28 oilseed rape Pol CMS three-line hybrid combinations diallel-crossed were compared in the yield and harvest index and analyzed on the correlation between the experimental yields and harvest indexes in this study. Th...28 oilseed rape Pol CMS three-line hybrid combinations diallel-crossed were compared in the yield and harvest index and analyzed on the correlation between the experimental yields and harvest indexes in this study. The correlation coeffcient was only 0.365 4, lower than a signifcant level, which indicated that there was no signifcant positive （or negative） correlation between the economic yields and the harvest indexes in oilseed rape. Among them, 8 hybrid combinations including 7 with a harvest index〉0.30 and one with a harvest index〈0.27 increased signifcantly in the yields compared with the control, and then were screened for production experiment. Under different cultivation methods, all the 8 combinations had a stable harvest index, and the combinations with higher harvest indexes also had a stable performance in yields. An oilseed rape variety Fengyou 737 with higher yield and harvest index selected through a further screening was grown with the harvest indexhigher than 0.33 whether transplanted or directly seeded in Yangtze River Basin Demonstration Area, demonstrating stable high yields as well as good ecological adaptability. The combination of yield and harvest index in the study is conducive to breeding a new oilseed rape variety with stable yields and good tolerance to close planting.展开更多
Screening variables with significant features as the input data of network, is an important step in application of neural network to predict and analysis problems. This paper proposed a method using MIV algorithm to s...Screening variables with significant features as the input data of network, is an important step in application of neural network to predict and analysis problems. This paper proposed a method using MIV algorithm to screen variables of BP neural network.And experimental results show that, the proposed technique is practical and reliable.展开更多
There are two fundamental goals in statistical learning： identifying relevant predictors and ensuring high prediction accuracy. The first goal, by means of variable selection, is of particular importance when the tru...There are two fundamental goals in statistical learning： identifying relevant predictors and ensuring high prediction accuracy. The first goal, by means of variable selection, is of particular importance when the true underlying model has a sparse representation. Discovering relevant predictors can enhance the performance of the prediction for the fitted model. Usually an estimate is considered desirable if it is consistent in terms of both coefficient estimate and variable selection. Hence, before we try to estimate the regression coefficients β , it is preferable that we have a set of useful predictors m hand. The emphasis of our task in this paper is to propose a method, in the aim of identifying relevant predictors to ensure screening consistency in variable selection. The primary interest is on Orthogonal Matching Pursuit（OMP）.展开更多
High-dimensional data have frequently been collected in many scientific areas including genomewide association study, biomedical imaging, tomography, tumor classifications, and finance. Analysis of highdimensional dat...High-dimensional data have frequently been collected in many scientific areas including genomewide association study, biomedical imaging, tomography, tumor classifications, and finance. Analysis of highdimensional data poses many challenges for statisticians. Feature selection and variable selection are fundamental for high-dimensional data analysis. The sparsity principle, which assumes that only a small number of predictors contribute to the response, is frequently adopted and deemed useful in the analysis of high-dimensional data.Following this general principle, a large number of variable selection approaches via penalized least squares or likelihood have been developed in the recent literature to estimate a sparse model and select significant variables simultaneously. While the penalized variable selection methods have been successfully applied in many highdimensional analyses, modern applications in areas such as genomics and proteomics push the dimensionality of data to an even larger scale, where the dimension of data may grow exponentially with the sample size. This has been called ultrahigh-dimensional data in the literature. This work aims to present a selective overview of feature screening procedures for ultrahigh-dimensional data. We focus on insights into how to construct marginal utilities for feature screening on specific models and motivation for the need of model-free feature screening procedures.展开更多
文摘28 oilseed rape Pol CMS three-line hybrid combinations diallel-crossed were compared in the yield and harvest index and analyzed on the correlation between the experimental yields and harvest indexes in this study. The correlation coeffcient was only 0.365 4, lower than a signifcant level, which indicated that there was no signifcant positive （or negative） correlation between the economic yields and the harvest indexes in oilseed rape. Among them, 8 hybrid combinations including 7 with a harvest index〉0.30 and one with a harvest index〈0.27 increased signifcantly in the yields compared with the control, and then were screened for production experiment. Under different cultivation methods, all the 8 combinations had a stable harvest index, and the combinations with higher harvest indexes also had a stable performance in yields. An oilseed rape variety Fengyou 737 with higher yield and harvest index selected through a further screening was grown with the harvest indexhigher than 0.33 whether transplanted or directly seeded in Yangtze River Basin Demonstration Area, demonstrating stable high yields as well as good ecological adaptability. The combination of yield and harvest index in the study is conducive to breeding a new oilseed rape variety with stable yields and good tolerance to close planting.
文摘Screening variables with significant features as the input data of network, is an important step in application of neural network to predict and analysis problems. This paper proposed a method using MIV algorithm to screen variables of BP neural network.And experimental results show that, the proposed technique is practical and reliable.
文摘There are two fundamental goals in statistical learning： identifying relevant predictors and ensuring high prediction accuracy. The first goal, by means of variable selection, is of particular importance when the true underlying model has a sparse representation. Discovering relevant predictors can enhance the performance of the prediction for the fitted model. Usually an estimate is considered desirable if it is consistent in terms of both coefficient estimate and variable selection. Hence, before we try to estimate the regression coefficients β , it is preferable that we have a set of useful predictors m hand. The emphasis of our task in this paper is to propose a method, in the aim of identifying relevant predictors to ensure screening consistency in variable selection. The primary interest is on Orthogonal Matching Pursuit（OMP）.
基金supported by National Natural Science Foundation of China(Grant Nos.11401497 and 11301435)the Fundamental Research Funds for the Central Universities(Grant No.T2013221043)+3 种基金the Scientific Research Foundation for the Returned Overseas Chinese Scholars,State Education Ministry,the Fundamental Research Funds for the Central Universities(Grant No.20720140034)National Institute on Drug Abuse,National Institutes of Health(Grant Nos.P50 DA036107 and P50 DA039838)National Science Foundation(Grant No.DMS1512422)The content is solely the responsibility of the authors and does not necessarily represent the official views of National Institute on Drug Abuse, National Institutes of Health, National Science Foundation or National Natural Science Foundation of China
文摘High-dimensional data have frequently been collected in many scientific areas including genomewide association study, biomedical imaging, tomography, tumor classifications, and finance. Analysis of highdimensional data poses many challenges for statisticians. Feature selection and variable selection are fundamental for high-dimensional data analysis. The sparsity principle, which assumes that only a small number of predictors contribute to the response, is frequently adopted and deemed useful in the analysis of high-dimensional data.Following this general principle, a large number of variable selection approaches via penalized least squares or likelihood have been developed in the recent literature to estimate a sparse model and select significant variables simultaneously. While the penalized variable selection methods have been successfully applied in many highdimensional analyses, modern applications in areas such as genomics and proteomics push the dimensionality of data to an even larger scale, where the dimension of data may grow exponentially with the sample size. This has been called ultrahigh-dimensional data in the literature. This work aims to present a selective overview of feature screening procedures for ultrahigh-dimensional data. We focus on insights into how to construct marginal utilities for feature screening on specific models and motivation for the need of model-free feature screening procedures.
