Compositional data, such as relative information, is a crucial aspect of machine learning and other related fields. It is typically recorded as closed data or sums to a constant, like 100%. The statistical linear mode...Compositional data, such as relative information, is a crucial aspect of machine learning and other related fields. It is typically recorded as closed data or sums to a constant, like 100%. The statistical linear model is the most used technique for identifying hidden relationships between underlying random variables of interest. However, data quality is a significant challenge in machine learning, especially when missing data is present. The linear regression model is a commonly used statistical modeling technique used in various applications to find relationships between variables of interest. When estimating linear regression parameters which are useful for things like future prediction and partial effects analysis of independent variables, maximum likelihood estimation (MLE) is the method of choice. However, many datasets contain missing observations, which can lead to costly and time-consuming data recovery. To address this issue, the expectation-maximization (EM) algorithm has been suggested as a solution for situations including missing data. The EM algorithm repeatedly finds the best estimates of parameters in statistical models that depend on variables or data that have not been observed. This is called maximum likelihood or maximum a posteriori (MAP). Using the present estimate as input, the expectation (E) step constructs a log-likelihood function. Finding the parameters that maximize the anticipated log-likelihood, as determined in the E step, is the job of the maximization (M) phase. This study looked at how well the EM algorithm worked on a made-up compositional dataset with missing observations. It used both the robust least square version and ordinary least square regression techniques. The efficacy of the EM algorithm was compared with two alternative imputation techniques, k-Nearest Neighbor (k-NN) and mean imputation (), in terms of Aitchison distances and covariance.展开更多
It is well known that the nonparametric estimation of the regression function is highly sensitive to the presence of even a small proportion of outliers in the data.To solve the problem of typical observations when th...It is well known that the nonparametric estimation of the regression function is highly sensitive to the presence of even a small proportion of outliers in the data.To solve the problem of typical observations when the covariates of the nonparametric component are functional,the robust estimates for the regression parameter and regression operator are introduced.The main propose of the paper is to consider data-driven methods of selecting the number of neighbors in order to make the proposed processes fully automatic.We use thek Nearest Neighbors procedure(kNN)to construct the kernel estimator of the proposed robust model.Under some regularity conditions,we state consistency results for kNN functional estimators,which are uniform in the number of neighbors(UINN).Furthermore,a simulation study and an empirical application to a real data analysis of octane gasoline predictions are carried out to illustrate the higher predictive performances and the usefulness of the kNN approach.展开更多
Winding is one of themost important components in power transformers.Ensuring the health state of the winding is of great importance to the stable operation of the power system.To efficiently and accurately diagnose t...Winding is one of themost important components in power transformers.Ensuring the health state of the winding is of great importance to the stable operation of the power system.To efficiently and accurately diagnose the disc space variation(DSV)fault degree of transformer winding,this paper presents a diagnostic method of winding fault based on the K-Nearest Neighbor(KNN)algorithmand the frequency response analysis(FRA)method.First,a laboratory winding model is used,and DSV faults with four different degrees are achieved by changing disc space of the discs in the winding.Then,a series of FRA tests are conducted to obtain the FRA results and set up the FRA dataset.Second,ten different numerical indices are utilized to obtain features of FRA curves of faulted winding.Third,the 10-fold cross-validation method is employed to determine the optimal k-value of KNN.In addition,to improve the accuracy of the KNN model,a comparative analysis is made between the accuracy of the KNN algorithm and k-value under four distance functions.After getting the most appropriate distance metric and kvalue,the fault classificationmodel based on theKNN and FRA is constructed and it is used to classify the degrees of DSV faults.The identification accuracy rate of the proposed model is up to 98.30%.Finally,the performance of the model is presented by comparing with the support vector machine(SVM),SVM optimized by the particle swarmoptimization(PSO-SVM)method,and randomforest(RF).The results show that the diagnosis accuracy of the proposed model is the highest and the model can be used to accurately diagnose the DSV fault degrees of the winding.展开更多
Hemisphere photos are now widely applied to provide information about solar radiation dynamics,canopy structure and their contribution to biophysical processes,plant productivity and ecosystem properties.The present s...Hemisphere photos are now widely applied to provide information about solar radiation dynamics,canopy structure and their contribution to biophysical processes,plant productivity and ecosystem properties.The present study aims to improve the original‘edge detection’method for binary classifcation between sky and canopy,which works not well for closed canopies.We supposed such inaccuracy probably is due to the infuence of sky pixels on their neighbor canopy pixels.Here,we introduced a new term‘neighbor distance’,defned as the distance between pixels participated in the calculation of contrast at the edges between classifed canopy and sky,into the‘edge detection’method.We showed that choosing a suitable neighbor distance for a photo with a specifc gap fraction can signifcantly improve the accuracy of the original‘edge detection’method.We developed an ND-IS(Neighbor Distance-Iteration Selection)method that can automatically determine the threshold values of hemisphere photos with high accuracy and reproductivity.It combines the modifed‘edge detection’method and an iterative selection method,with the aid of an empirical power function for the relationship between neighbor distance and manually verifed gap fraction.This procedure worked well throughout a broad range of gap fractions(0.019-0.945)with different canopy compositions and structures,in fve forest biomes along a broad gradient of latitude and longitude across Eastern China.Our results highlight the necessity of integrating neighbor distance into the original‘edge detection’algorithm.The advantages and limitations of the method,and the application of the method in the feld were also discussed.展开更多
文摘Compositional data, such as relative information, is a crucial aspect of machine learning and other related fields. It is typically recorded as closed data or sums to a constant, like 100%. The statistical linear model is the most used technique for identifying hidden relationships between underlying random variables of interest. However, data quality is a significant challenge in machine learning, especially when missing data is present. The linear regression model is a commonly used statistical modeling technique used in various applications to find relationships between variables of interest. When estimating linear regression parameters which are useful for things like future prediction and partial effects analysis of independent variables, maximum likelihood estimation (MLE) is the method of choice. However, many datasets contain missing observations, which can lead to costly and time-consuming data recovery. To address this issue, the expectation-maximization (EM) algorithm has been suggested as a solution for situations including missing data. The EM algorithm repeatedly finds the best estimates of parameters in statistical models that depend on variables or data that have not been observed. This is called maximum likelihood or maximum a posteriori (MAP). Using the present estimate as input, the expectation (E) step constructs a log-likelihood function. Finding the parameters that maximize the anticipated log-likelihood, as determined in the E step, is the job of the maximization (M) phase. This study looked at how well the EM algorithm worked on a made-up compositional dataset with missing observations. It used both the robust least square version and ordinary least square regression techniques. The efficacy of the EM algorithm was compared with two alternative imputation techniques, k-Nearest Neighbor (k-NN) and mean imputation (), in terms of Aitchison distances and covariance.
文摘It is well known that the nonparametric estimation of the regression function is highly sensitive to the presence of even a small proportion of outliers in the data.To solve the problem of typical observations when the covariates of the nonparametric component are functional,the robust estimates for the regression parameter and regression operator are introduced.The main propose of the paper is to consider data-driven methods of selecting the number of neighbors in order to make the proposed processes fully automatic.We use thek Nearest Neighbors procedure(kNN)to construct the kernel estimator of the proposed robust model.Under some regularity conditions,we state consistency results for kNN functional estimators,which are uniform in the number of neighbors(UINN).Furthermore,a simulation study and an empirical application to a real data analysis of octane gasoline predictions are carried out to illustrate the higher predictive performances and the usefulness of the kNN approach.
基金supported in part by Shaanxi Natural Science Foundation Project (2023-JC-QN-0438)in part by Fundamental Research Funds for the Central Universities (2452021050).
文摘Winding is one of themost important components in power transformers.Ensuring the health state of the winding is of great importance to the stable operation of the power system.To efficiently and accurately diagnose the disc space variation(DSV)fault degree of transformer winding,this paper presents a diagnostic method of winding fault based on the K-Nearest Neighbor(KNN)algorithmand the frequency response analysis(FRA)method.First,a laboratory winding model is used,and DSV faults with four different degrees are achieved by changing disc space of the discs in the winding.Then,a series of FRA tests are conducted to obtain the FRA results and set up the FRA dataset.Second,ten different numerical indices are utilized to obtain features of FRA curves of faulted winding.Third,the 10-fold cross-validation method is employed to determine the optimal k-value of KNN.In addition,to improve the accuracy of the KNN model,a comparative analysis is made between the accuracy of the KNN algorithm and k-value under four distance functions.After getting the most appropriate distance metric and kvalue,the fault classificationmodel based on theKNN and FRA is constructed and it is used to classify the degrees of DSV faults.The identification accuracy rate of the proposed model is up to 98.30%.Finally,the performance of the model is presented by comparing with the support vector machine(SVM),SVM optimized by the particle swarmoptimization(PSO-SVM)method,and randomforest(RF).The results show that the diagnosis accuracy of the proposed model is the highest and the model can be used to accurately diagnose the DSV fault degrees of the winding.
基金supported by the Fang Jingyun ecological study studio of Yunnan province,the National Natural Science Foundation of China(32271652,32201258)the Major Program for Basic Research Project of Yunnan Province(202101BC070002)。
文摘Hemisphere photos are now widely applied to provide information about solar radiation dynamics,canopy structure and their contribution to biophysical processes,plant productivity and ecosystem properties.The present study aims to improve the original‘edge detection’method for binary classifcation between sky and canopy,which works not well for closed canopies.We supposed such inaccuracy probably is due to the infuence of sky pixels on their neighbor canopy pixels.Here,we introduced a new term‘neighbor distance’,defned as the distance between pixels participated in the calculation of contrast at the edges between classifed canopy and sky,into the‘edge detection’method.We showed that choosing a suitable neighbor distance for a photo with a specifc gap fraction can signifcantly improve the accuracy of the original‘edge detection’method.We developed an ND-IS(Neighbor Distance-Iteration Selection)method that can automatically determine the threshold values of hemisphere photos with high accuracy and reproductivity.It combines the modifed‘edge detection’method and an iterative selection method,with the aid of an empirical power function for the relationship between neighbor distance and manually verifed gap fraction.This procedure worked well throughout a broad range of gap fractions(0.019-0.945)with different canopy compositions and structures,in fve forest biomes along a broad gradient of latitude and longitude across Eastern China.Our results highlight the necessity of integrating neighbor distance into the original‘edge detection’algorithm.The advantages and limitations of the method,and the application of the method in the feld were also discussed.
