Extracting Rules from Composite Neural Networks for Medical Diagnostic Problems

Recently, neural networks have been applied to many medical diagnostic problems because of their appealing properties, robustness, capability of generalization and fault tolerance. Although the predictive accuracy of neural networks may be higher than that of traditional methods (e.g., statistical methods) or human experts, the lack of explanation from a trained neural network leads to the difficulty that users would hesitate to take the advise of a black box on faith alone. This paper presents a class of composite neural networks which are trained in such a way that the values of the network parameters can be utilized to generate If-Then rules on the basis of preselected meaningful coordinates. The concepts and methods presented in the paper are illustrated through one practical example from medical diagnosis.     

Ӧ�õز���Ȼ��б���ɵĶ����ам���

通过对川西南地区常规钻井井斜资料的统计和整理,探索出本地区倾斜地层中钻井的地层自然造斜规律。提出沿地层自然造斜的相反方向移动可计算到的距离作为地面勘定井位的新方法。经自19井、音27井、界27井现场验证,均钻达目的层的靶心近处。     

An Operational Approach to Belief Revision

A deduction system,called RE-proof system,is constructed for generating the revisions of first order belief sets.When a belief set is rejected by a given fact,all maximal subsets of the belief set consistent with the fact can be deduced from the proof system.The soundness and completeness of the RE-proof system are proved,which imply that there exists a resolution method to decide whether a revision retains a maximal subset of a belief set.     

计算机化织物悬垂性测试器

用最低限度硬件和最合理软件研制的悬垂性测试器,测量精确、操作简便、效果显著。     

在辐射工作中推广 ALARA 原则的价值

本文论述了 ALARA(As Law As Reasonal Achievable)原则的基本概念,以实例说明了 ALARA 原则在辐射工作中的应用价值。实践证明,认真执行 ALARA 原则,必能将辐射防护工作提高到一个新的水平。     

An evaluation of two approaches to discipline in industry.

A case involving clear-cut violation of a no-smoking rule, with a clearly defined penalty, was role-played by groups of industrial supervisors acting as foreman, union steward, and worker. After role-playing, 52% of the foremen altered their decisions and reached "adjusted" decisions (human relations approach); 35% persisted in following the rule (judicial approach); 13% failed to settle the matter in the time allowed. The human relations approach was more successful than the judicial in that the participants were better satisfied. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A Comparison of Two Approaches to Data Mining from Imbalanced Data

Our objective is a comparison of two data mining approaches to dealing with imbalanced data sets. The first approach is based on saving the original rule set, induced by the LEM2 (Learning from Example Module) algorithm, and changing the rule strength for all rules for the smaller class (concept) during classification. In the second approach, rule induction is split: the rule set for the larger class is induced by LEM2, while the rule set for the smaller class is induced by EXPLORE, another data mining algorithm. Results of our experiments show that both approaches increase the sensitivity compared to the original LEM2. However, the difference in performance of both approaches is statistically insignificant. Thus the appropriate approach for dealing with imbalanced data sets should be selected individually for a specific data set.     

Manufacturing process performance prediction by integrating crisp and granular information

This study deals with the integration of crisp and granular information for predicting the performance of a manufacturing process. Supporting and computing a set of two If-Then rules is considered the central idea for this integration. In these rules, the antecedent part deals with the recommended ranges of the control variables of the process, while the consequent part deals with the acceptable ranges of the performance measures of the process. The rules specify that if the control variables are kept within their recommended ranges, then it is likely or unlikely to get the performance measures within their acceptable ranges. The rules are supported by using the following conditional probabilities: the probability of getting the performance measures acceptable given that the control variables are within their recommended ranges (which should be likely), and the probability of getting performance measures acceptable given that the control variables are not within their recommended ranges (which should be unlikely). The remarkable thing is that both acceptable ranges and recommended ranges are subjectively defined concepts. So are likelihood perceptions such as likely and unlikely. Therefore, all of them can be defined by using some kind of fuzzy-granular information. The usefulness of this new approach is demonstrated by solving a machining decision-making problem (select cutting conditions and inserts satisfying subjectively defined surface finish requirement in terms of roughness and fractal dimension of machined surface). Further study should be directed toward understanding these rules in the context of predictive process planning.This revised version was published in June 2005 with corrected page numbers.