Masao Mukaidono

A maximum-entropy approach to fuzzy clustering

In this paper, we propose a new approach to fuzzy clustering by means of a maximum-entropy inference (MEI) method. The resulting formulas have a better form and clearer physical meaning than those obtained by means of the fuzzy c-means (FCM) method. In order to solve the cluster validity problem, we introduce a structure strength function as clustering criterion, which is valid for any membership assignments, thereby being capable of determining the plausible number of clusters according to our subjective requisition. With the proposed structure strength function, we also discuss global minimum problem in terms of simulated annealing. Finally, we simulate a numerical example to demonstrate the approach discussed, and compare our results with those obtained by the traditional approaches.<<ETX>>

Fundamentals of fuzzy prolog

Abstract In this paper, a Fuzzy Prolog is introduced that is based on the fuzzy resolution principle. There are three levels of concern: (1) the fuzzy truth values of predicates that depend on several values of individual variables, (2) the weights of rules that depend on several fuzzy truth values of premise and conclusion, and (3) the confidence of resolvent that depends on the fuzzy resolution principle. With these three levels, we introduce fuzziness into the resolution principle and unification and cause fuzzy logical inference to be significant in Fuzzy Prolog when the values of all variables are taken in the closed interval [0, 1].

A fuzzy neural network for pattern classification and feature selection

A fuzzy neural network with memory connections for classification, and weight connections for selection is introduced, thereby solving simultaneously two major problems in pattern recognition: pattern classification and feature selection. The proposed network attempts to select important features from among the originally given plausible features, while maintaining the maximum recognition rate. The resulting value of weight connection represents the degree of importance of feature. Moreover, the knowledge acquired by the network can be described as a set of interpretable rules. The effectiveness of this new method has been validated by using Andersons IRIS data. The results are: first, the use of two features selected by our method from among the original four in the proposed network results in virtually identical classifier performance; and second, the constructed classifier is described by three simple rules that are of if-then form.

Gaussian clustering method based on maximum-fuzzy-entropy interpretation

Abstract A new method of fuzzy clustering is proposed. This is a complete Gaussian membership function derived by means of the maximum-entropy interpretation. Compared to the traditional fuzzy c-means (FCM) method, our approach exhibits the following two advantages: (1) having clearer physical meaning and well-defined mathematical features; (2) having an optimal choice for feature parameter σ in theory. Moreover, we also review some existing measures of uncertainty of fuzzy sets, and redefine fuzzy entropy as analogous to probabilistic entropy.

Fuzzy resolution principle

The resolution principle based on reduction and absurdum is extended from binary logic to fuzzy logic. The extension is dependent on introducing the concepts of fuzzy contradictory, contradictory degree, fuzzy resolvent, and confidence of resolvent. The concept of fuzzy resolvent is first interpreted, as it is the most important concept and is the basis of fuzzy resolution. Then the fuzzy resolution principle is considered for fuzzy propositional logic and extended to the fuzzy firs-order logic. The completeness of the fuzzy resolution principle is proved. The fuzzy resolution principle has been used as the basis of a powerful fuzzy Prolog system.<<ETX>>

Conceptual matching and its applications to selection of TV programs and BGMs

We propose a method for representing common concepts by fusing conceptual fuzzy sets (CFSs) with ontology. We also describe a method of conceptual matching for retrieving information that meets a users intentions. The matching is done based on the region of the ontological structure covered by the CFS representing the users intention as well as on the original keywords. We apply the proposed conceptual-matching method to two types of agents. One agent recommends TV programs to watch. The recommended programs have EPGs (electronic program guides) similar to those of previously watched programs or that contain words matching the learning data. Practical examples demonstrate that the proposed system recommend TV programs matching the users tastes. The other selects music matching the tone of a text composition.

Enumerating fuzzy switching functions and free kleene algebras

Abstract We investigate the free Kleene algebra on n free generators, FK( n ). This algebra is essentially the same as the set of n -variable fuzzy switching functions. The cardinality of FK( n ) has been previously determined only for n = 1, 2, and 3. We present a general method for enumeration problems of this kind. We show FK(4) has 160,297,985,276 elements. The final section contains new upper and lower bounds for the cardinality of FK( n ). We also consider the number of regular functions and show that there are 11,197,129,615, and 430,904,428,717 such functions in 1, 2, 3, and 4 variables.

Fuzzy functional dependency and its application to approximate data querying

Reviews a new definition of fuzzy functional dependency based on conditional probability and its application to approximate data reduction related to the operation of projection in classical relational databases in order to construct fuzzy integrity constraints. We introduce the concept of partial fuzzy functional dependency, which expresses the fact that a given attribute X does not determine Y completely, but in the partial area of X it might determine Y. Finally, we discuss another application of fuzzy functional dependency in constructing fuzzy query relations for data querying and approximate joins of two or more fuzzy query relations in the framework of an extended query system.

Conditional Probability Relations in Fuzzy Relational Database

In 1982, Buckles and Petry [1] proposed fuzzy relational database for incorporating non-ideal or fuzzy information in a relational database. The fuzzy relational database relies on the spesification of similarity relation [8] in order to distinguish each scalar domain in the fuzzy database. These relations are reflexive, symmetric, and max-min transitive. In 1989, Shenoi and Melton extended the fuzzy relational database model of Buckles and Petry to deal with proximity relation [2] for scalar domain. Since reflexivity and symmetry are the only constraints placed on proximity relations, proximity relation is considered as generalization of similarity relation. In this paper, we propose design of fuzzy relational database to deal with conditional probability relation for scalar domain. These relations are reflexive and not symmetric.We show that naturally relation between fuzzy information is not symmetric. In addition, we define a notion of redundancy which generalizes redundancy in classical relational database. We also discuss partitioning of domains with the objective of developing equivalence class.

The Japanese Smart Grid Initiatives, Investments, and Collaborations

A smart grid delivers power around the country and has an intelligent monitoring system, which not only keeps track of all the energy coming in from diverse sources but also can detect where energy is needed through a two-way communication system that collects data about how and when consumers use power. It is safer in many ways, compared with the current one-directional power supply system that seems susceptible to either sabotage or natural disasters, including being more resistant to attack and power outages. In such an autonomic and advanced-grid environment, investing in a pilot study and knowing the nation’s readiness to adopt a smart grid absolves the government of complex intervention from any failure to bring Japan into the autonomic-grid environment. This paper looks closely into the concept of the Japanese government’s ‘go green’ effort, the objective of which is to make Japan a leading nation in environmental and energy sustainability through green innovation, such as creating a low-carbon society and embracing the natural grid community. This paper paints a clearer conceptual picture of how Japan’s smart grid effort compares with that of the US. The structure of Japan’s energy sources is describe including its major power generation plants, photovoltaic power generation development, and a comparison of energy sources between Japan and the US. Japan’s smart community initiatives are also highlighted, illustrating the Japanese government planned social security system, which focuses on a regional energy management system and lifestyle changes under such an energy supply structure. This paper also discusses Japan’s involvement in smart grid pilot projects for development and investment, and its aim of obtaining successful outcomes. Engagement in the pilot projects is undertaken in conjunction with Japan’s attempt to implement a fully smart grid city in the near future. In addition, major smart grid awareness activities promotion bodies in Japan are discuss in this paper because of their important initiatives for influencing and shaping policy, architecture, standards, and traditional utility operations. Implementing a smart grid will not happen quickly, because when Japan does adopt one, it will continue to undergo transformation and be updated to support new technologies and functionality.