This paper proposes a method for improving the precision of Network Traffic Prediction based on the Maximum Correntropy Criterion(NTPMCC),where the nonlinear characteristics of network traffic are considered.This meth...This paper proposes a method for improving the precision of Network Traffic Prediction based on the Maximum Correntropy Criterion(NTPMCC),where the nonlinear characteristics of network traffic are considered.This method utilizes the MCC as a new error evaluation criterion or named the cost function(CF)to train neural networks(NN).MCC is based on a new similarity function(Generalized correlation entropy function,Correntropy),which has as its foundation the Parzen window evaluation and Renyi entropy of error probability density function.At the same time,by combining the MCC with the Mean Square Error(MSE),a mixed evaluation criterion with MCC and MSE is proposed as a cost function of NN training.According to the traffic network characteristics including the nonlinear,non-Gaussian,and mutation,the Elman neural network is trained by MCC and MCC-MSE,and then the trained neural network is used as the model for predicting network traffic.The simulation results based on the evaluation by Mean Absolute Error(MAE),MSE,and Sum Squared Error(SSE)show that the accuracy of the prediction based on MCC is superior to the results of the Elman neural network with MSE.The overall performance is improved by about 0.0131.展开更多
In the practical measurement of signal to noise ratio(SNR)of analog-to-digital converters(ADCs)by using fast Fourier transformation(FFT)method,the non-coherent sampling is inevitable,leading to spectral leakage which ...In the practical measurement of signal to noise ratio(SNR)of analog-to-digital converters(ADCs)by using fast Fourier transformation(FFT)method,the non-coherent sampling is inevitable,leading to spectral leakage which in turn affects the calculation accuracy and final measurement results.In this paper,a new method based on the Blackman-Harris windowed triple-spectrum-line interpolation is presented for the measurement of ADCs SNR by FFT.The simulation platform is built based on MATLAB and the behavioral dynamic models of the high-speed ADC products of Analog Devices Inc.(ADI)are simulated.The simulation results show that,even in the case of the maximum non-coherent degree,the SNR error is less than0.23dB and reaches the testing standards provided by ADI,confirming that the proposed method is effective for suppressing the spectral leakage effects and improving the SNR test accuracy.展开更多
Support vector machines (SVM) have been widely used in pattern recognition and have also drawn considerable interest in control areas. Based on rolling optimization method and on-line learning strategies, a novel appr...Support vector machines (SVM) have been widely used in pattern recognition and have also drawn considerable interest in control areas. Based on rolling optimization method and on-line learning strategies, a novel approach based on weighted least squares support vector machines (WLS-SVM) is proposed for nonlinear dynamic modeling. The good robust property of the novel approach enhances the generalization ability of kernel method-based modeling and some experimental results are presented to illustrate the feasibility of the proposed method.展开更多
Distinguished from commonly used Fe2O3 and Fe3O4,a three-dimensional multilevel macromicro-mesoporous structure of FeC2O4/graphene composite has been prepared as binderfree electrode for supercapacitors.The as-prepare...Distinguished from commonly used Fe2O3 and Fe3O4,a three-dimensional multilevel macromicro-mesoporous structure of FeC2O4/graphene composite has been prepared as binderfree electrode for supercapacitors.The as-prepared materials are composed of macroporous graphene and microporous/mesoporous ferrous oxalate.Generally,the decomposition voltage of water is 1.23 V and the practical voltage window limit is about 2 V for asymmetric supercapacitors in aqueous electrolytes.When FeC2O4/rGO hydrogel was used as the negative electrode and a pure rGO hydrogel was used as the positive electrode,the asymmetrical supercapacitor voltage window raised to 1.7 V in KOH(1.0 mol/L)electrolyte and reached up to 2.5 V in a neutral aqueous Na2SO4(1.0 mol/L)electrolyte.Correspondingly it also exhibits a high performance with an energy density of 59.7 Wh/kg.By means of combining a metal oxide that owns micro-mesoporous structure with graphene,this work provides a new opportunity for preparing high-voltage aqueous asymmetric supercapacitors without addition of conductive agent and binder.展开更多
By applying two nonlinear Granger causality testing methods and rolling window strategy to explore the relationship between speculative activities and crude oil prices, the unidirectional Granger causality from specul...By applying two nonlinear Granger causality testing methods and rolling window strategy to explore the relationship between speculative activities and crude oil prices, the unidirectional Granger causality from speculative activities to returns of crude oil prices during the high price phase is discovered. It is proved that speculative activities did contribute to high crude oil prices after the Asian financial crisis and OPEC＇s output cut in 1998. The unidirectional Granger causality from returns of crude oil prices to speculative activities is significant in general. But after 2000, with the sharp rise in crude oil prices, this unidirectional Granger causality became a complex nonlinear relationship, which cannot be detected by any linear Granger causaIity test.展开更多
基金supported in part by the National Natural Science Foundation of China under Grant No.61071126the National Radio Project under Grants No. 2010ZX03004001, No.2010ZX03004-002, No.2011ZX03002001
文摘This paper proposes a method for improving the precision of Network Traffic Prediction based on the Maximum Correntropy Criterion(NTPMCC),where the nonlinear characteristics of network traffic are considered.This method utilizes the MCC as a new error evaluation criterion or named the cost function(CF)to train neural networks(NN).MCC is based on a new similarity function(Generalized correlation entropy function,Correntropy),which has as its foundation the Parzen window evaluation and Renyi entropy of error probability density function.At the same time,by combining the MCC with the Mean Square Error(MSE),a mixed evaluation criterion with MCC and MSE is proposed as a cost function of NN training.According to the traffic network characteristics including the nonlinear,non-Gaussian,and mutation,the Elman neural network is trained by MCC and MCC-MSE,and then the trained neural network is used as the model for predicting network traffic.The simulation results based on the evaluation by Mean Absolute Error(MAE),MSE,and Sum Squared Error(SSE)show that the accuracy of the prediction based on MCC is superior to the results of the Elman neural network with MSE.The overall performance is improved by about 0.0131.
基金Summit of the Six Top Talents Program of Jiangsu Province(No.2013-DZXX-027)Fundamental Research Funds for the Central Universities(Nos.JUSRP51510,JUSRP51323B)Graduate Student Innovation Program for Universities of Jiangsu Province(Nos.SJLX16_0500,KYLX16_0776,SJCX17_0510)
文摘In the practical measurement of signal to noise ratio(SNR)of analog-to-digital converters(ADCs)by using fast Fourier transformation(FFT)method,the non-coherent sampling is inevitable,leading to spectral leakage which in turn affects the calculation accuracy and final measurement results.In this paper,a new method based on the Blackman-Harris windowed triple-spectrum-line interpolation is presented for the measurement of ADCs SNR by FFT.The simulation platform is built based on MATLAB and the behavioral dynamic models of the high-speed ADC products of Analog Devices Inc.(ADI)are simulated.The simulation results show that,even in the case of the maximum non-coherent degree,the SNR error is less than0.23dB and reaches the testing standards provided by ADI,confirming that the proposed method is effective for suppressing the spectral leakage effects and improving the SNR test accuracy.
基金This work was supportedin part bythe national 973 keyfundamental research project of China under grant 2002CB312200 and national 863high technology projects foundation of China under grant 2002AA412010
文摘Support vector machines (SVM) have been widely used in pattern recognition and have also drawn considerable interest in control areas. Based on rolling optimization method and on-line learning strategies, a novel approach based on weighted least squares support vector machines (WLS-SVM) is proposed for nonlinear dynamic modeling. The good robust property of the novel approach enhances the generalization ability of kernel method-based modeling and some experimental results are presented to illustrate the feasibility of the proposed method.
基金supported by the National Natural Science Foundation of China (No.51673180 and No. 51673180)
文摘Distinguished from commonly used Fe2O3 and Fe3O4,a three-dimensional multilevel macromicro-mesoporous structure of FeC2O4/graphene composite has been prepared as binderfree electrode for supercapacitors.The as-prepared materials are composed of macroporous graphene and microporous/mesoporous ferrous oxalate.Generally,the decomposition voltage of water is 1.23 V and the practical voltage window limit is about 2 V for asymmetric supercapacitors in aqueous electrolytes.When FeC2O4/rGO hydrogel was used as the negative electrode and a pure rGO hydrogel was used as the positive electrode,the asymmetrical supercapacitor voltage window raised to 1.7 V in KOH(1.0 mol/L)electrolyte and reached up to 2.5 V in a neutral aqueous Na2SO4(1.0 mol/L)electrolyte.Correspondingly it also exhibits a high performance with an energy density of 59.7 Wh/kg.By means of combining a metal oxide that owns micro-mesoporous structure with graphene,this work provides a new opportunity for preparing high-voltage aqueous asymmetric supercapacitors without addition of conductive agent and binder.
基金supported by the National Natural Science Foundation of China
文摘By applying two nonlinear Granger causality testing methods and rolling window strategy to explore the relationship between speculative activities and crude oil prices, the unidirectional Granger causality from speculative activities to returns of crude oil prices during the high price phase is discovered. It is proved that speculative activities did contribute to high crude oil prices after the Asian financial crisis and OPEC＇s output cut in 1998. The unidirectional Granger causality from returns of crude oil prices to speculative activities is significant in general. But after 2000, with the sharp rise in crude oil prices, this unidirectional Granger causality became a complex nonlinear relationship, which cannot be detected by any linear Granger causaIity test.
