Akihiro Kanagawa

A design for single sampling attribute plan based on fuzzy sets theory

Abstract Problems in the design of sampling inspection plans have been studied for a long time as an important subject in quality control. Especially, in the case of a single sampling attribute plan, one would like the producers risk to equal α and the consumers risk to equal β exactly, but this is usually not possible since the sample size n and the acceptance number c must be integers. In this paper a new design procedure for the single sampling attribute plan based on fuzzy sets theory is presented by means of formulating this problem as a fuzzy mathematical programming one.

Variable sampling plans for normal distribution indexed by Taguchi's loss function

Taguchi has presented an approach to quality improvement in which reduction of deviation from the target value is the guiding principle. In this approach any measured value x of a product characteristic X brings a loss to consumer in general, where the loss is expressed as a quadratic form with respect to the difference between the measured value x and the target value T of a product characteristic. Then, it is natural to reject the lot which may bring a large loss to consumer. This concept induces us to construct new variable sampling plans based on the Taguchis loss criterion. In this article, a design procedure of the sampling plans for assuring the loss in the Taguchis method is proposed. Some numerical results based on the proposed design procedures are illustrated.

Fuzzy design for fixed-number life tests

The authors present a fuzzy design procedure for fixed-number life tests, in which the producer and consumer risks are treated as fuzzy numbers. The procedure enables one to balance both risks based on a membership function. >

Identification of membership functions based on fuzzy observation data

Abstract For the classification problem, of which categories having vague or verbal definition, Okuda et al. [Proc. 3rd IFSA Congr. (1989) 755] proposed a model in which each category is defined by fuzzy sets, and each appearance frequency is explained by the probability of Zadehs fuzzy event. They called this model fuzzy observation. Membership functions are usually given directly by the users subjectivity. But these membership functions cannot be used in the fuzzy observation model because they have no assurance to meet the restriction as the fuzzy event. In this paper we propose a method to obtain the membership functions which satisfy the restriction as the fuzzy event against to given probability density function, and discuss the effectiveness of the method.

A Robust Gesture Recognition Using Depth Data

In this paper, we propose a novel gesture recognition system using depth data captured by Kinect sensor. Conventionally, the features which have been used for hand gesture recognition are divided into two parts, hand shape features and arm movement features. However, these traditional features are not robust for environmental changing such as individual differences in body size, camera position and so on. In this paper, we propose a novel hand gesture recognition system using depth data, which is robust for environmental changing. Our approach involves an extraction of hand shape features based on gradient value instead of conventional 2D shape features, and arm movement features based on angles between each joints. In order to show the effectiveness of the proposed method, a performance is evaluated comparing with the conventional method by using Japanese sign language.

Associative memories in cellular neural networks using a singular value decomposition

Using various templates, many applications of cellular neural network (CNN), such as a feature extraction, an edge detection and a pattern classification have been considered. In a Hopfield network, an image to be stored corresponds to the minimum value of the energy of the network. However, in CNN, an image corresponds to the equilibrium state of a differential equation. A synthesis procedure for designing a CNN that will store a set of desired vectors as memory points using a singular value matrix decomposition is considered. Also analyzed here is the indeterminate phenomenon of the equilibrium states of some cells that arise in the case in which more than two similar patterns are stored for Chinese characters.

Analysis of liver damage from radon, X-ray, or alcohol treatments in mice using a self-organizing map

In our previous studies, we found that low-dose radiation inhibits oxidative stress–induced diseases due to increased antioxidants. Although these effects of low-dose radiation were demonstrated, further research was needed to clarify the effects. However, the analysis of oxidative stress is challenging, especially that of low levels of oxidative stress, because antioxidative substances are intricately involved. Thus, we proposed an approach for analysing oxidative liver damage via use of a self-organizing map (SOM)—a novel and comprehensive technique for evaluating hepatic and antioxidative function. Mice were treated with radon inhalation, irradiated with X-rays, or subjected to intraperitoneal injection of alcohol. We evaluated the oxidative damage levels in the liver from the SOM results for hepatic function and antioxidative substances. The results showed that the effects of low-dose irradiation (radon inhalation at a concentration of up to 2000 Bq/m3, or X-irradiation at a dose of up to 2.0 Gy) were comparable with the effect of alcohol administration at 0.5 g/kg bodyweight. Analysis using the SOM to discriminate small changes was made possible by its ability to ‘learn’ to adapt to unexpected changes. Moreover, when using a spherical SOM, the method comprehensively examined liver damage by radon, X-ray, and alcohol. We found that the types of liver damage caused by radon, X-rays, and alcohol have different characteristics. Therefore, our approaches would be useful as a method for evaluating oxidative liver damage caused by radon, X-rays and alcohol.

Guiding Visual Attention Based on Visual Saliency Map with Projector-Camera System.

Many attention retargeting methods based on a visual saliency model of bottom-up attention for guiding a human’s attention to a region of interest (ROI) have recently been proposed. However, conventional attention retargeting methods focus only on modulating an image or a movie that is presented on a display device. In this paper, we propose an attention retargeting method used with a projector-camera system to realize attention retargeting in real space. We focus on the realization of an appearance control method for attention retargeting to the plane of a real space as a first step of our research.

Attention retargeting in real space with projector camera system.

Many attention retargeting methods based on the visual saliency model of bottom-up attention to guide a humans attention to a ROI have recently been proposed. However, conventional attention retargeting methods focus only on modulating an image or a movie presented to a display. In this paper, we propose the use of a projector-camera system to realize attention retargeting in real space. As a first step of our research, we focus on the realization of the appearance control method for attention retargeting to the plane of real space.

Classification Method by Using the Associative Memories in Cellular Neural Networks

This paper deals with a classification problem, such as medical diag-nosis, which classes are defined by categorical forms. Classification should be done by careful and synthetical judgement for a lot of characteristic values taking each individual variations into account. We use the associative memory function of the cellular neural networks to classify by means of remembering one category from among the preregistered categories.