The present work reports the development of nonlinear time series prediction method of genetic algorithm(GA) with singular spectrum analysis(SSA) for forecasting the surface wind of a point station in the South China ...The present work reports the development of nonlinear time series prediction method of genetic algorithm(GA) with singular spectrum analysis(SSA) for forecasting the surface wind of a point station in the South China Sea(SCS) with scatterometer observations.Before the nonlinear technique GA is used for forecasting the time series of surface wind,the SSA is applied to reduce the noise.The surface wind speed and surface wind components from scatterometer observations at three locations in the SCS have been used to develop and test the technique.The predictions have been compared with persistence forecasts in terms of root mean square error.The predicted surface wind with GA and SSA made up to four days(longer for some point station) in advance have been found to be significantly superior to those made by persistence model.This method can serve as a cost-effective alternate prediction technique for forecasting surface wind of a point station in the SCS basin.展开更多
Some problems in using v-support vector machine(v-SVM)for the prediction of nonlinear time series arediscussed.The problems include selection of various net parameters,which affect the performance of prediction,mixtur...Some problems in using v-support vector machine(v-SVM)for the prediction of nonlinear time series arediscussed.The problems include selection of various net parameters,which affect the performance of prediction,mixtureof kernels,and decomposition cooperation linear programming v-SVM regression,which result in improvements of thealgorithm.Computer simulations in the prediction of nonlinear time series produced by Mackey-Glass equation andLorenz equation provide some improved results.展开更多
<div style="text-align:justify;"> This paper proposes a prediction method based on improved Echo State Network for COVID-19 nonlinear time series, which improves the Echo State Network from the reservo...<div style="text-align:justify;"> This paper proposes a prediction method based on improved Echo State Network for COVID-19 nonlinear time series, which improves the Echo State Network from the reservoir topology and the output weight matrix, and adopt the ABC (Artificial Bee Colony) algorithm based on crossover and crowding strategy to optimize the parameters. Finally, the proposed method is simulated and the results show that it has stronger prediction ability for COVID-19 nonlinear time series. </div>展开更多
Streamflow forecasting in drylands is challenging.Data are scarce,catchments are highly humanmodified and streamflow exhibits strong nonlinear responses to rainfall.The goal of this study was to evaluate the monthly a...Streamflow forecasting in drylands is challenging.Data are scarce,catchments are highly humanmodified and streamflow exhibits strong nonlinear responses to rainfall.The goal of this study was to evaluate the monthly and seasonal streamflow forecasting in two large catchments in the Jaguaribe River Basin in the Brazilian semi-arid area.We adopted four different lead times:one month ahead for monthly scale and two,three and four months ahead for seasonal scale.The gaps of the historic streamflow series were filled up by using rainfall-runoff modelling.Then,time series model techniques were applied,i.e.,the locally constant,the locally averaged,the k-nearest-neighbours algorithm(k-NN)and the autoregressive(AR)model.The criterion of reliability of the validation results is that the forecast is more skillful than streamflow climatology.Our approach outperformed the streamflow climatology for all monthly streamflows.On average,the former was 25%better than the latter.The seasonal streamflow forecasting(SSF)was also reliable(on average,20%better than the climatology),failing slightly only for the high flow season of one catchment(6%worse than the climatology).Considering an uncertainty envelope(probabilistic forecasting),which was considerably narrower than the data standard deviation,the streamflow forecasting performance increased by about 50%at both scales.The forecast errors were mainly driven by the streamflow intra-seasonality at monthly scale,while they were by the forecast lead time at seasonal scale.The best-fit and worst-fit time series model were the k-NN approach and the AR model,respectively.The rainfall-runoff modelling outputs played an important role in improving streamflow forecasting for one streamgauge that showed 35%of data gaps.The developed data-driven approach is mathematical and computationally very simple,demands few resources to accomplish its operational implementation and is applicable to other dryland watersheds.Our findings may be part of drought forecasting systems and potentially help allocating water months in advance.Moreover,the developed strategy can serve as a baseline for more complex streamflow forecast systems.展开更多
Intelligent tpower systems scanimprove operational efficiency by installing a large number of sensors.Data-based methods of supervised learning have gained popularity because of available Big Data and computing resour...Intelligent tpower systems scanimprove operational efficiency by installing a large number of sensors.Data-based methods of supervised learning have gained popularity because of available Big Data and computing resources.However,the common paradigm of the loss function in supervised learning requires large amounts of labeled data and cannot process unlabeled data.The scarcity of fault data and a large amount of normal data in practical use pose great challenges to fault detection algorithms.Moreover,sensor data faults in power systems are dynamically changing and pose another challenge.Therefore,a fault detection method based on self-supervised feature learning was proposed to address the above two challenges.First,self-supervised learning was employed to extract features under various working conditions only using large amounts of normal data.The self-supervised representation learning uses a sequence-based Triplet Loss.The extracted features of large amounts of normal data are then fed into a unary classifier.The proposed method is validated on exhaust gas temperatures(EGTs)of a real-world 9F gas turbine with sudden,progressive,and hybrid faults.A comprehensive comparison study was also conducted with various feature extractors and unary classifiers.The results show that the proposed method can achieve a relatively high recall for all kinds of typical faults.The model can detect progressive faults very quickly and achieve improved results for comparison without feature extractors in terms ofF1 score.展开更多
Nonparametric stochastic volatility models,although providing great flexibility for modelling thevolatility equation,often fail to account for useful shape information.For example,a model maynot use the knowledge that...Nonparametric stochastic volatility models,although providing great flexibility for modelling thevolatility equation,often fail to account for useful shape information.For example,a model maynot use the knowledge that the autoregressive component of the volatility equation is monotonically increasing as the lagged volatility increases.We propose a class of additive stochasticvolatility models that allow for different shape constraints and can incorporate the leverageeffect–asymmetric impact of positive and negative return shocks on volatilities.We developa Bayesian fitting algorithm and demonstrate model performance on simulated and empiricaldatasets.Unlike general nonparametric models,our model sacrifices little when the true volatility equation is linear.In nonlinear situations we improve the model fit and the ability to estimatevolatilities over general,unconstrained,nonparametric models.展开更多
基金Project supported by the National Natural Science Foundation of China(Grant Nos.41230421 and 41605075)the National Basic Research Program of China(Grant No.2013CB430101)
文摘The present work reports the development of nonlinear time series prediction method of genetic algorithm(GA) with singular spectrum analysis(SSA) for forecasting the surface wind of a point station in the South China Sea(SCS) with scatterometer observations.Before the nonlinear technique GA is used for forecasting the time series of surface wind,the SSA is applied to reduce the noise.The surface wind speed and surface wind components from scatterometer observations at three locations in the SCS have been used to develop and test the technique.The predictions have been compared with persistence forecasts in terms of root mean square error.The predicted surface wind with GA and SSA made up to four days(longer for some point station) in advance have been found to be significantly superior to those made by persistence model.This method can serve as a cost-effective alternate prediction technique for forecasting surface wind of a point station in the SCS basin.
基金National Natural Science Foundation of China under Grant No.90203008the Doctoral Foundation of Ministry of Education of China under Grant No.2002055009
文摘Some problems in using v-support vector machine(v-SVM)for the prediction of nonlinear time series arediscussed.The problems include selection of various net parameters,which affect the performance of prediction,mixtureof kernels,and decomposition cooperation linear programming v-SVM regression,which result in improvements of thealgorithm.Computer simulations in the prediction of nonlinear time series produced by Mackey-Glass equation andLorenz equation provide some improved results.
文摘<div style="text-align:justify;"> This paper proposes a prediction method based on improved Echo State Network for COVID-19 nonlinear time series, which improves the Echo State Network from the reservoir topology and the output weight matrix, and adopt the ABC (Artificial Bee Colony) algorithm based on crossover and crowding strategy to optimize the parameters. Finally, the proposed method is simulated and the results show that it has stronger prediction ability for COVID-19 nonlinear time series. </div>
基金The first author thanks the Brazilian National Council for Scientific and Technological Development for the Post-Doc scholarship(155814/2018-4).
文摘Streamflow forecasting in drylands is challenging.Data are scarce,catchments are highly humanmodified and streamflow exhibits strong nonlinear responses to rainfall.The goal of this study was to evaluate the monthly and seasonal streamflow forecasting in two large catchments in the Jaguaribe River Basin in the Brazilian semi-arid area.We adopted four different lead times:one month ahead for monthly scale and two,three and four months ahead for seasonal scale.The gaps of the historic streamflow series were filled up by using rainfall-runoff modelling.Then,time series model techniques were applied,i.e.,the locally constant,the locally averaged,the k-nearest-neighbours algorithm(k-NN)and the autoregressive(AR)model.The criterion of reliability of the validation results is that the forecast is more skillful than streamflow climatology.Our approach outperformed the streamflow climatology for all monthly streamflows.On average,the former was 25%better than the latter.The seasonal streamflow forecasting(SSF)was also reliable(on average,20%better than the climatology),failing slightly only for the high flow season of one catchment(6%worse than the climatology).Considering an uncertainty envelope(probabilistic forecasting),which was considerably narrower than the data standard deviation,the streamflow forecasting performance increased by about 50%at both scales.The forecast errors were mainly driven by the streamflow intra-seasonality at monthly scale,while they were by the forecast lead time at seasonal scale.The best-fit and worst-fit time series model were the k-NN approach and the AR model,respectively.The rainfall-runoff modelling outputs played an important role in improving streamflow forecasting for one streamgauge that showed 35%of data gaps.The developed data-driven approach is mathematical and computationally very simple,demands few resources to accomplish its operational implementation and is applicable to other dryland watersheds.Our findings may be part of drought forecasting systems and potentially help allocating water months in advance.Moreover,the developed strategy can serve as a baseline for more complex streamflow forecast systems.
基金supported by the National Science and Technology Major Project of China(Grant No.2017-V-0011-0063).
文摘Intelligent tpower systems scanimprove operational efficiency by installing a large number of sensors.Data-based methods of supervised learning have gained popularity because of available Big Data and computing resources.However,the common paradigm of the loss function in supervised learning requires large amounts of labeled data and cannot process unlabeled data.The scarcity of fault data and a large amount of normal data in practical use pose great challenges to fault detection algorithms.Moreover,sensor data faults in power systems are dynamically changing and pose another challenge.Therefore,a fault detection method based on self-supervised feature learning was proposed to address the above two challenges.First,self-supervised learning was employed to extract features under various working conditions only using large amounts of normal data.The self-supervised representation learning uses a sequence-based Triplet Loss.The extracted features of large amounts of normal data are then fed into a unary classifier.The proposed method is validated on exhaust gas temperatures(EGTs)of a real-world 9F gas turbine with sudden,progressive,and hybrid faults.A comprehensive comparison study was also conducted with various feature extractors and unary classifiers.The results show that the proposed method can achieve a relatively high recall for all kinds of typical faults.The model can detect progressive faults very quickly and achieve improved results for comparison without feature extractors in terms ofF1 score.
基金Peter Craigmile and Jiangyong Yin were supported in part by the National Science Foundation(NSF)under grant DMS-0906864Xinyi Xu,Jiangyong Yin and Steven MacEachern were supported in part by the NSF under grant DMS-1209194+2 种基金Peter Craigmile is additionally supported in part by the NSF under grants SES-1024709,DMS-1407604 and SES-1424481the National Cancer Institute of the National Institutes of Health under Award Number 1R21CA212308-01the project title is‘Evaluating how licensing-law strategies will change neighborhood disparities in tobacco retailer density’.Xinyi Xu and Steven MacEachern are supported under grant DMS-1613110.
文摘Nonparametric stochastic volatility models,although providing great flexibility for modelling thevolatility equation,often fail to account for useful shape information.For example,a model maynot use the knowledge that the autoregressive component of the volatility equation is monotonically increasing as the lagged volatility increases.We propose a class of additive stochasticvolatility models that allow for different shape constraints and can incorporate the leverageeffect–asymmetric impact of positive and negative return shocks on volatilities.We developa Bayesian fitting algorithm and demonstrate model performance on simulated and empiricaldatasets.Unlike general nonparametric models,our model sacrifices little when the true volatility equation is linear.In nonlinear situations we improve the model fit and the ability to estimatevolatilities over general,unconstrained,nonparametric models.