Since neural networks in the brain have superior information processing functions, many investigators are modeling biological neurons and neural networks. Furthermore, a number of studies have recently been made on hardware models of asynchronous neural networks because their purpose is to apply a scientific approach to the brain. In this paper, the approach to the information processing function of the brain using hardware models is described.

View full abstract

The signals of acceleration plethysmogram is obtained as a fingertip content pulse wave detected by an optical sensor. It is observed nonivasively and is used mainly for estimation of arteriosclerosis and blood vessel age. In the estimation and classification of acceleration plethysmogram, the traditional method has a problem that its method cannot classify the plethysmogram exactly because of imperfect sampling of its waveform. In this paper, the authors propose a method of applying fuzzy neural network to taking the precise waveform information in the classification of plethysmogram data. The authors add a technique of genetic algorithm to the optimization of fuzzy reasoning using the steepest descent method. In a technique using the genetic algorithm, the gene can select some kinds of MSFs. This method models acceleration plethysmogram. In addition, the authors take the values of the waveform out of the modeling data as a vector, and classify the data of plethysmogram using self-organizing map. The advantages of this new method have been proved by comparing to the traditional method.

View full abstract

Spinal deformity is one of serious disease and it is mainly suffer by teenagers during their growth stage particularly fifth year in the elementary school to second year in the middle school. To detect the spinal deformity, medical doctors check a large number of moire images for mass screening. Therefore realization of automated spinal deformity inspection based on the moire images has long been desired among orthopedists. In this paper, we propose a new method for spinal deformity detection based on four statistical features from the difference of symmetric degree on moire topographic images. We perform the proposed technique to 1200 real moire images in the classification employing Artificial Neural Networks and Support Vector Machines. The method can classify as normal or abnormal from the moire topographic images automatically.

View full abstract

The primary prevention of lifestyle related disease are essential medical research themes. It is said that treating a disease before it arises is important in traditional Chinese medicine (TCM). Therefore, we investigated of diagnostic methods of TCM. The purpose of this study attempt constructing the Health Supporting System using TCM. The results of the health survey in TCM can take the changes in the state of the mind and body was proved in this investigation.

View full abstract

Improvements effaces after facial laser treatment in the plastic and reconstructive surgery were conventionally judged by the subjective evaluation. Objective evaluation methods were earnestly desired. In this paper, the imaging data of faces of 42 patients in the hospital by the digital camera was analyzed. This imaging data has the numerical data with color information of RGB. We deal with the digital information of the skin color classified into four groups of "Dark", "Grey (dark)", "Grey (light)" and Healthy skin corresponding by the subjective evaluation of medical doctors and analyzed this digital information of RGB data. From the analytical result, we could divide the digital information of RGB into four regions. Moreover, for the healthy skin we showed to classify the facial color into three categories of "dark-complexioned", "external color" and "pale-complexioned". This result would suggest giving a fundamental basis to the objective method of evaluation after laser treatment.

View full abstract

This paper discusses fuzzy discriminant analysis for diabetes data by using a simplified distance-type reasoning method, which is a simplified version of distance-type fuzzy reasoning method. Moreover, learning algorithm is proposed for the distance-type reasoning method and applied to a diabetes diagnostic system, showing the satisfactory learning results.

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

The dynamic behavior ofnano-scale magnet in materials is not well known. Although the interaction of magnetic force is clear, interactions between the coat of the magnet and the solvent molecules are not so clear. So the basic knowledge on the dynamic movement in the various materials should be accumulated. Using strong photon beams in SPring-8 facility, we trace the magnet and investigate the response of the magnets under the outer magnetic fields.

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

A cluster analysis method is proposed in this paper. As benchmark data, the Fisher's iris dataset and Wine recognition data were used. As a result of the numerical experiment, a clustering method by the dendrogram took 97 % in accuracy. It is difficult to display a multi-dimensional data by the dendrogram in the one dimension. The ultimate of the visualization is 3 dimensional expressions. We can conclude that it should be the best way that a multi-dimensional data is expressed by a sphere where the phase relationship is smooth.

View full abstract

In this article, we describe a Web browsing method with an automatic color correction (palette changing) for personal user's visibility. Especially we describe a paired comparison test and SOM (Self-Organizing Map) analysis for white background and chromatic character colors, and we consider our proposed "Web Color Set Prediction Method" with SOM for personal visibility on Web browsing. We are evaluating our web application system for this method as CGI (Common Gateway Interface) software on a HTTP server of the Internet. Since a user profiling is required beforehand for every user, we have to consider about this problem with SOM. The proposed method is available for this problem by the 9 conditions of the prediction method, which are "achromatic", "low luminance group (B-R-M)", "high luminance group (G-C-Y)", and fundamental 6 color series.

View full abstract

In this article, we describe about an analysis of fundamental visibility on Web color sets by Self-Organizing Maps (SOM), and a paired comparison test for its training. In recent years, people in many age groups use the Web frequently. However, there are few Web contents in consideration of their accessibilities. Therefore, there are also many pages that are hard to see for people in a specific age group (elderly people). We think that the visibility of the Web will be very important in the near future. As visibility, we focused only on the combination of character and background colors, which is called color sets, among the design-elements of Web contents. In the combination of character and background colors, we conducted the paired comparison test for collecting the standard data of visibility, and analyzed the paired comparison data using the Self-Organization Maps.

View full abstract

Fuzzy Analytic Hierarchy Process (Fuzzy AHP) consists of a hierarchical structure and link weights which are obtained by a linear programming. The AHP can be used to evaluate uncertainty in decision problems. Using of matrices pair-wise comparison the AHP steers the evaluation of data to the agreement with practical data. The fuzzy AHP approach can estimate interval priorities among the items discussed. These interval weights are interpreted in terms of the concept of possibility and express the range of the possibility. The method decides the interval weights so as to minimize the range included in the given data. The rage of the possibility can be illustrated as the interval or width of calculated values. Today, there are a number of companies which contribute to Official Development Assistance (ODA). The ODA is publicized at each of projects, contributions and companies on their website. Each donation and contribution are opened on the website as well. The objective of this paper is to evaluate these companies in terms of the best performance which classifies the support of donations for the ODA into 4 fields: infrastructure, medical service, education and security.

View full abstract

Generally, we could efficiently analyze the inexact information and investigate the fuzzy relation by applying the fuzzy graph theory. We would extend the fuzzy graph theory, and propose a fuzzy node fuzzy graph. Since a fuzzy node fuzzy graph is complicated to analyze, we would transform it to a simple fuzzy graph by using T-norm family. In this paper, we would discuss about the decision analysis of the optimal fuzzy graph {G_λ} in the fuzzy graph sequence {G_λ}. Moreover, we would illustrate its practical effectiveness with the case study concerning sociometry analysis.

View full abstract

This paper describes a concept of decision making support system using DP. The system has been developed using Web and XML technology, and supports man for his dynamical and effective decision. It is hopefiil that the support of human decision making and action, in general, will be capable by the information obtained from this system.

View full abstract

In this paper, a behavior emergence model with curiosity is proposed. The proposed model is applied to an agent of "Optimal Patch Use". The agent changes the strategy according to a present degree of full stomach. The agent with curiosity searches efficiently by diversive curiosity and specific curiosity's effects. The effectiveness of the proposed model is verified by simulation of "Optimal Patch Use".

View full abstract

Advanced industrial societies have created routine tasks that involve production line positions, limited positions, etc. and do not offer any opportunities for achievement, recognition, psychological growth, or other sources of satisfaction. One of the main reasons for dissatisfaction can be routine. In this paper, we build a model of a workplace where employees in a variety of job functions are sharing tasks, information, etc. through close interpersonal relationships, and we suppose a personnel network which contains strong terms of mutual understanding. In this paper, we apply double-stranded DNA molecules to this job rotation problem.

View full abstract

A bio-inspired computing method with fixed-length DNA to solve a system optimization is presented in this paper. The elevator dispatching problem is taken as an example, the fixed-length DNA strands are used in representing the nodes and costs, where the costs are varied by the melting temperature of DNA strands. The optimal solution to a 6-story 2-elevator dispatching problem is searched by biochemical techniques based on the thermodynamic properties of designed DNA strands. This research has shown that bio-inspired computing has the potential to solve the engineering applications.

View full abstract

It is difficult to recognize the state of a human body. In this paper we employ biometrics in order to recognize human behavior. Information obtained form human bodies such as temperature, blood pressure, α brainwave and etc. can be employed to recognize the state of a human body, in other words, the human behaviors. The objective of this paper is to achieve the recognition of the state whether a human is active or relaxed by his biometrics. It is required to recognize the aged person's behavior.

View full abstract

Our purpose is to study the effect on the blood flow caused by the valve in blood vessel. We examine the possibility that thrombosis is caused by pressing the artificial valve. We tried to solve the flow of blood by numerical analysis with an incompressibility Navier-Stokes equation. We supposed the static boundary condition about vessel shape, although realitic shape was dynamic, and the valve of blood vessels changed by a flow and pressure of bloodstream.

View full abstract

In the range of about ISOObp in length of 3368 type strains of 16SrDNA, A shorter DNA of about 500bp are cut out using forward and backward primers. The information quantity of the shorter DNA is reduced to simply about one third. The method to cut out the 500bp is considerably simple, so it is useful in an experimental side. Our knowledge is accumulated by the short DNA based on this method. In order to make clarified whether the knowledge based on the shorter DNA is meaningful or not, we discuss about the quantity of the information.

View full abstract

The dynamic behavior ofnano-scale magnets in materials is not -well known in vivo.. Although the interaction of magnetic force is clear, comportments of nano-magnets in the vivo or plants are not so clear. So the basic knowledge on the dynamic movement in Tanaoetum Vulgra instead of animals should be accumulated. Using strong photon beams in SPring-8 facility, we trace the magnets and investigate the accumulation of the magnets in Tanaoetum Vulgra.

View full abstract

In this paper, an orthognathic surgery support system, in which an esthetic score of postoperative profile is considered, is proposed. The Self-Organizing Relationship Network (SORN) is used for extracting a desired relationsihp between features before surgery and hard tissue movement. The SORN also generates classification maps of features and movements. The reasonable hard tissue can be estimated by observing these two maps.

View full abstract

The study of finding the optimum method for getting the maximum diagnostic accuracy based on multiple tests has been achieved. The problem arrives basically at how to calculate the weights of a linear combination of the test results. Logistic model has a merit in which each weight of the test is obtained as natural logarithm of the odds ratio of each test. Logistic model was compared with the Case Grading Method that I proposed previously. These methods were verified by the actual clinical data and by the simulation data.

View full abstract

The system and the alarm were designed as the operator operates properly it. However, the operator sometimes disregards consciously the alarms. In this paper, we discuss by the operator-machine-alarm model why operator disregards the alarms. The operator-machine-alarm model is the simplified model of the complex system. The model has three parameters which include the reliability by operator, the machine failure rate and the alarm failure rate. It can calculate the ratio of the machine state by giving each parameter.

View full abstract

The aim of this study is to construct a multi-camera tracking system for vehicle plate recognition. Generally, recognizing a vehicle plate for a toll-gate system or parking system is easier than recognizing a car plate in a highway system. There are many cameras installed on the highway to capture images and every camera has different angles of images. As a result, the images are captured in varied imaging conditions and not focusing on the vehicle plate itself. Therefore, we need a system that is able to recognize the location of a vehicle plate first. In this paper we will propose different techniques for vehicle plate location detection. First, we used segmentation method and second we applied Fast Fourier Transform and histogram method to recognize the location of a vehicle plate. The result will be discussed and the methods are compared at the end of this paper.

View full abstract

Location selection for distribution centers (DCs) is one of the most important decision issues that logistic managers concern with. The optimal or suitable location gives an influencing impact on company profits. This paper proposes a molecular algorithm to efficiently identify the optimal location of the DCs. The optimal selection of the DCs is a combination of two main problems that are to select the most economical DCs and to figure out which of local cities will connect to which of DCs with the least cost, respectively. These two problems can be classified into an NP problem. DNA computing can efficiently solve these two problems in super parallel computation. Finally, we discuss the result obtained in finding the most suitable location of DCs as a solution.

View full abstract

Face recognition is an important technology in computer vision because of its applicability to various computer systems such as man-machine interface and security system. In order to develop the face recognition system, estimation technique of face direction can contribute to get robust performance of recognition. In this paper, we discuss about development of estimation system of face direction using stereo vision system that can achieve independent performance of background scene and color of the face in the image. From the results of numerical experiments, the estimation technique found to be promising for development of computer vision application.

View full abstract

In our previous study, the visibility of web-safe colors on the white background was examined, and the Blue used for unvisited standard link color was found high visibility in wide range of ages. In this report, the visibility between the standard link color and 124 background colors was examined using pair comparison method. As the results, it was shown that the high contrast led the high visibility and the color harmony of the link color and the complementary background colors also made the high visibility.

View full abstract

We have used the fuzzy reasoning method "Min-Max Gravity Method", "Product- Sum-Gravity Method" and "Simplified Fuzzy Reasoning" for the fuzzy control and the soft science. The monotonicity is the important point for applying fuzzy reasoning to these fields. In this paper, we would present that the numerical reasoning functions of these methods do not always hold the monotonicity condition.

View full abstract

This article presents the past and the present of study on fuzzy theory and soft computing in Architectural Institute of Japan (AIJ), related Japan Society for Fuzzy Theory and Systems (SOFT) and Japan Society for Fuzzy Theory and Intelligent Informatics (SOFT).

View full abstract