Finding out reasonable structures from bulky data is one of the difficulties in modeling of Bayesian network （BN）, which is also necessary in promoting the application of BN. This pa- per proposes an immune algorith...Finding out reasonable structures from bulky data is one of the difficulties in modeling of Bayesian network （BN）, which is also necessary in promoting the application of BN. This pa- per proposes an immune algorithm based method （BN-IA） for the learning of the BN structure with the idea of vaccination. Further- more, the methods on how to extract the effective vaccines from local optimal structure and root nodes are also described in details. Finally, the simulation studies are implemented with the helicopter convertor BN model and the car start BN model. The comparison results show that the proposed vaccines and the BN-IA can learn the BN structure effectively and efficiently.展开更多
A new method to evaluate the fitness of the Bayesian networks according to the observed data is provided. The main advantage of this criterion is that it is suitable for both the complete and incomplete cases while th...A new method to evaluate the fitness of the Bayesian networks according to the observed data is provided. The main advantage of this criterion is that it is suitable for both the complete and incomplete cases while the others not. Moreover it facilitates the computation greatly. In order to reduce the search space, the notation of equivalent class proposed by David Chickering is adopted. Instead of using the method directly, the novel criterion, variable ordering, and equivalent class are combined,moreover the proposed mthod avoids some problems caused by the previous one. Later, the genetic algorithm which allows global convergence, lack in the most of the methods searching for Bayesian network is applied to search for a good model in thisspace. To speed up the convergence, the genetic algorithm is combined with the greedy algorithm. Finally, the simulation shows the validity of the proposed approach.展开更多
The structural integrity monitoring of high-density polyethylene(HDPE)geomembranes in landfill containment systems presents a critical engineering challenge due to the material’s vulnerability to mechanical degradati...The structural integrity monitoring of high-density polyethylene(HDPE)geomembranes in landfill containment systems presents a critical engineering challenge due to the material’s vulnerability to mechanical degradation and the complex vibration propagation characteristics in large-scale installations.This study proposes a dual-stream deep learning framework that synergistically integrates raw vibration signal analysis with physics-guided feature extraction to achieve precise rupture detection and localization.Themethodology employs a hierarchical neural architecture comprising two parallel branches:a 1D convolutional network processing raw accelerometer signals to capture multi-scale temporal patterns,and a physics-informed branch extracting material-specific resonance features through continuous wavelet transform(CWT)and energy ratio quantification.A novel gated attention mechanism dynamically fuses these heterogeneous modalities,adaptively weighting their contributions based on localized signal characteristics—prioritizing high-frequency transient features near damage zones while emphasizing physics-derived energy anomalies in intact regions.Spatial correlations among distributed sensors aremodeled via graph convolutional networks(GCNs)that incorporate geometric topology and vibration transmission dynamics,enabling robust anomaly propagation analysis.展开更多
With the breakthrough of AlphaFold2,nearly all single-domain protein structures can be built at experimental resolution.However,accurate modelling of full-chain structures of multidomain proteins,particularly all rele...With the breakthrough of AlphaFold2,nearly all single-domain protein structures can be built at experimental resolution.However,accurate modelling of full-chain structures of multidomain proteins,particularly all relevant conformations for those with multiple states remain challenging.In this study,we develop a multidomain protein assembly method,M-SADA,for assembling multiple conformational states.In M-SADA,a multiple population-based evolutionary algorithm is proposed to sample multiple conformational states under the guidance of multi-ple energy functions constructed by combining homologous and analogous templates with inter-domain distances predicted by deep learning.On a developed benchmark dataset containing 72 multidomain proteins with multi-ple conformational states,the performance of M-SADA is significantly better than that of AlphaFold2 on multiple conformational states modelling,where 29/72(40.3%)of proteins can be assembled with a TM-score>0.90 for two highly distinct conformational states with M-SADA.Furthermore,M-SADA is tested on a developed bench-mark dataset containing 296 multidomain proteins with single conformational state,and results show that the average TM-score of M-SADA on the best models is 0.913,which is 5.2%higher than that of AlphaFold2 models(0.868).Results on CASP15 multidomain targets also show that M-SADA can predict new domain arrangements when individual domain structures are correct.展开更多
A gravitational search algorithm(GSA)uses gravitational force among individuals to evolve population.Though GSA is an effective population-based algorithm,it exhibits low search performance and premature convergence.T...A gravitational search algorithm(GSA)uses gravitational force among individuals to evolve population.Though GSA is an effective population-based algorithm,it exhibits low search performance and premature convergence.To ameliorate these issues,this work proposes a multi-layered GSA called MLGSA.Inspired by the two-layered structure of GSA,four layers consisting of population,iteration-best,personal-best and global-best layers are constructed.Hierarchical interactions among four layers are dynamically implemented in different search stages to greatly improve both exploration and exploitation abilities of population.Performance comparison between MLGSA and nine existing GSA variants on twenty-nine CEC2017 test functions with low,medium and high dimensions demonstrates that MLGSA is the most competitive one.It is also compared with four particle swarm optimization variants to verify its excellent performance.Moreover,the analysis of hierarchical interactions is discussed to illustrate the influence of a complete hierarchy on its performance.The relationship between its population diversity and fitness diversity is analyzed to clarify its search performance.Its computational complexity is given to show its efficiency.Finally,it is applied to twenty-two CEC2011 real-world optimization problems to show its practicality.展开更多
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
With increasingly more smart cameras deployed in infrastructure and commercial buildings,3D reconstruction can quickly obtain cities’information and improve the efficiency of government services.Images collected in o...With increasingly more smart cameras deployed in infrastructure and commercial buildings,3D reconstruction can quickly obtain cities’information and improve the efficiency of government services.Images collected in outdoor hazy environments are prone to color distortion and low contrast;thus,the desired visual effect cannot be achieved and the difficulty of target detection is increased.Artificial intelligence(AI)solutions provide great help for dehazy images,which can automatically identify patterns or monitor the environment.Therefore,we propose a 3D reconstruction method of dehazed images for smart cities based on deep learning.First,we propose a fine transmission image deep convolutional regression network(FT-DCRN)dehazing algorithm that uses fine transmission image and atmospheric light value to compute dehazed image.The DCRN is used to obtain the coarse transmission image,which can not only expand the receptive field of the network but also retain the features to maintain the nonlinearity of the overall network.The fine transmission image is obtained by refining the coarse transmission image using a guided filter.The atmospheric light value is estimated according to the position and brightness of the pixels in the original hazy image.Second,we use the dehazed images generated by the FT-DCRN dehazing algorithm for 3D reconstruction.An advanced relaxed iterative fine matching based on the structure from motion(ARI-SFM)algorithm is proposed.The ARISFM algorithm,which obtains the fine matching corner pairs and reduces the number of iterations,establishes an accurate one-to-one matching corner relationship.The experimental results show that our FT-DCRN dehazing algorithm improves the accuracy compared to other representative algorithms.In addition,the ARI-SFM algorithm guarantees the precision and improves the efficiency.展开更多
How to improve the efficiency of exact learning of the Bayesian network structure is a challenging issue.In this paper,four different causal constraints algorithms are added into score calculations to prune possible p...How to improve the efficiency of exact learning of the Bayesian network structure is a challenging issue.In this paper,four different causal constraints algorithms are added into score calculations to prune possible parent sets,improving state-ofthe-art learning algorithms’efficiency.Experimental results indicate that exact learning algorithms can significantly improve the efficiency with only a slight loss of accuracy.Under causal constraints,these exact learning algorithms can prune about 70%possible parent sets and reduce about 60%running time while only losing no more than 2%accuracy on average.Additionally,with sufficient samples,exact learning algorithms with causal constraints can also obtain the optimal network.In general,adding max-min parents and children constraints has better results in terms of efficiency and accuracy among these four causal constraints algorithms.展开更多
To get simpler operation in modified fuzzy adaptive learning control network （FALCON） in some engineering application, sigmoid nonlinear function is employed as a substitute of traditional Gaussian membership functi...To get simpler operation in modified fuzzy adaptive learning control network （FALCON） in some engineering application, sigmoid nonlinear function is employed as a substitute of traditional Gaussian membership function. For making the modified FALCON learning more efficient and stable, a simulated annealing （SA） learning coefficient is introduced into learning algorithm. At first, the basic concepts and main advantages of FALCON were briefly reviewed. Subsequently, the topological structure and nodes operation were illustrated; the gradient-descent learning algorithm with SA learning coefficient was derived; and the distinctions between the archetype and the modification were analyzed. Eventually, the significance and worthiness of the modified FALCON were validated by its application to probability prediction of anode effect in aluminium electrolysis cells.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
The typical characteristic of the topology of Bayesian networks (BNs) is the interdependence among different nodes (variables), which makes it impossible to optimize one variable independently of others, and the learn...The typical characteristic of the topology of Bayesian networks (BNs) is the interdependence among different nodes (variables), which makes it impossible to optimize one variable independently of others, and the learning of BNs structures by general genetic algorithms is liable to converge to local extremum. To resolve efficiently this problem, a self-organizing genetic algorithm (SGA) based method for constructing BNs from databases is presented. This method makes use of a self-organizing mechanism to develop a genetic algorithm that extended the crossover operator from one to two, providing mutual competition between them, even adjusting the numbers of parents in recombination (crossover/recomposition) schemes. With the K2 algorithm, this method also optimizes the genetic operators, and utilizes adequately the domain knowledge. As a result, with this method it is able to find a global optimum of the topology of BNs, avoiding premature convergence to local extremum. The experimental results proved to be and the convergence of the SGA was discussed.展开更多
Interval Uncertainty Propagation(IUP)holds significant importance in quantifying uncertainties in structural outputs when confronted with interval input parameters.In the aviation field,the precise determination of pr...Interval Uncertainty Propagation(IUP)holds significant importance in quantifying uncertainties in structural outputs when confronted with interval input parameters.In the aviation field,the precise determination of probability models for input parameters of aeronautical structures entails substantial costs in both time and finances.As an alternative,the use of interval variables to describe input parameter uncertainty becomes a pragmatic approach.The complex task of solving the IUP for aeronautical structures,particularly in scenarios marked by pronounced nonlinearity and multiple outputs,necessitates innovative methodologies.This study introduces an efficient deep learning-driven approach to address the challenges associated with IUP.The proposed approach combines the Deep Neural Network(DNN)with intelligent optimization algorithms for dealing with the IUP in aeronautical structures.An inventive extremal value-oriented weighting technique is presented,assigning varying weights to different training samples within the loss function,thereby enhancing the computational accuracy of the DNN in predicting extremal values of structural outputs.Moreover,an adaptive framework is established to strategically balance the global exploration and local exploitation capabilities of the DNN,resulting in a predictive model that is both robust and accurate.To illustrate the effectiveness of the developed approach,various applications are explored,including a high-dimensional numerical example and two aeronautical structures.The obtained results highlight the high computational accuracy and efficiency achieved by the proposed approach,showcasing its potential for addressing complex IUP challenges in aeronautical engineering.展开更多
基金supported by the National Natural Science Foundation of China(7110111671271170)+1 种基金the Program for New Century Excellent Talents in University(NCET-13-0475)the Basic Research Foundation of NPU(JC20120228)
文摘Finding out reasonable structures from bulky data is one of the difficulties in modeling of Bayesian network （BN）, which is also necessary in promoting the application of BN. This pa- per proposes an immune algorithm based method （BN-IA） for the learning of the BN structure with the idea of vaccination. Further- more, the methods on how to extract the effective vaccines from local optimal structure and root nodes are also described in details. Finally, the simulation studies are implemented with the helicopter convertor BN model and the car start BN model. The comparison results show that the proposed vaccines and the BN-IA can learn the BN structure effectively and efficiently.
基金This project was supported by the National Natural Science Foundation of China (70572045).
文摘A new method to evaluate the fitness of the Bayesian networks according to the observed data is provided. The main advantage of this criterion is that it is suitable for both the complete and incomplete cases while the others not. Moreover it facilitates the computation greatly. In order to reduce the search space, the notation of equivalent class proposed by David Chickering is adopted. Instead of using the method directly, the novel criterion, variable ordering, and equivalent class are combined,moreover the proposed mthod avoids some problems caused by the previous one. Later, the genetic algorithm which allows global convergence, lack in the most of the methods searching for Bayesian network is applied to search for a good model in thisspace. To speed up the convergence, the genetic algorithm is combined with the greedy algorithm. Finally, the simulation shows the validity of the proposed approach.
基金supported by the Research and Talent Development Base for Intelligent Monitoring,Early Warning,and Emergency Management of Major Environmental Risk Sources in the Yellow River Basin(24RCXM58)Research and Demonstration of Key Technologies for Long-Term Service and Smart Operation of Major Environmental Safety Infrastructure(Solid and Hazardous Wastes)in the Yellow River Basin(24ZYQA025).
文摘The structural integrity monitoring of high-density polyethylene(HDPE)geomembranes in landfill containment systems presents a critical engineering challenge due to the material’s vulnerability to mechanical degradation and the complex vibration propagation characteristics in large-scale installations.This study proposes a dual-stream deep learning framework that synergistically integrates raw vibration signal analysis with physics-guided feature extraction to achieve precise rupture detection and localization.Themethodology employs a hierarchical neural architecture comprising two parallel branches:a 1D convolutional network processing raw accelerometer signals to capture multi-scale temporal patterns,and a physics-informed branch extracting material-specific resonance features through continuous wavelet transform(CWT)and energy ratio quantification.A novel gated attention mechanism dynamically fuses these heterogeneous modalities,adaptively weighting their contributions based on localized signal characteristics—prioritizing high-frequency transient features near damage zones while emphasizing physics-derived energy anomalies in intact regions.Spatial correlations among distributed sensors aremodeled via graph convolutional networks(GCNs)that incorporate geometric topology and vibration transmission dynamics,enabling robust anomaly propagation analysis.
基金supported by the National Science and Technol-ogy Major Project(2022ZD0115103)the National Nature Science Foun-dation of China(62173304 and 62203389)the Key Project of Zhejiang Provincial Natural Science Foundation of China(LZ20F030002).
文摘With the breakthrough of AlphaFold2,nearly all single-domain protein structures can be built at experimental resolution.However,accurate modelling of full-chain structures of multidomain proteins,particularly all relevant conformations for those with multiple states remain challenging.In this study,we develop a multidomain protein assembly method,M-SADA,for assembling multiple conformational states.In M-SADA,a multiple population-based evolutionary algorithm is proposed to sample multiple conformational states under the guidance of multi-ple energy functions constructed by combining homologous and analogous templates with inter-domain distances predicted by deep learning.On a developed benchmark dataset containing 72 multidomain proteins with multi-ple conformational states,the performance of M-SADA is significantly better than that of AlphaFold2 on multiple conformational states modelling,where 29/72(40.3%)of proteins can be assembled with a TM-score>0.90 for two highly distinct conformational states with M-SADA.Furthermore,M-SADA is tested on a developed bench-mark dataset containing 296 multidomain proteins with single conformational state,and results show that the average TM-score of M-SADA on the best models is 0.913,which is 5.2%higher than that of AlphaFold2 models(0.868).Results on CASP15 multidomain targets also show that M-SADA can predict new domain arrangements when individual domain structures are correct.
基金supported by National Natural Science Foundation of China(61872271,61673403,61873105,11972115)the Fundamental Research Funds for the Central Universities(22120190208)JSPS KAKENHI(JP17K12751)。
文摘A gravitational search algorithm(GSA)uses gravitational force among individuals to evolve population.Though GSA is an effective population-based algorithm,it exhibits low search performance and premature convergence.To ameliorate these issues,this work proposes a multi-layered GSA called MLGSA.Inspired by the two-layered structure of GSA,four layers consisting of population,iteration-best,personal-best and global-best layers are constructed.Hierarchical interactions among four layers are dynamically implemented in different search stages to greatly improve both exploration and exploitation abilities of population.Performance comparison between MLGSA and nine existing GSA variants on twenty-nine CEC2017 test functions with low,medium and high dimensions demonstrates that MLGSA is the most competitive one.It is also compared with four particle swarm optimization variants to verify its excellent performance.Moreover,the analysis of hierarchical interactions is discussed to illustrate the influence of a complete hierarchy on its performance.The relationship between its population diversity and fitness diversity is analyzed to clarify its search performance.Its computational complexity is given to show its efficiency.Finally,it is applied to twenty-two CEC2011 real-world optimization problems to show its practicality.
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 in part by the National Natural Science Foundation of China under Grant 61902311in part by the Japan Society for the Promotion of Science(JSPS)Grants-in-Aid for Scientific Research(KAKENHI)under Grant JP18K18044.
文摘With increasingly more smart cameras deployed in infrastructure and commercial buildings,3D reconstruction can quickly obtain cities’information and improve the efficiency of government services.Images collected in outdoor hazy environments are prone to color distortion and low contrast;thus,the desired visual effect cannot be achieved and the difficulty of target detection is increased.Artificial intelligence(AI)solutions provide great help for dehazy images,which can automatically identify patterns or monitor the environment.Therefore,we propose a 3D reconstruction method of dehazed images for smart cities based on deep learning.First,we propose a fine transmission image deep convolutional regression network(FT-DCRN)dehazing algorithm that uses fine transmission image and atmospheric light value to compute dehazed image.The DCRN is used to obtain the coarse transmission image,which can not only expand the receptive field of the network but also retain the features to maintain the nonlinearity of the overall network.The fine transmission image is obtained by refining the coarse transmission image using a guided filter.The atmospheric light value is estimated according to the position and brightness of the pixels in the original hazy image.Second,we use the dehazed images generated by the FT-DCRN dehazing algorithm for 3D reconstruction.An advanced relaxed iterative fine matching based on the structure from motion(ARI-SFM)algorithm is proposed.The ARISFM algorithm,which obtains the fine matching corner pairs and reduces the number of iterations,establishes an accurate one-to-one matching corner relationship.The experimental results show that our FT-DCRN dehazing algorithm improves the accuracy compared to other representative algorithms.In addition,the ARI-SFM algorithm guarantees the precision and improves the efficiency.
基金supported by the National Natural Science Foundation of China(61573285).
文摘How to improve the efficiency of exact learning of the Bayesian network structure is a challenging issue.In this paper,four different causal constraints algorithms are added into score calculations to prune possible parent sets,improving state-ofthe-art learning algorithms’efficiency.Experimental results indicate that exact learning algorithms can significantly improve the efficiency with only a slight loss of accuracy.Under causal constraints,these exact learning algorithms can prune about 70%possible parent sets and reduce about 60%running time while only losing no more than 2%accuracy on average.Additionally,with sufficient samples,exact learning algorithms with causal constraints can also obtain the optimal network.In general,adding max-min parents and children constraints has better results in terms of efficiency and accuracy among these four causal constraints algorithms.
文摘To get simpler operation in modified fuzzy adaptive learning control network （FALCON） in some engineering application, sigmoid nonlinear function is employed as a substitute of traditional Gaussian membership function. For making the modified FALCON learning more efficient and stable, a simulated annealing （SA） learning coefficient is introduced into learning algorithm. At first, the basic concepts and main advantages of FALCON were briefly reviewed. Subsequently, the topological structure and nodes operation were illustrated; the gradient-descent learning algorithm with SA learning coefficient was derived; and the distinctions between the archetype and the modification were analyzed. Eventually, the significance and worthiness of the modified FALCON were validated by its application to probability prediction of anode effect in aluminium electrolysis cells.
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.
文摘The typical characteristic of the topology of Bayesian networks (BNs) is the interdependence among different nodes (variables), which makes it impossible to optimize one variable independently of others, and the learning of BNs structures by general genetic algorithms is liable to converge to local extremum. To resolve efficiently this problem, a self-organizing genetic algorithm (SGA) based method for constructing BNs from databases is presented. This method makes use of a self-organizing mechanism to develop a genetic algorithm that extended the crossover operator from one to two, providing mutual competition between them, even adjusting the numbers of parents in recombination (crossover/recomposition) schemes. With the K2 algorithm, this method also optimizes the genetic operators, and utilizes adequately the domain knowledge. As a result, with this method it is able to find a global optimum of the topology of BNs, avoiding premature convergence to local extremum. The experimental results proved to be and the convergence of the SGA was discussed.
基金supported by the National Natural Science Foundation of China(Nos. 52205252 and 72331002)the Natural Science Foundation of Sichuan Province, China(No.2023NSFSC0876)the support of the Alexander von Humboldt Foundation of Germany
文摘Interval Uncertainty Propagation(IUP)holds significant importance in quantifying uncertainties in structural outputs when confronted with interval input parameters.In the aviation field,the precise determination of probability models for input parameters of aeronautical structures entails substantial costs in both time and finances.As an alternative,the use of interval variables to describe input parameter uncertainty becomes a pragmatic approach.The complex task of solving the IUP for aeronautical structures,particularly in scenarios marked by pronounced nonlinearity and multiple outputs,necessitates innovative methodologies.This study introduces an efficient deep learning-driven approach to address the challenges associated with IUP.The proposed approach combines the Deep Neural Network(DNN)with intelligent optimization algorithms for dealing with the IUP in aeronautical structures.An inventive extremal value-oriented weighting technique is presented,assigning varying weights to different training samples within the loss function,thereby enhancing the computational accuracy of the DNN in predicting extremal values of structural outputs.Moreover,an adaptive framework is established to strategically balance the global exploration and local exploitation capabilities of the DNN,resulting in a predictive model that is both robust and accurate.To illustrate the effectiveness of the developed approach,various applications are explored,including a high-dimensional numerical example and two aeronautical structures.The obtained results highlight the high computational accuracy and efficiency achieved by the proposed approach,showcasing its potential for addressing complex IUP challenges in aeronautical engineering.
