction syndrome,hypoalbuminemia,acute heart failure,respiratory failure,acute kidney injury,anemia,stress-related gastrointestinal bleeding,shock,hypertension,coronary artery disease,malignant tumors,and rehabilitation therapy ratios were significantly higher in the ICU-AW group,demonstrating statistical significance.The most influential factors contributing to ICU-AW were identified as the length of ICU stay(100.0%)and the duration of mechanical ventilation(54.9%).The neural network model predicted ICU-AW with an area under the curve of 0.941,sensitivity of 92.2%,and specificity of 82.7%.CONCLUSION The main factors influencing ICU-AW are the length of ICU stay and the duration of mechanical ventilation.A primary preventive strategy,when feasible,involves minimizing both ICU stay and mechanical ventilation duration.
基金supported in part by the National Natural Science Foundation of China(62371116 and 62231020)in part by the Science and Technology Project of Hebei Province Education Department(ZD2022164)+2 种基金in part by the Fundamental Research Funds for the Central Universities(N2223031)in part by the Open Research Project of Xidian University(ISN24-08)Key Laboratory of Cognitive Radio and Information Processing,Ministry of Education(Guilin University of Electronic Technology,China,CRKL210203)。
文摘High-efficiency and low-cost knowledge sharing can improve the decision-making ability of autonomous vehicles by mining knowledge from the Internet of Vehicles(IoVs).However,it is challenging to ensure high efficiency of local data learning models while preventing privacy leakage in a high mobility environment.In order to protect data privacy and improve data learning efficiency in knowledge sharing,we propose an asynchronous federated broad learning(FBL)framework that integrates broad learning(BL)into federated learning(FL).In FBL,we design a broad fully connected model(BFCM)as a local model for training client data.To enhance the wireless channel quality for knowledge sharing and reduce the communication and computation cost of participating clients,we construct a joint resource allocation and reconfigurable intelligent surface(RIS)configuration optimization framework for FBL.The problem is decoupled into two convex subproblems.Aiming to improve the resource scheduling efficiency in FBL,a double Davidon–Fletcher–Powell(DDFP)algorithm is presented to solve the time slot allocation and RIS configuration problem.Based on the results of resource scheduling,we design a reward-allocation algorithm based on federated incentive learning(FIL)in FBL to compensate clients for their costs.The simulation results show that the proposed FBL framework achieves better performance than the comparison models in terms of efficiency,accuracy,and cost for knowledge sharing in the IoV.
基金This work has been supported by the Conselleria de Inno-vación,Universidades,Ciencia y Sociedad Digital de la Generalitat Valenciana(CIAICO/2021/335).
文摘Jet grouting is one of the most popular soil improvement techniques,but its design usually involves great uncertainties that can lead to economic cost overruns in construction projects.The high dispersion in the properties of the improved material leads to designers assuming a conservative,arbitrary and unjustified strength,which is even sometimes subjected to the results of the test fields.The present paper presents an approach for prediction of the uniaxial compressive strength(UCS)of jet grouting columns based on the analysis of several machine learning algorithms on a database of 854 results mainly collected from different research papers.The selected machine learning model(extremely randomized trees)relates the soil type and various parameters of the technique to the value of the compressive strength.Despite the complex mechanism that surrounds the jet grouting process,evidenced by the high dispersion and low correlation of the variables studied,the trained model allows to optimally predict the values of compressive strength with a significant improvement with respect to the existing works.Consequently,this work proposes for the first time a reliable and easily applicable approach for estimation of the compressive strength of jet grouting columns.
基金supported in part by NSFC (62102099, U22A2054, 62101594)in part by the Pearl River Talent Recruitment Program (2021QN02S643)+9 种基金Guangzhou Basic Research Program (2023A04J1699)in part by the National Research Foundation, SingaporeInfocomm Media Development Authority under its Future Communications Research Development ProgrammeDSO National Laboratories under the AI Singapore Programme under AISG Award No AISG2-RP-2020-019Energy Research Test-Bed and Industry Partnership Funding Initiative, Energy Grid (EG) 2.0 programmeDesCartes and the Campus for Research Excellence and Technological Enterprise (CREATE) programmeMOE Tier 1 under Grant RG87/22in part by the Singapore University of Technology and Design (SUTD) (SRG-ISTD-2021- 165)in part by the SUTD-ZJU IDEA Grant SUTD-ZJU (VP) 202102in part by the Ministry of Education, Singapore, through its SUTD Kickstarter Initiative (SKI 20210204)。
文摘Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metaverses. However, avatar tasks include a multitude of human-to-avatar and avatar-to-avatar interactive applications, e.g., augmented reality navigation,which consumes intensive computing resources. It is inefficient and impractical for vehicles to process avatar tasks locally. Fortunately, migrating avatar tasks to the nearest roadside units(RSU)or unmanned aerial vehicles(UAV) for execution is a promising solution to decrease computation overhead and reduce task processing latency, while the high mobility of vehicles brings challenges for vehicles to independently perform avatar migration decisions depending on current and future vehicle status. To address these challenges, in this paper, we propose a novel avatar task migration system based on multi-agent deep reinforcement learning(MADRL) to execute immersive vehicular avatar tasks dynamically. Specifically, we first formulate the problem of avatar task migration from vehicles to RSUs/UAVs as a partially observable Markov decision process that can be solved by MADRL algorithms. We then design the multi-agent proximal policy optimization(MAPPO) approach as the MADRL algorithm for the avatar task migration problem. To overcome slow convergence resulting from the curse of dimensionality and non-stationary issues caused by shared parameters in MAPPO, we further propose a transformer-based MAPPO approach via sequential decision-making models for the efficient representation of relationships among agents. Finally, to motivate terrestrial or non-terrestrial edge servers(e.g., RSUs or UAVs) to share computation resources and ensure traceability of the sharing records, we apply smart contracts and blockchain technologies to achieve secure sharing management. Numerical results demonstrate that the proposed approach outperforms the MAPPO approach by around 2% and effectively reduces approximately 20% of the latency of avatar task execution in UAV-assisted vehicular Metaverses.
基金the National Key R&D Program of China(No.2021YFB3701705).
文摘This work constructed a machine learning(ML)model to predict the atmospheric corrosion rate of low-alloy steels(LAS).The material properties of LAS,environmental factors,and exposure time were used as the input,while the corrosion rate as the output.6 dif-ferent ML algorithms were used to construct the proposed model.Through optimization and filtering,the eXtreme gradient boosting(XG-Boost)model exhibited good corrosion rate prediction accuracy.The features of material properties were then transformed into atomic and physical features using the proposed property transformation approach,and the dominant descriptors that affected the corrosion rate were filtered using the recursive feature elimination(RFE)as well as XGBoost methods.The established ML models exhibited better predic-tion performance and generalization ability via property transformation descriptors.In addition,the SHapley additive exPlanations(SHAP)method was applied to analyze the relationship between the descriptors and corrosion rate.The results showed that the property transformation model could effectively help with analyzing the corrosion behavior,thereby significantly improving the generalization ability of corrosion rate prediction models.