• Journal of the Korean Ceramic Society
• /
• v.56 no.6
• /
• pp.596-600
• /
• 2019

Artificial intelligence with a sufficient amount of realistic big data in certain applications has been demonstrated to play an important role in designing new materials or in manufacturing high-quality products. To reduce cracks in ceramic products using machine learning, it is desirable to utilize big data in recently developed data-driven optimization schemes. However, there is insufficient big data for ceramic processes. Therefore, we developed a numerical algorithm to make "virtual" manufacturing data sets using indirect methods such as computer simulations and image processing. In this study, a numerical algorithm based on the random walk was demonstrated to generate images of cracks by adjusting the conditions of the random walk process such as the number of steps, changes in direction, and the number of cracks.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1996.06a
• /
• pp.195-198
• /
• 1996

In this paper, we introduce the notion of the smoothly perfect 8-connected (SP8C) contour and propose a coding technique for the SP8C contours. Based on the contour simplification using the majority filter proposed by Gu[6], SP8C contours are extracted on the contour lattice from the segmented image. By noting that, unlike the perfect 8-connected contours, the SP8C contours are restricted to travel in only 3 different directions along the contours, we also propose two techniques for encoding the SP8C contours. The one is the modified version of the neighbouring direction segment coding by Kandeko[2], while the other is to employ the notion of the entropy coding. From the comparison in terms of the entropy, it is shown that the proposed SP8C contours require les bits in encoding the diagonal contours than the 4-connected contours employed by Gu. And computer simulations reveal that the contours can be efficiently encoded by the proposed technique.

• Investigative Magnetic Resonance Imaging
• /
• v.3 no.1
• /
• pp.13-19
• /
• 1999

MRI imaging provides many benefits such as noninvasive, 3-dimensional imaging capabilities. But it has relatively serious drawback that is the long data collection time, compared with other imaging modality. Many studies have been performed for fast MR imaging. But EPI and SEPI (4-6) are required to expensive hardware. In this paper, we introduce to Burst imaging technique. It can reduce imaging time by use of a mulitple RF excitation technique. Further it is easily implemented to the normal MRI system. But a pixel profile in the conventional burst sequence is so poor that excited area by burst sequence is a small portion of a pixel. This causes poor signal to noise ratio in burst image. therefore frequency sweeping of RF pulse for burst imaging sequence is proposed to improve pixel profile. A burst pulse train is shaped by liner or nonlinear frequency sweeping function so that all the spins within a pixel are excited, thereby improving the signal to noise ratio. It also shows that the pixel profiles are dependent on how frequency sweep is made. Computer simulations with Bloch equation and experimental results obtained using a 1.0 T NMR imaging system are presented.

• Journal of Korean Institute of Industrial Engineers
• /
• v.27 no.3
• /
• pp.305-314
• /
• 2001

In this paper, we construct an automatic evaluation system of psychological feeling for corporate identity (CI) symbol mark based on a fuzzy neural network technique. The system is modelled by trainable fuzzy inference rules with several input variables (qualitative and quantitative design components of CI symbol mark) and a single output variable (consumer's feeling). The back propagation learning algorithm, which is a conventional learning method of multilayer feedforward neural networks, is used for parameter identification of the fuzzy inference system. The learning ability to train data and the generalization ability to test data are evaluated for the proposed evaluation system by computer simulations.

• Proceedings of the KOSOMBE Conference
• /
• v.1992 no.05
• /
• pp.92-97
• /
• 1992

The pulsatile nature of blood flow makes artefacts in 2D Fourier transform image. Spatial presaturation is known to be effective in eliminating flow artefacts when the spin echo acquisition is employed. However. this method requires additional RF pulse and spoiling gradient for presaturation. In this paper a new flow saturation technique which does not require additional saturation-RF and gradient is proposed. The proposed technique is equivalent to the existing saturation technique but the elimination of the flow component is achieved by a pair of tailored $90^{\circ}-180^{\circ}$ RF pulses in tile spin echo sequence. By use of two tailored RF pulses with opposite phase polarity, a linear phase gradient is generated for those moving materials and consequently all the spins of moving materials become dephased thereby no signal is observable. Computer simulations and experimental results obtained using both a phantom and a human volunteer with a 2.0 T whole body system are also presented.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2619-2621
• /
• 2005

Electrical resistance tomography(ERT) maps resistivity values of the soil subsurface and characterizes buried objects. The characterization includes location, size, and resistivity of buried objects. In this paper, Gauss-Newton and truncated least squares(TLS) are presented for the solution of the ERT image reconstruction. Computer simulations show that the spatial resolution of the reconstructed images by the TLS approach is improved as compared to that obtained by the Gauss-Newton method.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.480-485
• /
• 2005

Perspective dynamical systems arise in machine vision problems, in which only perspective observation is available. This paper considers the state estimation problem for a rigid body moving in three dimensional spaces using the image data obtained by a CCD camera or some other means. Because the motion of the rigid body and the observed data are generally corrupted by noises, it is necessary to seek a state estimation method to reduce the influence of the noises. In this paper, by means of computer simulations for a simple example, we examine the sensitivity to the noises of the nonlinear observer developed in the recent paper ([1] R. Abdursul, H. Inaba and B. Ghosh, Nonlinear observers for perspective time-invariant linear systems, Automatica, vol. 40, Issue 3, pp. 481-490, 2004) and the effectiveness of the Extended Kalman Filter.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1897-1902
• /
• 2005

The objective of this paper is to estimate the concentration distribution in flow field inside the pipeline based on electrical impedance tomography. Special emphasis is given to the development of dynamic imaging technique for two-phase field undergoing a rapid transient change. Nonlinearity-compensation extended Kalman filter is employed to cope with unexpected measurement uncertainty. The nonlinearity-compensation extended Kalman filter compensates for the influence of measurement uncertainty and solves the instability of extended Kalman filter. Extensive computer simulations are carried out to show that nonlinearity-compensation extended Kalman filter has enhanced estimation performance especially in the unexpected measurement environment.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.8
• /
• pp.1074-1084
• /
• 1995

In this paper, we investigate edge extraction and segmentation of range images. We first discuss problems that arise in the conventional region-based segmentation methods and edge-based ones using principal curvatures, then we propose an edge-based algorithm. In the proposed algorithm, we extract edge contours by using the Gaussian filter and directional derivatives, and segment a range image based on extracted edge contours, Also we present the problem that arises in the conventional thresholding, then we propose a new threshold selection method. To solve the problem that local maxima of the first- and second- order derivatives gather near step edges, we first find closed roof edge contours, fill the step edge region, and finally thin edge boundaries. Computer simulations with several range images show that the proposed method yields better performance than the conventional one.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.1
• /
• pp.114-121
• /
• 1998

In this paper, we introudce the notion of the smoothly perfect 8-conntected (SP8C) contour and describe a coding technique for the SP8C contours. Based on the simplificationusing the majority filter proposed by Gu, SP8C contours are restricted on the contour lattice from the segmented image. By noting thating SP8C contours are restricted to travel in only 3 different directions along the contours, we attempt to encode the SP8C contours using the following two techniques. The one is the neighbouring direction segmentcoding, while the other is to employ the notion of the entropy endoding. Computer simulations reveal that the contours can be efficiently encoded by the two technique.