Background Plant tissue culture has emerged as a tool for improving cotton propagation and genetics,but recalcitrance nature of cotton makes it difficult to develop in vitro regeneration.Cotton’s recalcitrance is inf...Background Plant tissue culture has emerged as a tool for improving cotton propagation and genetics,but recalcitrance nature of cotton makes it difficult to develop in vitro regeneration.Cotton’s recalcitrance is influenced by genotype,explant type,and environmental conditions.To overcome these issues,this study uses different machine learning-based predictive models by employing multiple input factors.Cotyledonary node explants of two commercial cotton cultivars(STN-468 and GSN-12)were isolated from 7–8 days old seedlings,preconditioned with 5,10,and 20 mg·L^(-1) kinetin(KIN)for 10 days.Thereafter,explants were postconditioned on full Murashige and Skoog(MS),1/2MS,1/4MS,and full MS+0.05 mg·L^(-1) KIN,cultured in growth room enlightened with red and blue light-emitting diodes(LED)combination.Statistical analysis(analysis of variance,regression analysis)was employed to assess the impact of different treatments on shoot regeneration,with artificial intelligence(AI)models used for confirming the findings.Results GSN-12 exhibited superior shoot regeneration potential compared with STN-468,with an average of 4.99 shoots per explant versus 3.97.Optimal results were achieved with 5 mg·L^(-1) KIN preconditioning,1/4MS postconditioning,and 80%red LED,with maximum of 7.75 shoot count for GSN-12 under these conditions;while STN-468 reached 6.00 shoots under the conditions of 10 mg·L^(-1) KIN preconditioning,MS with 0.05 mg·L^(-1) KIN(postconditioning)and 75.0%red LED.Rooting was successfully achieved with naphthalene acetic acid and activated charcoal.Additionally,three different powerful AI-based models,namely,extreme gradient boost(XGBoost),random forest(RF),and the artificial neural network-based multilayer perceptron(MLP)regression models validated the findings.Conclusion GSN-12 outperformed STN-468 with optimal results from 5 mg·L^(-1) KIN+1/4MS+80%red LED.Application of machine learning-based prediction models to optimize cotton tissue culture protocols for shoot regeneration is helpful to improve cotton regeneration efficiency.展开更多
Deep neural networks(DNNs)have achieved great success in many data processing applications.However,high computational complexity and storage cost make deep learning difficult to be used on resource-constrained devices...Deep neural networks(DNNs)have achieved great success in many data processing applications.However,high computational complexity and storage cost make deep learning difficult to be used on resource-constrained devices,and it is not environmental-friendly with much power cost.In this paper,we focus on low-rank optimization for efficient deep learning techniques.In the space domain,DNNs are compressed by low rank approximation of the network parameters,which directly reduces the storage requirement with a smaller number of network parameters.In the time domain,the network parameters can be trained in a few subspaces,which enables efficient training for fast convergence.The model compression in the spatial domain is summarized into three categories as pre-train,pre-set,and compression-aware methods,respectively.With a series of integrable techniques discussed,such as sparse pruning,quantization,and entropy coding,we can ensemble them in an integration framework with lower computational complexity and storage.In addition to summary of recent technical advances,we have two findings for motivating future works.One is that the effective rank,derived from the Shannon entropy of the normalized singular values,outperforms other conventional sparse measures such as the?_1 norm for network compression.The other is a spatial and temporal balance for tensorized neural networks.For accelerating the training of tensorized neural networks,it is crucial to leverage redundancy for both model compression and subspace training.展开更多
In this paper,the optimal control of non-linear switching system is investigated without knowing the system dynamics.First,the Hamilton-Jacobi-Bellman(HJB)equation is derived with the consideration of hybrid action sp...In this paper,the optimal control of non-linear switching system is investigated without knowing the system dynamics.First,the Hamilton-Jacobi-Bellman(HJB)equation is derived with the consideration of hybrid action space.Then,a novel data-based hybrid Q-learning(HQL)algorithm is proposed to find the optimal solution in an iterative manner.In addition,the theoretical analysis is provided to illustrate the convergence and optimality of the proposed algorithm.Finally,the algorithm is implemented with the actor-critic(AC)structure,and two linear-in-parameter neural networks are utilized to approximate the functions.Simulation results validate the effectiveness of the data-driven method.展开更多
It is unpractical to learn the optimal structure of a big Bayesian network(BN)by exhausting the feasible structures,since the number of feasible structures is super exponential on the number of nodes.This paper propos...It is unpractical to learn the optimal structure of a big Bayesian network(BN)by exhausting the feasible structures,since the number of feasible structures is super exponential on the number of nodes.This paper proposes an approach to layer nodes of a BN by using the conditional independence testing.The parents of a node layer only belong to the layer,or layers who have priority over the layer.When a set of nodes has been layered,the number of feasible structures over the nodes can be remarkably reduced,which makes it possible to learn optimal BN structures for bigger sizes of nodes by accurate algorithms.Integrating the dynamic programming(DP)algorithm with the layering approach,we propose a hybrid algorithm—layered optimal learning(LOL)to learn BN structures.Benefitted by the layering approach,the complexity of the DP algorithm reduces to O(ρ2^n?1)from O(n2^n?1),whereρ<n.Meanwhile,the memory requirements for storing intermediate results are limited to O(C k#/k#^2 )from O(Cn/n^2 ),where k#<n.A case study on learning a standard BN with 50 nodes is conducted.The results demonstrate the superiority of the LOL algorithm,with respect to the Bayesian information criterion(BIC)score criterion,over the hill-climbing,max-min hill-climbing,PC,and three-phrase dependency analysis algorithms.展开更多
To solve the problem of the low interference success rate of air defense missile radio fuzes due to the unified interference form of the traditional fuze interference system,an interference decision method based Q-lea...To solve the problem of the low interference success rate of air defense missile radio fuzes due to the unified interference form of the traditional fuze interference system,an interference decision method based Q-learning algorithm is proposed.First,dividing the distance between the missile and the target into multiple states to increase the quantity of state spaces.Second,a multidimensional motion space is utilized,and the search range of which changes with the distance of the projectile,to select parameters and minimize the amount of ineffective interference parameters.The interference effect is determined by detecting whether the fuze signal disappears.Finally,a weighted reward function is used to determine the reward value based on the range state,output power,and parameter quantity information of the interference form.The effectiveness of the proposed method in selecting the range of motion space parameters and designing the discrimination degree of the reward function has been verified through offline experiments involving full-range missile rendezvous.The optimal interference form for each distance state has been obtained.Compared with the single-interference decision method,the proposed decision method can effectively improve the success rate of interference.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
This paper proposes a liner active disturbance rejection control(LADRC) method based on the Q-Learning algorithm of reinforcement learning(RL) to control the six-degree-of-freedom motion of an autonomous underwater ve...This paper proposes a liner active disturbance rejection control(LADRC) method based on the Q-Learning algorithm of reinforcement learning(RL) to control the six-degree-of-freedom motion of an autonomous underwater vehicle(AUV).The number of controllers is increased to realize AUV motion decoupling.At the same time, in order to avoid the oversize of the algorithm, combined with the controlled content, a simplified Q-learning algorithm is constructed to realize the parameter adaptation of the LADRC controller.Finally, through the simulation experiment of the controller with fixed parameters and the controller based on the Q-learning algorithm, the rationality of the simplified algorithm, the effectiveness of parameter adaptation, and the unique advantages of the LADRC controller are verified.展开更多
To solve the path following control problem for unmanned surface vehicles(USVs),a control method based on deep reinforcement learning(DRL)with long short-term memory(LSTM)networks is proposed.A distributed proximal po...To solve the path following control problem for unmanned surface vehicles(USVs),a control method based on deep reinforcement learning(DRL)with long short-term memory(LSTM)networks is proposed.A distributed proximal policy opti-mization(DPPO)algorithm,which is a modified actor-critic-based type of reinforcement learning algorithm,is adapted to improve the controller performance in repeated trials.The LSTM network structure is introduced to solve the strong temporal cor-relation USV control problem.In addition,a specially designed path dataset,including straight and curved paths,is established to simulate various sailing scenarios so that the reinforcement learning controller can obtain as much handling experience as possible.Extensive numerical simulation results demonstrate that the proposed method has better control performance under missions involving complex maneuvers than trained with limited scenarios and can potentially be applied in practice.展开更多
Underground excavation can lead to stress redistribution and result in an excavation damaged zone(EDZ),which is an important factor affecting the excavation stability and support design.Accurately estimating the thick...Underground excavation can lead to stress redistribution and result in an excavation damaged zone(EDZ),which is an important factor affecting the excavation stability and support design.Accurately estimating the thickness of EDZ is essential to ensure the safety of the underground excavation.In this study,four novel hybrid ensemble learning models were developed by optimizing the extreme gradient boosting(XGBoost)and random forest(RF)algorithms through simulated annealing(SA)and Bayesian optimization(BO)approaches,namely SA-XGBoost,SA-RF,BO XGBoost and BO-RF models.A total of 210 cases were collected from Xiangxi Gold Mine in Hunan Province and Fankou Lead-zinc Mine in Guangdong Province,China,including seven input indicators:embedding depth,drift span,uniaxial compressive strength of rock,rock mass rating,unit weight of rock,lateral pressure coefficient of roadway and unit consumption of blasting explosive.The performance of the proposed models was evaluated by the coefficient of determination,root mean squared error,mean absolute error and variance accounted for.The results indicated that the SA-XGBoost model performed best.The Shapley additive explanations method revealed that the embedding depth was the most important indicator.Moreover,the convergence curves suggested that the SA-XGBoost model can reduce the generalization error and avoid overfitting.展开更多
Fault diagnosis technology plays an important role in the industries due to the emergency fault of a machine could bring the heavy lost for the people and the company. A fault diagnosis model based on multi-manifold l...Fault diagnosis technology plays an important role in the industries due to the emergency fault of a machine could bring the heavy lost for the people and the company. A fault diagnosis model based on multi-manifold learning and particle swarm optimization support vector machine(PSO-SVM) is studied. This fault diagnosis model is used for a rolling bearing experimental of three kinds faults. The results are verified that this model based on multi-manifold learning and PSO-SVM is good at the fault sensitive features acquisition with effective accuracy.展开更多
The recently invented artificial bee colony （ABC） al- gorithm is an optimization algorithm based on swarm intelligence that has been used to solve many kinds of numerical function optimization problems. It performs ...The recently invented artificial bee colony （ABC） al- gorithm is an optimization algorithm based on swarm intelligence that has been used to solve many kinds of numerical function optimization problems. It performs well in most cases, however, there still exists an insufficiency in the ABC algorithm that ignores the fitness of related pairs of individuals in the mechanism of find- ing a neighboring food source. This paper presents an improved ABC algorithm with mutual learning （MutualABC） that adjusts the produced candidate food source with the higher fitness between two individuals selected by a mutual learning factor. The perfor- mance of the improved MutualABC algorithm is tested on a set of benchmark functions and compared with the basic ABC algo- rithm and some classical versions of improved ABC algorithms. The experimental results show that the MutualABC algorithm with appropriate parameters outperforms other ABC algorithms in most experiments.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
文摘Background Plant tissue culture has emerged as a tool for improving cotton propagation and genetics,but recalcitrance nature of cotton makes it difficult to develop in vitro regeneration.Cotton’s recalcitrance is influenced by genotype,explant type,and environmental conditions.To overcome these issues,this study uses different machine learning-based predictive models by employing multiple input factors.Cotyledonary node explants of two commercial cotton cultivars(STN-468 and GSN-12)were isolated from 7–8 days old seedlings,preconditioned with 5,10,and 20 mg·L^(-1) kinetin(KIN)for 10 days.Thereafter,explants were postconditioned on full Murashige and Skoog(MS),1/2MS,1/4MS,and full MS+0.05 mg·L^(-1) KIN,cultured in growth room enlightened with red and blue light-emitting diodes(LED)combination.Statistical analysis(analysis of variance,regression analysis)was employed to assess the impact of different treatments on shoot regeneration,with artificial intelligence(AI)models used for confirming the findings.Results GSN-12 exhibited superior shoot regeneration potential compared with STN-468,with an average of 4.99 shoots per explant versus 3.97.Optimal results were achieved with 5 mg·L^(-1) KIN preconditioning,1/4MS postconditioning,and 80%red LED,with maximum of 7.75 shoot count for GSN-12 under these conditions;while STN-468 reached 6.00 shoots under the conditions of 10 mg·L^(-1) KIN preconditioning,MS with 0.05 mg·L^(-1) KIN(postconditioning)and 75.0%red LED.Rooting was successfully achieved with naphthalene acetic acid and activated charcoal.Additionally,three different powerful AI-based models,namely,extreme gradient boost(XGBoost),random forest(RF),and the artificial neural network-based multilayer perceptron(MLP)regression models validated the findings.Conclusion GSN-12 outperformed STN-468 with optimal results from 5 mg·L^(-1) KIN+1/4MS+80%red LED.Application of machine learning-based prediction models to optimize cotton tissue culture protocols for shoot regeneration is helpful to improve cotton regeneration efficiency.
基金supported by the National Natural Science Foundation of China(62171088,U19A2052,62020106011)the Medico-Engineering Cooperation Funds from University of Electronic Science and Technology of China(ZYGX2021YGLH215,ZYGX2022YGRH005)。
文摘Deep neural networks(DNNs)have achieved great success in many data processing applications.However,high computational complexity and storage cost make deep learning difficult to be used on resource-constrained devices,and it is not environmental-friendly with much power cost.In this paper,we focus on low-rank optimization for efficient deep learning techniques.In the space domain,DNNs are compressed by low rank approximation of the network parameters,which directly reduces the storage requirement with a smaller number of network parameters.In the time domain,the network parameters can be trained in a few subspaces,which enables efficient training for fast convergence.The model compression in the spatial domain is summarized into three categories as pre-train,pre-set,and compression-aware methods,respectively.With a series of integrable techniques discussed,such as sparse pruning,quantization,and entropy coding,we can ensemble them in an integration framework with lower computational complexity and storage.In addition to summary of recent technical advances,we have two findings for motivating future works.One is that the effective rank,derived from the Shannon entropy of the normalized singular values,outperforms other conventional sparse measures such as the?_1 norm for network compression.The other is a spatial and temporal balance for tensorized neural networks.For accelerating the training of tensorized neural networks,it is crucial to leverage redundancy for both model compression and subspace training.
基金supported by the National Key R&D Program of China(2018AAA0101400)the Natural Science Foundation of Jiangsu Province of China(BK20202006)the National Natural Science Foundation of China(61921004,62173251).
文摘In this paper,the optimal control of non-linear switching system is investigated without knowing the system dynamics.First,the Hamilton-Jacobi-Bellman(HJB)equation is derived with the consideration of hybrid action space.Then,a novel data-based hybrid Q-learning(HQL)algorithm is proposed to find the optimal solution in an iterative manner.In addition,the theoretical analysis is provided to illustrate the convergence and optimality of the proposed algorithm.Finally,the algorithm is implemented with the actor-critic(AC)structure,and two linear-in-parameter neural networks are utilized to approximate the functions.Simulation results validate the effectiveness of the data-driven method.
基金supported by the National Natural Science Foundation of China(61573285)
文摘It is unpractical to learn the optimal structure of a big Bayesian network(BN)by exhausting the feasible structures,since the number of feasible structures is super exponential on the number of nodes.This paper proposes an approach to layer nodes of a BN by using the conditional independence testing.The parents of a node layer only belong to the layer,or layers who have priority over the layer.When a set of nodes has been layered,the number of feasible structures over the nodes can be remarkably reduced,which makes it possible to learn optimal BN structures for bigger sizes of nodes by accurate algorithms.Integrating the dynamic programming(DP)algorithm with the layering approach,we propose a hybrid algorithm—layered optimal learning(LOL)to learn BN structures.Benefitted by the layering approach,the complexity of the DP algorithm reduces to O(ρ2^n?1)from O(n2^n?1),whereρ<n.Meanwhile,the memory requirements for storing intermediate results are limited to O(C k#/k#^2 )from O(Cn/n^2 ),where k#<n.A case study on learning a standard BN with 50 nodes is conducted.The results demonstrate the superiority of the LOL algorithm,with respect to the Bayesian information criterion(BIC)score criterion,over the hill-climbing,max-min hill-climbing,PC,and three-phrase dependency analysis algorithms.
基金National Natural Science Foundation of China(61973037)National 173 Program Project(2019-JCJQ-ZD-324).
文摘To solve the problem of the low interference success rate of air defense missile radio fuzes due to the unified interference form of the traditional fuze interference system,an interference decision method based Q-learning algorithm is proposed.First,dividing the distance between the missile and the target into multiple states to increase the quantity of state spaces.Second,a multidimensional motion space is utilized,and the search range of which changes with the distance of the projectile,to select parameters and minimize the amount of ineffective interference parameters.The interference effect is determined by detecting whether the fuze signal disappears.Finally,a weighted reward function is used to determine the reward value based on the range state,output power,and parameter quantity information of the interference form.The effectiveness of the proposed method in selecting the range of motion space parameters and designing the discrimination degree of the reward function has been verified through offline experiments involving full-range missile rendezvous.The optimal interference form for each distance state has been obtained.Compared with the single-interference decision method,the proposed decision method can effectively improve the success rate of interference.
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supported by the National Natural Science Foundation of China (6197317561973172)Tianjin Natural Science Foundation (19JCZDJC32800)。
文摘This paper proposes a liner active disturbance rejection control(LADRC) method based on the Q-Learning algorithm of reinforcement learning(RL) to control the six-degree-of-freedom motion of an autonomous underwater vehicle(AUV).The number of controllers is increased to realize AUV motion decoupling.At the same time, in order to avoid the oversize of the algorithm, combined with the controlled content, a simplified Q-learning algorithm is constructed to realize the parameter adaptation of the LADRC controller.Finally, through the simulation experiment of the controller with fixed parameters and the controller based on the Q-learning algorithm, the rationality of the simplified algorithm, the effectiveness of parameter adaptation, and the unique advantages of the LADRC controller are verified.
基金supported by the National Natural Science Foundation(61601491)the Natural Science Foundation of Hubei Province(2018CFC865)the China Postdoctoral Science Foundation Funded Project(2016T45686).
文摘To solve the path following control problem for unmanned surface vehicles(USVs),a control method based on deep reinforcement learning(DRL)with long short-term memory(LSTM)networks is proposed.A distributed proximal policy opti-mization(DPPO)algorithm,which is a modified actor-critic-based type of reinforcement learning algorithm,is adapted to improve the controller performance in repeated trials.The LSTM network structure is introduced to solve the strong temporal cor-relation USV control problem.In addition,a specially designed path dataset,including straight and curved paths,is established to simulate various sailing scenarios so that the reinforcement learning controller can obtain as much handling experience as possible.Extensive numerical simulation results demonstrate that the proposed method has better control performance under missions involving complex maneuvers than trained with limited scenarios and can potentially be applied in practice.
基金Project(52204117)supported by the National Natural Science Foundation of ChinaProject(2022JJ40601)supported by the Natural Science Foundation of Hunan Province,China。
文摘Underground excavation can lead to stress redistribution and result in an excavation damaged zone(EDZ),which is an important factor affecting the excavation stability and support design.Accurately estimating the thickness of EDZ is essential to ensure the safety of the underground excavation.In this study,four novel hybrid ensemble learning models were developed by optimizing the extreme gradient boosting(XGBoost)and random forest(RF)algorithms through simulated annealing(SA)and Bayesian optimization(BO)approaches,namely SA-XGBoost,SA-RF,BO XGBoost and BO-RF models.A total of 210 cases were collected from Xiangxi Gold Mine in Hunan Province and Fankou Lead-zinc Mine in Guangdong Province,China,including seven input indicators:embedding depth,drift span,uniaxial compressive strength of rock,rock mass rating,unit weight of rock,lateral pressure coefficient of roadway and unit consumption of blasting explosive.The performance of the proposed models was evaluated by the coefficient of determination,root mean squared error,mean absolute error and variance accounted for.The results indicated that the SA-XGBoost model performed best.The Shapley additive explanations method revealed that the embedding depth was the most important indicator.Moreover,the convergence curves suggested that the SA-XGBoost model can reduce the generalization error and avoid overfitting.
基金Supported by National Natural Science Foundation of China （60496322）, Natural Science Foundation of Beijing （4083034）, and Scientific Research Common Program of Beijing Municipal Commission.of Education （KM200610005020）_ _ _
基金Beijing Natural Science Foundation(KZ201211232039)National Natural Science Foundation of China(51275052)+1 种基金Funding Project for Academic Human Resources Development in Institutions of Higher Learning under the Jurisdiction of Beijing Municipalipality(PHR201106132)PXM2014_014224_000080
文摘Fault diagnosis technology plays an important role in the industries due to the emergency fault of a machine could bring the heavy lost for the people and the company. A fault diagnosis model based on multi-manifold learning and particle swarm optimization support vector machine(PSO-SVM) is studied. This fault diagnosis model is used for a rolling bearing experimental of three kinds faults. The results are verified that this model based on multi-manifold learning and PSO-SVM is good at the fault sensitive features acquisition with effective accuracy.
基金supported by the National Natural Science Foundation of China (60803074)the Fundamental Research Funds for the Central Universities (DUT10JR06)
文摘The recently invented artificial bee colony （ABC） al- gorithm is an optimization algorithm based on swarm intelligence that has been used to solve many kinds of numerical function optimization problems. It performs well in most cases, however, there still exists an insufficiency in the ABC algorithm that ignores the fitness of related pairs of individuals in the mechanism of find- ing a neighboring food source. This paper presents an improved ABC algorithm with mutual learning （MutualABC） that adjusts the produced candidate food source with the higher fitness between two individuals selected by a mutual learning factor. The perfor- mance of the improved MutualABC algorithm is tested on a set of benchmark functions and compared with the basic ABC algo- rithm and some classical versions of improved ABC algorithms. The experimental results show that the MutualABC algorithm with appropriate parameters outperforms other ABC algorithms in most experiments.
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.
