Based on the principle of Bayesian discriminant analysis, we established a model of Bayesian discriminant analysis for predicting coal and gas outbursts. We selected five major indices which affect outbursts, i.e., in...Based on the principle of Bayesian discriminant analysis, we established a model of Bayesian discriminant analysis for predicting coal and gas outbursts. We selected five major indices which affect outbursts, i.e., initial speed of methane diffusion, a consistent coal coefficient, gas pressure, destructive style of coal and mining depth, as discriminating factors of the model. In our model, we divided the type of coal and gas outbursts into four grades regarded as four normal populations. We then obtained the corresponding discriminant functions through training a set of data from engineering examples as learning samples and evaluated their criteria by a back substitution method to verify the optimal properties of the model. Finally, we applied the model to the prediction of coal and gas outbursts in the Yunnan Enhong Mine. Our results coincided completely with the actual situation. These results show that a model of Bayesian discriminant analysis has excellent recognition performance, high prediction accuracy and a low error rate and is an effective method to predict coal and gas outbursts.展开更多
By studying different compressive strengths and changes in the characteristics of rocks,five variables were selected to predict faults in coal mines. Drillholes in the mined area were divided into two populations, i.e...By studying different compressive strengths and changes in the characteristics of rocks,five variables were selected to predict faults in coal mines. Drillholes in the mined area were divided into two populations, i.e., drillholes containing faults and drillholes without faults. Discriminant functions were established from the values of the five variables using Fisher's approach. Drillholes in the non-mined areas were allocated to one of the two populations by using discriminant functions. The terrenes of each drillhole were divided into 10 sections, above and below a minable coal seam. Each section has 10 layers of rocks. The population to which each drillhole in a section belongs is sorted out and the probability of each drillhole with faults obtained,i.e., a contour map of predicting the probability of faults in coal mining is shown. A comparison with the real distribution of faults shows that the precision of accurately predicting faults is greater than 70 per cent.展开更多
The problem of the firm bankruptcy prediction was investigated by foreign researchers in the 1930s and it still remains relevant. Since the publishing of Altman＇s （1968） major work, based on multiple discriminant a...The problem of the firm bankruptcy prediction was investigated by foreign researchers in the 1930s and it still remains relevant. Since the publishing of Altman＇s （1968） major work, based on multiple discriminant analysis （MDA）, this methodological area has considerably changed. Taking into consideration that new data have appeared in the course of time, companies＇ average size has changed, and the accounting standards have changed （Altman, Haldeman, ＆ Narayanan, 1977）, methods and models should be renewed so as to be appropriate for current situation. The purpose of this paper1 is to reveal factors causing bankruptcy and use models appropriate for prediction bankruptcy in the area of a construction industry during the financial crisis. This investigation has been carried out on the basis of logit and probit analysis. The main reasons of bankruptcy revealed in the course of this investigation are the following： （1） non-optimal capital structure formation; （2） ineffective liquidity management; （3） decrease in assets profitability; and （4） decrease in short-term assets turnover. The most reliable indicators which give warning of bankruptcy ahead of others are financial instability and liquidity ratios.展开更多
Statistical classification methods are frequently applied to analyze metabolomics data, especially from medicinal plants. Combined with variable selection techniques, we are able to identify marker candidates, which c...Statistical classification methods are frequently applied to analyze metabolomics data, especially from medicinal plants. Combined with variable selection techniques, we are able to identify marker candidates, which can be used to discriminate the group to which unknown subjects belong. After preprocessing, such as outlier checking, normalization, missing value imputation and transformation, we then mainly utilized four novel classification methods： RF （random forest）, NSC （nearest shrunken centroid）, PLS-DA （partial least square discriminant analysis） and SAM （significant analysis ofmicroarrays）. Each method has its own device to measure the importance of single metabolite, so that, it is probable to choose highly ranked metabolites, which show the best prediction accuracy. Adapting above strategy, we have successfully analyzed several kinds of metabolomics data including Panax ginseng, Lespedeza species, Anemarrhean asphodeloides and Gastrodia elata.展开更多
The use of visible-near infrared (NIR) spectroscopy was explored as a tool to discriminate two new tomato plant varieties in China (Zheza205 and Zheza207). In this study, 82 top-canopy leaves of Zheza205 and 86 top-ca...The use of visible-near infrared (NIR) spectroscopy was explored as a tool to discriminate two new tomato plant varieties in China (Zheza205 and Zheza207). In this study, 82 top-canopy leaves of Zheza205 and 86 top-canopy leaves of Zheza207 were measured in visible-NIR reflectance mode. Discriminant models were developed using principal component analysis (PCA), discriminant analysis (DA), and discriminant partial least squares (DPLS) regression methods. After outliers detection, the samples were randomly split into two sets, one used as a calibration set (n=82) and the remaining samples as a validation set (n=82). When predicting the variety of the samples in validation set, the classification correctness of the DPLS model after optimizing spectral pretreatment was up to 93%. The DPLS model with raw spectra after multiplicative scatter cor- rection and Savitzky-Golay filter smoothing pretreatments had the best satisfactory calibration and prediction abilities (correlation coefficient of calibration (Rc)=0.920, root mean square errors of calibration=0.196, and root mean square errors of predic- tion=0.216). The results show that visible-NIR spectroscopy might be a suitable alternative tool to discriminate tomato plant varieties on-site.展开更多
Here we use a Discriminant Genetic Algorithm Extended (DGAE) model to diagnose and predict seasonal sand and dust storm (SDS) activities occurring in Northeast Asia. The study employed the regular meteorological data,...Here we use a Discriminant Genetic Algorithm Extended (DGAE) model to diagnose and predict seasonal sand and dust storm (SDS) activities occurring in Northeast Asia. The study employed the regular meteorological data, including surface data, upper air data, and NCEP reanalysis data, collected from 1980–2006. The regional, seasonal, and annual differences of 3-D atmospheric circulation structures and SDS activities in the context of spatial and temporal distributions were given. Genetic algorithms were introduced with the further extension of promoting SDS seasonal predication from multi-level resolution. Genetic probability was used as a substitute for posterior probability of multi-level discriminants, to show the dual characteristics of crossover inheritance and mutation and to build a non-linear adaptability function in line with extended genetic algorithms. This has unveiled the spatial distribution of the maximum adaptability, allowing the forecast field to be defined by the population with the largest probability, and made discriminant genetic extension possible. In addition, the effort has led to the establishment of a regional model for predicting seasonal SDS activities in East Asia. The model was tested to predict the spring SDS activities occurring in North China from 2007 to 2009. The experimental forecast resulted in highly discriminant intensity ratings and regional distributions of SDS activities, which are a meaningful reference for seasonal SDS predictions in the future.展开更多
基金supported by the National Hi-tech Research and Development Program of China (No.2006BAK03B02-04) the New Century Excellent Talent Support Plan of Ministry of Education of China (No.NCET-06-0477)
文摘Based on the principle of Bayesian discriminant analysis, we established a model of Bayesian discriminant analysis for predicting coal and gas outbursts. We selected five major indices which affect outbursts, i.e., initial speed of methane diffusion, a consistent coal coefficient, gas pressure, destructive style of coal and mining depth, as discriminating factors of the model. In our model, we divided the type of coal and gas outbursts into four grades regarded as four normal populations. We then obtained the corresponding discriminant functions through training a set of data from engineering examples as learning samples and evaluated their criteria by a back substitution method to verify the optimal properties of the model. Finally, we applied the model to the prediction of coal and gas outbursts in the Yunnan Enhong Mine. Our results coincided completely with the actual situation. These results show that a model of Bayesian discriminant analysis has excellent recognition performance, high prediction accuracy and a low error rate and is an effective method to predict coal and gas outbursts.
基金Project 40772198 supported by the National Natural Science Foundation of China
文摘By studying different compressive strengths and changes in the characteristics of rocks,five variables were selected to predict faults in coal mines. Drillholes in the mined area were divided into two populations, i.e., drillholes containing faults and drillholes without faults. Discriminant functions were established from the values of the five variables using Fisher's approach. Drillholes in the non-mined areas were allocated to one of the two populations by using discriminant functions. The terrenes of each drillhole were divided into 10 sections, above and below a minable coal seam. Each section has 10 layers of rocks. The population to which each drillhole in a section belongs is sorted out and the probability of each drillhole with faults obtained,i.e., a contour map of predicting the probability of faults in coal mining is shown. A comparison with the real distribution of faults shows that the precision of accurately predicting faults is greater than 70 per cent.
文摘The problem of the firm bankruptcy prediction was investigated by foreign researchers in the 1930s and it still remains relevant. Since the publishing of Altman＇s （1968） major work, based on multiple discriminant analysis （MDA）, this methodological area has considerably changed. Taking into consideration that new data have appeared in the course of time, companies＇ average size has changed, and the accounting standards have changed （Altman, Haldeman, ＆ Narayanan, 1977）, methods and models should be renewed so as to be appropriate for current situation. The purpose of this paper1 is to reveal factors causing bankruptcy and use models appropriate for prediction bankruptcy in the area of a construction industry during the financial crisis. This investigation has been carried out on the basis of logit and probit analysis. The main reasons of bankruptcy revealed in the course of this investigation are the following： （1） non-optimal capital structure formation; （2） ineffective liquidity management; （3） decrease in assets profitability; and （4） decrease in short-term assets turnover. The most reliable indicators which give warning of bankruptcy ahead of others are financial instability and liquidity ratios.
文摘Statistical classification methods are frequently applied to analyze metabolomics data, especially from medicinal plants. Combined with variable selection techniques, we are able to identify marker candidates, which can be used to discriminate the group to which unknown subjects belong. After preprocessing, such as outlier checking, normalization, missing value imputation and transformation, we then mainly utilized four novel classification methods： RF （random forest）, NSC （nearest shrunken centroid）, PLS-DA （partial least square discriminant analysis） and SAM （significant analysis ofmicroarrays）. Each method has its own device to measure the importance of single metabolite, so that, it is probable to choose highly ranked metabolites, which show the best prediction accuracy. Adapting above strategy, we have successfully analyzed several kinds of metabolomics data including Panax ginseng, Lespedeza species, Anemarrhean asphodeloides and Gastrodia elata.
基金Project (No.60405003) supported by the National Natural Science Foundation of China
文摘The use of visible-near infrared (NIR) spectroscopy was explored as a tool to discriminate two new tomato plant varieties in China (Zheza205 and Zheza207). In this study, 82 top-canopy leaves of Zheza205 and 86 top-canopy leaves of Zheza207 were measured in visible-NIR reflectance mode. Discriminant models were developed using principal component analysis (PCA), discriminant analysis (DA), and discriminant partial least squares (DPLS) regression methods. After outliers detection, the samples were randomly split into two sets, one used as a calibration set (n=82) and the remaining samples as a validation set (n=82). When predicting the variety of the samples in validation set, the classification correctness of the DPLS model after optimizing spectral pretreatment was up to 93%. The DPLS model with raw spectra after multiplicative scatter cor- rection and Savitzky-Golay filter smoothing pretreatments had the best satisfactory calibration and prediction abilities (correlation coefficient of calibration (Rc)=0.920, root mean square errors of calibration=0.196, and root mean square errors of predic- tion=0.216). The results show that visible-NIR spectroscopy might be a suitable alternative tool to discriminate tomato plant varieties on-site.
基金supported by National S & T Support Program (Grant No. 2008BAC40B02)National Basic Research Program of China (Grant Nos. 2006CB403703 and 2006CB403701)Basic Research Fund under Chinese Academy of Meteorological Sciences (Grant Nos. 2009Y002, 2009Y001)
文摘Here we use a Discriminant Genetic Algorithm Extended (DGAE) model to diagnose and predict seasonal sand and dust storm (SDS) activities occurring in Northeast Asia. The study employed the regular meteorological data, including surface data, upper air data, and NCEP reanalysis data, collected from 1980–2006. The regional, seasonal, and annual differences of 3-D atmospheric circulation structures and SDS activities in the context of spatial and temporal distributions were given. Genetic algorithms were introduced with the further extension of promoting SDS seasonal predication from multi-level resolution. Genetic probability was used as a substitute for posterior probability of multi-level discriminants, to show the dual characteristics of crossover inheritance and mutation and to build a non-linear adaptability function in line with extended genetic algorithms. This has unveiled the spatial distribution of the maximum adaptability, allowing the forecast field to be defined by the population with the largest probability, and made discriminant genetic extension possible. In addition, the effort has led to the establishment of a regional model for predicting seasonal SDS activities in East Asia. The model was tested to predict the spring SDS activities occurring in North China from 2007 to 2009. The experimental forecast resulted in highly discriminant intensity ratings and regional distributions of SDS activities, which are a meaningful reference for seasonal SDS predictions in the future.
