The method of Random Forest （RF） was used to classify whether rockburst will happen and the intensity of rockburst in the underground rock projects. Some main control factors of rockburst, such as the values of in-s...The method of Random Forest （RF） was used to classify whether rockburst will happen and the intensity of rockburst in the underground rock projects. Some main control factors of rockburst, such as the values of in-situ stresses, uniaxial compressive strength and tensile strength of rock, and the elastic energy index of rock, were selected in the analysis. The traditional indicators were summarized and divided into indexes I and 1I. Random Forest model and criterion were obtained through training 36 sets of rockburst samples which come from underground rock projects in domestic and abroad. Another 10 samples were tested and evaluated with the model. The evaluated results agree well with the practical records. Comparing the results of support vector machine （SVM） method, and artificial neural network （ANN） method with random forest method, the corresponding misjudgment ratios are 10%, 20%, and 0, respectively. The misjudgment ratio using index I is smaller than that using index II. It is suggested that using the index I and RF model can accurately classify rockburst grade.展开更多
Accurate assessment of undrained shear strength(USS)for soft sensitive clays is a great concern in geotechnical engineering practice.This study applies novel data-driven extreme gradient boosting(XGBoost)and random fo...Accurate assessment of undrained shear strength(USS)for soft sensitive clays is a great concern in geotechnical engineering practice.This study applies novel data-driven extreme gradient boosting(XGBoost)and random forest(RF)ensemble learning methods for capturing the relationships between the USS and various basic soil parameters.Based on the soil data sets from TC304 database,a general approach is developed to predict the USS of soft clays using the two machine learning methods above,where five feature variables including the preconsolidation stress(PS),vertical effective stress(VES),liquid limit(LL),plastic limit(PL)and natural water content(W)are adopted.To reduce the dependence on the rule of thumb and inefficient brute-force search,the Bayesian optimization method is applied to determine the appropriate model hyper-parameters of both XGBoost and RF.The developed models are comprehensively compared with three comparison machine learning methods and two transformation models with respect to predictive accuracy and robustness under 5-fold cross-validation(CV).It is shown that XGBoost-based and RF-based methods outperform these approaches.Besides,the XGBoostbased model provides feature importance ranks,which makes it a promising tool in the prediction of geotechnical parameters and enhances the interpretability of model.展开更多
In this paper, a notion of negative side ρ \|mixing ( ρ\+- \|mixing) which can be regarded as asymptotic negative association is defined, and some Rosenthal type inequalities for ρ\+- \|mixing random fields are est...In this paper, a notion of negative side ρ \|mixing ( ρ\+- \|mixing) which can be regarded as asymptotic negative association is defined, and some Rosenthal type inequalities for ρ\+- \|mixing random fields are established. The complete convergence and almost sure summability on the convergence rates with respect to the strong law of large numbers are also discussed for ρ\+-\| mixing random fields. The results obtained extend those for negatively associated sequences and ρ\+*\| mixing random fields.展开更多
This paper studies the moderate deviations of real-valued extended negatively dependent(END) random variables with consistently varying tails.The moderate deviations of partial sums are first given.The results are the...This paper studies the moderate deviations of real-valued extended negatively dependent(END) random variables with consistently varying tails.The moderate deviations of partial sums are first given.The results are then used to establish the necessary and sufficient conditions for the moderate deviations of random sums under certain circumstances.展开更多
开放领域新词发现研究对于中文自然语言处理的性能提升有着重要的意义.利用条件随机场(condition random field,简称CRF)可对序列输入标注的特点,将新词发现问题转化为预测已分词词语边界是否为新词边界的问题.在对海量规模中文互联网...开放领域新词发现研究对于中文自然语言处理的性能提升有着重要的意义.利用条件随机场(condition random field,简称CRF)可对序列输入标注的特点,将新词发现问题转化为预测已分词词语边界是否为新词边界的问题.在对海量规模中文互联网语料进行分析挖掘的基础上,提出了一系列区分新词边界的统计特征,并采用CRF方法综合这些特征实现了开放领域新词发现的算法,同时比较了K-Means聚类、等频率、基于信息增益这3种离散化方法对新词发现结果的影响.通过在SogouT大规模中文语料库上的新词发现实验,验证了所提出的方法有较好的效果.展开更多
To analyze the effect of basic variable on failure probability in reliability analysis,a moment-independent importance measure of the basic random variable is proposed,and its properties are analyzed and verified.Base...To analyze the effect of basic variable on failure probability in reliability analysis,a moment-independent importance measure of the basic random variable is proposed,and its properties are analyzed and verified.Based on this work,the importance measure of the basic variable on the failure probability is compared with that on the distribution density of the response.By use of the probability density evolution method,a solution is established to solve two importance measures,which can efficiently avoid the difficulty in solving the importance measures.Some numerical examples and engineering examples are used to demonstrate the proposed importance measure on the failure probability and that on the distribution density of the response.The results show that the proposed importance measure can effectively describe the effect of the basic variable on the failure probability from the distribution density of the basic variable.Additionally,the results show that the established solution on the probability density evolution is efficient for the importance measures.展开更多
基金Projects (50934006, 10872218) supported by the National Natural Science Foundation of ChinaProject (2010CB732004) supported bythe National Basic Research Program of China+1 种基金Project (kjdb2010-6) supported by Doctoral Candidate Innovation Research Support Program of Science & Technology Review, ChinaProject (201105) supported by Scholarship Award for Excellent Doctoral Student,Ministry of Education, China
文摘The method of Random Forest （RF） was used to classify whether rockburst will happen and the intensity of rockburst in the underground rock projects. Some main control factors of rockburst, such as the values of in-situ stresses, uniaxial compressive strength and tensile strength of rock, and the elastic energy index of rock, were selected in the analysis. The traditional indicators were summarized and divided into indexes I and 1I. Random Forest model and criterion were obtained through training 36 sets of rockburst samples which come from underground rock projects in domestic and abroad. Another 10 samples were tested and evaluated with the model. The evaluated results agree well with the practical records. Comparing the results of support vector machine （SVM） method, and artificial neural network （ANN） method with random forest method, the corresponding misjudgment ratios are 10%, 20%, and 0, respectively. The misjudgment ratio using index I is smaller than that using index II. It is suggested that using the index I and RF model can accurately classify rockburst grade.
基金financial support from High-end Foreign Expert Introduction program(No.G20190022002)Chongqing Construction Science and Technology Plan Project(2019-0045)as well as Chongqing Engineering Research Center of Disaster Prevention&Control for Banks and Structures in Three Gorges Reservoir Area(Nos.SXAPGC18ZD01 and SXAPGC18YB03)。
文摘Accurate assessment of undrained shear strength(USS)for soft sensitive clays is a great concern in geotechnical engineering practice.This study applies novel data-driven extreme gradient boosting(XGBoost)and random forest(RF)ensemble learning methods for capturing the relationships between the USS and various basic soil parameters.Based on the soil data sets from TC304 database,a general approach is developed to predict the USS of soft clays using the two machine learning methods above,where five feature variables including the preconsolidation stress(PS),vertical effective stress(VES),liquid limit(LL),plastic limit(PL)and natural water content(W)are adopted.To reduce the dependence on the rule of thumb and inefficient brute-force search,the Bayesian optimization method is applied to determine the appropriate model hyper-parameters of both XGBoost and RF.The developed models are comprehensively compared with three comparison machine learning methods and two transformation models with respect to predictive accuracy and robustness under 5-fold cross-validation(CV).It is shown that XGBoost-based and RF-based methods outperform these approaches.Besides,the XGBoostbased model provides feature importance ranks,which makes it a promising tool in the prediction of geotechnical parameters and enhances the interpretability of model.
文摘In this paper, a notion of negative side ρ \|mixing ( ρ\+- \|mixing) which can be regarded as asymptotic negative association is defined, and some Rosenthal type inequalities for ρ\+- \|mixing random fields are established. The complete convergence and almost sure summability on the convergence rates with respect to the strong law of large numbers are also discussed for ρ\+-\| mixing random fields. The results obtained extend those for negatively associated sequences and ρ\+*\| mixing random fields.
基金supported by National Natural Science Foundation of China(Grant No.10571139)the Research Foundation of Education Bureau of Hubei Province,China (Grant No.Q200710002)
文摘This paper studies the moderate deviations of real-valued extended negatively dependent(END) random variables with consistently varying tails.The moderate deviations of partial sums are first given.The results are then used to establish the necessary and sufficient conditions for the moderate deviations of random sums under certain circumstances.
文摘开放领域新词发现研究对于中文自然语言处理的性能提升有着重要的意义.利用条件随机场(condition random field,简称CRF)可对序列输入标注的特点,将新词发现问题转化为预测已分词词语边界是否为新词边界的问题.在对海量规模中文互联网语料进行分析挖掘的基础上,提出了一系列区分新词边界的统计特征,并采用CRF方法综合这些特征实现了开放领域新词发现的算法,同时比较了K-Means聚类、等频率、基于信息增益这3种离散化方法对新词发现结果的影响.通过在SogouT大规模中文语料库上的新词发现实验,验证了所提出的方法有较好的效果.
基金supported by the National Natural Science Foundation of China (Grant Nos NSFC1057211, 50875213)New Century Excellent Talents in University of China (Grant No NCET-05-0868)+2 种基金Aviation Science Foundation of China (Grant No 2007ZA53012)National High Technology Research and Development Program of China (Grant No 2007AA04Z401)the Important National Science & Technology Specific Projects (Grant No 2009ZX04014-015-03)
文摘To analyze the effect of basic variable on failure probability in reliability analysis,a moment-independent importance measure of the basic random variable is proposed,and its properties are analyzed and verified.Based on this work,the importance measure of the basic variable on the failure probability is compared with that on the distribution density of the response.By use of the probability density evolution method,a solution is established to solve two importance measures,which can efficiently avoid the difficulty in solving the importance measures.Some numerical examples and engineering examples are used to demonstrate the proposed importance measure on the failure probability and that on the distribution density of the response.The results show that the proposed importance measure can effectively describe the effect of the basic variable on the failure probability from the distribution density of the basic variable.Additionally,the results show that the established solution on the probability density evolution is efficient for the importance measures.
