The digital map is used for the car navigation and as a form of service for map retrieval through the internet. Recently, it has been increasingly used for mobile devices such as smart phones and as a form of service for the superimpose display of aerial images. Furthermore, it is an important element for city planning, and disaster prevention planning. However, the generation of digital maps depends on manual operation and it takes much time and money to generate and update them. Thus, there are many research studies of generating digital maps automatically using a computer. In this paper, we introduce a method of automatic road map generation that the authors have been researching until now. Then, we describe current technical issues of road map generation and future works.

View full abstract

In accordance with the widespread use of digital cameras, digital displays and color printers, color images have become common in our daily lives. Colors are used frequently to express information even on television and the Internet. Thus, it can be said that colors play a fundamental part in conveying information. In general, the color gamut spreads to the three-dimensional color space. However, in certain circumstances, it becomes necessary to express colors in the gamut represented in a low-dimensional space. For example, colors should be expressed in a one-dimensional gamut when a color image is printed as a grayscale image. Furthermore, the number of dimensions of a valid color gamut for people with color vision impairment such as dichromats is decreased. In this paper, color transformation techniques that improve the visibility of an image in a low-dimensional color gamut are explained. In particular, a detailed description of such transformation techniques for obtaining a monochrome image from a color image is given. Moreover, color transformation techniques for dichromacy are described.

View full abstract

To decrease the number of labor injuries, it is necessary to implement essential safety protection measures for machine and manufacturing systems. The cost of such protection measures will be treated from an investment aspect. Thus, being able to prove the investment to be sufficiently beneficial, protection measures become a motivation to move forward. Therefore, an evaluation index of investment effectiveness related to safety protection measures is necessary.

View full abstract

There have been many research studies of various neuron models that typically take the form of ordinary nonlinear differential equations of several dimensions. The pattern of spiking is of great importance, because it is presumed that it codifies information transmitted by neurons. It is an actively studied problem to apply various neuron models to artificial neural networks (ANNs) for intelligent information processing in the field of nonlinear dynamics and brain research. One important aspects in this situation is the lack of universal discussion about the dynamical behaviors of various neuron models, although perturbation and bifurcation theories exist. Thus, we reveal that each model has its own potential function and active areas on the potential. Negative resistance is one of the active areas. This concept realizes the universal discussion of the dynamical behaviors of models, for example, bursting and spiking. On the other hand, Hopfield neural network is capable of solving combinatorial optimization problems and is a parallel-processing version of the gradient method. However, it has some drawbacks. One of its most serious drawbacks is that it frequently finds locally minimum solutions instead of global minima. The active areas of neuron models make the state of the network escape from local minima by their destabilization. In computer simulation and theoretical estimation, we have already shown that the ID network, which is active ANN for implementing associative memory and combinatorial optimization problems, can converge on optimal solutions only.

View full abstract