An approach based on artificial neural network （ANN） is used to develop predictive relations between hydrodynamic inline force on a vertical cylinder and some effective parameters. The data used to calibrate and val...An approach based on artificial neural network （ANN） is used to develop predictive relations between hydrodynamic inline force on a vertical cylinder and some effective parameters. The data used to calibrate and validate the ANN models are obtained from an experiment. Multilayer feed-forward neural networks that are trained with the back-propagation algorithm are constructed by use of three design parameters （i.e. wave surface height, horizontal and vertical velocities） as network inputs and the ultimate inline force as the only output. A sensitivity analysis is conducted on the ANN models to investigate the generalization ability （robustness） of the developed models, and predictions from the ANN models are compared to those obtained from Morison equation which is usually used to determine inline force as a computational method. With the existing data, it is found that least square method （LSM） gives less error in determining drag and inertia coefficients of Morison equation. With regard to the predicted results agreeing with calculations achieved from Morison equation that used LSM method, neural network has high efficiency considering its convenience, simplicity and promptitude. The outcome of this study can contribute to reducing the errors in predicting hydrodynamic inline force by use of ANN and to improve the reliability of that in comparison with the more practical state of Morison equation. Therefore, this method can be applied to relevant engineering projects with satisfactory results展开更多
In this paper, sixty-eight research articles published between 2000 and 2017 as well as textbooks which employed four classification algorithms: K-Nearest-Neighbor (KNN), Support Vector Machines (SVM), Random Forest (...In this paper, sixty-eight research articles published between 2000 and 2017 as well as textbooks which employed four classification algorithms: K-Nearest-Neighbor (KNN), Support Vector Machines (SVM), Random Forest (RF) and Neural Network (NN) as the main statistical tools were reviewed. The aim was to examine and compare these nonparametric classification methods on the following attributes: robustness to training data, sensitivity to changes, data fitting, stability, ability to handle large data sizes, sensitivity to noise, time invested in parameter tuning, and accuracy. The performances, strengths and shortcomings of each of the algorithms were examined, and finally, a conclusion was arrived at on which one has higher performance. It was evident from the literature reviewed that RF is too sensitive to small changes in the training dataset and is occasionally unstable and tends to overfit in the model. KNN is easy to implement and understand but has a major drawback of becoming significantly slow as the size of the data in use grows, while the ideal value of K for the KNN classifier is difficult to set. SVM and RF are insensitive to noise or overtraining, which shows their ability in dealing with unbalanced data. Larger input datasets will lengthen classification times for NN and KNN more than for SVM and RF. Among these nonparametric classification methods, NN has the potential to become a more widely used classification algorithm, but because of their time-consuming parameter tuning procedure, high level of complexity in computational processing, the numerous types of NN architectures to choose from and the high number of algorithms used for training, most researchers recommend SVM and RF as easier and wieldy used methods which repeatedly achieve results with high accuracies and are often faster to implement.展开更多
Randomized weights neural networks have fast learning speed and good generalization performance with one single hidden layer structure. Input weighs of the hidden layer are produced randomly. By employing certain acti...Randomized weights neural networks have fast learning speed and good generalization performance with one single hidden layer structure. Input weighs of the hidden layer are produced randomly. By employing certain activation function, outputs of the hidden layer are calculated with some randomization. Output weights are computed using pseudo inverse. Mutual information can be used to measure mutual dependence of two variables quantitatively based on the probability theory. In this paper, these hidden layer’s outputs that relate to prediction variable closely are selected with the simple mutual information based feature selection method. These hidden nodes with high mutual information values are maintained as a new hidden layer. Thus, the size of the hidden layer is reduced. The new hidden layer’s output weights are learned with the pseudo inverse method. The proposed method is compared with the original randomized algorithms using concrete compressive strength benchmark dataset.展开更多
The construction of a pest detection algorithm is an important step to couple"ground-space"characteristics,which is also the basis for rapid and accurate monitoring and detection of pest damage.In four exper...The construction of a pest detection algorithm is an important step to couple"ground-space"characteristics,which is also the basis for rapid and accurate monitoring and detection of pest damage.In four experimental areas in Sanming City,Jiangle County,Sha County and Yanping District in Fujian Province,sample data on pest damage in 182 sets of Dendrolimus punctatus were collected.The data were randomly divided into a training set and testing set,and five duplicate tests and one eliminating-indicator test were done.Based on the characterization analysis of the host for D.punctatus damage,seven characteristic indicators of ground and remote sensing including leaf area index,standard error of leaf area index(SEL)of pine forest,normalized difference vegetation index(NDVI),wetness from tasseled cap transformation(WET),green band(B2),red band(B3),near-infrared band(B4)of remote sensing image are obtained to construct BP neural networks and random forest models of pest levels.The detection results of these two algorithms were comprehensively compared from the aspects of detection precision,kappa coefficient,receiver operating characteristic curve,and a paired t test.The results showed that the seven indicators all were responsive to pest damage,and NDVI was relatively weak;the average pest damage detection precision of six tests by BP neural networks was 77.29%,the kappa coefficient was 0.6869 and after the RF algorithm,the respective values were 79.30%and 0.7151,showing that the latter is more optimized,but there was no significant difference(p>0.05);the detection precision,kappa coefficient and AUC of the RF algorithm was higher than the BP neural networks for three pest levels(no damage,moderate damage and severe damage).The detection precision and AUC of BP neural networks were a little higher for mild damage,but the difference was not significant(p>0.05)except for the kappa coefficient for the no damage level(p<0.05).An"over-fitting"phenomenon tends to occur in BP neural networks,while RF method is more robust,providing a detection effect that is better than the BP neural networks.Thus,the application of the random forest algorithm for pest damage and multilevel dispersed variables is thus feasible and suggests that attention to the proportionality of sample data from various categories is needed when collecting data.展开更多
In this paper,the asymptotical mean-square stability analysis problem is considered for a class of cellular neural networks (CNNs) with random delay. Compared with the previous work,the delay is modeled by a continuou...In this paper,the asymptotical mean-square stability analysis problem is considered for a class of cellular neural networks (CNNs) with random delay. Compared with the previous work,the delay is modeled by a continuous-time homogeneous Markov process with a finite number of states. The main purpose of this paper is to establish easily verifiable conditions under which the random delayed cellular neural network is asymptotic mean-square stability. By using some stochastic analysis techniques and Lyapunov-Krasovskii functional,some conditions are derived to ensure that the cellular neural networks with random delay is asymptotical mean-square stability. A numerical example is exploited to show the vadlidness of the established results.展开更多
This paper presents an artificial neural network（ANN）-based response surface method that can be used to predict the failure probability of c-φslopes with spatially variable soil.In this method,the Latin hypercube s...This paper presents an artificial neural network（ANN）-based response surface method that can be used to predict the failure probability of c-φslopes with spatially variable soil.In this method,the Latin hypercube sampling technique is adopted to generate input datasets for establishing an ANN model;the random finite element method is then utilized to calculate the corresponding output datasets considering the spatial variability of soil properties;and finally,an ANN model is trained to construct the response surface of failure probability and obtain an approximate function that incorporates the relevant variables.The results of the illustrated example indicate that the proposed method provides credible and accurate estimations of failure probability.As a result,the obtained approximate function can be used as an alternative to the specific analysis process in c-φslope reliability analyses.展开更多
On the assumption that random interruptions in the observation process are modeled by a sequence of independent Bernoulli random variables, we firstly generalize two kinds of nonlinear filtering methods with random in...On the assumption that random interruptions in the observation process are modeled by a sequence of independent Bernoulli random variables, we firstly generalize two kinds of nonlinear filtering methods with random interruption failures in the observation based on the extended Kalman filtering （EKF） and the unscented Kalman filtering （UKF）, which were shortened as GEKF and CUKF in this paper, respectively. Then the nonlinear filtering model is established by using the radial basis function neural network （RBFNN） prototypes and the network weights as state equation and the output of RBFNN to present the observation equation. Finally, we take the filtering problem under missing observed data as a special case of nonlinear filtering with random intermittent failures by setting each missing data to be zero without needing to pre-estimate the missing data, and use the GEKF-based RBFNN and the GUKF-based RBFNN to predict the ground radioactivity time series with missing data. Experimental results demonstrate that the prediction results of GUKF-based RBFNN accord well with the real ground radioactivity time series while the prediction results of GEKF-based RBFNN are divergent.展开更多
This paper presents a texture segmentation approach which is based on the Markov random field model (MRF) and feed forward neural network.Image texture is modeled by the second order Gauss MRF model, and the least squ...This paper presents a texture segmentation approach which is based on the Markov random field model (MRF) and feed forward neural network.Image texture is modeled by the second order Gauss MRF model, and the least square error estimation is employed for the solution of model parameters. To perform texture segmentation, we introduced an improved BP algorithm to get faster learning speed. Experiment shows that better segmentation results can be obtained than the traditional Euclidean distance method.展开更多
In this paper, we discuss the driving-response synchronization problem for two memristive neural networks with retarded and advanced arguments under the condition of additional noise. The control law is related to the...In this paper, we discuss the driving-response synchronization problem for two memristive neural networks with retarded and advanced arguments under the condition of additional noise. The control law is related to the linear time-delay feedback term, and the discontinuous feedback term. Moreover, the random different equation is used to prove the stability of this theory. At the end, the simulation results verify the correctness of the theoretical results.展开更多
In the contemporary era, the proliferation of information technology has led to an unprecedented surge in data generation, with this data being dispersed across a multitude of mobile devices. Facing these situations a...In the contemporary era, the proliferation of information technology has led to an unprecedented surge in data generation, with this data being dispersed across a multitude of mobile devices. Facing these situations and the training of deep learning model that needs great computing power support, the distributed algorithm that can carry out multi-party joint modeling has attracted everyone’s attention. The distributed training mode relieves the huge pressure of centralized model on computer computing power and communication. However, most distributed algorithms currently work in a master-slave mode, often including a central server for coordination, which to some extent will cause communication pressure, data leakage, privacy violations and other issues. To solve these problems, a decentralized fully distributed algorithm based on deep random weight neural network is proposed. The algorithm decomposes the original objective function into several sub-problems under consistency constraints, combines the decentralized average consensus (DAC) and alternating direction method of multipliers (ADMM), and achieves the goal of joint modeling and training through local calculation and communication of each node. Finally, we compare the proposed decentralized algorithm with several centralized deep neural networks with random weights, and experimental results demonstrate the effectiveness of the proposed algorithm.展开更多
The purpose of this study was to address the challenges in predicting and classifying accuracy in modeling Container Dwell Time (CDT) using Artificial Neural Networks (ANN). This objective was driven by the suboptimal...The purpose of this study was to address the challenges in predicting and classifying accuracy in modeling Container Dwell Time (CDT) using Artificial Neural Networks (ANN). This objective was driven by the suboptimal outcomes reported in previous studies and sought to apply an innovative approach to improve these results. To achieve this, the study applied the Fusion of Activation Functions (FAFs) to a substantial dataset. This dataset included 307,594 container records from the Port of Tema from 2014 to 2022, encompassing both import and transit containers. The RandomizedSearchCV algorithm from Python’s Scikit-learn library was utilized in the methodological approach to yield the optimal activation function for prediction accuracy. The results indicated that “ajaLT”, a fusion of the Logistic and Hyperbolic Tangent Activation Functions, provided the best prediction accuracy, reaching a high of 82%. Despite these encouraging findings, it’s crucial to recognize the study’s limitations. While Fusion of Activation Functions is a promising method, further evaluation is necessary across different container types and port operations to ascertain the broader applicability and generalizability of these findings. The original value of this study lies in its innovative application of FAFs to CDT. Unlike previous studies, this research evaluates the method based on prediction accuracy rather than training time. It opens new avenues for machine learning engineers and researchers in applying FAFs to enhance prediction accuracy in CDT modeling, contributing to a previously underexplored area.展开更多
文摘An approach based on artificial neural network （ANN） is used to develop predictive relations between hydrodynamic inline force on a vertical cylinder and some effective parameters. The data used to calibrate and validate the ANN models are obtained from an experiment. Multilayer feed-forward neural networks that are trained with the back-propagation algorithm are constructed by use of three design parameters （i.e. wave surface height, horizontal and vertical velocities） as network inputs and the ultimate inline force as the only output. A sensitivity analysis is conducted on the ANN models to investigate the generalization ability （robustness） of the developed models, and predictions from the ANN models are compared to those obtained from Morison equation which is usually used to determine inline force as a computational method. With the existing data, it is found that least square method （LSM） gives less error in determining drag and inertia coefficients of Morison equation. With regard to the predicted results agreeing with calculations achieved from Morison equation that used LSM method, neural network has high efficiency considering its convenience, simplicity and promptitude. The outcome of this study can contribute to reducing the errors in predicting hydrodynamic inline force by use of ANN and to improve the reliability of that in comparison with the more practical state of Morison equation. Therefore, this method can be applied to relevant engineering projects with satisfactory results
文摘In this paper, sixty-eight research articles published between 2000 and 2017 as well as textbooks which employed four classification algorithms: K-Nearest-Neighbor (KNN), Support Vector Machines (SVM), Random Forest (RF) and Neural Network (NN) as the main statistical tools were reviewed. The aim was to examine and compare these nonparametric classification methods on the following attributes: robustness to training data, sensitivity to changes, data fitting, stability, ability to handle large data sizes, sensitivity to noise, time invested in parameter tuning, and accuracy. The performances, strengths and shortcomings of each of the algorithms were examined, and finally, a conclusion was arrived at on which one has higher performance. It was evident from the literature reviewed that RF is too sensitive to small changes in the training dataset and is occasionally unstable and tends to overfit in the model. KNN is easy to implement and understand but has a major drawback of becoming significantly slow as the size of the data in use grows, while the ideal value of K for the KNN classifier is difficult to set. SVM and RF are insensitive to noise or overtraining, which shows their ability in dealing with unbalanced data. Larger input datasets will lengthen classification times for NN and KNN more than for SVM and RF. Among these nonparametric classification methods, NN has the potential to become a more widely used classification algorithm, but because of their time-consuming parameter tuning procedure, high level of complexity in computational processing, the numerous types of NN architectures to choose from and the high number of algorithms used for training, most researchers recommend SVM and RF as easier and wieldy used methods which repeatedly achieve results with high accuracies and are often faster to implement.
文摘Randomized weights neural networks have fast learning speed and good generalization performance with one single hidden layer structure. Input weighs of the hidden layer are produced randomly. By employing certain activation function, outputs of the hidden layer are calculated with some randomization. Output weights are computed using pseudo inverse. Mutual information can be used to measure mutual dependence of two variables quantitatively based on the probability theory. In this paper, these hidden layer’s outputs that relate to prediction variable closely are selected with the simple mutual information based feature selection method. These hidden nodes with high mutual information values are maintained as a new hidden layer. Thus, the size of the hidden layer is reduced. The new hidden layer’s output weights are learned with the pseudo inverse method. The proposed method is compared with the original randomized algorithms using concrete compressive strength benchmark dataset.
基金supported by the National Natural Science Foundation of China(Grant Nos.41501361,41401385,30871965)the China Postdoctoral Science Foundation(No.2018M630728)+2 种基金the Open Fund of Fujian Provincial Key Laboratory of Resources and Environment Monitoring&Sustainable Management and Utilization(No.ZD1403)the Open Fund of Fujian Mine Ecological Restoration Engineering Technology Research Center(No.KS2018005)the Scientific Research Foundation of Fuzhou University(No.XRC1345)
文摘The construction of a pest detection algorithm is an important step to couple"ground-space"characteristics,which is also the basis for rapid and accurate monitoring and detection of pest damage.In four experimental areas in Sanming City,Jiangle County,Sha County and Yanping District in Fujian Province,sample data on pest damage in 182 sets of Dendrolimus punctatus were collected.The data were randomly divided into a training set and testing set,and five duplicate tests and one eliminating-indicator test were done.Based on the characterization analysis of the host for D.punctatus damage,seven characteristic indicators of ground and remote sensing including leaf area index,standard error of leaf area index(SEL)of pine forest,normalized difference vegetation index(NDVI),wetness from tasseled cap transformation(WET),green band(B2),red band(B3),near-infrared band(B4)of remote sensing image are obtained to construct BP neural networks and random forest models of pest levels.The detection results of these two algorithms were comprehensively compared from the aspects of detection precision,kappa coefficient,receiver operating characteristic curve,and a paired t test.The results showed that the seven indicators all were responsive to pest damage,and NDVI was relatively weak;the average pest damage detection precision of six tests by BP neural networks was 77.29%,the kappa coefficient was 0.6869 and after the RF algorithm,the respective values were 79.30%and 0.7151,showing that the latter is more optimized,but there was no significant difference(p>0.05);the detection precision,kappa coefficient and AUC of the RF algorithm was higher than the BP neural networks for three pest levels(no damage,moderate damage and severe damage).The detection precision and AUC of BP neural networks were a little higher for mild damage,but the difference was not significant(p>0.05)except for the kappa coefficient for the no damage level(p<0.05).An"over-fitting"phenomenon tends to occur in BP neural networks,while RF method is more robust,providing a detection effect that is better than the BP neural networks.Thus,the application of the random forest algorithm for pest damage and multilevel dispersed variables is thus feasible and suggests that attention to the proportionality of sample data from various categories is needed when collecting data.
基金Sponsored by the National Natural Science Foundation of China(Grant No.10771044)the Natural Science Foundation of Hunan Province(Grant No.09JJ6006)+2 种基金the Excellent Youth Foundation of Educational Committee of Hunan Provincial (Grant No.08B005)the Hunan Postdoctoral Scientific Pro-gram(Grant No.2009RS3020)the Scientific Research Funds of Hunan Provincial Education Department of China(Grant No.09C059)
文摘In this paper,the asymptotical mean-square stability analysis problem is considered for a class of cellular neural networks (CNNs) with random delay. Compared with the previous work,the delay is modeled by a continuous-time homogeneous Markov process with a finite number of states. The main purpose of this paper is to establish easily verifiable conditions under which the random delayed cellular neural network is asymptotic mean-square stability. By using some stochastic analysis techniques and Lyapunov-Krasovskii functional,some conditions are derived to ensure that the cellular neural networks with random delay is asymptotical mean-square stability. A numerical example is exploited to show the vadlidness of the established results.
基金financially supported by the National Natural Science Foundation of China(Grant No.51278217)
文摘This paper presents an artificial neural network（ANN）-based response surface method that can be used to predict the failure probability of c-φslopes with spatially variable soil.In this method,the Latin hypercube sampling technique is adopted to generate input datasets for establishing an ANN model;the random finite element method is then utilized to calculate the corresponding output datasets considering the spatial variability of soil properties;and finally,an ANN model is trained to construct the response surface of failure probability and obtain an approximate function that incorporates the relevant variables.The results of the illustrated example indicate that the proposed method provides credible and accurate estimations of failure probability.As a result,the obtained approximate function can be used as an alternative to the specific analysis process in c-φslope reliability analyses.
基金Project supported by the State Key Program of the National Natural Science of China (Grant No. 60835004)the Natural Science Foundation of Jiangsu Province of China (Grant No. BK2009727)+1 种基金the Natural Science Foundation of Higher Education Institutions of Jiangsu Province of China (Grant No. 10KJB510004)the National Natural Science Foundation of China (Grant No. 61075028)
文摘On the assumption that random interruptions in the observation process are modeled by a sequence of independent Bernoulli random variables, we firstly generalize two kinds of nonlinear filtering methods with random interruption failures in the observation based on the extended Kalman filtering （EKF） and the unscented Kalman filtering （UKF）, which were shortened as GEKF and CUKF in this paper, respectively. Then the nonlinear filtering model is established by using the radial basis function neural network （RBFNN） prototypes and the network weights as state equation and the output of RBFNN to present the observation equation. Finally, we take the filtering problem under missing observed data as a special case of nonlinear filtering with random intermittent failures by setting each missing data to be zero without needing to pre-estimate the missing data, and use the GEKF-based RBFNN and the GUKF-based RBFNN to predict the ground radioactivity time series with missing data. Experimental results demonstrate that the prediction results of GUKF-based RBFNN accord well with the real ground radioactivity time series while the prediction results of GEKF-based RBFNN are divergent.
文摘This paper presents a texture segmentation approach which is based on the Markov random field model (MRF) and feed forward neural network.Image texture is modeled by the second order Gauss MRF model, and the least square error estimation is employed for the solution of model parameters. To perform texture segmentation, we introduced an improved BP algorithm to get faster learning speed. Experiment shows that better segmentation results can be obtained than the traditional Euclidean distance method.
文摘In this paper, we discuss the driving-response synchronization problem for two memristive neural networks with retarded and advanced arguments under the condition of additional noise. The control law is related to the linear time-delay feedback term, and the discontinuous feedback term. Moreover, the random different equation is used to prove the stability of this theory. At the end, the simulation results verify the correctness of the theoretical results.
文摘In the contemporary era, the proliferation of information technology has led to an unprecedented surge in data generation, with this data being dispersed across a multitude of mobile devices. Facing these situations and the training of deep learning model that needs great computing power support, the distributed algorithm that can carry out multi-party joint modeling has attracted everyone’s attention. The distributed training mode relieves the huge pressure of centralized model on computer computing power and communication. However, most distributed algorithms currently work in a master-slave mode, often including a central server for coordination, which to some extent will cause communication pressure, data leakage, privacy violations and other issues. To solve these problems, a decentralized fully distributed algorithm based on deep random weight neural network is proposed. The algorithm decomposes the original objective function into several sub-problems under consistency constraints, combines the decentralized average consensus (DAC) and alternating direction method of multipliers (ADMM), and achieves the goal of joint modeling and training through local calculation and communication of each node. Finally, we compare the proposed decentralized algorithm with several centralized deep neural networks with random weights, and experimental results demonstrate the effectiveness of the proposed algorithm.
文摘The purpose of this study was to address the challenges in predicting and classifying accuracy in modeling Container Dwell Time (CDT) using Artificial Neural Networks (ANN). This objective was driven by the suboptimal outcomes reported in previous studies and sought to apply an innovative approach to improve these results. To achieve this, the study applied the Fusion of Activation Functions (FAFs) to a substantial dataset. This dataset included 307,594 container records from the Port of Tema from 2014 to 2022, encompassing both import and transit containers. The RandomizedSearchCV algorithm from Python’s Scikit-learn library was utilized in the methodological approach to yield the optimal activation function for prediction accuracy. The results indicated that “ajaLT”, a fusion of the Logistic and Hyperbolic Tangent Activation Functions, provided the best prediction accuracy, reaching a high of 82%. Despite these encouraging findings, it’s crucial to recognize the study’s limitations. While Fusion of Activation Functions is a promising method, further evaluation is necessary across different container types and port operations to ascertain the broader applicability and generalizability of these findings. The original value of this study lies in its innovative application of FAFs to CDT. Unlike previous studies, this research evaluates the method based on prediction accuracy rather than training time. It opens new avenues for machine learning engineers and researchers in applying FAFs to enhance prediction accuracy in CDT modeling, contributing to a previously underexplored area.
