A new approach to knowledge acquisition in incomplete information system with fuzzy decisions is proposed. In such incomplete information system, the universe of discourse is classified by the maximal tolerance classe...A new approach to knowledge acquisition in incomplete information system with fuzzy decisions is proposed. In such incomplete information system, the universe of discourse is classified by the maximal tolerance classes, and fuzzy approximations are defined based on them. Three types of relative reducts of maximal tolerance classes are then proposed, and three types of fuzzy decision rules based on the proposed attribute description are defined. The judgment theorems and approximation discernibility functions with respect to them are presented to compute the relative reduct by using Boolean reasoning techniques, from which we can derive optimal fuzzy decision rules from the systems. At last, three types of relative reducts of the system and their computing methods are given.展开更多
It is important to study the relationship between marketing factors and purchase decisions of middle-class consumers in Nanning housing market.This study will investigate the factors influencing people decision to pur...It is important to study the relationship between marketing factors and purchase decisions of middle-class consumers in Nanning housing market.This study will investigate the factors influencing people decision to purchase houses in Nanning City.The extrinsic housing attributes at this study consist of environmental attributes and location attributes.I have a limited understanding of the purchase behavior of Nanning home buyers in Nanning City.This study adopts the data collection methods of e-mail and field survey.Based on 509 questionnaires,the data were analyzed using descriptive statistics analysis and logistic regression.The results show that location attributes,such as school districts,positively influence housing purchase decisions in Nanning City.This study contributes to an improved understanding of home buyers’decision making in Nanning City.The beneficiaries of this study include home buyers and marketers and academic institutions.To better meet home buyers’needs and achieve a competitive advantage,marketers can use the research outcomes to focus more on those housing purchase factors that significantly influence house buyers’purchase decision making.展开更多
The main challenges of data streams classification include infinite length, concept-drifting, arrival of novel classes and lack of labeled instances. Most existing techniques address only some of them and ignore other...The main challenges of data streams classification include infinite length, concept-drifting, arrival of novel classes and lack of labeled instances. Most existing techniques address only some of them and ignore others. So an ensemble classification model based on decision-feedback（ECM-BDF） is presented in this paper to address all these challenges. Firstly, a data stream is divided into sequential chunks and a classification model is trained from each labeled data chunk. To address the infinite length and concept-drifting problem, a fixed number of such models constitute an ensemble model E and subsequent labeled chunks are used to update E. To deal with the appearance of novel classes and limited labeled instances problem, the model incorporates a novel class detection mechanism to detect the arrival of a novel class without training E with labeled instances of that class. Meanwhile, unsupervised models are trained from unlabeled instances to provide useful constraints for E. An extended ensemble model Ex can be acquired with the constraints as feedback information, and then unlabeled instances can be classified more accurately by satisfying the maximum consensus of Ex. Experimental results demonstrate that the proposed ECM-BDF outperforms traditional techniques in classifying data streams with limited labeled data.展开更多
随机森林是机器学习领域中一种常用的分类算法,具有适用范围广且不易过拟合等优点.为了提高随机森林处理多分类问题的能力,提出一种基于空间变换的随机森林算法(space transformation based random forest algorithm,ST-RF).首先,给出...随机森林是机器学习领域中一种常用的分类算法,具有适用范围广且不易过拟合等优点.为了提高随机森林处理多分类问题的能力,提出一种基于空间变换的随机森林算法(space transformation based random forest algorithm,ST-RF).首先,给出一种考虑优先类别的线性判别分析方法(priority class based linear discriminant analysis,PCLDA),利用针对优先类别的投影矩阵对样本进行空间变换,以增强优先类别样本与其他类别样本的区分效果.进而,将PCLDA方法引入随机森林构建过程中,在为每棵决策树随机选择一个优先类别保证随机森林多样性的基础上,利用PCLDA方法创建侧重于不同优先类别的决策树,以提高单棵决策树的分类准确性,从而实现集成模型整体分类性能的有效提升.最后,在10个标准数据集上对ST-RF算法与7种典型随机森林算法进行比较分析,验证所提算法的有效性,并将基于PCLDA的空间变换策略应用到对比算法中,对改进前后的算法性能进行比较分析.实验结果表明:ST-RF算法在处理多分类问题方面具有明显优势,所提出的空间变换策略具有较强的普适性,可以显著提升原算法的分类性能.展开更多
基金supported by the National Natural Science Foundation of China (61070241)the Natural Science Foundation of Shandong Province (ZR2010FM035)Science Research Foundation of University of Jinan (XKY0808)
文摘A new approach to knowledge acquisition in incomplete information system with fuzzy decisions is proposed. In such incomplete information system, the universe of discourse is classified by the maximal tolerance classes, and fuzzy approximations are defined based on them. Three types of relative reducts of maximal tolerance classes are then proposed, and three types of fuzzy decision rules based on the proposed attribute description are defined. The judgment theorems and approximation discernibility functions with respect to them are presented to compute the relative reduct by using Boolean reasoning techniques, from which we can derive optimal fuzzy decision rules from the systems. At last, three types of relative reducts of the system and their computing methods are given.
文摘It is important to study the relationship between marketing factors and purchase decisions of middle-class consumers in Nanning housing market.This study will investigate the factors influencing people decision to purchase houses in Nanning City.The extrinsic housing attributes at this study consist of environmental attributes and location attributes.I have a limited understanding of the purchase behavior of Nanning home buyers in Nanning City.This study adopts the data collection methods of e-mail and field survey.Based on 509 questionnaires,the data were analyzed using descriptive statistics analysis and logistic regression.The results show that location attributes,such as school districts,positively influence housing purchase decisions in Nanning City.This study contributes to an improved understanding of home buyers’decision making in Nanning City.The beneficiaries of this study include home buyers and marketers and academic institutions.To better meet home buyers’needs and achieve a competitive advantage,marketers can use the research outcomes to focus more on those housing purchase factors that significantly influence house buyers’purchase decision making.
基金supported by the National Natural Science Foundation of China(61202082)the Fundamental Research Funds for the Central Universities(BUPT2012RC0218,BUPT2012RC0219)
文摘The main challenges of data streams classification include infinite length, concept-drifting, arrival of novel classes and lack of labeled instances. Most existing techniques address only some of them and ignore others. So an ensemble classification model based on decision-feedback（ECM-BDF） is presented in this paper to address all these challenges. Firstly, a data stream is divided into sequential chunks and a classification model is trained from each labeled data chunk. To address the infinite length and concept-drifting problem, a fixed number of such models constitute an ensemble model E and subsequent labeled chunks are used to update E. To deal with the appearance of novel classes and limited labeled instances problem, the model incorporates a novel class detection mechanism to detect the arrival of a novel class without training E with labeled instances of that class. Meanwhile, unsupervised models are trained from unlabeled instances to provide useful constraints for E. An extended ensemble model Ex can be acquired with the constraints as feedback information, and then unlabeled instances can be classified more accurately by satisfying the maximum consensus of Ex. Experimental results demonstrate that the proposed ECM-BDF outperforms traditional techniques in classifying data streams with limited labeled data.
文摘随机森林是机器学习领域中一种常用的分类算法,具有适用范围广且不易过拟合等优点.为了提高随机森林处理多分类问题的能力,提出一种基于空间变换的随机森林算法(space transformation based random forest algorithm,ST-RF).首先,给出一种考虑优先类别的线性判别分析方法(priority class based linear discriminant analysis,PCLDA),利用针对优先类别的投影矩阵对样本进行空间变换,以增强优先类别样本与其他类别样本的区分效果.进而,将PCLDA方法引入随机森林构建过程中,在为每棵决策树随机选择一个优先类别保证随机森林多样性的基础上,利用PCLDA方法创建侧重于不同优先类别的决策树,以提高单棵决策树的分类准确性,从而实现集成模型整体分类性能的有效提升.最后,在10个标准数据集上对ST-RF算法与7种典型随机森林算法进行比较分析,验证所提算法的有效性,并将基于PCLDA的空间变换策略应用到对比算法中,对改进前后的算法性能进行比较分析.实验结果表明:ST-RF算法在处理多分类问题方面具有明显优势,所提出的空间变换策略具有较强的普适性,可以显著提升原算法的分类性能.
