According to the nonlinear theory, the experiments have been conducted on sample ECG (electrocardiogram) signals of healthy human beings, coronary heart disease patients and adult canines. On the basis of the analyses...According to the nonlinear theory, the experiments have been conducted on sample ECG (electrocardiogram) signals of healthy human beings, coronary heart disease patients and adult canines. On the basis of the analyses of the power spectra, the computation of the correlation dimension and the Lyapunov exponent to a large number of ECG signals, the following conclusions are shown: through the comparative research, (1) the analyses of the power spectra, the computation of the correlation dimension and the Lyapunov exponent to the ECG signals reflect the whole dynamic characteristics of the hearts, and they may become a new method of researching ECG quantitatively to an early diagnose of heart disease. (2) Under normal physiological conditions the cardiac activities are chaotic, while under pathologic conditions the cardiac activities approach regularity. (3) On the basis of the comparative research of human beings and canines, it is revealed that chaos may be a quantitative index to measure the evolution展开更多
According to the chaotic and non-linear characters of power load data,the time series matrix is established with the theory of phase-space reconstruction,and then Lyapunov exponents with chaotic time series are comput...According to the chaotic and non-linear characters of power load data,the time series matrix is established with the theory of phase-space reconstruction,and then Lyapunov exponents with chaotic time series are computed to determine the time delay and the embedding dimension.Due to different features of the data,data mining algorithm is conducted to classify the data into different groups.Redundant information is eliminated by the advantage of data mining technology,and the historical loads that have highly similar features with the forecasting day are searched by the system.As a result,the training data can be decreased and the computing speed can also be improved when constructing support vector machine(SVM) model.Then,SVM algorithm is used to predict power load with parameters that get in pretreatment.In order to prove the effectiveness of the new model,the calculation with data mining SVM algorithm is compared with that of single SVM and back propagation network.It can be seen that the new DSVM algorithm effectively improves the forecast accuracy by 0.75%,1.10% and 1.73% compared with SVM for two random dimensions of 11-dimension,14-dimension and BP network,respectively.This indicates that the DSVM gains perfect improvement effect in the short-term power load forecasting.展开更多
基金This work was supported by the National Natural Science Foundation of China (Grant No. 69974008)the Chinese Postdoctoral Science Foundation and the Natural Science Foundation of Liaoning Province (Grant No. 972194).
文摘According to the nonlinear theory, the experiments have been conducted on sample ECG (electrocardiogram) signals of healthy human beings, coronary heart disease patients and adult canines. On the basis of the analyses of the power spectra, the computation of the correlation dimension and the Lyapunov exponent to a large number of ECG signals, the following conclusions are shown: through the comparative research, (1) the analyses of the power spectra, the computation of the correlation dimension and the Lyapunov exponent to the ECG signals reflect the whole dynamic characteristics of the hearts, and they may become a new method of researching ECG quantitatively to an early diagnose of heart disease. (2) Under normal physiological conditions the cardiac activities are chaotic, while under pathologic conditions the cardiac activities approach regularity. (3) On the basis of the comparative research of human beings and canines, it is revealed that chaos may be a quantitative index to measure the evolution
基金Project(70671039) supported by the National Natural Science Foundation of China
文摘According to the chaotic and non-linear characters of power load data,the time series matrix is established with the theory of phase-space reconstruction,and then Lyapunov exponents with chaotic time series are computed to determine the time delay and the embedding dimension.Due to different features of the data,data mining algorithm is conducted to classify the data into different groups.Redundant information is eliminated by the advantage of data mining technology,and the historical loads that have highly similar features with the forecasting day are searched by the system.As a result,the training data can be decreased and the computing speed can also be improved when constructing support vector machine(SVM) model.Then,SVM algorithm is used to predict power load with parameters that get in pretreatment.In order to prove the effectiveness of the new model,the calculation with data mining SVM algorithm is compared with that of single SVM and back propagation network.It can be seen that the new DSVM algorithm effectively improves the forecast accuracy by 0.75%,1.10% and 1.73% compared with SVM for two random dimensions of 11-dimension,14-dimension and BP network,respectively.This indicates that the DSVM gains perfect improvement effect in the short-term power load forecasting.
