The existing strategy for evaluating the damage condition of structures mostly focuses on feedback supplied by traditional visualmethods,which may result in an unreliable damage characterization due to inspector subje...The existing strategy for evaluating the damage condition of structures mostly focuses on feedback supplied by traditional visualmethods,which may result in an unreliable damage characterization due to inspector subjectivity or insufficient level of expertise.As a result,a robust,reliable,and repeatable method of damage identification is required.Ensemble learning algorithms for identifying structural damage are evaluated in this article,which use deep convolutional neural networks,including simple averaging,integrated stacking,separate stacking,and hybridweighted averaging ensemble and differential evolution(WAE-DE)ensemblemodels.Damage identification is carried out on three types of damage.The proposed algorithms are used to analyze the damage of 4585 structural images.The effectiveness of the ensemble learning techniques is evaluated using the confusion matrix.For the testing dataset,the confusion matrix achieved an accuracy of 94 percent and a minimum recall of 92 percent for the best model(WAE-DE)in distinguishing damage types as flexural,shear,combined,or undamaged.展开更多
Sodium homeostasis disorder is one of the most common abnormal symptoms of elderly patients in intensive care unit(ICU),which may lead to physiological disorders of many organs.The current prediction of serum sodium i...Sodium homeostasis disorder is one of the most common abnormal symptoms of elderly patients in intensive care unit(ICU),which may lead to physiological disorders of many organs.The current prediction of serum sodium in ICU is mainly based on the subjective judgment of doctors’experience.This study aims at this problem by studying the clinical retrospective electronic medical record data of ICU to establish a machine learning model to predict the short-term serum sodium value of ICU patients.The data set used in this study is the open-source intensive care medical information set Medical Information Mart for Intensive Care(MIMIC)-IV.The time point of serum sodium detection was selected from the ICU clinical records,and the ICU records of 25risk factors related to serum sodium were extracted from the patients within the first 12 h for statistical analysis.A prediction model of serum sodium value within 48 h was established using a feedforward neural network,and compared with previous methods.Our research results show that the neural network learning model can predict the development of serum sodium in patients using physiological indicators recorded in clinical electronic medical records within 12 h,and has better prediction effect than the serum sodium formula and other machine learning models.展开更多
This paper proposes an y2-y∞ learning law as a new learning method for dynamic neural networks with external disturbance. Based on linear matrix inequality (LMI) formulation, the y2-y∞ learning law is presented to...This paper proposes an y2-y∞ learning law as a new learning method for dynamic neural networks with external disturbance. Based on linear matrix inequality (LMI) formulation, the y2-y∞ learning law is presented to not only guarantee asymptotical stability of dynamic neural networks but also reduce the effect of external disturbance to an y2-y∞ induced norm constraint. It is shown that the design of the y2-y∞ learning law for such neural networks can be achieved by solving LMIs, which can be easily facilitated by using some standard numerical packages. A numerical example is presented to demonstrate the validity of the proposed learning law.展开更多
This paper first proposes a new self-learning data-driven methodology that can develop the failure criteria of unknown anisotropic ductile materials from the minimal number of experimental tests.Establishing failure c...This paper first proposes a new self-learning data-driven methodology that can develop the failure criteria of unknown anisotropic ductile materials from the minimal number of experimental tests.Establishing failure criteria of anisotropic ductile materials requires time-consuming tests and manual data evaluation.The proposed method can overcome such practical challenges.The methodology is formalized by combining four ideas:1)The deep learning neural network(DLNN)-based material constitutive model,2)Self-learning inverse finite element(SELIFE)simulation,3)Algorithmic identification of failure points from the selflearned stress-strain curves and 4)Derivation of the failure criteria through symbolic regression of the genetic programming.Stress update and the algorithmic tangent operator were formulated in terms of DLNN parameters for nonlinear finite element analysis.Then,the SELIFE simulation algorithm gradually makes the DLNN model learn highly complex multi-axial stress and strain relationships,being guided by the experimental boundary measurements.Following the failure point identification,a self-learning data-driven failure criteria are eventually developed with the help of a reliable symbolic regression algorithm.The methodology and the self-learning data-driven failure criteria were verified by comparing with a reference failure criteria and simulating with different materials orientations,respectively.展开更多
In this article we introduce a large class of optimization problems that can be approximated by neural networks. Furthermore for some large category of optimization problems the action of the corresponding neural netw...In this article we introduce a large class of optimization problems that can be approximated by neural networks. Furthermore for some large category of optimization problems the action of the corresponding neural network will be reduced to linear or quadratic programming, therefore the global optimum could be obtained immediately.展开更多
Protein Secondary Structure Prediction (PSSP) is considered as one of the major challenging tasks in bioinformatics, so many solutions have been proposed to solve that problem via trying to achieve more accurate predi...Protein Secondary Structure Prediction (PSSP) is considered as one of the major challenging tasks in bioinformatics, so many solutions have been proposed to solve that problem via trying to achieve more accurate prediction results. The goal of this paper is to develop and implement an intelligent based system to predict secondary structure of a protein from its primary amino acid sequence by using five models of Neural Network (NN). These models are Feed Forward Neural Network (FNN), Learning Vector Quantization (LVQ), Probabilistic Neural Network (PNN), Convolutional Neural Network (CNN), and CNN Fine Tuning for PSSP. To evaluate our approaches two datasets have been used. The first one contains 114 protein samples, and the second one contains 1845 protein samples.展开更多
This paper investigates exponential stability and trajectory bounds of motions of equilibria of a class of associative neural networks under structural variations as learning a new pattern. Some conditions for the pos...This paper investigates exponential stability and trajectory bounds of motions of equilibria of a class of associative neural networks under structural variations as learning a new pattern. Some conditions for the possible maximum estimate of the domain of structural exponential stability are determined. The filtering ability of the associative neural networks contaminated by input noises is analyzed. Employing the obtained results as valuable guidelines, a systematic synthesis procedure for constructing a dynamical associative neural network that stores a given set of vectors as the stable equilibrium points as well as learns new patterns can be developed. Some new concepts defined here are expected to be the instruction for further studies of learning associative neural networks.展开更多
Fetal ECG extraction has the vital significance for fetal monitoring.This paper introduces a method of extracting fetal ECG based on adaptive linear neural network.The method can be realized by training a small quanti...Fetal ECG extraction has the vital significance for fetal monitoring.This paper introduces a method of extracting fetal ECG based on adaptive linear neural network.The method can be realized by training a small quantity of data.In addition,a better result can be achieved by improving neural network structure.Thus,more easily identified fetal ECG can be extracted.Experimental results show that the adaptive linear neural network can be used to extract fetal ECG from maternal abdominal signal effectively.What's more,a clearer fetal ECG can be extracted by improving neural network structure.展开更多
The objective of dynamical system learning tasks is to forecast the future behavior of a system by leveraging observed data.However,such systems can sometimes exhibit rigidity due to significant variations in componen...The objective of dynamical system learning tasks is to forecast the future behavior of a system by leveraging observed data.However,such systems can sometimes exhibit rigidity due to significant variations in component parameters or the presence of slow and fast variables,leading to challenges in learning.To overcome this limitation,we propose a multiscale differential-algebraic neural network(MDANN)method that utilizes Lagrangian mechanics and incorporates multiscale information for dynamical system learning.The MDANN method consists of two main components:the Lagrangian mechanics module and the multiscale module.The Lagrangian mechanics module embeds the system in Cartesian coordinates,adopts a differential-algebraic equation format,and uses Lagrange multipliers to impose constraints explicitly,simplifying the learning problem.The multiscale module converts high-frequency components into low-frequency components using radial scaling to learn subprocesses with large differences in velocity.Experimental results demonstrate that the proposed MDANN method effectively improves the learning of dynamical systems under rigid conditions.展开更多
This project uses knowledge of neural network to analyze if the person under study is analyzed to be Parkinson disease patient or not. Binary classification is constructed based on the multi-feature database. A decisi...This project uses knowledge of neural network to analyze if the person under study is analyzed to be Parkinson disease patient or not. Binary classification is constructed based on the multi-feature database. A decision boundary is clearly plotted to separate patient with and without Parkinson disease. Results show that over 80% accuracy could be obtained with the preliminary results. Future efforts could be performed to construct more complicated neural network to improve the accuracy.展开更多
Reinforcement learning(RL) has roots in dynamic programming and it is called adaptive/approximate dynamic programming(ADP) within the control community. This paper reviews recent developments in ADP along with RL and ...Reinforcement learning(RL) has roots in dynamic programming and it is called adaptive/approximate dynamic programming(ADP) within the control community. This paper reviews recent developments in ADP along with RL and its applications to various advanced control fields. First, the background of the development of ADP is described, emphasizing the significance of regulation and tracking control problems. Some effective offline and online algorithms for ADP/adaptive critic control are displayed, where the main results towards discrete-time systems and continuous-time systems are surveyed, respectively.Then, the research progress on adaptive critic control based on the event-triggered framework and under uncertain environment is discussed, respectively, where event-based design, robust stabilization, and game design are reviewed. Moreover, the extensions of ADP for addressing control problems under complex environment attract enormous attention. The ADP architecture is revisited under the perspective of data-driven and RL frameworks,showing how they promote ADP formulation significantly.Finally, several typical control applications with respect to RL and ADP are summarized, particularly in the fields of wastewater treatment processes and power systems, followed by some general prospects for future research. Overall, the comprehensive survey on ADP and RL for advanced control applications has d emonstrated its remarkable potential within the artificial intelligence era. In addition, it also plays a vital role in promoting environmental protection and industrial intelligence.展开更多
Accurately estimating the ocean subsurface salinity structure(OSSS)is crucial for understanding ocean dynamics and predicting climate variations.We present a convolutional neural network(CNN)model to estimate the OSSS...Accurately estimating the ocean subsurface salinity structure(OSSS)is crucial for understanding ocean dynamics and predicting climate variations.We present a convolutional neural network(CNN)model to estimate the OSSS in the Indian Ocean using satellite data and Argo observations.We evaluated the performance of the CNN model in terms of its vertical and spatial distribution,as well as seasonal variation of OSSS estimation.Results demonstrate that the CNN model accurately estimates the most significant salinity features in the Indian Ocean using sea surface data with no significant differences from Argo-derived OSSS.However,the estimation accuracy of the CNN model varies with depth,with the most challenging depth being approximately 70 m,corresponding to the halocline layer.Validations of the CNN model’s accuracy in estimating OSSS in the Indian Ocean are also conducted by comparing Argo observations and CNN model estimations along two selected sections and four selected boxes.The results show that the CNN model effectively captures the seasonal variability of salinity,demonstrating its high performance in salinity estimation using sea surface data.Our analysis reveals that sea surface salinity has the strongest correlation with OSSS in shallow layers,while sea surface height anomaly plays a more significant role in deeper layers.These preliminary results provide valuable insights into the feasibility of estimating OSSS using satellite observations and have implications for studying upper ocean dynamics using machine learning techniques.展开更多
Evapotranspiration is an essential component of the hydrological cycle that is of particular interest for water resource planning.Its quantification is helpful in irrigation scheduling,water balance studies,water allo...Evapotranspiration is an essential component of the hydrological cycle that is of particular interest for water resource planning.Its quantification is helpful in irrigation scheduling,water balance studies,water allocation,etc.Modelling of reference evapotranspiration(ET0)using both gene expression programming(GEP)and artificial neural network(ANN)techniques was done using the daily meteorological data of the Pantnagar region,India,from 2010 to 2019.A total of 15 combinations of inputs were used in developing the ET0 models.The model with the least number of inputs consisted of maximum and minimum air temperatures,whereas the model with the highest number of inputs consisted of maximum air temperature,minimum air temperature,mean relative humidity,number of sunshine hours,wind speed at 2mheight and extra-terrestrial radiation as inputs and with ET0 as the output for all the models.All the GEP models were developed for a single functional set and pre-defined genetic operator values,while the best structure in each ANN model was found based on the performance during the testing phase.It was found that ANN models were superior to GEP models for the estimation purpose.It was evident from the reduction in RMSE values ranging from 2%to 56%during training and testing phases in all the ANN models compared with GEP models.The ANN models showed an increase of about 0.96%to 9.72%of R2 value compared to the respective GEP models.The comparative study of these models with multiple linear regression(MLR)depicted that the ANN and GEP models were superior to MLR models.展开更多
Node classification has a wide range of application scenarios such as citation analysis and social network analysis.In many real-world attributed networks,a large portion of classes only contain limited labeled nodes....Node classification has a wide range of application scenarios such as citation analysis and social network analysis.In many real-world attributed networks,a large portion of classes only contain limited labeled nodes.Most of the existing node classification methods cannot be used for few-shot node classification.To train the model effectively and improve the robustness and reliability of the model with scarce labeled samples,in this paper,we propose a local adaptive discriminant structure learning(LADSL)method for few-shot node classification.LADSL aims to properly represent the nodes in the attributed graphs and learn a metric space with a strong discriminating power by reducing the intra-class variations and enlargingginter-classdifferences.Extensiveexperiments conducted on various attributed networks datasets demonstrate that LADSL is superior to the other methods on few-shot node classification task.展开更多
A hierarchical-processed frame construction of artificial emotion model for intelligent system is proposed in the paper according to the basic conclusion of emotional psychology. The general method of emotion processi...A hierarchical-processed frame construction of artificial emotion model for intelligent system is proposed in the paper according to the basic conclusion of emotional psychology. The general method of emotion processing, which considers only one single layer, has been changed in the presented construction. An artificial emotional development model is put forward based on reinforcement learning mechanism of neural network. The new model takes the emotion itself as reinforcement signal and describes its different influences on action learning efficiency corresponding to different individualities. In the end, simulation result based on child playmate robot is discussed and the effectiveness of the model is verified.展开更多
The Tibetan Plateau is characterized by complex geological conditions and a relatively fragile ecological environment.In recent years,there has been continuous development and increased human activity in the Tibetan P...The Tibetan Plateau is characterized by complex geological conditions and a relatively fragile ecological environment.In recent years,there has been continuous development and increased human activity in the Tibetan Plateau region,leading to a rising risk of landslides.The landslide in Banbar County,Xizang(Tibet),have been perturbed by ongoing disturbances from human engineering activities,making it susceptible to instability and displaying distinct features.In this study,small baseline subset synthetic aperture radar interferometry(SBAS-InSAR)technology is used to obtain the Line of Sight(LOS)deformation velocity field in the study area,and then the slope-orientation deformation field of the landslide is obtained according to the spatial geometric relationship between the satellite’s LOS direction and the landslide.Subsequently,the landslide thickness is inverted by applying the mass conservation criterion.The results show that the movement area of the landslide is about 6.57×10^(4)m^(2),and the landslide volume is about 1.45×10^(6)m^(3).The maximum estimated thickness and average thickness of the landslide are 39 m and 22 m,respectively.The thickness estimation results align with the findings from on-site investigation,indicating the applicability of this method to large-scale earth slides.The deformation rate of the landslide exhibits a notable correlation with temperature variations,with rainfall playing a supportive role in the deformation process and displaying a certain lag.Human activities exert the most substantial influence on the spatial heterogeneity of landslide deformation,leading to the direct impact of several prominent deformation areas due to human interventions.Simultaneously,utilizing the long short-term memory(LSTM)model to predict landslide displacement,and the forecast results demonstrate the effectiveness of the LSTM model in predicting landslides that are in a continuous development and movement phase.The landslide is still active,and based on the spatial heterogeneity of landslide deformation,new recommendations have been proposed for the future management of the landslide in order to mitigate potential hazards associated with landslide instability.展开更多
In this paper,we present a technique for ensuring the stability of a large class of adaptively controlled systems.We combine IQC models of both the controlled system and the controller with a method of filtering contr...In this paper,we present a technique for ensuring the stability of a large class of adaptively controlled systems.We combine IQC models of both the controlled system and the controller with a method of filtering control parameter updates to ensure stable behavior of the controlled system under adaptation of the controller.We present a specific application to a system that uses recurrent neural networks adapted via reinforcement learning techniques.The work presented extends earlier works on stable reinforcement learning with neural networks.Specifically,we apply an improved IQC analysis for RNNs with time-varying weights and evaluate the approach on more complex control system.展开更多
We propose the deep Lagrange method(DLM),which is a new optimization method,in this study.It is based on a deep neural network to solve optimization problems.The method takes the advantage of deep learning artificial ...We propose the deep Lagrange method(DLM),which is a new optimization method,in this study.It is based on a deep neural network to solve optimization problems.The method takes the advantage of deep learning artificial neural networks to find the optimal values of the optimization function instead of solving optimization problems by calculating sensitivity analysis.The DLM method is non-linear and could potentially deal with nonlinear optimization problems.Several test cases on sizing optimization and shape optimization are performed,and their results are then compared with analytical and numerical solutions.展开更多
RNAs play crucial and versatile roles in biological processes. Computational prediction approaches can help to understand RNA structures and their stabilizing factors, thus providing information on their functions, an...RNAs play crucial and versatile roles in biological processes. Computational prediction approaches can help to understand RNA structures and their stabilizing factors, thus providing information on their functions, and facilitating the design of new RNAs. Machine learning (ML) techniques have made tremendous progress in many fields in the past few years. Although their usage in protein-related fields has a long history, the use of ML methods in predicting RNA tertiary structures is new and rare. Here, we review the recent advances of using ML methods on RNA structure predictions and discuss the advantages and limitation, the difficulties and potentials of these approaches when applied in the field.展开更多
文摘The existing strategy for evaluating the damage condition of structures mostly focuses on feedback supplied by traditional visualmethods,which may result in an unreliable damage characterization due to inspector subjectivity or insufficient level of expertise.As a result,a robust,reliable,and repeatable method of damage identification is required.Ensemble learning algorithms for identifying structural damage are evaluated in this article,which use deep convolutional neural networks,including simple averaging,integrated stacking,separate stacking,and hybridweighted averaging ensemble and differential evolution(WAE-DE)ensemblemodels.Damage identification is carried out on three types of damage.The proposed algorithms are used to analyze the damage of 4585 structural images.The effectiveness of the ensemble learning techniques is evaluated using the confusion matrix.For the testing dataset,the confusion matrix achieved an accuracy of 94 percent and a minimum recall of 92 percent for the best model(WAE-DE)in distinguishing damage types as flexural,shear,combined,or undamaged.
基金supported by the National Natural Science Foundation of China(No.12345678)。
文摘Sodium homeostasis disorder is one of the most common abnormal symptoms of elderly patients in intensive care unit(ICU),which may lead to physiological disorders of many organs.The current prediction of serum sodium in ICU is mainly based on the subjective judgment of doctors’experience.This study aims at this problem by studying the clinical retrospective electronic medical record data of ICU to establish a machine learning model to predict the short-term serum sodium value of ICU patients.The data set used in this study is the open-source intensive care medical information set Medical Information Mart for Intensive Care(MIMIC)-IV.The time point of serum sodium detection was selected from the ICU clinical records,and the ICU records of 25risk factors related to serum sodium were extracted from the patients within the first 12 h for statistical analysis.A prediction model of serum sodium value within 48 h was established using a feedforward neural network,and compared with previous methods.Our research results show that the neural network learning model can predict the development of serum sodium in patients using physiological indicators recorded in clinical electronic medical records within 12 h,and has better prediction effect than the serum sodium formula and other machine learning models.
基金Project supported by the Grant of the Korean Ministry of Education, Science and Technology (The Regional Core Research Program/Center for Healthcare Technology Development)
文摘This paper proposes an y2-y∞ learning law as a new learning method for dynamic neural networks with external disturbance. Based on linear matrix inequality (LMI) formulation, the y2-y∞ learning law is presented to not only guarantee asymptotical stability of dynamic neural networks but also reduce the effect of external disturbance to an y2-y∞ induced norm constraint. It is shown that the design of the y2-y∞ learning law for such neural networks can be achieved by solving LMIs, which can be easily facilitated by using some standard numerical packages. A numerical example is presented to demonstrate the validity of the proposed learning law.
基金the National Research Foundation of Korea(NRF)grant of the Korea government(MSIP)(2020R1A2B5B01001899)(Grantee:GJY,http://www.nrf.re.kr)and Institute of Engineering Research at Seoul National University(Grantee:GJY,http://www.snu.ac.kr).The authors are grateful for their supports.
文摘This paper first proposes a new self-learning data-driven methodology that can develop the failure criteria of unknown anisotropic ductile materials from the minimal number of experimental tests.Establishing failure criteria of anisotropic ductile materials requires time-consuming tests and manual data evaluation.The proposed method can overcome such practical challenges.The methodology is formalized by combining four ideas:1)The deep learning neural network(DLNN)-based material constitutive model,2)Self-learning inverse finite element(SELIFE)simulation,3)Algorithmic identification of failure points from the selflearned stress-strain curves and 4)Derivation of the failure criteria through symbolic regression of the genetic programming.Stress update and the algorithmic tangent operator were formulated in terms of DLNN parameters for nonlinear finite element analysis.Then,the SELIFE simulation algorithm gradually makes the DLNN model learn highly complex multi-axial stress and strain relationships,being guided by the experimental boundary measurements.Following the failure point identification,a self-learning data-driven failure criteria are eventually developed with the help of a reliable symbolic regression algorithm.The methodology and the self-learning data-driven failure criteria were verified by comparing with a reference failure criteria and simulating with different materials orientations,respectively.
文摘In this article we introduce a large class of optimization problems that can be approximated by neural networks. Furthermore for some large category of optimization problems the action of the corresponding neural network will be reduced to linear or quadratic programming, therefore the global optimum could be obtained immediately.
文摘Protein Secondary Structure Prediction (PSSP) is considered as one of the major challenging tasks in bioinformatics, so many solutions have been proposed to solve that problem via trying to achieve more accurate prediction results. The goal of this paper is to develop and implement an intelligent based system to predict secondary structure of a protein from its primary amino acid sequence by using five models of Neural Network (NN). These models are Feed Forward Neural Network (FNN), Learning Vector Quantization (LVQ), Probabilistic Neural Network (PNN), Convolutional Neural Network (CNN), and CNN Fine Tuning for PSSP. To evaluate our approaches two datasets have been used. The first one contains 114 protein samples, and the second one contains 1845 protein samples.
文摘This paper investigates exponential stability and trajectory bounds of motions of equilibria of a class of associative neural networks under structural variations as learning a new pattern. Some conditions for the possible maximum estimate of the domain of structural exponential stability are determined. The filtering ability of the associative neural networks contaminated by input noises is analyzed. Employing the obtained results as valuable guidelines, a systematic synthesis procedure for constructing a dynamical associative neural network that stores a given set of vectors as the stable equilibrium points as well as learns new patterns can be developed. Some new concepts defined here are expected to be the instruction for further studies of learning associative neural networks.
基金Foundation of Young Backbone Teacher of Beijing Citygrant number:102KB000845
文摘Fetal ECG extraction has the vital significance for fetal monitoring.This paper introduces a method of extracting fetal ECG based on adaptive linear neural network.The method can be realized by training a small quantity of data.In addition,a better result can be achieved by improving neural network structure.Thus,more easily identified fetal ECG can be extracted.Experimental results show that the adaptive linear neural network can be used to extract fetal ECG from maternal abdominal signal effectively.What's more,a clearer fetal ECG can be extracted by improving neural network structure.
基金supported by the National Natural Science Foundations of China(Nos.12172186 and 11772166).
文摘The objective of dynamical system learning tasks is to forecast the future behavior of a system by leveraging observed data.However,such systems can sometimes exhibit rigidity due to significant variations in component parameters or the presence of slow and fast variables,leading to challenges in learning.To overcome this limitation,we propose a multiscale differential-algebraic neural network(MDANN)method that utilizes Lagrangian mechanics and incorporates multiscale information for dynamical system learning.The MDANN method consists of two main components:the Lagrangian mechanics module and the multiscale module.The Lagrangian mechanics module embeds the system in Cartesian coordinates,adopts a differential-algebraic equation format,and uses Lagrange multipliers to impose constraints explicitly,simplifying the learning problem.The multiscale module converts high-frequency components into low-frequency components using radial scaling to learn subprocesses with large differences in velocity.Experimental results demonstrate that the proposed MDANN method effectively improves the learning of dynamical systems under rigid conditions.
文摘This project uses knowledge of neural network to analyze if the person under study is analyzed to be Parkinson disease patient or not. Binary classification is constructed based on the multi-feature database. A decision boundary is clearly plotted to separate patient with and without Parkinson disease. Results show that over 80% accuracy could be obtained with the preliminary results. Future efforts could be performed to construct more complicated neural network to improve the accuracy.
基金supported in part by the National Natural Science Foundation of China(62222301, 62073085, 62073158, 61890930-5, 62021003)the National Key Research and Development Program of China (2021ZD0112302, 2021ZD0112301, 2018YFC1900800-5)Beijing Natural Science Foundation (JQ19013)。
文摘Reinforcement learning(RL) has roots in dynamic programming and it is called adaptive/approximate dynamic programming(ADP) within the control community. This paper reviews recent developments in ADP along with RL and its applications to various advanced control fields. First, the background of the development of ADP is described, emphasizing the significance of regulation and tracking control problems. Some effective offline and online algorithms for ADP/adaptive critic control are displayed, where the main results towards discrete-time systems and continuous-time systems are surveyed, respectively.Then, the research progress on adaptive critic control based on the event-triggered framework and under uncertain environment is discussed, respectively, where event-based design, robust stabilization, and game design are reviewed. Moreover, the extensions of ADP for addressing control problems under complex environment attract enormous attention. The ADP architecture is revisited under the perspective of data-driven and RL frameworks,showing how they promote ADP formulation significantly.Finally, several typical control applications with respect to RL and ADP are summarized, particularly in the fields of wastewater treatment processes and power systems, followed by some general prospects for future research. Overall, the comprehensive survey on ADP and RL for advanced control applications has d emonstrated its remarkable potential within the artificial intelligence era. In addition, it also plays a vital role in promoting environmental protection and industrial intelligence.
基金Supported by the National Key Research and Development Program of China(No.2022YFF0801400)the National Natural Science Foundation of China(No.42176010)the Natural Science Foundation of Shandong Province,China(No.ZR2021MD022)。
文摘Accurately estimating the ocean subsurface salinity structure(OSSS)is crucial for understanding ocean dynamics and predicting climate variations.We present a convolutional neural network(CNN)model to estimate the OSSS in the Indian Ocean using satellite data and Argo observations.We evaluated the performance of the CNN model in terms of its vertical and spatial distribution,as well as seasonal variation of OSSS estimation.Results demonstrate that the CNN model accurately estimates the most significant salinity features in the Indian Ocean using sea surface data with no significant differences from Argo-derived OSSS.However,the estimation accuracy of the CNN model varies with depth,with the most challenging depth being approximately 70 m,corresponding to the halocline layer.Validations of the CNN model’s accuracy in estimating OSSS in the Indian Ocean are also conducted by comparing Argo observations and CNN model estimations along two selected sections and four selected boxes.The results show that the CNN model effectively captures the seasonal variability of salinity,demonstrating its high performance in salinity estimation using sea surface data.Our analysis reveals that sea surface salinity has the strongest correlation with OSSS in shallow layers,while sea surface height anomaly plays a more significant role in deeper layers.These preliminary results provide valuable insights into the feasibility of estimating OSSS using satellite observations and have implications for studying upper ocean dynamics using machine learning techniques.
文摘Evapotranspiration is an essential component of the hydrological cycle that is of particular interest for water resource planning.Its quantification is helpful in irrigation scheduling,water balance studies,water allocation,etc.Modelling of reference evapotranspiration(ET0)using both gene expression programming(GEP)and artificial neural network(ANN)techniques was done using the daily meteorological data of the Pantnagar region,India,from 2010 to 2019.A total of 15 combinations of inputs were used in developing the ET0 models.The model with the least number of inputs consisted of maximum and minimum air temperatures,whereas the model with the highest number of inputs consisted of maximum air temperature,minimum air temperature,mean relative humidity,number of sunshine hours,wind speed at 2mheight and extra-terrestrial radiation as inputs and with ET0 as the output for all the models.All the GEP models were developed for a single functional set and pre-defined genetic operator values,while the best structure in each ANN model was found based on the performance during the testing phase.It was found that ANN models were superior to GEP models for the estimation purpose.It was evident from the reduction in RMSE values ranging from 2%to 56%during training and testing phases in all the ANN models compared with GEP models.The ANN models showed an increase of about 0.96%to 9.72%of R2 value compared to the respective GEP models.The comparative study of these models with multiple linear regression(MLR)depicted that the ANN and GEP models were superior to MLR models.
基金supported by the National Key R&D Program of China(2018YFB1402600)the National Natural Science Foundation of China(Grant Nos.61802028,62192784,61877006,and 62002027)。
文摘Node classification has a wide range of application scenarios such as citation analysis and social network analysis.In many real-world attributed networks,a large portion of classes only contain limited labeled nodes.Most of the existing node classification methods cannot be used for few-shot node classification.To train the model effectively and improve the robustness and reliability of the model with scarce labeled samples,in this paper,we propose a local adaptive discriminant structure learning(LADSL)method for few-shot node classification.LADSL aims to properly represent the nodes in the attributed graphs and learn a metric space with a strong discriminating power by reducing the intra-class variations and enlargingginter-classdifferences.Extensiveexperiments conducted on various attributed networks datasets demonstrate that LADSL is superior to the other methods on few-shot node classification task.
基金supported by the Hi-Tech Research and Development Program of China (2007AA04Z200)the National Nature Science Foundation of China (60573059)
文摘A hierarchical-processed frame construction of artificial emotion model for intelligent system is proposed in the paper according to the basic conclusion of emotional psychology. The general method of emotion processing, which considers only one single layer, has been changed in the presented construction. An artificial emotional development model is put forward based on reinforcement learning mechanism of neural network. The new model takes the emotion itself as reinforcement signal and describes its different influences on action learning efficiency corresponding to different individualities. In the end, simulation result based on child playmate robot is discussed and the effectiveness of the model is verified.
基金supported by the second Tibetan Plateau Scientific Expedition and Research(STEP)program(Grant NO.2019QZKK0904)the National Natural Science Foundation of China(Grant No.41941019)the National Natural Science Foundation of China(Grant NO.42307217)。
文摘The Tibetan Plateau is characterized by complex geological conditions and a relatively fragile ecological environment.In recent years,there has been continuous development and increased human activity in the Tibetan Plateau region,leading to a rising risk of landslides.The landslide in Banbar County,Xizang(Tibet),have been perturbed by ongoing disturbances from human engineering activities,making it susceptible to instability and displaying distinct features.In this study,small baseline subset synthetic aperture radar interferometry(SBAS-InSAR)technology is used to obtain the Line of Sight(LOS)deformation velocity field in the study area,and then the slope-orientation deformation field of the landslide is obtained according to the spatial geometric relationship between the satellite’s LOS direction and the landslide.Subsequently,the landslide thickness is inverted by applying the mass conservation criterion.The results show that the movement area of the landslide is about 6.57×10^(4)m^(2),and the landslide volume is about 1.45×10^(6)m^(3).The maximum estimated thickness and average thickness of the landslide are 39 m and 22 m,respectively.The thickness estimation results align with the findings from on-site investigation,indicating the applicability of this method to large-scale earth slides.The deformation rate of the landslide exhibits a notable correlation with temperature variations,with rainfall playing a supportive role in the deformation process and displaying a certain lag.Human activities exert the most substantial influence on the spatial heterogeneity of landslide deformation,leading to the direct impact of several prominent deformation areas due to human interventions.Simultaneously,utilizing the long short-term memory(LSTM)model to predict landslide displacement,and the forecast results demonstrate the effectiveness of the LSTM model in predicting landslides that are in a continuous development and movement phase.The landslide is still active,and based on the spatial heterogeneity of landslide deformation,new recommendations have been proposed for the future management of the landslide in order to mitigate potential hazards associated with landslide instability.
基金supported by the National Natural Science Foundation (No.0245291)
文摘In this paper,we present a technique for ensuring the stability of a large class of adaptively controlled systems.We combine IQC models of both the controlled system and the controller with a method of filtering control parameter updates to ensure stable behavior of the controlled system under adaptation of the controller.We present a specific application to a system that uses recurrent neural networks adapted via reinforcement learning techniques.The work presented extends earlier works on stable reinforcement learning with neural networks.Specifically,we apply an improved IQC analysis for RNNs with time-varying weights and evaluate the approach on more complex control system.
文摘We propose the deep Lagrange method(DLM),which is a new optimization method,in this study.It is based on a deep neural network to solve optimization problems.The method takes the advantage of deep learning artificial neural networks to find the optimal values of the optimization function instead of solving optimization problems by calculating sensitivity analysis.The DLM method is non-linear and could potentially deal with nonlinear optimization problems.Several test cases on sizing optimization and shape optimization are performed,and their results are then compared with analytical and numerical solutions.
基金Project supported by the National Natural Science Foundation of China (Grant Nos. 11774158, 11974173, 11774157, and 11934008)。
文摘RNAs play crucial and versatile roles in biological processes. Computational prediction approaches can help to understand RNA structures and their stabilizing factors, thus providing information on their functions, and facilitating the design of new RNAs. Machine learning (ML) techniques have made tremendous progress in many fields in the past few years. Although their usage in protein-related fields has a long history, the use of ML methods in predicting RNA tertiary structures is new and rare. Here, we review the recent advances of using ML methods on RNA structure predictions and discuss the advantages and limitation, the difficulties and potentials of these approaches when applied in the field.