The machine learning models of multiple linear regression(MLR),support vector regression(SVR),and extreme learning ma-chine(ELM)and the proposed ELM models of online sequential ELM(OS-ELM)and OS-ELM with forgetting me...The machine learning models of multiple linear regression(MLR),support vector regression(SVR),and extreme learning ma-chine(ELM)and the proposed ELM models of online sequential ELM(OS-ELM)and OS-ELM with forgetting mechanism(FOS-ELM)are applied in the prediction of the lime utilization ratio of dephosphorization in the basic oxygen furnace steelmaking process.The ELM model exhibites the best performance compared with the models of MLR and SVR.OS-ELM and FOS-ELM are applied for sequential learning and model updating.The optimal number of samples in validity term of the FOS-ELM model is determined to be 1500,with the smallest population mean absolute relative error(MARE)value of 0.058226 for the population.The variable importance analysis reveals lime weight,initial P content,and hot metal weight as the most important variables for the lime utilization ratio.The lime utilization ratio increases with the decrease in lime weight and the increases in the initial P content and hot metal weight.A prediction system based on FOS-ELM is applied in actual industrial production for one month.The hit ratios of the predicted lime utilization ratio in the error ranges of±1%,±3%,and±5%are 61.16%,90.63%,and 94.11%,respectively.The coefficient of determination,MARE,and root mean square error are 0.8670,0.06823,and 1.4265,respectively.The system exhibits desirable performance for applications in actual industrial pro-duction.展开更多
A novel sequential neural network learning algorithm for function approximation is presented. The multi-step-ahead output predictor of the stochastic time series is introduced to the growing and pruning network for co...A novel sequential neural network learning algorithm for function approximation is presented. The multi-step-ahead output predictor of the stochastic time series is introduced to the growing and pruning network for constructing network structure. And the network parameters are adjusted by the proportional differential filter （PDF） rather than EKF when the network growing criteria are not met. Experimental results show that the proposed algorithm can obtain a more compact network along with a smaller error in mean square sense than other typical sequential learning algorithms.展开更多
Learning Vector Quantization(LVQ)originally proposed by Kohonen(1989)is aneurally-inspired classifier which pays attention to approximating the optimal Bayes decisionboundaries associated with a classification task.Wi...Learning Vector Quantization(LVQ)originally proposed by Kohonen(1989)is aneurally-inspired classifier which pays attention to approximating the optimal Bayes decisionboundaries associated with a classification task.With respect to several defects of LVQ2 algorithmstudied in this paper,some‘soft’competition schemes such as‘majority voting’scheme andcredibility calculation are proposed for improving the ability of classification as well as the learningspeed.Meanwhile,the probabilities of winning are introduced into the corrections for referencevectors in the‘soft’competition.In contrast with the conventional sequential learning technique,a novel parallel learning technique is developed to perform LVQ2 procedure.Experimental resultsof speech recognition show that these new approaches can lead to better performance as comparedwith the conventional展开更多
This study presents a time series prediction model with output self feedback which is implemented based on online sequential extreme learning machine. The output variables derived from multilayer perception can feedba...This study presents a time series prediction model with output self feedback which is implemented based on online sequential extreme learning machine. The output variables derived from multilayer perception can feedback to the network input layer to create a temporal relation between the current node inputs and the lagged node outputs while overcoming the limitation of memory which is a vital port for any time-series prediction application. The model can overcome the static prediction problem with most time series prediction models and can effectively cope with the dynamic properties of time series data. A linear and a nonlinear forecasting algorithms based on online extreme learning machine are proposed to implement the output feedback forecasting model. They are both recursive estimator and have two distinct phases： Predict and Update. The proposed model was tested against different kinds of time series data and the results indicate that the model outperforms the original static model without feedback.展开更多
Based on detailed study on several kinds of fuzzy neural networks, we propose a novel compensationbased recurrent fuzzy neural network （CRFNN） by adding recurrent element and compensatory element to the conventional...Based on detailed study on several kinds of fuzzy neural networks, we propose a novel compensationbased recurrent fuzzy neural network （CRFNN） by adding recurrent element and compensatory element to the conventional fuzzy neural network. Then, we propose a sequential learning method for the structure identification of the CRFNN in order to confirm the fuzzy rules and their correlative parameters effectively. Furthermore, we improve the BP algorithm based on the characteristics of the proposed CRFNN to train the network. By modeling the typical nonlinear systems, we draw the conclusion that the proposed CRFNN has excellent dynamic response and strong learning ability.展开更多
Online sequential extreme learning machine(OS-ELM)for single-hidden layer feedforward networks(SLFNs)is an effective machine learning algorithm.But OS-ELM has some underlying weaknesses of neglecting time series timel...Online sequential extreme learning machine(OS-ELM)for single-hidden layer feedforward networks(SLFNs)is an effective machine learning algorithm.But OS-ELM has some underlying weaknesses of neglecting time series timeliness and being incapable to provide quantitative uncertainty for prediction.To overcome these shortcomings,a time series prediction method is presented based on the combination of OS-ELM with adaptive forgetting factor(AFF-OS-ELM)and bootstrap(B-AFF-OS-ELM).Firstly,adaptive forgetting factor is added into OS-ELM for adjusting the effective window length of training data during OS-ELM sequential learning phase.Secondly,the current bootstrap is developed to fit time series prediction online.Then associated with improved bootstrap,the proposed method can compute prediction interval as uncertainty information,meanwhile the improved bootstrap enhances prediction accuracy and stability of AFF-OS-ELM.Performances of B-AFF-OS-ELM are benchmarked with other traditional and improved OS-ELM on simulation and practical time series data.Results indicate the significant performances achieved by B-AFF-OS-ELM.展开更多
基金supported by the National Natural Science Foundation of China (No.U1960202).
文摘The machine learning models of multiple linear regression(MLR),support vector regression(SVR),and extreme learning ma-chine(ELM)and the proposed ELM models of online sequential ELM(OS-ELM)and OS-ELM with forgetting mechanism(FOS-ELM)are applied in the prediction of the lime utilization ratio of dephosphorization in the basic oxygen furnace steelmaking process.The ELM model exhibites the best performance compared with the models of MLR and SVR.OS-ELM and FOS-ELM are applied for sequential learning and model updating.The optimal number of samples in validity term of the FOS-ELM model is determined to be 1500,with the smallest population mean absolute relative error(MARE)value of 0.058226 for the population.The variable importance analysis reveals lime weight,initial P content,and hot metal weight as the most important variables for the lime utilization ratio.The lime utilization ratio increases with the decrease in lime weight and the increases in the initial P content and hot metal weight.A prediction system based on FOS-ELM is applied in actual industrial production for one month.The hit ratios of the predicted lime utilization ratio in the error ranges of±1%,±3%,and±5%are 61.16%,90.63%,and 94.11%,respectively.The coefficient of determination,MARE,and root mean square error are 0.8670,0.06823,and 1.4265,respectively.The system exhibits desirable performance for applications in actual industrial pro-duction.
基金Sponsored by the Ministerial Level Foundation(230032)
文摘A novel sequential neural network learning algorithm for function approximation is presented. The multi-step-ahead output predictor of the stochastic time series is introduced to the growing and pruning network for constructing network structure. And the network parameters are adjusted by the proportional differential filter （PDF） rather than EKF when the network growing criteria are not met. Experimental results show that the proposed algorithm can obtain a more compact network along with a smaller error in mean square sense than other typical sequential learning algorithms.
文摘Learning Vector Quantization(LVQ)originally proposed by Kohonen(1989)is aneurally-inspired classifier which pays attention to approximating the optimal Bayes decisionboundaries associated with a classification task.With respect to several defects of LVQ2 algorithmstudied in this paper,some‘soft’competition schemes such as‘majority voting’scheme andcredibility calculation are proposed for improving the ability of classification as well as the learningspeed.Meanwhile,the probabilities of winning are introduced into the corrections for referencevectors in the‘soft’competition.In contrast with the conventional sequential learning technique,a novel parallel learning technique is developed to perform LVQ2 procedure.Experimental resultsof speech recognition show that these new approaches can lead to better performance as comparedwith the conventional
基金Foundation item： the National Natural Science Foundation of China （No. 61203337）
文摘This study presents a time series prediction model with output self feedback which is implemented based on online sequential extreme learning machine. The output variables derived from multilayer perception can feedback to the network input layer to create a temporal relation between the current node inputs and the lagged node outputs while overcoming the limitation of memory which is a vital port for any time-series prediction application. The model can overcome the static prediction problem with most time series prediction models and can effectively cope with the dynamic properties of time series data. A linear and a nonlinear forecasting algorithms based on online extreme learning machine are proposed to implement the output feedback forecasting model. They are both recursive estimator and have two distinct phases： Predict and Update. The proposed model was tested against different kinds of time series data and the results indicate that the model outperforms the original static model without feedback.
基金Supported by the National High-Tech Research and Development Program of China (Grant No. 2006AA05A107)Special Fund of JiangsuProvince for Technology Transfer (Grant No. BA2007008)
文摘Based on detailed study on several kinds of fuzzy neural networks, we propose a novel compensationbased recurrent fuzzy neural network （CRFNN） by adding recurrent element and compensatory element to the conventional fuzzy neural network. Then, we propose a sequential learning method for the structure identification of the CRFNN in order to confirm the fuzzy rules and their correlative parameters effectively. Furthermore, we improve the BP algorithm based on the characteristics of the proposed CRFNN to train the network. By modeling the typical nonlinear systems, we draw the conclusion that the proposed CRFNN has excellent dynamic response and strong learning ability.
文摘Online sequential extreme learning machine(OS-ELM)for single-hidden layer feedforward networks(SLFNs)is an effective machine learning algorithm.But OS-ELM has some underlying weaknesses of neglecting time series timeliness and being incapable to provide quantitative uncertainty for prediction.To overcome these shortcomings,a time series prediction method is presented based on the combination of OS-ELM with adaptive forgetting factor(AFF-OS-ELM)and bootstrap(B-AFF-OS-ELM).Firstly,adaptive forgetting factor is added into OS-ELM for adjusting the effective window length of training data during OS-ELM sequential learning phase.Secondly,the current bootstrap is developed to fit time series prediction online.Then associated with improved bootstrap,the proposed method can compute prediction interval as uncertainty information,meanwhile the improved bootstrap enhances prediction accuracy and stability of AFF-OS-ELM.Performances of B-AFF-OS-ELM are benchmarked with other traditional and improved OS-ELM on simulation and practical time series data.Results indicate the significant performances achieved by B-AFF-OS-ELM.
