John Yen

Simplifying fuzzy rule-based models using orthogonal transformation methods

An important issue in fuzzy-rule-based modeling is how to select a set of important fuzzy rules from a given rule base. Even though it is conceivable that removal of redundant or less important fuzzy rules from the rule base can result in a compact fuzzy model with better generalizing ability, the decision as to which rules are redundant or less important is not an easy exercise. In this paper, we introduce several orthogonal transformation-based methods that provide new or alternative tools for rule selection. These methods include an orthogonal least squares (OLS) method, an eigenvalue decomposition (ED) method, a singular value decomposition and QR with column pivoting (SVD-QR) method, a total least squares (TLS) method, and a direct singular value decomposition (D-SVD) method. A common attribute of these methods is that they all work on a firing strength matrix and employ some measure index to detect the rules that should be retained and eliminated. We show the performance of these methods by applying them to solving a nonlinear plant modeling problem. Our conclusions based on analysis and simulation can be used as a guideline for choosing a proper rule selection method for a specific application.

Improving the interpretability of TSK fuzzy models by combining global learning and local learning

The fuzzy inference system proposed by Takagi, Sugeno, and Kang, known as the TSK model in fuzzy system literature, provides a powerful tool for modeling complex nonlinear systems. Unlike conventional modeling where a single model is used to describe the global behavior of a system, TSK modeling is essentially a multimodel approach in which simple submodels (typically linear models) are combined to describe the global behavior of the system. Most existing learning algorithms for identifying the TSK model are based on minimizing the square of the residual between the overall outputs of the real system and the identified model. Although these algorithms can generate a TSK model with good global performance (i.e., the model is capable of approximating the given system with arbitrary accuracy, provided that sufficient rules are used and sufficient training data are available), they cannot guarantee the resulting model to have a good local performance. Often, the submodels in the TSK model may exhibit an erratic local behavior, which is difficult to interpret. Since one of the important motivations of using the TSK model (also other fuzzy models) is to gain insights into the model, it is important to investigate the interpretability issue of the TSK model. We propose a new learning algorithm that integrates global learning and local learning in a single algorithmic framework. This algorithm uses the idea of local weighed regression and local approximation in nonparametric statistics, but remains the component of global fitting in the existing learning algorithms. The algorithm is capable of adjusting its parameters based on the users preference, generating models with good tradeoff in terms of global fitting and local interpretation. We illustrate the performance of the proposed algorithm using a motorcycle crash modeling example.

Generalizing the Dempster-Schafer theory to fuzzy sets

A generalization of the Dempster-Schafer (D-S) theory to deal with fuzzy sets is described in which the belief and plausibility functions are treated as lower and upper probabilities. It is shown that computing the degree of belief in a hypothesis in the D-S theory can be formulated as an optimization problem. The extended belief function is thus obtained by generalizing the objective function and the constraints of the optimization problem. To combine bodies of evidence that may contain vague information, Dempsters rule (1967) is extended by (1) combining generalized compatibility relations based on the possibility theory, and (2) normalizing combination results to account for partially conflicting evidence. The generalization not only extends the application of the D-S theory but also illustrates a way that probability theory and fuzzy set theory can be integrated in a sound manner in order to deal with different kinds of uncertain information in intelligent systems. >

A hybrid approach to modeling metabolic systems using a genetic algorithm and simplex method

One of the main obstacles in applying genetic algorithms (GAs) to complex problems has been the high computational cost due to their slow convergence rate. We encountered such a difficulty in our attempt to use the classical GA for estimating parameters of a metabolic model. To alleviate this difficulty, we developed a hybrid approach that combines a GA with a stochastic variant of the simplex method in function optimization. Our motivation for developing the stochastic simplex method is to introduce a cost-effective exploration component into the conventional simplex method. In an attempt to make effective use of the simplex operation in a hybrid GA framework, we used an elite-based hybrid architecture that applies one simplex step to a top portion of the ranked population. We compared our approach with five alternative optimization techniques including a simplex-GA hybrid independently developed by Renders-Bersini (R-B) and adaptive simulated annealing (ASA). Our empirical evaluations showed that our hybrid approach for the metabolic modeling problem outperformed all other techniques in terms of accuracy and convergence rate. We used two additional function optimization problems to compare our approach with the five alternative methods.

House of quality: A fuzzy logic-based requirements analysis

House Of Quality (HOQ) is one of the matrices of an iterative process called Quality Function Deployment (QFD). The foundation of the HOQ is the belief that products should be designed to reflect customers’ desires and taste. HOQ is performed by a multidisciplinary team representing marketing, design engineering, manufacturing engineering, and any other functions considered critical by the company. In general, it provides a framework in which all participants can communicate their thoughts about a product. More specifically, HOQ is often used to identify the relationships between requirements based on diAerent viewpoints. There are two issues in analyzing these requirements using HOQ. First, requirements are often described informally using vague terms. However, lack of formal way in interpreting the semantics of these requirements makes it diAcult to determine if a realization of the system meets its customer’s needs. Second, identifying relationships between requirements is often time consuming. Sometimes, it is diAcult to arrive at a group consensus on a particular relationship between requirements. To address these issues, we have developed a fuzzy logic-based extension to HOQ for capturing imprecise requirements to both facilitate communication of team members and have a formal representation of requirements. Based on this representation, we developed a heuristic inference scheme to reason about the implicit relationships between requirements. We illustrate our approach using a textile mill supply business application. ” 1999 Elsevier Science B.V. All rights reserved.

A fuzzy logic based extension to Payton and Rosenblatt's command fusion method for mobile robot navigation

Payton and Rosenblatt (1990) have proposed a command fusion method for combining outputs of multiple behaviors in a mobile robot navigation system such that information loss due to command fusion can be reduced. Using linguistic fuzzy rules to explicitly capture heuristics implicit in the Payton-Rosenblatt approach, we have extended their approach to a fuzzy logic architecture for mobile robot navigation in dynamic environments, which is simpler and easier to understand and modify. We have also developed and empirically tested a new defuzzification technique for alleviating difficulties in applying existing defuzzification methods to mobile robot navigation control. >

Emotionally expressive agents

The ability to express emotions is important for creating believable interactive characters. To simulate emotional expressions in an interactive environment, an intelligent agent needs both an adaptive model for generating believable responses, and a visualization model for mapping emotions into facial expressions. Recent advances in intelligent agents and in facial modeling have produced effective algorithms for these tasks independently. We describe a method for integrating these algorithms to create an interactive simulation of an agent that produces appropriate facial expressions in a dynamic environment. Our approach to combining a model of emotions with a facial model represents a first step towards developing the technology of a truly believable interactive agent which has a wide range of applications from designing intelligent training systems to video games and animation tools.

An adaptive algorithm for learning changes in user interests

In this paper, we describe a new scheme to learn dynamic users interests in an automated information filtering and gathering system running on the Internet. Our scheme is aimed to handle multiple domains of long-term and short-term users interests simultaneously, which is learned through positive and negative users relevance feedback. We developed a 3-descriptor approach to represent the users interest categories. Using a learning algorithm derived for this representation, our scheme adapts quickly to significant changes in user interest, and is also able to learn exceptions to interest categories.

Application of statistical information criteria for optimal fuzzy model construction

Theoretical studies have shown that fuzzy models are capable of approximating any continuous function on a compact domain to any degree of accuracy. However, constructing a good fuzzy model requires finding a good tradeoff between fitting the training data and keeping the model simple. A simpler model is not only easily understood, but also less likely to overfit the training data. Even though heuristic approaches to explore such a tradeoff for fuzzy modeling have been developed, few principled approaches exist in the literature due to the lack of a well-defined optimality criterion. In this paper, we propose several information theoretic optimality criteria for fuzzy models construction by extending three statistical information criteria: 1) the Akaike information criterion [AIC] (1974); 2) the Bhansali-Downham information criterion [BDIC] (1977); and 3) the information criterion of Schwarz (1978) and Rissanen (1978) [SRIC]. We then describe a principled approach to explore the fitness-complexity tradeoff using these optimality criteria together with a fuzzy model reduction technique based on the singular value decomposition (SVD). The role of these optimality criteria in fuzzy modeling is discussed and their practical applicability is illustrated using a nonlinear system modeling example.

Advances in Web Mining and Web Usage Analysis

Adaptive Website Design Using Caching Algorithms.- Incorporating Usage Information into Average-Clicks Algorithm.- Nearest-Biclusters Collaborative Filtering with Constant Values.- Fast Categorization of Web Documents Represented by Graphs.- Leveraging Structural Knowledge for Hierarchically-Informed Keyword Weight Propagation in the Web.- How to Define Searching Sessions on Web Search Engines.- Incorporating Concept Hierarchies into Usage Mining Based Recommendations.- A Random-Walk Based Scoring Algorithm Applied to Recommender Engines.- Towards a Scalable kNN CF Algorithm: Exploring Effective Applications of Clustering.- Detecting Profile Injection Attacks in Collaborative Filtering: A Classification-Based Approach.- Predicting the Political Sentiment of Web Log Posts Using Supervised Machine Learning Techniques Coupled with Feature Selection.- Analysis of Web Search Engine Query Session and Clicked Documents.- Understanding Content Reuse on the Web: Static and Dynamic Analyses.