Yi-Chung Hu

Finding fuzzy classification rules using data mining techniques

Data mining techniques can be used to discover useful patterns by exploring and analyzing data, so, it is feasible to incorporate data mining techniques into the classification process to discover useful patterns or classification rules from training samples. This paper thus proposes a data mining technique to discover fuzzy classification rules based on the well-known Apriori algorithm. Significantly, since it is difficult for users to specify the minimum fuzzy support used to determine the frequent fuzzy grids or the minimum fuzzy confidence used to determine the effective classification rules derived from frequent fuzzy grids, therefore the genetic algorithms are incorporated into the proposed method to determine those two thresholds with binary chromosomes. For classification generalization ability, the simulation results from the iris data and the appendicitis data demonstrate that the proposed method performs well in comparison with other classification methods.

Discovering fuzzy association rules using fuzzy partition methods

Fuzzy association rules described by the natural language are well suited for the thinking of human subjects and will help to increase the flexibility for supporting users in making decisions or designing the fuzzy systems. In this paper, a new algorithm named fuzzy grids based rules mining algorithm (FGBRMA) is proposed to generate fuzzy association rules from a relational database. The proposed algorithm consists of two phases: one to generate the large fuzzy grids, and the other to generate the fuzzy association rules. A numerical example is presented to illustrate a detailed process for finding the fuzzy association rules from a specified database, demonstrating the effectiveness of the proposed algorithm.

Mining fuzzy association rules for classification problems

The effective development of data mining techniques for the discovery of knowledge from training samples for classification problems in industrial engineering is necessary in applications, such as group technology. This paper proposes a learning algorithm, which can be viewed as a knowledge acquisition tool, to effectively discover fuzzy association rules for classification problems. The consequence part of each rule is one class label. The proposed learning algorithm consists of two phases: one to generate large fuzzy grids from training samples by fuzzy partitioning in each attribute, and the other to generate fuzzy association rules for classification problems by large fuzzy grids. The proposed learning algorithm is implemented by scanning training samples stored in a database only once and applying a sequence of Boolean operations to generate fuzzy grids and fuzzy rules; therefore, it can be easily extended to discover other types of fuzzy association rules. The simulation results from the iris data demonstrate that the proposed learning algorithm can effectively derive fuzzy association rules for classification problems.

Grey self-organizing feature maps

In each training iteration of the self-organizing feature maps (SOFM), the adjustable output nodes can be determined by the neighborhood size ofthe winning node. However, it seems that the SOFM ignores some important information, which is the relationships that actually exist between the input training data and each adjustable output node, in the learning rule. By viewing input data and each adjustable node as a reference sequence and a comparative sequence, respectively, the grey relations between these sequences can be seen. This paper thus incorporates the grey relational coe8cient into the learning rule ofthe SOFM, and a grey clustering method, namely the GSOFM, is proposed. From the simulation results, we can see that the best result ofthe proposed method applied f or analysis ofthe iris data outperf orms those ofother known unsupervised neural network models. Furthermore, the proposed method can e:ectively solve the traveling salesman problem. c 2002 Elsevier Science B.V. All rights reserved.

Fuzzy integral-based perceptron for two-class pattern classification problems

The single-layer perceptron with single output node is a well-known neural network for two-class classification problems. Furthermore, the sigmoid or logistic function is usually used as the activation function in the output neuron. A critical step is to compute the sum of the products of the connection weights with the corresponding inputs, which indicates the assumption of additivity among individual variables. Unfortunately, because the input variables are not always independent of each other, an assumption of additivity may not be reasonable enough. In this paper, the inner product can be replaced with an aggregation value obtained by a useful fuzzy integral by viewing each of the connection weights as a value of a @l-fuzzy measure for the corresponding variable. A genetic algorithm is then employed to obtain connection weights by maximizing the number of correctly classified training patterns and minimizing the errors between the actual and desired outputs of individual training patterns. The experimental results further demonstrate that the proposed method outperforms the traditional single-layer perceptron and performs well in comparison with other fuzzy or non-fuzzy classification methods.

A PROMETHEE-based classification method using concordance and discordance relations and its application to bankruptcy prediction

Outranking relation theory has been widely used to study pattern classification. Here we propose a classification method with concepts from the flows used in PROMETHEE methods, which are extensively applied in multi-criteria decision aids. PROMETHEE uses a flow, generated on the basis of a preference index and measured by various preference functions for each criterion, to represent the preference intensity for one pattern over another pattern. However, only criteria that are concordant with the preference contribute to a preference index. In the present study, the opinions from discordant criteria are also taken into account. The proposed method newly defines an overall preference index using both concordance and discordance relations for ordinal sorting problems. The final classification decision for a new pattern depends on its net flow. The criteria weights are determined using a genetic-algorithm-based approach. Empirical results obtained for a real-world problem regarding bankruptcy prediction demonstrate that the proposed method performs well compared to other well-known classification methods.

On generalized geometric programming problems with non-positive variables

Generalized geometric programming (GGP) problems occur frequently in engineering design and management. Some exponential-based decomposition methods have been developed for solving global optimization of GGP problems. However, the use of logarithmic/exponential transformations restricts these methods to handle the problems with strictly positive variables. This paper proposes a technique for treating non-positive variables with integer powers in GGP problems. By means of variable transformation, the GGP problem with non-positive variables can be equivalently solved with another one having positive variables. In addition, we present some computationally efficient convexification rules for signomial terms to enhance the efficiency of the optimization approach. Numerical examples are presented to demonstrate the usefulness of the proposed method in GGP problems with non-positive variables.

Finding useful fuzzy concepts for pattern classification using genetic algorithm

In this paper, a fuzzy classifier is treated as a fuzzy information retrieval system. To construct such a system, a fuzzy data mining method is employed to determine useful fuzzy concepts. Subsequently, each of the classes and patterns can be represented by a fuzzy set of useful fuzzy concepts. From the viewpoint of fuzzy information retrieval, a pattern can be categorized into one class if there exists a maximum degree of similarity between them. The genetic algorithm (GA), whose objective is to find a compact set consisting of useful fuzzy concepts with high classification capability, is further employed to automatically determine parameter specifications that are not easily specified by users. To evaluate classification performance of the proposed method, computer simulations are performed on some well-known classification problems, demonstrating that the generalization ability of the proposed method is comparable to other fuzzy classification methods.

Finding multiple solutions to general integer linear programs

Integer linear programming (ILP) problems occur frequently in many applications. In practice, alternative optima are useful since they allow the decision maker to choose from multiple solutions without experiencing any deterioration in the objective function. This study proposes a general integer cut to exclude the previous solution and presents an algorithm to identify all alternative optimal solutions of an ILP problem. Numerical examples in real applications are presented to demonstrate the usefulness of the proposed method.

Assessing weights of product attributes from fuzzy knowledge in a dynamic environment

Abstract Fuzzy knowledge of consumers’ frequent purchase behaviors can be extracted from transaction databases. To effectively supporting decision makers, it is necessary to use fuzzy knowledge to assess weights or degrees of consumers’ attentiveness to product attributes. From the standpoint of habitual domains, frequent purchase behaviors can be viewed as ideas that are contained in the reachable domain of customers. In addition, this reachable domain is changeable with time, due to the dynamic environment. This paper thus proposes a two-phase learning method with adaptive capability. The first phase builds a fuzzy knowledge base by discovering frequent purchase behaviors from transaction databases; the second phase finds weights of product attributes by a single-layer perceptron neural network. Indeed, customers are asked to evaluate alternatives and attributes through questionnaire. Then, each alternative can be transformed into a piece of input training data for the neural network by the fuzzy knowledge base and part-worths of attributes’ levels. After completing the training task, we can find weights from connection weights. Simulation results demonstrate that the proposed methods can use fuzzy knowledge to effectively find customers’ attentive degrees of attributes.