Objective:To study on Prof. GAO Zhong-ying’s drug selection law for treatment of chronic gastritis with data mining technique. Methods: The 407 medical records of chronic gastritis treated by Prof. GAO Zhong-ying wer...Objective:To study on Prof. GAO Zhong-ying’s drug selection law for treatment of chronic gastritis with data mining technique. Methods: The 407 medical records of chronic gastritis treated by Prof. GAO Zhong-ying were collected and the study on these drugs in the recipes was carried out with data mining method. Among them, the recipe composed of one drug was studied with frequency statistical method, correlativity between drug pairs with improved mutual information, correlativity among multi-drugs with complex system entropy cluster technique. Results: In treatment of chronic gastritis by Prof. GAO Zhong-ying there were 30 drugs with a higher use frequency of over 38 times, 94 commonly-used drug pairs with correlation coefficient of over 0.05, 11 commonly-used drug core combinations. Conclusion: The results attained with data mining technique for studying experience of famous and old TCM physicians conform to the clinical practice and the method is of an important significance for summarization of famous and old TCM physicians’ experiences.展开更多
Objective:To explore Yan Zhenghua’s drug selection rule for treating digestive system diseases using data mining.Methods:The 609 medical records of digestive system diseases treated by Yan Zhenghua were collected and...Objective:To explore Yan Zhenghua’s drug selection rule for treating digestive system diseases using data mining.Methods:The 609 medical records of digestive system diseases treated by Yan Zhenghua were collected and the herbs in these recipes were examined using a data mining technique.The correlativity between herb pairs and association rules was studied using an Apriori algorithm and the correlativity among multi-herbs was studied using a complex system entropy cluster technique.Results:Yan Zhenghua’s treatment of digestive system diseases featured 15 herbs prescribed at least 159 times each,22 herb pairs prescribed at least 155 times each,and eight frequently used herb core combinations.A confidence greater than 0.91 and a support level greater than 20%were achieved using the modified mutual information method.Conclusion:The data mining results conformed to findings from clinical practice.The data mining method is a valuable technique with which to study the experience of famous,elderly traditional Chinese medicine physicians.展开更多
Feature selection is always an important issue in the research on data mining technologies. However, the problem of optimal feature selection is NP hard. Therefore, heuristic approaches are more practical to actual le...Feature selection is always an important issue in the research on data mining technologies. However, the problem of optimal feature selection is NP hard. Therefore, heuristic approaches are more practical to actual learning systems. Usually, that kind of algorithm selects features with the help of a heuristic metric compactum to measure the relative importance of features in a learning system. Here a new notion of ‘system entropy’ is described in terms of rough set theory, and then some of its algebraic characteristics are studied. After its intrinsic value biase is effectively counteracted, the system entropy is applied in BSE, a new heuristic algorithm for feature selection. BSE is efficient, whose time complexity is lower than that of analogous algorithms; BSE is also effective, which can produce the optimal results in the mini-feature biased sense from varieties of learning systems. Besides, BSE is tolerant and also flexible to the inconsistency of a learning system, consequently able to elegantly handle data noise in the learning system.展开更多
A micro-level analysis on man-land system is important in understanding the content of human geography in rural areas, particularly in the different regions. This paper is based on a survey undertaken in the three vil...A micro-level analysis on man-land system is important in understanding the content of human geography in rural areas, particularly in the different regions. This paper is based on a survey undertaken in the three villages of Wugou Village, Hutuo Village, and Xiaonan Village of Gongyi City, ltenan Province in April 2003. The survey covers three types of economic and social activities from 214 households. Data collected include 120 attributes for each household. By using theories from the relevant disciplines such as geography, mathcmatics, physics, ecology, and system sciences, this paper develops a framework employing the concept of system entropy in the status function of the man-land system. In this framework, the entropy change is used to show the evolution of the system, and the entropy flow to express the flow among the spatial parts of the system. Following the framework, and using a large set of household data from surveys, the paper makes a quantitative analysis of the village-level man-land system from a micro-perspective. After a theoretical investigation, the corresponding strategies in the paper are then put forward in order to adjust the unbalanced trend of the village man-land system from both perspectives of small-area and individual actors.展开更多
The temporal evolution of entropy of Jiuzhaigou ecotourism areal system has been quantitatively analyzed by using equation of system entropy V = k In M - k In C. The computed entropy for Jiuzhaigou ecotourism areal sy...The temporal evolution of entropy of Jiuzhaigou ecotourism areal system has been quantitatively analyzed by using equation of system entropy V = k In M - k In C. The computed entropy for Jiuzhaigou ecotourism areal system for 20 years indicates a negative value during 1986-1996, which implies that the system had remained a healthy state during this period. The system entropy value, however, showed a constant increase since 1996 until it turned to be positive in 2000 when the system became chaotic. After 2000 the entropy value declined until 2003 when it escalated once again. By analyzing the causes and process of entropy change of the system, it is argued that fluctuation of entropy value is due to the overloading of tourist service capacity by tourism activities. It is desired to curb the flow of tourist volume and reinforce conservation efforts as well as, so that an ideal balance between conservation and development could be maintained.展开更多
The article gives the definition of the deflection from the equiprobability distribution(DFED), and proves that the entropy decreases with the increasing of DFED.
文摘Objective:To study on Prof. GAO Zhong-ying’s drug selection law for treatment of chronic gastritis with data mining technique. Methods: The 407 medical records of chronic gastritis treated by Prof. GAO Zhong-ying were collected and the study on these drugs in the recipes was carried out with data mining method. Among them, the recipe composed of one drug was studied with frequency statistical method, correlativity between drug pairs with improved mutual information, correlativity among multi-drugs with complex system entropy cluster technique. Results: In treatment of chronic gastritis by Prof. GAO Zhong-ying there were 30 drugs with a higher use frequency of over 38 times, 94 commonly-used drug pairs with correlation coefficient of over 0.05, 11 commonly-used drug core combinations. Conclusion: The results attained with data mining technique for studying experience of famous and old TCM physicians conform to the clinical practice and the method is of an important significance for summarization of famous and old TCM physicians’ experiences.
基金the National Science and Technology Support Program of China(No.2007BAI10B01)the Science and Technology Development Project of TCM of Beijing(No.JJ-2010-70)+1 种基金the Scientific Research Innovation Team Project of Beijing University of Chinese Medicine(No.2011-CXTD-14)the open project of key disciplines of Beijing University of Chinese Medicine(No.2013-ZDXKKF-19).
文摘Objective:To explore Yan Zhenghua’s drug selection rule for treating digestive system diseases using data mining.Methods:The 609 medical records of digestive system diseases treated by Yan Zhenghua were collected and the herbs in these recipes were examined using a data mining technique.The correlativity between herb pairs and association rules was studied using an Apriori algorithm and the correlativity among multi-herbs was studied using a complex system entropy cluster technique.Results:Yan Zhenghua’s treatment of digestive system diseases featured 15 herbs prescribed at least 159 times each,22 herb pairs prescribed at least 155 times each,and eight frequently used herb core combinations.A confidence greater than 0.91 and a support level greater than 20%were achieved using the modified mutual information method.Conclusion:The data mining results conformed to findings from clinical practice.The data mining method is a valuable technique with which to study the experience of famous,elderly traditional Chinese medicine physicians.
文摘Feature selection is always an important issue in the research on data mining technologies. However, the problem of optimal feature selection is NP hard. Therefore, heuristic approaches are more practical to actual learning systems. Usually, that kind of algorithm selects features with the help of a heuristic metric compactum to measure the relative importance of features in a learning system. Here a new notion of ‘system entropy’ is described in terms of rough set theory, and then some of its algebraic characteristics are studied. After its intrinsic value biase is effectively counteracted, the system entropy is applied in BSE, a new heuristic algorithm for feature selection. BSE is efficient, whose time complexity is lower than that of analogous algorithms; BSE is also effective, which can produce the optimal results in the mini-feature biased sense from varieties of learning systems. Besides, BSE is tolerant and also flexible to the inconsistency of a learning system, consequently able to elegantly handle data noise in the learning system.
基金Under the auspices of Key Program of National Natural Science Foundation of China (No.40535025), Planning Itemof Youthful Cadreman Teachers of University in Henan Province (No. DOC2005-461), the Social Science of Henan EducationalDepartment (No. 2005-ZX-238) and Key Program of Henan University's Fund (No. 04ZDRW009)
文摘A micro-level analysis on man-land system is important in understanding the content of human geography in rural areas, particularly in the different regions. This paper is based on a survey undertaken in the three villages of Wugou Village, Hutuo Village, and Xiaonan Village of Gongyi City, ltenan Province in April 2003. The survey covers three types of economic and social activities from 214 households. Data collected include 120 attributes for each household. By using theories from the relevant disciplines such as geography, mathcmatics, physics, ecology, and system sciences, this paper develops a framework employing the concept of system entropy in the status function of the man-land system. In this framework, the entropy change is used to show the evolution of the system, and the entropy flow to express the flow among the spatial parts of the system. Following the framework, and using a large set of household data from surveys, the paper makes a quantitative analysis of the village-level man-land system from a micro-perspective. After a theoretical investigation, the corresponding strategies in the paper are then put forward in order to adjust the unbalanced trend of the village man-land system from both perspectives of small-area and individual actors.
基金the National Basic Research Program of China (973 Program) (2003CB415201-5)
文摘The temporal evolution of entropy of Jiuzhaigou ecotourism areal system has been quantitatively analyzed by using equation of system entropy V = k In M - k In C. The computed entropy for Jiuzhaigou ecotourism areal system for 20 years indicates a negative value during 1986-1996, which implies that the system had remained a healthy state during this period. The system entropy value, however, showed a constant increase since 1996 until it turned to be positive in 2000 when the system became chaotic. After 2000 the entropy value declined until 2003 when it escalated once again. By analyzing the causes and process of entropy change of the system, it is argued that fluctuation of entropy value is due to the overloading of tourist service capacity by tourism activities. It is desired to curb the flow of tourist volume and reinforce conservation efforts as well as, so that an ideal balance between conservation and development could be maintained.
文摘The article gives the definition of the deflection from the equiprobability distribution(DFED), and proves that the entropy decreases with the increasing of DFED.
