In this paper, we propose a new method that combines collage error in fractal domain and Hu moment invariants for image retrieval with a statistical method - variable bandwidth Kernel Density Estimation (KDE). The pro...In this paper, we propose a new method that combines collage error in fractal domain and Hu moment invariants for image retrieval with a statistical method - variable bandwidth Kernel Density Estimation (KDE). The proposed method is called CHK (KDE of Collage error and Hu moment) and it is tested on the Vistex texture database with 640 natural images. Experimental results show that the Average Retrieval Rate (ARR) can reach into 78.18%, which demonstrates that the proposed method performs better than the one with parameters respectively as well as the commonly used histogram method both on retrieval rate and retrieval time.展开更多
Monte Carlo simulation was applied to Assembly Success Bate (ASK) analyses. ASR of two peg-in-hole robot assemblies was used as an example by taking component parts' sizes, manufacturing tolerances and robot repea...Monte Carlo simulation was applied to Assembly Success Bate (ASK) analyses. ASR of two peg-in-hole robot assemblies was used as an example by taking component parts' sizes, manufacturing tolerances and robot repeatability into account. A statistic arithmetic expression was proposed and deduced in this paper, which offers an alternative method of estimating the accuracy of ASR, without having to repeat the simulations. This statistic method also helps to choose a suitable sample size, if error reduction is desired. Monte Carlo simulation results demonstrated the feasibility of the method.展开更多
The quality of background error statistics is one of the key components for successful assimilation of observations in a numerical model.The background error covariance(BEC) of ocean waves is generally estimated under...The quality of background error statistics is one of the key components for successful assimilation of observations in a numerical model.The background error covariance(BEC) of ocean waves is generally estimated under an assumption that it is stationary over a period of time and uniform over a domain.However,error statistics are in fact functions of the physical processes governing the meteorological situation and vary with the wave condition.In this paper,we simulated the BEC of the significant wave height(SWH) employing Monte Carlo methods.An interesting result is that the BEC varies consistently with the mean wave direction(MWD).In the model domain,the BEC of the SWH decreases significantly when the MWD changes abruptly.A new BEC model of the SWH based on the correlation between the BEC and MWD was then developed.A case study of regional data assimilation was performed,where the SWH observations of buoy 22001 were used to assess the SWH hindcast.The results show that the new BEC model benefits wave prediction and allows reasonable approximations of anisotropy and inhomogeneous errors.展开更多
The least squares support vector machine (LS-SVM) is used to study the nonlinear time series prediction. First, the parameter gamma and multi-step prediction capabilities of the LS-SVM network are discussed. Then we e...The least squares support vector machine (LS-SVM) is used to study the nonlinear time series prediction. First, the parameter gamma and multi-step prediction capabilities of the LS-SVM network are discussed. Then we employ clustering method in the model to prune the number of the support values.. The learning rate and the capabilities of filtering noise for LS-SVM are all greatly improved.展开更多
In order to get prepared for the coming extreme pollution events and minimize their harmful impacts, the first and most important step is to predict their possible intensity in the future. Firstly, the generalized Par...In order to get prepared for the coming extreme pollution events and minimize their harmful impacts, the first and most important step is to predict their possible intensity in the future. Firstly, the generalized Pareto distribution （GPD） in extreme value theory was used to fit the extreme pollution concentrations of three main pollutants： PM10, NO2 and SO：, from 2005 to 2010 in Changsha, China. Secondly, the prediction results were compared with actual data by a scatter plot. Four statistical indicators： EMA （mean absolute error）, ERMS （root mean square error）, IA （index of agreement） and R2 （coefficient of determination） were used to evaluate the goodness-of-fit as well. Thirdly, the return levels corresponding to different return periods were calculated by the fitted distributions. The fitting results show that the distribution of PM10 and SO2 belongs to exponential distribution with a short tail while that of the NOe belongs to beta distribution with a bounded tail. The scatter plot and four statistical indicators suggest that GPD agrees well with the actual data. Therefore, the fitted distribution is reliable to predict the return levels corresponding to different return periods. The predicted return levels suggest that the intensity of coming pollution events for PM10 and SO2 will be even worse in the future, which means people have to get enough preparation for them.展开更多
基金Supported by the Fundamental Research Funds for the Central Universities (No. NS2012093)
文摘In this paper, we propose a new method that combines collage error in fractal domain and Hu moment invariants for image retrieval with a statistical method - variable bandwidth Kernel Density Estimation (KDE). The proposed method is called CHK (KDE of Collage error and Hu moment) and it is tested on the Vistex texture database with 640 natural images. Experimental results show that the Average Retrieval Rate (ARR) can reach into 78.18%, which demonstrates that the proposed method performs better than the one with parameters respectively as well as the commonly used histogram method both on retrieval rate and retrieval time.
文摘Monte Carlo simulation was applied to Assembly Success Bate (ASK) analyses. ASR of two peg-in-hole robot assemblies was used as an example by taking component parts' sizes, manufacturing tolerances and robot repeatability into account. A statistic arithmetic expression was proposed and deduced in this paper, which offers an alternative method of estimating the accuracy of ASR, without having to repeat the simulations. This statistic method also helps to choose a suitable sample size, if error reduction is desired. Monte Carlo simulation results demonstrated the feasibility of the method.
基金Supported by the National Natural Science Foundation of China (Nos.40806011,U1133001)the Open Fund of the Key Laboratory of Ocean Circulation and Waves,Chinese Academy of Sciences(No. KLOCAW0806)
文摘The quality of background error statistics is one of the key components for successful assimilation of observations in a numerical model.The background error covariance(BEC) of ocean waves is generally estimated under an assumption that it is stationary over a period of time and uniform over a domain.However,error statistics are in fact functions of the physical processes governing the meteorological situation and vary with the wave condition.In this paper,we simulated the BEC of the significant wave height(SWH) employing Monte Carlo methods.An interesting result is that the BEC varies consistently with the mean wave direction(MWD).In the model domain,the BEC of the SWH decreases significantly when the MWD changes abruptly.A new BEC model of the SWH based on the correlation between the BEC and MWD was then developed.A case study of regional data assimilation was performed,where the SWH observations of buoy 22001 were used to assess the SWH hindcast.The results show that the new BEC model benefits wave prediction and allows reasonable approximations of anisotropy and inhomogeneous errors.
文摘The least squares support vector machine (LS-SVM) is used to study the nonlinear time series prediction. First, the parameter gamma and multi-step prediction capabilities of the LS-SVM network are discussed. Then we employ clustering method in the model to prune the number of the support values.. The learning rate and the capabilities of filtering noise for LS-SVM are all greatly improved.
基金Project(51178466) supported by the National Natural Science Foundation of ChinaProject(200545) supported by the Foundation for the Author of National Excellent Doctoral Dissertation of China+1 种基金Project(2011JQ006) supported by the Fundamental Research Funds of the Central Universities of ChinaProject(2008BAJ12B03) supported by the National Key Program of Scientific and Technical Supporting Programs of China
文摘In order to get prepared for the coming extreme pollution events and minimize their harmful impacts, the first and most important step is to predict their possible intensity in the future. Firstly, the generalized Pareto distribution （GPD） in extreme value theory was used to fit the extreme pollution concentrations of three main pollutants： PM10, NO2 and SO：, from 2005 to 2010 in Changsha, China. Secondly, the prediction results were compared with actual data by a scatter plot. Four statistical indicators： EMA （mean absolute error）, ERMS （root mean square error）, IA （index of agreement） and R2 （coefficient of determination） were used to evaluate the goodness-of-fit as well. Thirdly, the return levels corresponding to different return periods were calculated by the fitted distributions. The fitting results show that the distribution of PM10 and SO2 belongs to exponential distribution with a short tail while that of the NOe belongs to beta distribution with a bounded tail. The scatter plot and four statistical indicators suggest that GPD agrees well with the actual data. Therefore, the fitted distribution is reliable to predict the return levels corresponding to different return periods. The predicted return levels suggest that the intensity of coming pollution events for PM10 and SO2 will be even worse in the future, which means people have to get enough preparation for them.
