In recent days high perfermance graphic operation is needed, since computer graphics is widely used for computer-aided design and simulator using high resolution graphic card. In this paper a graphic accelerator is designd with the functions of graphic primitives generation and geometrical transformations. 1-D Systolic Array Processor for Matris Vector operation is designed and used in main ALU of a graphic accelerator, since these graphic algorithms have comonon operation of Matris Vector. Conclusively, in case that the resolution of graphic domain is 800$\times$600, and 33.3nsec operator is used in a graphic accelerator, 29732 lines per second and approximately 6244 circles per second is generated.

This paper analyzes succinct graph descriptions and its complexity of connectivity problems on context free graph languages under various restrictions. It defines SNLC(Simple Context Free Node Label Controlled) grammar and presents reduction method that solves graph problems without expanding the hierarchical description. It exemplifies the method by giving efficient solutions to connectivity problems on graphs and presents parallel algorithm for reduction and analyzes the complexity. Its results will help application of desing for NETWORK. CAD. VLSI and other engineering problems.

Processes in the real-time distributed control systems share a network medium to exchange their data. Performance of feedback control loops in the real-time distributed control systems is subject to the network-induced delays from sensor to controller, and from controller to actuator. The network-induced delays are directly dependent upon the data sampling times of control components which share a network medium. In this study, an algorithm of determining data sampling times is developed using the "window concept". where the sampling datafrom the control components dynamically share a limited number of windows. The scheduling algorithm is validated through the aimulation experiments.

The purpose of this paper is to estimate the attitude and the position of SPOT satellite which are needed in producing DEM(Digital Elevation Model) using SPOT satellite image pairs. DEM extraction is consists of three parts. First part is the modeling of satellite position and atitude, second part is the matching of two images to find corresponding point of them and third part is to calculate the elevation of each point by using the result of the first and second part. For modeling inaccessible area, extended modeling algorithm which removes the GCP(Ground Control Point) most errorneous from the GCPs extracted from map iteratively is proposed According to the experiments using a collinearity equation, the second order polynomials are shown to the optimal for .omega.(pitch), and Zs parameters while the first order ones for .kappa.(yaw) .PHI.(roll), Xs, and Ys parameters. The input images used in this paper are 6000*6000 level 1A panchromatic digital SPOT images of Chungchong-do, Korea. With 30 GCPs, experiments on SPOT images show that the planimetric and altimetric RMS errors are 7.11m and 7.10m, respectively, for test points.

A model for BICMOS buffer switching operation is presented, including the influence of bipolar base transit time and collector-base capacitances. A closed-form solution for the propagation delay-time is obtained assuming low level injection and channel velocity limitation. For the high level injection case, the delay-times are numerically obtained using effective current gain. These results are compared with those by HSPICE simulation, which shows good agreement. It is noted that the collector-base capacitance strongly affects the delay-time. The effects of voltage scaling are also investigated, which shows the model can be applied for the reduced supply voltages.

In this paper, a two-stage block matching algorithm (BMA), which can reduce greatly the computational complexity of the conventional BMAs, is proposed, in which the onedimensional distortion measure based on the integral projection is introduced to determine the candidate motion vectors and then among them a final motion vector is detected based on the conventional two-dimensional distortion measure. Due to the one-dimensional calculation of a distortion measure, the proposed algorithm can reduce the computational complexity of the conventional BMA (full search method with a 16$\times$16 block) by a factor of 4, with its performance comparable to those of the conventional ones. Simulation results based on the original and noisy image sequences are shown. Also the simulation of the proposed method combined with the MPEG (Moving Picture Experts Group) SM3 (Simulation Model Three) is presented. Computer simulation shows that the proposed algorithm is fast with its performance comparable to those of the conventional ones.

OWT is a tool for block transform coding with wavelet basis functions that overlap adjacent blocks. The OWT can reduce the block effect. In this paper performances of OWT are evaluated for AR model. Some simulation results show that performances are nearly same to DCT, but block effect is reduced to very low level.

An efficient RVQ image coding method is proposed using the segmentation-based coding and CVQ techniques. In the proposed method the residual image, the difference between an original image and the synthesized one obtained from the segmentation-based coding, is first dividel into $\times$4 subblocks. They are then individually coded in the spatial domain using a simple CVQ. Experimental results show that the proposed method yields better quality of the reconstructed images in both PSNR and subjective test over the basic VQ and SMVQ.

While the rules for an expert system are obtained through the interviewing with domain experts or by designer's own experience, these are not adequate for fuzzy controllers dealing quantitative control values. In this paper, by considering a state of the controlled system as a pattern, we propose a method to obtain the control rules by a statistical method. Namely, we propose a method to obtain the control rules by a statistical method. Namely, we propose an rule acquisition method that is objective, mechanical, and inductive inference using a cluster-seeking algorithm, or K-means clustering algorithm. To validate this study, we show an example of an IRIS control in a CAMCODER and analyse the rules acquired from 98 sample patterns consisting of 45 features.

This paper deals with a computer aided control of an adjustment process for the complete electronic devices by means of an application of artificial neural network and an implementation of neuro-controller for intelligent control. Multi-layer neural network model is employed as artificial neural network with the learning method of the error back propagation. Information initially available from real plant under control are the initial values of plant output, and the augmented plant input and its corresponding plant output at that time. For the intelligent control of adjustment process utilizing artificial neural network, the neural network emulator (NNE) and the neural network controller(NNC) are developed. The initial weights of each neural network are determined through off line learning for the given product and it is also employed to cope with environments of the another product by on line learning. Computer simulation, as well as the application to the real situation of proposed intelligent control system is investigated.

A Gaussian is formed by diffusing a spot excitation. In this paper, a diffusion neural network model is derived from the diffusion equation. And it is shown that a difference of two Gaussians(DOG) may have the same shape as a Laplacian of Gaussian(LOG), A neural network model executing a DOG convolution by diffusing an external excitation is proposed. By this model intensity changes of image may be detected. This model may be implemented economically because each neuron has only four fixed-valued synapes.