Biological domain has been blessed with more and more data from biotechnologies as well as data integration tools.In the renaissance of machine learning and artificial intelligence,there is so much promise of data-dri...Biological domain has been blessed with more and more data from biotechnologies as well as data integration tools.In the renaissance of machine learning and artificial intelligence,there is so much promise of data-driven biological knowledge discovery.However,it is not straight forward due to the complexity of the domain knowledge hidden in the data.At any level,be it atoms,molecules,cells or organisms,there are rich interdependencies among biological components.Machine learning approaches in this domain usually involves analyzing interdependency structures encoded in graphs and related formalisms.In this report,we review our work in developing new Machine Learning methods for these applications with improved performances in comparison with state-of-the-art methods.We show how the networks among biological components can be used to predict properties.展开更多
Ordering based search methods have advantages over graph based search methods for structure learning of Bayesian networks in terms on the efficiency. With the aim of further increasing the accuracy of ordering based s...Ordering based search methods have advantages over graph based search methods for structure learning of Bayesian networks in terms on the efficiency. With the aim of further increasing the accuracy of ordering based search methods, we first propose to increase the search space, which can facilitate escaping from the local optima. We present our search operators with majorizations, which are easy to implement. Experiments show that the proposed algorithm can obtain significantly more accurate results. With regard to the problem of the decrease on efficiency due to the increase of the search space, we then propose to add path priors as constraints into the swap process. We analyze the coefficient which may influence the performance of the proposed algorithm, the experiments show that the constraints can enhance the efficiency greatly, while has little effect on the accuracy. The final experiments show that, compared to other competitive methods, the proposed algorithm can find better solutions while holding high efficiency at the same time on both synthetic and real data sets.展开更多
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
Structure learning of Bayesian networks is a wellresearched but computationally hard task.For learning Bayesian networks,this paper proposes an improved algorithm based on unconstrained optimization and ant colony opt...Structure learning of Bayesian networks is a wellresearched but computationally hard task.For learning Bayesian networks,this paper proposes an improved algorithm based on unconstrained optimization and ant colony optimization（U-ACO-B） to solve the drawbacks of the ant colony optimization（ACO-B）.In this algorithm,firstly,an unconstrained optimization problem is solved to obtain an undirected skeleton,and then the ACO algorithm is used to orientate the edges,thus returning the final structure.In the experimental part of the paper,we compare the performance of the proposed algorithm with ACO-B algorithm.The experimental results show that our method is effective and greatly enhance convergence speed than ACO-B algorithm.展开更多
In view of the shortcomings of traditional Bayesian network(BN)structure learning algorithm,such as low efficiency,premature algorithm and poor learning effect,the intelligent algorithm of cuckoo search(CS)and particl...In view of the shortcomings of traditional Bayesian network(BN)structure learning algorithm,such as low efficiency,premature algorithm and poor learning effect,the intelligent algorithm of cuckoo search(CS)and particle swarm optimization(PSO)is selected.Combined with the characteristics of BN structure,a BN structure learning algorithm of CS-PSO is proposed.Firstly,the CS algorithm is improved from the following three aspects:the maximum spanning tree is used to guide the initialization direction of the CS algorithm,the fitness of the solution is used to adjust the optimization and abandoning process of the solution,and PSO algorithm is used to update the position of the CS algorithm.Secondly,according to the structure characteristics of BN,the CS-PSO algorithm is applied to the structure learning of BN.Finally,chest clinic,credit and car diagnosis classic network are utilized as the simulation model,and the modeling and simulation comparison of greedy algorithm,K2 algorithm,CS algorithm and CS-PSO algorithm are carried out.The results show that the CS-PSO algorithm has fast convergence speed,high convergence accuracy and good stability in the structure learning of BN,and it can get the accurate BN structure model faster and better.展开更多
The learning Bayesian network （BN） structure from data is an NP-hard problem and still one of the most exciting chal- lenges in the machine learning. In this work, a novel algorithm is presented which combines ideas...The learning Bayesian network （BN） structure from data is an NP-hard problem and still one of the most exciting chal- lenges in the machine learning. In this work, a novel algorithm is presented which combines ideas from local learning, constraint- based, and search-and-score techniques in a principled and ef- fective way. It first reconstructs the junction tree of a BN and then performs a K2-scoring greedy search to orientate the local edges in the cliques of junction tree. Theoretical and experimental results show the proposed algorithm is capable of handling networks with a large number of variables. Its comparison with the well-known K2 algorithm is also presented.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
Learning Bayesian network structure is one of the most exciting challenges in machine learning. Discovering a correct skeleton of a directed acyclic graph（DAG） is the foundation for dependency analysis algorithms fo...Learning Bayesian network structure is one of the most exciting challenges in machine learning. Discovering a correct skeleton of a directed acyclic graph（DAG） is the foundation for dependency analysis algorithms for this problem. Considering the unreliability of high order condition independence（CI） tests, and to improve the efficiency of a dependency analysis algorithm, the key steps are to use few numbers of CI tests and reduce the sizes of conditioning sets as much as possible. Based on these reasons and inspired by the algorithm PC, we present an algorithm, named fast and efficient PC（FEPC）, for learning the adjacent neighbourhood of every variable. FEPC implements the CI tests by three kinds of orders, which reduces the high order CI tests significantly. Compared with current algorithm proposals, the experiment results show that FEPC has better accuracy with fewer numbers of condition independence tests and smaller size of conditioning sets. The highest reduction percentage of CI test is 83.3% by EFPC compared with PC algorithm.展开更多
In soft sensor field, just-in-time learning(JITL) is an effective approach to model nonlinear and time varying processes. However, most similarity criterions in JITL are computed in the input space only while ignoring...In soft sensor field, just-in-time learning(JITL) is an effective approach to model nonlinear and time varying processes. However, most similarity criterions in JITL are computed in the input space only while ignoring important output information, which may lead to inaccurate construction of relevant sample set. To solve this problem, we propose a novel supervised feature extraction method suitable for the regression problem called supervised local and non-local structure preserving projections(SLNSPP), in which both input and output information can be easily and effectively incorporated through a newly defined similarity index. The SLNSPP can not only retain the virtue of locality preserving projections but also prevent faraway points from nearing after projection,which endues SLNSPP with powerful discriminating ability. Such two good properties of SLNSPP are desirable for JITL as they are expected to enhance the accuracy of similar sample selection. Consequently, we present a SLNSPP-JITL framework for developing adaptive soft sensor, including a sparse learning strategy to limit the scale and update the frequency of database. Finally, two case studies are conducted with benchmark datasets to evaluate the performance of the proposed schemes. The results demonstrate the effectiveness of LNSPP and SLNSPP.展开更多
With the rapid development of the 5G communications,the edge intelligence enables Internet of Vehicles(IoV)to provide traffic forecasting to alleviate traffic congestion and improve quality of experience of users simu...With the rapid development of the 5G communications,the edge intelligence enables Internet of Vehicles(IoV)to provide traffic forecasting to alleviate traffic congestion and improve quality of experience of users simultaneously.To enhance the forecasting performance,a novel edge-enabled probabilistic graph structure learning model(PGSLM)is proposed,which learns the graph structure and parameters by the edge sensing information and discrete probability distribution on the edges of the traffic road network.To obtain the spatio-temporal dependencies of traffic data,the learned dynamic graphs are combined with a predefined static graph to generate the graph convolution part of the recurrent graph convolution module.During the training process,a new graph training loss is introduced,which is composed of the K nearest neighbor(KNN)graph constructed by the traffic feature tensors and the graph structure.Detailed experimental results show that,compared with existing models,the proposed PGSLM improves the traffic prediction performance in terms of average absolute error and root mean square error in IoV.展开更多
To obtain the optimal Bayesian network(BN)structure,researchers often use the hybrid learning algorithm that combines the constraint-based(CB)method and the score-and-search(SS)method.This hybrid method has the proble...To obtain the optimal Bayesian network(BN)structure,researchers often use the hybrid learning algorithm that combines the constraint-based(CB)method and the score-and-search(SS)method.This hybrid method has the problemthat the search efficiency could be improved due to the ample search space.The search process quickly falls into the local optimal solution,unable to obtain the global optimal.Based on this,the Particle SwarmOptimization(PSO)algorithm based on the search space constraint process is proposed.In the first stage,the method uses dynamic adjustment factors to constrain the structure search space and enrich the diversity of the initial particles.In the second stage,the update mechanism is redefined,so that each step of the update process is consistent with the current structure which forms a one-to-one correspondence.At the same time,the“self-awakened”mechanism is added to prevent precocious particles frombeing part of the best.After the fitness value of the particle converges prematurely,the activation operation makes the particles jump out of the local optimal values to prevent the algorithmfromconverging too quickly into the local optimum.Finally,the standard network dataset was compared with other algorithms.The experimental results showed that the algorithmcould find the optimal solution at a small number of iterations and a more accurate network structure to verify the algorithm’s effectiveness.展开更多
At present Bayesian Networks(BN)are being used widely for demonstrating uncertain knowledge in many disciplines,including biology,computer science,risk analysis,service quality analysis,and business.But they suffer fr...At present Bayesian Networks(BN)are being used widely for demonstrating uncertain knowledge in many disciplines,including biology,computer science,risk analysis,service quality analysis,and business.But they suffer from the problem that when the nodes and edges increase,the structure learning difficulty increases and algorithms become inefficient.To solve this problem,heuristic optimization algorithms are used,which tend to find a near-optimal answer rather than an exact one,with particle swarm optimization(PSO)being one of them.PSO is a swarm intelligence-based algorithm having basic inspiration from flocks of birds(how they search for food).PSO is employed widely because it is easier to code,converges quickly,and can be parallelized easily.We use a recently proposed version of PSO called generalized particle swarm optimization(GEPSO)to learn bayesian network structure.We construct an initial directed acyclic graph(DAG)by using the max-min parent’s children(MMPC)algorithm and cross relative average entropy.ThisDAGis used to create a population for theGEPSO optimization procedure.Moreover,we propose a velocity update procedure to increase the efficiency of the algorithmic search process.Results of the experiments show that as the complexity of the dataset increases,our algorithm Bayesian network generalized particle swarm optimization(BN-GEPSO)outperforms the PSO algorithm in terms of the Bayesian information criterion(BIC)score.展开更多
The use of dynamic programming(DP)algorithms to learn Bayesian network structures is limited by their high space complexity and difficulty in learning the structure of large-scale networks.Therefore,this study propose...The use of dynamic programming(DP)algorithms to learn Bayesian network structures is limited by their high space complexity and difficulty in learning the structure of large-scale networks.Therefore,this study proposes a DP algorithm based on node block sequence constraints.The proposed algorithm constrains the traversal process of the parent graph by using the M-sequence matrix to considerably reduce the time consumption and space complexity by pruning the traversal process of the order graph using the node block sequence.Experimental results show that compared with existing DP algorithms,the proposed algorithm can obtain learning results more efficiently with less than 1%loss of accuracy,and can be used for learning larger-scale networks.展开更多
This paper focuses on the problem of traffic flow forecasting,with the aim of forecasting future traffic conditions based on historical traffic data.This problem is typically tackled by utilizing spatio-temporal graph...This paper focuses on the problem of traffic flow forecasting,with the aim of forecasting future traffic conditions based on historical traffic data.This problem is typically tackled by utilizing spatio-temporal graph neural networks to model the intricate spatio-temporal correlations among traffic data.Although these methods have achieved performance improvements,they often suffer from the following limitations:These methods face challenges in modeling high-order correlations between nodes.These methods overlook the interactions between nodes at different scales.To tackle these issues,in this paper,we propose a novel model named multi-scale dynamic hypergraph convolutional network(MSDHGCN)for traffic flow forecasting.Our MSDHGCN can effectively model the dynamic higher-order relationships between nodes at multiple time scales,thereby enhancing the capability for traffic forecasting.Experiments on two real-world datasets demonstrate the effectiveness of the proposed method.展开更多
To solve the drawbacks of the ant colony optimization for learning Bayesian networks(ACO-B),this paper proposes an improved algorithm based on the conditional independence test and ant colony optimization(I-ACO-B).Fir...To solve the drawbacks of the ant colony optimization for learning Bayesian networks(ACO-B),this paper proposes an improved algorithm based on the conditional independence test and ant colony optimization(I-ACO-B).First,the I-ACO-B uses order-0 independence tests to effectively restrict the space of candidate solutions,so that many unnecessary searches of ants can be avoided.And then,by combining the global score increase of a solution and local mutual information between nodes,a new heuristic function with better heuristic ability is given to induct the process of stochastic searches.The experimental results on the benchmark data sets show that the new algorithm is effective and efficient in large scale databases,and greatly enhances convergence speed compared to the original algorithm.展开更多
BACKGROUND The management of offenders with mental disorders has been a significant concern in forensic psychiatry.In Japan,the introduction of the Medical Treatment and Supervision Act in 2005 addressed the issue.How...BACKGROUND The management of offenders with mental disorders has been a significant concern in forensic psychiatry.In Japan,the introduction of the Medical Treatment and Supervision Act in 2005 addressed the issue.However,numerous psychiatric patients at risk of violence still find themselves subject to the administrative involuntary hospitalization(AIH)scheme,which lacks clarity and updated standards.AIM To explore current as well as optimized learning strategies for risk assessment in AIH decision making.METHODS We conducted a questionnaire survey among designated psychiatrists to explore their experiences and expectations regarding training methods for psychiatric assessments of offenders with mental disorders.RESULTS The findings of this study’s survey suggest a prevalent reliance on traditional learning approaches such as oral education and on-the-job training.CONCLUSION This underscores the pressing need for structured training protocols in AIH consultations.Moreover,feedback derived from inpatient treatment experiences is identified as a crucial element for enhancing risk assessment skills.展开更多
Discernment of seismic soil liquefaction is a complex and non-linear procedure that is affected by diversified factors of uncertainties and complexity.The Bayesian belief network(BBN)is an effective tool to present a ...Discernment of seismic soil liquefaction is a complex and non-linear procedure that is affected by diversified factors of uncertainties and complexity.The Bayesian belief network(BBN)is an effective tool to present a suitable framework to handle insights into such uncertainties and cause–effect relationships.The intention of this study is to use a hybrid approach methodology for the development of BBN model based on cone penetration test(CPT)case history records to evaluate seismic soil liquefaction potential.In this hybrid approach,naive model is developed initially only by an interpretive structural modeling(ISM)technique using domain knowledge(DK).Subsequently,some useful information about the naive model are embedded as DK in the K2 algorithm to develop a BBN-K2 and DK model.The results of the BBN models are compared and validated with the available artificial neural network(ANN)and C4.5 decision tree(DT)models and found that the BBN model developed by hybrid approach showed compatible and promising results for liquefaction potential assessment.The BBN model developed by hybrid approach provides a viable tool for geotechnical engineers to assess sites conditions susceptible to seismic soil liquefaction.This study also presents sensitivity analysis of the BBN model based on hybrid approach and the most probable explanation of liquefied sites,owing to know the most likely scenario of the liquefaction phenomenon.展开更多
High-dimensional data arising from diverse scientific research fields and industrial development have led to increased interest in sparse learning due to model parsimony and computational advantage. With the assumptio...High-dimensional data arising from diverse scientific research fields and industrial development have led to increased interest in sparse learning due to model parsimony and computational advantage. With the assumption of sparsity, many computational problems can be handled efficiently in practice. Structured sparse learning encodes the structural information of the variables and has been quite successful in numerous research fields. With various types of structures discovered, sorts of structured regularizations have been proposed. These regularizations have greatly improved the efficacy of sparse learning algorithms through the use of specific structural information. In this article, we present a systematic review of structured sparse learning including ideas, formulations, algorithms, and applications. We present these algorithms in the unified framework of minimizing the sum of loss and penalty functions, summarize publicly accessible software implementations, and compare the computational complexity of typical optimization methods to solve structured sparse learning problems. In experiments, we present applications in unsupervised learning, for structured signal recovery and hierarchical image reconstruction, and in supervised learning in the context of a novel graph-guided logistic regression.展开更多
We propose an approach for dependence tree structure learning via copula. A nonparametric algorithm for copula estimation is presented. Then a Chow-Liu like method based on dependence measure via copula is proposed to...We propose an approach for dependence tree structure learning via copula. A nonparametric algorithm for copula estimation is presented. Then a Chow-Liu like method based on dependence measure via copula is proposed to estimate maximum spanning bivariate copula associated with bivariate dependence relations. The main advantage of the approach is that learning with empirical copula focuses on dependence relations among random variables, without the need to know the properties of individual variables as well as without the requirement to specify parametric family of entire underlying distribution for individual variables. Experiments on two real-application data sets show the effectiveness of the proposed method.展开更多
基金The work is partially supported by Japan MEXT Kakenhi 18K11434 and Vingroup In-novation Foundation(VINIF)project code VINIF.2019.DA18.
文摘Biological domain has been blessed with more and more data from biotechnologies as well as data integration tools.In the renaissance of machine learning and artificial intelligence,there is so much promise of data-driven biological knowledge discovery.However,it is not straight forward due to the complexity of the domain knowledge hidden in the data.At any level,be it atoms,molecules,cells or organisms,there are rich interdependencies among biological components.Machine learning approaches in this domain usually involves analyzing interdependency structures encoded in graphs and related formalisms.In this report,we review our work in developing new Machine Learning methods for these applications with improved performances in comparison with state-of-the-art methods.We show how the networks among biological components can be used to predict properties.
基金supported by the National Natural Science Fundation of China(61573285)the Doctoral Fundation of China(2013ZC53037)
文摘Ordering based search methods have advantages over graph based search methods for structure learning of Bayesian networks in terms on the efficiency. With the aim of further increasing the accuracy of ordering based search methods, we first propose to increase the search space, which can facilitate escaping from the local optima. We present our search operators with majorizations, which are easy to implement. Experiments show that the proposed algorithm can obtain significantly more accurate results. With regard to the problem of the decrease on efficiency due to the increase of the search space, we then propose to add path priors as constraints into the swap process. We analyze the coefficient which may influence the performance of the proposed algorithm, the experiments show that the constraints can enhance the efficiency greatly, while has little effect on the accuracy. The final experiments show that, compared to other competitive methods, the proposed algorithm can find better solutions while holding high efficiency at the same time on both synthetic and real data sets.
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 National Natural Science Foundation of China (60974082,11171094)the Fundamental Research Funds for the Central Universities (K50510700004)+1 种基金the Foundation and Advanced Technology Research Program of Henan Province (102300410264)the Basic Research Program of the Education Department of Henan Province (2010A110010)
文摘Structure learning of Bayesian networks is a wellresearched but computationally hard task.For learning Bayesian networks,this paper proposes an improved algorithm based on unconstrained optimization and ant colony optimization（U-ACO-B） to solve the drawbacks of the ant colony optimization（ACO-B）.In this algorithm,firstly,an unconstrained optimization problem is solved to obtain an undirected skeleton,and then the ACO algorithm is used to orientate the edges,thus returning the final structure.In the experimental part of the paper,we compare the performance of the proposed algorithm with ACO-B algorithm.The experimental results show that our method is effective and greatly enhance convergence speed than ACO-B algorithm.
基金National Natural Science Foundation of China(Nos.61164010,61233003)。
文摘In view of the shortcomings of traditional Bayesian network(BN)structure learning algorithm,such as low efficiency,premature algorithm and poor learning effect,the intelligent algorithm of cuckoo search(CS)and particle swarm optimization(PSO)is selected.Combined with the characteristics of BN structure,a BN structure learning algorithm of CS-PSO is proposed.Firstly,the CS algorithm is improved from the following three aspects:the maximum spanning tree is used to guide the initialization direction of the CS algorithm,the fitness of the solution is used to adjust the optimization and abandoning process of the solution,and PSO algorithm is used to update the position of the CS algorithm.Secondly,according to the structure characteristics of BN,the CS-PSO algorithm is applied to the structure learning of BN.Finally,chest clinic,credit and car diagnosis classic network are utilized as the simulation model,and the modeling and simulation comparison of greedy algorithm,K2 algorithm,CS algorithm and CS-PSO algorithm are carried out.The results show that the CS-PSO algorithm has fast convergence speed,high convergence accuracy and good stability in the structure learning of BN,and it can get the accurate BN structure model faster and better.
基金supported by the National Natural Science Fundation of China (6097408261075055)the Fundamental Research Funds for the Central Universities (K50510700004)
文摘The learning Bayesian network （BN） structure from data is an NP-hard problem and still one of the most exciting chal- lenges in the machine learning. In this work, a novel algorithm is presented which combines ideas from local learning, constraint- based, and search-and-score techniques in a principled and ef- fective way. It first reconstructs the junction tree of a BN and then performs a K2-scoring greedy search to orientate the local edges in the cliques of junction tree. Theoretical and experimental results show the proposed algorithm is capable of handling networks with a large number of variables. Its comparison with the well-known K2 algorithm is also presented.
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.
基金Supported by the National Natural Science Foundation of China(61403290,11301408,11401454)the Foundation for Youths of Shaanxi Province(2014JQ1020)+1 种基金the Foundation of Baoji City(2013R7-3)the Foundation of Baoji University of Arts and Sciences(ZK15081)
文摘Learning Bayesian network structure is one of the most exciting challenges in machine learning. Discovering a correct skeleton of a directed acyclic graph（DAG） is the foundation for dependency analysis algorithms for this problem. Considering the unreliability of high order condition independence（CI） tests, and to improve the efficiency of a dependency analysis algorithm, the key steps are to use few numbers of CI tests and reduce the sizes of conditioning sets as much as possible. Based on these reasons and inspired by the algorithm PC, we present an algorithm, named fast and efficient PC（FEPC）, for learning the adjacent neighbourhood of every variable. FEPC implements the CI tests by three kinds of orders, which reduces the high order CI tests significantly. Compared with current algorithm proposals, the experiment results show that FEPC has better accuracy with fewer numbers of condition independence tests and smaller size of conditioning sets. The highest reduction percentage of CI test is 83.3% by EFPC compared with PC algorithm.
基金Supported by the National Natural Science Foundation of China(61273160)the Fundamental Research Funds for the Central Universities(14CX06067A,13CX05021A)
文摘In soft sensor field, just-in-time learning(JITL) is an effective approach to model nonlinear and time varying processes. However, most similarity criterions in JITL are computed in the input space only while ignoring important output information, which may lead to inaccurate construction of relevant sample set. To solve this problem, we propose a novel supervised feature extraction method suitable for the regression problem called supervised local and non-local structure preserving projections(SLNSPP), in which both input and output information can be easily and effectively incorporated through a newly defined similarity index. The SLNSPP can not only retain the virtue of locality preserving projections but also prevent faraway points from nearing after projection,which endues SLNSPP with powerful discriminating ability. Such two good properties of SLNSPP are desirable for JITL as they are expected to enhance the accuracy of similar sample selection. Consequently, we present a SLNSPP-JITL framework for developing adaptive soft sensor, including a sparse learning strategy to limit the scale and update the frequency of database. Finally, two case studies are conducted with benchmark datasets to evaluate the performance of the proposed schemes. The results demonstrate the effectiveness of LNSPP and SLNSPP.
基金supported by the project of the National Natural Science Foundation of China(No.61772562)the Knowledge Innovation Program of Wuhan-Basic Research(No.2022010801010225)the Fundamental Research Funds for the Central Universities(No.2662022YJ012)。
文摘With the rapid development of the 5G communications,the edge intelligence enables Internet of Vehicles(IoV)to provide traffic forecasting to alleviate traffic congestion and improve quality of experience of users simultaneously.To enhance the forecasting performance,a novel edge-enabled probabilistic graph structure learning model(PGSLM)is proposed,which learns the graph structure and parameters by the edge sensing information and discrete probability distribution on the edges of the traffic road network.To obtain the spatio-temporal dependencies of traffic data,the learned dynamic graphs are combined with a predefined static graph to generate the graph convolution part of the recurrent graph convolution module.During the training process,a new graph training loss is introduced,which is composed of the K nearest neighbor(KNN)graph constructed by the traffic feature tensors and the graph structure.Detailed experimental results show that,compared with existing models,the proposed PGSLM improves the traffic prediction performance in terms of average absolute error and root mean square error in IoV.
基金funded by the National Natural Science Foundation of China(62262016)in part by the Hainan Provincial Natural Science Foundation Innovation Research Team Project(620CXTD434)+1 种基金in part by the High-Level Talent Project Hainan Natural Science Foundation(620RC557)in part by the Hainan Provincial Key R&D Plan(ZDYF2021GXJS199).
文摘To obtain the optimal Bayesian network(BN)structure,researchers often use the hybrid learning algorithm that combines the constraint-based(CB)method and the score-and-search(SS)method.This hybrid method has the problemthat the search efficiency could be improved due to the ample search space.The search process quickly falls into the local optimal solution,unable to obtain the global optimal.Based on this,the Particle SwarmOptimization(PSO)algorithm based on the search space constraint process is proposed.In the first stage,the method uses dynamic adjustment factors to constrain the structure search space and enrich the diversity of the initial particles.In the second stage,the update mechanism is redefined,so that each step of the update process is consistent with the current structure which forms a one-to-one correspondence.At the same time,the“self-awakened”mechanism is added to prevent precocious particles frombeing part of the best.After the fitness value of the particle converges prematurely,the activation operation makes the particles jump out of the local optimal values to prevent the algorithmfromconverging too quickly into the local optimum.Finally,the standard network dataset was compared with other algorithms.The experimental results showed that the algorithmcould find the optimal solution at a small number of iterations and a more accurate network structure to verify the algorithm’s effectiveness.
基金The authors extended their appreciation to the Deanship of Scientific Research at King Khalid University for funding this work through the Large Groups Project under grant number RGP.2/132/43。
文摘At present Bayesian Networks(BN)are being used widely for demonstrating uncertain knowledge in many disciplines,including biology,computer science,risk analysis,service quality analysis,and business.But they suffer from the problem that when the nodes and edges increase,the structure learning difficulty increases and algorithms become inefficient.To solve this problem,heuristic optimization algorithms are used,which tend to find a near-optimal answer rather than an exact one,with particle swarm optimization(PSO)being one of them.PSO is a swarm intelligence-based algorithm having basic inspiration from flocks of birds(how they search for food).PSO is employed widely because it is easier to code,converges quickly,and can be parallelized easily.We use a recently proposed version of PSO called generalized particle swarm optimization(GEPSO)to learn bayesian network structure.We construct an initial directed acyclic graph(DAG)by using the max-min parent’s children(MMPC)algorithm and cross relative average entropy.ThisDAGis used to create a population for theGEPSO optimization procedure.Moreover,we propose a velocity update procedure to increase the efficiency of the algorithmic search process.Results of the experiments show that as the complexity of the dataset increases,our algorithm Bayesian network generalized particle swarm optimization(BN-GEPSO)outperforms the PSO algorithm in terms of the Bayesian information criterion(BIC)score.
基金Shaanxi Science Fund for Distinguished Young Scholars,Grant/Award Number:2024JC-JCQN-57Xi’an Science and Technology Plan Project,Grant/Award Number:2023JH-QCYJQ-0086+2 种基金Scientific Research Program Funded by Education Department of Shaanxi Provincial Government,Grant/Award Number:P23JP071Engineering Technology Research Center of Shaanxi Province for Intelligent Testing and Reliability Evaluation of Electronic Equipments,Grant/Award Number:2023-ZC-GCZX-00472022 Shaanxi University Youth Innovation Team Project。
文摘The use of dynamic programming(DP)algorithms to learn Bayesian network structures is limited by their high space complexity and difficulty in learning the structure of large-scale networks.Therefore,this study proposes a DP algorithm based on node block sequence constraints.The proposed algorithm constrains the traversal process of the parent graph by using the M-sequence matrix to considerably reduce the time consumption and space complexity by pruning the traversal process of the order graph using the node block sequence.Experimental results show that compared with existing DP algorithms,the proposed algorithm can obtain learning results more efficiently with less than 1%loss of accuracy,and can be used for learning larger-scale networks.
基金the National Key Research and Development Program of China(No.2021ZD0112400)。
文摘This paper focuses on the problem of traffic flow forecasting,with the aim of forecasting future traffic conditions based on historical traffic data.This problem is typically tackled by utilizing spatio-temporal graph neural networks to model the intricate spatio-temporal correlations among traffic data.Although these methods have achieved performance improvements,they often suffer from the following limitations:These methods face challenges in modeling high-order correlations between nodes.These methods overlook the interactions between nodes at different scales.To tackle these issues,in this paper,we propose a novel model named multi-scale dynamic hypergraph convolutional network(MSDHGCN)for traffic flow forecasting.Our MSDHGCN can effectively model the dynamic higher-order relationships between nodes at multiple time scales,thereby enhancing the capability for traffic forecasting.Experiments on two real-world datasets demonstrate the effectiveness of the proposed method.
基金Supported by National Natural Science Foundation of China(60496322)Natural Science Foundation of Beijing(4083034)Scientific Research Common Program of Beijing Municipal Commission.of Education(KM200610005020)
文摘To solve the drawbacks of the ant colony optimization for learning Bayesian networks(ACO-B),this paper proposes an improved algorithm based on the conditional independence test and ant colony optimization(I-ACO-B).First,the I-ACO-B uses order-0 independence tests to effectively restrict the space of candidate solutions,so that many unnecessary searches of ants can be avoided.And then,by combining the global score increase of a solution and local mutual information between nodes,a new heuristic function with better heuristic ability is given to induct the process of stochastic searches.The experimental results on the benchmark data sets show that the new algorithm is effective and efficient in large scale databases,and greatly enhances convergence speed compared to the original algorithm.
基金Supported by Research Project of the Ministry of Health,Labour and Welfare of Japan.
文摘BACKGROUND The management of offenders with mental disorders has been a significant concern in forensic psychiatry.In Japan,the introduction of the Medical Treatment and Supervision Act in 2005 addressed the issue.However,numerous psychiatric patients at risk of violence still find themselves subject to the administrative involuntary hospitalization(AIH)scheme,which lacks clarity and updated standards.AIM To explore current as well as optimized learning strategies for risk assessment in AIH decision making.METHODS We conducted a questionnaire survey among designated psychiatrists to explore their experiences and expectations regarding training methods for psychiatric assessments of offenders with mental disorders.RESULTS The findings of this study’s survey suggest a prevalent reliance on traditional learning approaches such as oral education and on-the-job training.CONCLUSION This underscores the pressing need for structured training protocols in AIH consultations.Moreover,feedback derived from inpatient treatment experiences is identified as a crucial element for enhancing risk assessment skills.
基金Projects(2016YFE0200100,2018YFC1505300-5.3)supported by the National Key Research&Development Plan of ChinaProject(51639002)supported by the Key Program of National Natural Science Foundation of China
文摘Discernment of seismic soil liquefaction is a complex and non-linear procedure that is affected by diversified factors of uncertainties and complexity.The Bayesian belief network(BBN)is an effective tool to present a suitable framework to handle insights into such uncertainties and cause–effect relationships.The intention of this study is to use a hybrid approach methodology for the development of BBN model based on cone penetration test(CPT)case history records to evaluate seismic soil liquefaction potential.In this hybrid approach,naive model is developed initially only by an interpretive structural modeling(ISM)technique using domain knowledge(DK).Subsequently,some useful information about the naive model are embedded as DK in the K2 algorithm to develop a BBN-K2 and DK model.The results of the BBN models are compared and validated with the available artificial neural network(ANN)and C4.5 decision tree(DT)models and found that the BBN model developed by hybrid approach showed compatible and promising results for liquefaction potential assessment.The BBN model developed by hybrid approach provides a viable tool for geotechnical engineers to assess sites conditions susceptible to seismic soil liquefaction.This study also presents sensitivity analysis of the BBN model based on hybrid approach and the most probable explanation of liquefied sites,owing to know the most likely scenario of the liquefaction phenomenon.
基金Project supported by the National Natural Science Foundation of China （No. 61303264）
文摘High-dimensional data arising from diverse scientific research fields and industrial development have led to increased interest in sparse learning due to model parsimony and computational advantage. With the assumption of sparsity, many computational problems can be handled efficiently in practice. Structured sparse learning encodes the structural information of the variables and has been quite successful in numerous research fields. With various types of structures discovered, sorts of structured regularizations have been proposed. These regularizations have greatly improved the efficacy of sparse learning algorithms through the use of specific structural information. In this article, we present a systematic review of structured sparse learning including ideas, formulations, algorithms, and applications. We present these algorithms in the unified framework of minimizing the sum of loss and penalty functions, summarize publicly accessible software implementations, and compare the computational complexity of typical optimization methods to solve structured sparse learning problems. In experiments, we present applications in unsupervised learning, for structured signal recovery and hierarchical image reconstruction, and in supervised learning in the context of a novel graph-guided logistic regression.
文摘We propose an approach for dependence tree structure learning via copula. A nonparametric algorithm for copula estimation is presented. Then a Chow-Liu like method based on dependence measure via copula is proposed to estimate maximum spanning bivariate copula associated with bivariate dependence relations. The main advantage of the approach is that learning with empirical copula focuses on dependence relations among random variables, without the need to know the properties of individual variables as well as without the requirement to specify parametric family of entire underlying distribution for individual variables. Experiments on two real-application data sets show the effectiveness of the proposed method.
