Atsuko Mutoh

A method to generate writing-brush-style Japanese Hiragana character calligraphy

We propose a method to generate writing-brush-style Japanese Hiragana characters. The information obtained while inputing characters with an electronic pen, such as the pen position, pen pressure and pen speed, are used as input. Since such information is different from person to person, the generated results of our method can reflect a users individuality. A fuzzy spline curve is used for the selection of control points. This enables us to use only a few control points to obtain the curve with the a very approximate shape of the sampling point queue. Moreover we propose a wielding-pen-style migration rule by analyzing the process of calligraphic writing by hand. The experimental results show that the proposed method is a reasonable and effective method for generating writing-brush-style Hiragana calligraphy using an electronic pen.

An Evolutionary Method Using Crossover in a Food Chain Simulation

A gene expression system n-BDD (n-output Binary Decision Diagram) was proposed in order to investigate co-evolution[5]. Although the system is suitable for behavior models of agents, it does not include crossover. This paper proposes a crossover operation using Bryants Apply operation[2]. The operation makes an n-BDD probabilistically inherit two functions expressed by two n-BDDs. In an experiment the proposed method had more than 40% high fitness than the conventional method. Moreover, in another environment where carnivores and herbivores are co-evolved, we have seen a food chain relation.

Concept lattice reduction using attribute inference

Formal Concept Analysis (FCA) Is a data analysis method and it outputs a concept structure called a concept lattice. One of the problems of FCA is that the size of a concept lattice becomes far larger as data become larger. Various methods for reducing a concept lattice have been proposed, but they have disadvantage, e.g. reduced one is not a lattice. In this paper, we propose a method for reduction using attribute inference based on an approximate implication. We also evaluated some methods regarding that a reduced lattice has noise.

Grouping Methods for Generating Friendship Based on Network Properties

This paper investigates the effect of group work with the assumption of three motivators to make friends. Obeying the assumption we proposed twelve variation of methods for grouping students. The effects are evaluated by some measures from social network analysis and by the changes of real friendship networks, which are observed by a friendship prediction method. The proposed methods brought new friendship among students to classes and made rearrange of community structure.

Efficient real-coded genetic algorithms with flexible-step crossover

Real-coded genetic algorithms (GAs) are effective methods for function optimization. Generally speaking, the major crossover methods used in real-coded GAs require a large execution time for calculating the fitness of many children at each crossover. Thus, a new crossover method is needed for searching such a large search space efficiently. A novel crossover method that generates children stepwise is proposed and applied to the conventional generation-alternation model. In experiments based on standard test functions and actual problems, the proposed model found an optimal solution 30-50% faster than did the conventional model.

A Proposal of an Efficient Crossover Using Fitness Prediction and Its Application

Genetic algorithm (GA) is an effective method of solving combinatorial optimization problems. Generally speaking most of search algorithms require a large execution time in order to calculate some evaluation value. Crossover is very important in GA because discovering a good solution efficiently requires that the good characteristics of the parent individuals be recombined. The Multiple Crossover Per Couple (MCPC) is a method that permits a variable number of children for each mating pair, and MCPC generates a huge search space. Thus this method requires a huge amount of execution time to find a good solution. This paper proposes a novel approach to reduce time needed for fitness evaluation by “prenatal diagnosis” using fitness prediction. In the experiments based on actual problems, the proposed method found an optimum solution 50% faster than the conventional method did. The experimental results from standard test functions show that the proposed method using the Distributed Genetic Algorithm is applicable to other problems as well.

Fuzzy reasoning for image compression using adaptive triangular plane patches

In this article, we present a method called adaptive patch adjustment that improves the performance of digital image data compression using triangular plane patches. The method is designed to adaptively adjust the three-dimension position of triangular plane patches that approximate the corresponding luminance curved surfaces of an original image. Such an adjustment considers the influence of all pixels contained in the projection of a patch, instead of defining a patch by only three pixels at the vertices. The influence is described and calculated with a soft computing technique, the simplified fuzzy reasoning. Experimental results show that such a flexible strategy significantly reduces the average distortion between the reconstructed image and the original one, avoiding excess block splitting, and as a result, increasing the data compression rate.

Analysis of characteristic motions and their relations in radio gymnastic exercises

This paper focuses on the hypothesis that some of elemental motions are classified into several groups which may correspond to cultural, geographical or generational human groups. We propose a method to find characteristic motions which express differences of different human groups. We used a method which describes an activity as a sequence of symbols. The proposed method discovers characteristic patterns by observing relation among frequent sub-sequences in the sequences. We applied the method to radio gymnastic exercises, and discovered characteristic patterns that group the exercisers.

Estimation of Phyletic Trees from Cladograms and Birth Orders

Abstract The purpose of computational phylogenetics is to assemble a branching diagram or tree that represents a hypothesis regarding the evolutionary relationships of an entity set. Phyletic trees and cladograms are well-known methods for expressing phyletic relationships. Although many estimating methods for cladograms have been proposed, few studies have examined automatic estimation of phyletic trees because, in our opinion, most biological entities do not have birth year information. On the other hand, targets in cultural phylogenetics may have birth year information. Therefore, we propose a method to estimate phyletic trees for cultural phylogenetics using estimated cladograms and birth order information. First, we define necessary conditions for estimating phyletic trees from cladograms and birth order. We then propose an algorithm for estimating phyletic trees that satisfy these conditions. We demonstrate that the phyletic trees estimated by the proposed algorithm satisfy the defined conditions. Our experimental results show that the proposed estimation method obtained approximately 70% estimation accuracy for some targets.

Clustering Mutual Funds Based on Investment Similarity

Abstract It is risky to invest to single or similar mutual funds because the variance of the return becomes large. Mutual funds are categorized based on the investment strategy by a company that rated funds based on performance, but the fund categories are different from its actual operations. While some previous studies have proposed methods to cluster mutual funds based on the historical performances, we cannot apply these methods to new mutual funds. In this paper, we clusters mutual funds based on the investment similarity instead of the historical performances. The contributions of this paper are: 1. To propose two new methods for classifying mutual funds based on the investment similarity, 2. To evaluate the proposed methods based on actual 551 Japanese mutual funds.