This paper mainly focuses on the development of a learning-based controller for a class of uncertain mechanical systems modeled by the Euler-Lagrange formulation.The considered system can depict the behavior of a larg...This paper mainly focuses on the development of a learning-based controller for a class of uncertain mechanical systems modeled by the Euler-Lagrange formulation.The considered system can depict the behavior of a large class of engineering systems,such as vehicular systems,robot manipulators and satellites.All these systems are often characterized by highly nonlinear characteristics,heavy modeling uncertainties and unknown perturbations,therefore,accurate-model-based nonlinear control approaches become unavailable.Motivated by the challenge,a reinforcement learning(RL)adaptive control methodology based on the actor-critic framework is investigated to compensate the uncertain mechanical dynamics.The approximation inaccuracies caused by RL and the exogenous unknown disturbances are circumvented via a continuous robust integral of the sign of the error(RISE)control approach.Different from a classical RISE control law,a tanh(·)function is utilized instead of a sign(·)function to acquire a more smooth control signal.The developed controller requires very little prior knowledge of the dynamic model,is robust to unknown dynamics and exogenous disturbances,and can achieve asymptotic output tracking.Eventually,co-simulations through ADAMS and MATLAB/Simulink on a three degrees-of-freedom(3-DOF)manipulator and experiments on a real-time electromechanical servo system are performed to verify the performance of the proposed approach.展开更多
Aiming at training the feed-forward threshold neural network consisting of nondifferentiable activation functions, the approach of noise injection forms a stochastic resonance based threshold network that can be optim...Aiming at training the feed-forward threshold neural network consisting of nondifferentiable activation functions, the approach of noise injection forms a stochastic resonance based threshold network that can be optimized by various gradientbased optimizers. The introduction of injected noise extends the noise level into the parameter space of the designed threshold network, but leads to a highly non-convex optimization landscape of the loss function. Thus, the hyperparameter on-line learning procedure with respective to network weights and noise levels becomes of challenge. It is shown that the Adam optimizer, as an adaptive variant of stochastic gradient descent, manifests its superior learning ability in training the stochastic resonance based threshold network effectively. Experimental results demonstrate the significant improvement of performance of the designed threshold network trained by the Adam optimizer for function approximation and image classification.展开更多
In this paper, a learning control approach is applied to the generalized projective synchronisation （GPS） of different chaotic systems with unknown periodically time-varying parameters. Using the Lyapunov--Krasovski...In this paper, a learning control approach is applied to the generalized projective synchronisation （GPS） of different chaotic systems with unknown periodically time-varying parameters. Using the Lyapunov--Krasovskii functional stability theory, a differential-difference mixed parametric learning law and an adaptive learning control law are constructed to make the states of two different chaotic systems asymptotically synchronised. The scheme is successfully applied to the generalized projective synchronisation between the Lorenz system and Chen system. Moreover, numerical simulations results are used to verify the effectiveness of the proposed scheme.展开更多
Adaptive optics techniques have been developed over the past half century and routinely used in large ground-based telescopes for more than 30 years.Although this technique has already been used in various application...Adaptive optics techniques have been developed over the past half century and routinely used in large ground-based telescopes for more than 30 years.Although this technique has already been used in various applications,the basic setup and methods have not changed over the past 40 years.In recent years,with the rapid development of artificial in-telligence,adaptive optics will be boosted dramatically.In this paper,the recent advances on almost all aspects of adapt-ive optics based on machine learning are summarized.The state-of-the-art performance of intelligent adaptive optics are reviewed.The potential advantages and deficiencies of intelligent adaptive optics are also discussed.展开更多
Prediction of primary quality variables in real time with adaptation capability for varying process conditions is a critical task in process industries.This article focuses on the development of non-linear adaptive so...Prediction of primary quality variables in real time with adaptation capability for varying process conditions is a critical task in process industries.This article focuses on the development of non-linear adaptive soft sensors for prediction of naphtha initial boiling point(IBP)and end boiling point(EBP)in crude distillation unit.In this work,adaptive inferential sensors with linear and non-linear local models are reported based on recursive just in time learning(JITL)approach.The different types of local models designed are locally weighted regression(LWR),multiple linear regression(MLR),partial least squares regression(PLS)and support vector regression(SVR).In addition to model development,the effect of relevant dataset size on model prediction accuracy and model computation time is also investigated.Results show that the JITL model based on support vector regression with iterative single data algorithm optimization(ISDA)local model(JITL-SVR:ISDA)yielded best prediction accuracy in reasonable computation time.展开更多
The multi-source passive localization problem is a problem of great interest in signal pro-cessing with many applications.In this paper,a sparse representation model based on covariance matrix is constructed for the l...The multi-source passive localization problem is a problem of great interest in signal pro-cessing with many applications.In this paper,a sparse representation model based on covariance matrix is constructed for the long-range localization scenario,and a sparse Bayesian learning algo-rithm based on Laplace prior of signal covariance is developed for the base mismatch problem caused by target deviation from the initial point grid.An adaptive grid sparse Bayesian learning targets localization(AGSBL)algorithm is proposed.The AGSBL algorithm implements a covari-ance-based sparse signal reconstruction and grid adaptive localization dictionary learning.Simula-tion results show that the AGSBL algorithm outperforms the traditional compressed-aware localiza-tion algorithm for different signal-to-noise ratios and different number of targets in long-range scenes.展开更多
Aimed at the lack of self-tuning PID parameters in conventional PID controllers, the structure and learning algorithm of an adaptive PID controller based on reinforcement learning were proposed. Actor-Critic learning ...Aimed at the lack of self-tuning PID parameters in conventional PID controllers, the structure and learning algorithm of an adaptive PID controller based on reinforcement learning were proposed. Actor-Critic learning was used to tune PID parameters in an adaptive way by taking advantage of the model-free and on-line learning properties of reinforcement learning effectively. In order to reduce the demand of storage space and to improve the learning efficiency, a single RBF neural network was used to approximate the policy function of Actor and the value function of Critic simultaneously. The inputs of RBF network are the system error, as well as the first and the second-order differences of error. The Actor can realize the mapping from the system state to PID parameters, while the Critic evaluates the outputs of the Actor and produces TD error. Based on TD error performance index and gradient descent method, the updating rules of RBF kernel function and network weights were given. Simulation results show that the proposed controller is efficient for complex nonlinear systems and it is perfectly adaptable and strongly robust, which is better than that of a conventional PID controller.展开更多
Conventional machine learning(CML)methods have been successfully applied for gas reservoir prediction.Their prediction accuracy largely depends on the quality of the sample data;therefore,feature optimization of the i...Conventional machine learning(CML)methods have been successfully applied for gas reservoir prediction.Their prediction accuracy largely depends on the quality of the sample data;therefore,feature optimization of the input samples is particularly important.Commonly used feature optimization methods increase the interpretability of gas reservoirs;however,their steps are cumbersome,and the selected features cannot sufficiently guide CML models to mine the intrinsic features of sample data efficiently.In contrast to CML methods,deep learning(DL)methods can directly extract the important features of targets from raw data.Therefore,this study proposes a feature optimization and gas-bearing prediction method based on a hybrid fusion model that combines a convolutional neural network(CNN)and an adaptive particle swarm optimization-least squares support vector machine(APSO-LSSVM).This model adopts an end-to-end algorithm structure to directly extract features from sensitive multicomponent seismic attributes,considerably simplifying the feature optimization.A CNN was used for feature optimization to highlight sensitive gas reservoir information.APSO-LSSVM was used to fully learn the relationship between the features extracted by the CNN to obtain the prediction results.The constructed hybrid fusion model improves gas-bearing prediction accuracy through two processes of feature optimization and intelligent prediction,giving full play to the advantages of DL and CML methods.The prediction results obtained are better than those of a single CNN model or APSO-LSSVM model.In the feature optimization process of multicomponent seismic attribute data,CNN has demonstrated better gas reservoir feature extraction capabilities than commonly used attribute optimization methods.In the prediction process,the APSO-LSSVM model can learn the gas reservoir characteristics better than the LSSVM model and has a higher prediction accuracy.The constructed CNN-APSO-LSSVM model had lower errors and a better fit on the test dataset than the other individual models.This method proves the effectiveness of DL technology for the feature extraction of gas reservoirs and provides a feasible way to combine DL and CML technologies to predict gas reservoirs.展开更多
The recent emergence of adaptive language learning systems calls for conceptual work to guide the design of assessment and learning in an adaptive environment.Although adaptive learning might have been touted as a uni...The recent emergence of adaptive language learning systems calls for conceptual work to guide the design of assessment and learning in an adaptive environment.Although adaptive learning might have been touted as a universal cure for learning problems,many adaptive language learning systems fall short of educators’expectations,partly due to a lack of standards and best practices in this area.To fill this gap,this paper proposes some major considerations in designing a high-quality assessment and learning experience in adaptive learning and ways to evaluate an adaptive learning system.The architecture of adaptive learning is decomposed,with a chain of inferences supporting the overall efficacy of an adaptive learning system presented,including user property representation,user property estimation,content representation,user interaction representation,and user interaction impact.A detailed analysis of key validity issues is provided for each inference,which motivates the major considerations in designing and evaluating assessment and learning.The paper first provides an overview of different types of assessment used in adaptive learning and an analysis of the assessment approach,priorities,and design considerations of each to optimize its use in adaptive learning.Then it proposes a framework for evaluating different aspects of an adaptive learning system.Some special connections are made to models,techniques,designs,and technologies specific to language learning and assessment,bringing more relevance to adaptive language learning solutions.Through establishing some guidelines on key aspects to evaluate and how to evaluate them,the work intends to bring more rigor to the field of adaptive language learning systems.展开更多
The rapid growth of modern mobile devices leads to a large number of distributed data,which is extremely valuable for learning models.Unfortunately,model training by collecting all these original data to a centralized...The rapid growth of modern mobile devices leads to a large number of distributed data,which is extremely valuable for learning models.Unfortunately,model training by collecting all these original data to a centralized cloud server is not applicable due to data privacy and communication costs concerns,hindering artificial intelligence from empowering mobile devices.Moreover,these data are not identically and independently distributed(Non-IID)caused by their different context,which will deteriorate the performance of the model.To address these issues,we propose a novel Distributed Learning algorithm based on hierarchical clustering and Adaptive Dataset Condensation,named ADC-DL,which learns a shared model by collecting the synthetic samples generated on each device.To tackle the heterogeneity of data distribution,we propose an entropy topsis comprehensive tiering model for hierarchical clustering,which distinguishes clients in terms of their data characteristics.Subsequently,synthetic dummy samples are generated based on the hierarchical structure utilizing adaptive dataset condensation.The procedure of dataset condensation can be adjusted adaptively according to the tier of the client.Extensive experiments demonstrate that the performance of our ADC-DL is more outstanding in prediction accuracy and communication costs compared with existing algorithms.展开更多
Transfer learning aims to transfer source models to a target domain.Leveraging the feature matching can alleviate the domain shift effectively,but this process ignores the relationship of the marginal distribution mat...Transfer learning aims to transfer source models to a target domain.Leveraging the feature matching can alleviate the domain shift effectively,but this process ignores the relationship of the marginal distribution matching and the conditional distribution matching.Simultaneously,the discriminative information of both domains is also neglected,which is important for improving the performance on the target domain.In this paper,we propose a novel method called Balanced Discriminative Transfer Feature Learning for Visual Domain Adaptation(BDTFL).The proposed method can adaptively balance the relationship of both distribution matchings and capture the category discriminative information of both domains.Therefore,balanced feature matching can achieve more accurate feature matching and adaptively adjust itself to different scenes.At the same time,discriminative information is exploited to alleviate category confusion during feature matching.And with assistance of the category discriminative information captured from both domains,the source classifier can be transferred to the target domain more accurately and boost the performance of target classification.Extensive experiments show the superiority of BDTFL on popular visual cross-domain benchmarks.展开更多
针对海上无线网状网通信环境复杂多变、船舶节点具有特殊移动模型等特点,提出一种基于Q-Learning的自适应路由(Q-Learning Based Adaptive Routing,QLAR)算法。综合考虑海上无线电波传播特性、船舶航程信息以及相应海区气象信息等因素...针对海上无线网状网通信环境复杂多变、船舶节点具有特殊移动模型等特点,提出一种基于Q-Learning的自适应路由(Q-Learning Based Adaptive Routing,QLAR)算法。综合考虑海上无线电波传播特性、船舶航程信息以及相应海区气象信息等因素的影响,提出链路可靠性、链路稳定性和节点航程相似度等概念,并对链路状态进行评估;然后,根据链路状态评估结果,利用Q-Learning算法寻找源、目的节点间最稳定的路径以传输数据分组;最后,利用OPNET搭建仿真平台对算法进行测试。仿真结果表明,与4种对比算法中性能最优的算法相比,QLAR算法最高可提升分组投递率4.89%,降低平均分组时延17.42%,减少归一化路由开销21.99%。展开更多
Traditional coal mine safety prediction methods are off-line and do not have dynamic prediction functions.The Support Vector Machine(SVM) is a new machine learning algorithm that has excellent properties.The least squ...Traditional coal mine safety prediction methods are off-line and do not have dynamic prediction functions.The Support Vector Machine(SVM) is a new machine learning algorithm that has excellent properties.The least squares support vector machine(LS-SVM) algorithm is an improved algorithm of SVM.But the common LS-SVM algorithm,used directly in safety predictions,has some problems.We have first studied gas prediction problems and the basic theory of LS-SVM.Given these problems,we have investigated the affect of the time factor about safety prediction and present an on-line prediction algorithm,based on LS-SVM.Finally,given our observed data,we used the on-line algorithm to predict gas emissions and used other related algorithm to compare its performance.The simulation results have verified the validity of the new algorithm.展开更多
Single gimbal control moment gyroscope(SGCMG)with high precision and fast response is an important attitude control system for high precision docking,rapid maneuvering navigation and guidance system in the aerospace f...Single gimbal control moment gyroscope(SGCMG)with high precision and fast response is an important attitude control system for high precision docking,rapid maneuvering navigation and guidance system in the aerospace field.In this paper,considering the influence of multi-source disturbance,a data-based feedback relearning(FR)algorithm is designed for the robust control of SGCMG gimbal servo system.Based on adaptive dynamic programming and least-square principle,the FR algorithm is used to obtain the servo control strategy by collecting the online operation data of SGCMG system.This is a model-free learning strategy in which no prior knowledge of the SGCMG model is required.Then,combining the reinforcement learning mechanism,the servo control strategy is interacted with system dynamic of SGCMG.The adaptive evaluation and improvement of servo control strategy against the multi-source disturbance are realized.Meanwhile,a data redistribution method based on experience replay is designed to reduce data correlation to improve algorithm stability and data utilization efficiency.Finally,by comparing with other methods on the simulation model of SGCMG,the effectiveness of the proposed servo control strategy is verified.展开更多
Estimating time-selective millimeter wave wireless channels and then deriving the optimum beam alignment for directional antennas is a challenging task.To solve this problem,one can focus on tracking the strongest mul...Estimating time-selective millimeter wave wireless channels and then deriving the optimum beam alignment for directional antennas is a challenging task.To solve this problem,one can focus on tracking the strongest multipath components(MPCs).Aligning antenna beams with the tracked MPCs increases the channel coherence time by several orders of magnitude.This contribution suggests tracking the MPCs geometrically.The derived geometric tracker is based on algorithms known as Doppler bearing tracking.A recent work on geometric-polar tracking is reformulated into an efficient recursive version.If the relative position of the MPCs is known,all other sensors on board a vehicle,e.g.,lidar,radar,and camera,will perform active learning based on their own observed data.By learning the relationship between sensor data and MPCs,onboard sensors can participate in channel tracking.Joint tracking of many integrated sensors will increase the reliability of MPC tracking.展开更多
基金supported in part by the National Key R&D Program of China under Grant 2021YFB2011300the National Natural Science Foundation of China under Grant 52075262。
文摘This paper mainly focuses on the development of a learning-based controller for a class of uncertain mechanical systems modeled by the Euler-Lagrange formulation.The considered system can depict the behavior of a large class of engineering systems,such as vehicular systems,robot manipulators and satellites.All these systems are often characterized by highly nonlinear characteristics,heavy modeling uncertainties and unknown perturbations,therefore,accurate-model-based nonlinear control approaches become unavailable.Motivated by the challenge,a reinforcement learning(RL)adaptive control methodology based on the actor-critic framework is investigated to compensate the uncertain mechanical dynamics.The approximation inaccuracies caused by RL and the exogenous unknown disturbances are circumvented via a continuous robust integral of the sign of the error(RISE)control approach.Different from a classical RISE control law,a tanh(·)function is utilized instead of a sign(·)function to acquire a more smooth control signal.The developed controller requires very little prior knowledge of the dynamic model,is robust to unknown dynamics and exogenous disturbances,and can achieve asymptotic output tracking.Eventually,co-simulations through ADAMS and MATLAB/Simulink on a three degrees-of-freedom(3-DOF)manipulator and experiments on a real-time electromechanical servo system are performed to verify the performance of the proposed approach.
基金Project supported by the Natural Science Foundation of Shandong Province,China(Grant No.ZR2021MF051)。
文摘Aiming at training the feed-forward threshold neural network consisting of nondifferentiable activation functions, the approach of noise injection forms a stochastic resonance based threshold network that can be optimized by various gradientbased optimizers. The introduction of injected noise extends the noise level into the parameter space of the designed threshold network, but leads to a highly non-convex optimization landscape of the loss function. Thus, the hyperparameter on-line learning procedure with respective to network weights and noise levels becomes of challenge. It is shown that the Adam optimizer, as an adaptive variant of stochastic gradient descent, manifests its superior learning ability in training the stochastic resonance based threshold network effectively. Experimental results demonstrate the significant improvement of performance of the designed threshold network trained by the Adam optimizer for function approximation and image classification.
基金supported by the National Natural Science Foundation of China (Grant No. 60374015)
文摘In this paper, a learning control approach is applied to the generalized projective synchronisation （GPS） of different chaotic systems with unknown periodically time-varying parameters. Using the Lyapunov--Krasovskii functional stability theory, a differential-difference mixed parametric learning law and an adaptive learning control law are constructed to make the states of two different chaotic systems asymptotically synchronised. The scheme is successfully applied to the generalized projective synchronisation between the Lorenz system and Chen system. Moreover, numerical simulations results are used to verify the effectiveness of the proposed scheme.
基金funded by the National Natural Science Foundation of China(12173041,11733005,11727805)Youth Innovation Promotion Association,Chinese Academy of Sciences (No.2020376)+2 种基金Frontier Research Fund of Institute of Optics and Electronics,Chinese Academy of Sciences (No.C21K002)Research Equipment Development Project of the Chinese Academy of Sciences (No.YA18K019)Laboratory Innovation Foundation of the Chinese Academy of Sciences (No.YJ20K002)
文摘Adaptive optics techniques have been developed over the past half century and routinely used in large ground-based telescopes for more than 30 years.Although this technique has already been used in various applications,the basic setup and methods have not changed over the past 40 years.In recent years,with the rapid development of artificial in-telligence,adaptive optics will be boosted dramatically.In this paper,the recent advances on almost all aspects of adapt-ive optics based on machine learning are summarized.The state-of-the-art performance of intelligent adaptive optics are reviewed.The potential advantages and deficiencies of intelligent adaptive optics are also discussed.
文摘Prediction of primary quality variables in real time with adaptation capability for varying process conditions is a critical task in process industries.This article focuses on the development of non-linear adaptive soft sensors for prediction of naphtha initial boiling point(IBP)and end boiling point(EBP)in crude distillation unit.In this work,adaptive inferential sensors with linear and non-linear local models are reported based on recursive just in time learning(JITL)approach.The different types of local models designed are locally weighted regression(LWR),multiple linear regression(MLR),partial least squares regression(PLS)and support vector regression(SVR).In addition to model development,the effect of relevant dataset size on model prediction accuracy and model computation time is also investigated.Results show that the JITL model based on support vector regression with iterative single data algorithm optimization(ISDA)local model(JITL-SVR:ISDA)yielded best prediction accuracy in reasonable computation time.
文摘The multi-source passive localization problem is a problem of great interest in signal pro-cessing with many applications.In this paper,a sparse representation model based on covariance matrix is constructed for the long-range localization scenario,and a sparse Bayesian learning algo-rithm based on Laplace prior of signal covariance is developed for the base mismatch problem caused by target deviation from the initial point grid.An adaptive grid sparse Bayesian learning targets localization(AGSBL)algorithm is proposed.The AGSBL algorithm implements a covari-ance-based sparse signal reconstruction and grid adaptive localization dictionary learning.Simula-tion results show that the AGSBL algorithm outperforms the traditional compressed-aware localiza-tion algorithm for different signal-to-noise ratios and different number of targets in long-range scenes.
基金Projects 0601033B supported by the Science Foundation for Post-doctoral Scientists of Jiangsu Province, 0C4466 and 0C060093the Scientific and Technological Foundation for Youth of China University of Mining & Technology
文摘Aimed at the lack of self-tuning PID parameters in conventional PID controllers, the structure and learning algorithm of an adaptive PID controller based on reinforcement learning were proposed. Actor-Critic learning was used to tune PID parameters in an adaptive way by taking advantage of the model-free and on-line learning properties of reinforcement learning effectively. In order to reduce the demand of storage space and to improve the learning efficiency, a single RBF neural network was used to approximate the policy function of Actor and the value function of Critic simultaneously. The inputs of RBF network are the system error, as well as the first and the second-order differences of error. The Actor can realize the mapping from the system state to PID parameters, while the Critic evaluates the outputs of the Actor and produces TD error. Based on TD error performance index and gradient descent method, the updating rules of RBF kernel function and network weights were given. Simulation results show that the proposed controller is efficient for complex nonlinear systems and it is perfectly adaptable and strongly robust, which is better than that of a conventional PID controller.
基金funded by the Natural Science Foundation of Shandong Province (ZR2021MD061ZR2023QD025)+3 种基金China Postdoctoral Science Foundation (2022M721972)National Natural Science Foundation of China (41174098)Young Talents Foundation of Inner Mongolia University (10000-23112101/055)Qingdao Postdoctoral Science Foundation (QDBSH20230102094)。
文摘Conventional machine learning(CML)methods have been successfully applied for gas reservoir prediction.Their prediction accuracy largely depends on the quality of the sample data;therefore,feature optimization of the input samples is particularly important.Commonly used feature optimization methods increase the interpretability of gas reservoirs;however,their steps are cumbersome,and the selected features cannot sufficiently guide CML models to mine the intrinsic features of sample data efficiently.In contrast to CML methods,deep learning(DL)methods can directly extract the important features of targets from raw data.Therefore,this study proposes a feature optimization and gas-bearing prediction method based on a hybrid fusion model that combines a convolutional neural network(CNN)and an adaptive particle swarm optimization-least squares support vector machine(APSO-LSSVM).This model adopts an end-to-end algorithm structure to directly extract features from sensitive multicomponent seismic attributes,considerably simplifying the feature optimization.A CNN was used for feature optimization to highlight sensitive gas reservoir information.APSO-LSSVM was used to fully learn the relationship between the features extracted by the CNN to obtain the prediction results.The constructed hybrid fusion model improves gas-bearing prediction accuracy through two processes of feature optimization and intelligent prediction,giving full play to the advantages of DL and CML methods.The prediction results obtained are better than those of a single CNN model or APSO-LSSVM model.In the feature optimization process of multicomponent seismic attribute data,CNN has demonstrated better gas reservoir feature extraction capabilities than commonly used attribute optimization methods.In the prediction process,the APSO-LSSVM model can learn the gas reservoir characteristics better than the LSSVM model and has a higher prediction accuracy.The constructed CNN-APSO-LSSVM model had lower errors and a better fit on the test dataset than the other individual models.This method proves the effectiveness of DL technology for the feature extraction of gas reservoirs and provides a feasible way to combine DL and CML technologies to predict gas reservoirs.
文摘The recent emergence of adaptive language learning systems calls for conceptual work to guide the design of assessment and learning in an adaptive environment.Although adaptive learning might have been touted as a universal cure for learning problems,many adaptive language learning systems fall short of educators’expectations,partly due to a lack of standards and best practices in this area.To fill this gap,this paper proposes some major considerations in designing a high-quality assessment and learning experience in adaptive learning and ways to evaluate an adaptive learning system.The architecture of adaptive learning is decomposed,with a chain of inferences supporting the overall efficacy of an adaptive learning system presented,including user property representation,user property estimation,content representation,user interaction representation,and user interaction impact.A detailed analysis of key validity issues is provided for each inference,which motivates the major considerations in designing and evaluating assessment and learning.The paper first provides an overview of different types of assessment used in adaptive learning and an analysis of the assessment approach,priorities,and design considerations of each to optimize its use in adaptive learning.Then it proposes a framework for evaluating different aspects of an adaptive learning system.Some special connections are made to models,techniques,designs,and technologies specific to language learning and assessment,bringing more relevance to adaptive language learning solutions.Through establishing some guidelines on key aspects to evaluate and how to evaluate them,the work intends to bring more rigor to the field of adaptive language learning systems.
基金the General Program of National Natural Science Foundation of China(62072049).
文摘The rapid growth of modern mobile devices leads to a large number of distributed data,which is extremely valuable for learning models.Unfortunately,model training by collecting all these original data to a centralized cloud server is not applicable due to data privacy and communication costs concerns,hindering artificial intelligence from empowering mobile devices.Moreover,these data are not identically and independently distributed(Non-IID)caused by their different context,which will deteriorate the performance of the model.To address these issues,we propose a novel Distributed Learning algorithm based on hierarchical clustering and Adaptive Dataset Condensation,named ADC-DL,which learns a shared model by collecting the synthetic samples generated on each device.To tackle the heterogeneity of data distribution,we propose an entropy topsis comprehensive tiering model for hierarchical clustering,which distinguishes clients in terms of their data characteristics.Subsequently,synthetic dummy samples are generated based on the hierarchical structure utilizing adaptive dataset condensation.The procedure of dataset condensation can be adjusted adaptively according to the tier of the client.Extensive experiments demonstrate that the performance of our ADC-DL is more outstanding in prediction accuracy and communication costs compared with existing algorithms.
文摘Transfer learning aims to transfer source models to a target domain.Leveraging the feature matching can alleviate the domain shift effectively,but this process ignores the relationship of the marginal distribution matching and the conditional distribution matching.Simultaneously,the discriminative information of both domains is also neglected,which is important for improving the performance on the target domain.In this paper,we propose a novel method called Balanced Discriminative Transfer Feature Learning for Visual Domain Adaptation(BDTFL).The proposed method can adaptively balance the relationship of both distribution matchings and capture the category discriminative information of both domains.Therefore,balanced feature matching can achieve more accurate feature matching and adaptively adjust itself to different scenes.At the same time,discriminative information is exploited to alleviate category confusion during feature matching.And with assistance of the category discriminative information captured from both domains,the source classifier can be transferred to the target domain more accurately and boost the performance of target classification.Extensive experiments show the superiority of BDTFL on popular visual cross-domain benchmarks.
文摘针对海上无线网状网通信环境复杂多变、船舶节点具有特殊移动模型等特点,提出一种基于Q-Learning的自适应路由(Q-Learning Based Adaptive Routing,QLAR)算法。综合考虑海上无线电波传播特性、船舶航程信息以及相应海区气象信息等因素的影响,提出链路可靠性、链路稳定性和节点航程相似度等概念,并对链路状态进行评估;然后,根据链路状态评估结果,利用Q-Learning算法寻找源、目的节点间最稳定的路径以传输数据分组;最后,利用OPNET搭建仿真平台对算法进行测试。仿真结果表明,与4种对比算法中性能最优的算法相比,QLAR算法最高可提升分组投递率4.89%,降低平均分组时延17.42%,减少归一化路由开销21.99%。
文摘Traditional coal mine safety prediction methods are off-line and do not have dynamic prediction functions.The Support Vector Machine(SVM) is a new machine learning algorithm that has excellent properties.The least squares support vector machine(LS-SVM) algorithm is an improved algorithm of SVM.But the common LS-SVM algorithm,used directly in safety predictions,has some problems.We have first studied gas prediction problems and the basic theory of LS-SVM.Given these problems,we have investigated the affect of the time factor about safety prediction and present an on-line prediction algorithm,based on LS-SVM.Finally,given our observed data,we used the on-line algorithm to predict gas emissions and used other related algorithm to compare its performance.The simulation results have verified the validity of the new algorithm.
基金This work was supported by the National Natural Science Foundation of China(No.62022061)Tianjin Natural Science Foundation(No.20JCYBJC00880)Beijing Key Laboratory Open Fund of Long-Life Technology of Precise Rotation and Transmission Mechanisms.
文摘Single gimbal control moment gyroscope(SGCMG)with high precision and fast response is an important attitude control system for high precision docking,rapid maneuvering navigation and guidance system in the aerospace field.In this paper,considering the influence of multi-source disturbance,a data-based feedback relearning(FR)algorithm is designed for the robust control of SGCMG gimbal servo system.Based on adaptive dynamic programming and least-square principle,the FR algorithm is used to obtain the servo control strategy by collecting the online operation data of SGCMG system.This is a model-free learning strategy in which no prior knowledge of the SGCMG model is required.Then,combining the reinforcement learning mechanism,the servo control strategy is interacted with system dynamic of SGCMG.The adaptive evaluation and improvement of servo control strategy against the multi-source disturbance are realized.Meanwhile,a data redistribution method based on experience replay is designed to reduce data correlation to improve algorithm stability and data utilization efficiency.Finally,by comparing with other methods on the simulation model of SGCMG,the effectiveness of the proposed servo control strategy is verified.
基金supported by the Austrian Federal Ministry for Digital and Economic Affairs
文摘Estimating time-selective millimeter wave wireless channels and then deriving the optimum beam alignment for directional antennas is a challenging task.To solve this problem,one can focus on tracking the strongest multipath components(MPCs).Aligning antenna beams with the tracked MPCs increases the channel coherence time by several orders of magnitude.This contribution suggests tracking the MPCs geometrically.The derived geometric tracker is based on algorithms known as Doppler bearing tracking.A recent work on geometric-polar tracking is reformulated into an efficient recursive version.If the relative position of the MPCs is known,all other sensors on board a vehicle,e.g.,lidar,radar,and camera,will perform active learning based on their own observed data.By learning the relationship between sensor data and MPCs,onboard sensors can participate in channel tracking.Joint tracking of many integrated sensors will increase the reliability of MPC tracking.
