• Journal of the Korean Society for Precision Engineering
• /
• v.33 no.5
• /
• pp.385-392
• /
• 2016

Recently in the display industry, demands for high-luminance and resolution of display devices have been steadily increasing. Generally, micro linear patterns are applied to an optical film in order to improve its properties of light. However, these patterns are easily viewed to eyes and moire phenomenon can be occurred. Micro random patterns are proposed as a method to solve these problems, increasing light-luminance and light-diffusion. However, conventional pattern manufacturing technologies have long processing times and high costs making it difficult to apply to large area molds. In order to combat this issue, micro-random patterns are formed by using a roll to plate indentation method along with abrasive paper tools composed of AlSiO2, SiC, and diamond grains. Also, forming properties, such as size and fill-factor of random patterns, are analyzed depending on type, mesh of abrasive paper tools, and indentation forces.

• Journal of IKEEE
• /
• v.24 no.1
• /
• pp.9-18
• /
• 2020

The pattern recognition or fuzzy inference, which is mainly used for the development of the automatic walking mode change of the above knee prosthesis, has a disadvantage in that it is difficult to estimate with the immediate change of the walking environment. In order to solve a disadvantage, this paper developed an algorithm that automatically converts the walking mode of the next step by estimating the walking environment at a specific gait phase. Since the proposed algorithm should be implanted and operated in the microcontroller, it is developed using the random forest base in consideration of calculation amount and estimated time. The developed random forest based gait and environmental estimation model were implanted in the microcontroller and evaluated for validity.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.362-364
• /
• 2003

기능 유전체학에서 클러스터링 기법은 고차원의 마이크로 어레이 데이터 분석을 위한 주된 도구 중의 하나이다. 본 논문에서는 정보병목(information bottleneck)기법 기반의 이중 클러스터링에 의한, 유전자 발현 데이터의 계층적 병합방식 클러스터링 기법을 제안한다. 정보병목기법은, 두 랜덤변수의 결합확률분포가 주어진 경우 두 변수의 상호 정보량을 최대한 보존하면서 한 변수를 압축하는 기법이며, 두 변수를 차례로 압축하는 것이 이중 클러스터링이다. 실제 마이크로 어레이 데이터인 NC160 데이터(암세포 내 유전자 발현 데이터)에 대한 실험에서, 먼저 유전자를 그 발현패턴에 따라 클러스터링 한 후 이를 이용하여 표본들을 클러스터링하고 그 성능을 다각도로 분석하였다. 상호 정보량과 유전자 및 표본 클러스터 수와 엔트로피 척도에 의한 성능을 검토해 본 결과, 표본이 추출 조직에 따라 구분 가능할 것이라는 가정을 검증할 수 있었으며, 적절한 클러스터의 수를 결정할 수 있는 임계점의 기준을 설정할 수 있었다.

• Journal of KIISE
• /
• v.42 no.7
• /
• pp.910-918
• /
• 2015

This paper presents a parameter visualization technique to overcome the limitation of the naked eye in contrast-enhanced ultrasonography. A method is also proposed to compensate for the distortion and noise in ultrasound image sequences. Meaningful parameters for diagnosing liver disease can be extracted from the dynamic patterns of the contrast enhancement in ultrasound images. The visualization technique can provide more accurate information by generating a parametric image from the dynamic data. Respiratory motions and noise from micro-bubble in ultrasound data may cause a degradation of the reliability of the diagnostic parameters. A multi-stage algorithm for respiratory motion tracking and an image enhancement technique based on the Markov Random Field are proposed. The usefulness of the proposed methods is empirically discussed through experiments by using a set of clinical data.