• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.4
• /
• pp.18-22
• /
• 1998

This paper presents a fuzzy c elliptic shells algorithm that detects culusters than can be expressed by hyperellipsoidal shells. The algorithm is computationally efficient since the prototyes of shell clusters are determined by a simple matrix inversion instead of by solving several nonlinear equations. The algorithm also works when the detected shells are partial the optimal number of clusters is unkonown initially. A set of simulation results validates the proposed clustering mehtod.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2013.05a
• /
• pp.309-310
• /
• 2013

• Proceedings of the Korean Society for Cognitive Science Conference
• /
• 2005.05a
• /
• pp.182-185
• /
• 2005

메스암페타민 중독환자의 기억 손상을 알아보기 위해 19명의 중독환자와 18명의 정상인을 대상으로 언어기억과 시각 기억을 검사하였다. 언어기억에서는 유의한 차이가 나타나지 않았으나, 시각 기억에서는 유의한 차이가 나타났다. 이 결과는 시각 기억과제에서 계획과 같은 집행기능이 더 요구되었기 때문으로 해석되었다.

• Proceedings of the Korea Concrete Institute Conference
• /
• 1999.04a
• /
• pp.659-664
• /
• 1999

The majority of published conclusions about structural configuration effects of bond strength were based on the observed performance of test specimens and their interpretations are mostly empirical and statistical. The empirical and statistical interpretation on bond strength have to be replaced by rational models based on simple, sound and verifiable mechanical principles. It is likely that such models also represent the key to a deeper understanding of some existing experimental data on bond strength. The presented truss model is capable of explaining failure modes involving bond slip that cannot be explained by current truss model.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.10a
• /
• pp.621-662
• /
• 2006

• Proceedings of the IEEK Conference
• /
• 2000.11c
• /
• pp.25-28
• /
• 2000

In this paper, an effective intention reading scheme is proposed for human-friendly interface. Soft computing techniques such as fuzzy logic and artificial neural networks are used for this. And Gabor filter based feature(GG feature) is also proposed to deal with local activity in the human face. It is based on human visual system and Gabor filter based approach is very popular in these days. The proposed scheme is adopted for human-friendly interface for rehabilitation service robotic system KARES II.

• Proceedings of the IEEK Conference
• /
• 2002.06c
• /
• pp.25-28
• /
• 2002

This paper introduce a personalized facial expression recognition system. Many previous works on facial expression recognition system focus on the formal six universal facial expressions. However, it is very difficult to make such expressions for normal person without much effort and training. And in these days, the personalized service is also mainly focused by many researchers in various fields. Thus, we Propose a novel facial expression recognition system with fuzzy neural networks and robust image processing.

• Proceedings of the IEEK Conference
• /
• 2002.06e
• /
• pp.137-140
• /
• 2002

We introduce a personal identification method which can find user's ID without any help of the user. To do this, there has been two approaches, vision-based and pressure-based. Pressure-based approach has some advantages compared than vision-based one in the aspects of illumination, occlusion, and the amount of data. In the previous study about pressure-based personal identification, there are some restrictions about human body posture for extracting normalized footprints. Since this approach cannot be extended unconscious and continuos identification, we suppose more natural method and verified it by experiments.

• KAPE Magazine
• /
• s.239
• /
• pp.12-13
• /
• 2016

예로부터 '곡식은 농부의 발소리를 듣고 자라며, 가축은 주인의 얼굴을 보고 자란다.'고 했다. 이곳 경상북도 포항시에는 매일 주인을 보며 자라는 소들이 있고, 그 옆에는 소를 사람처럼 생각하고 키우는 특별한 축산가가 있다. 전국 최고의 육우 개발과 낙농산업 발전에 이바지하고, 이어 경북대구낙농농협 조합장으로 지역 발전을 이끄는 <안덕목장>의 박남용 대표. 수십 년간 목장을 운영하며 육우시장을 개척하는 그에게 축산의 비결을 들어본다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.468-470
• /
• 2012

본 논문에서는 기존 VectorBoost기반 분류기의 문제점이었던 다중 분할 노드에서의 오판단 발생을 해결하기 위해, LDA를 이용해 학습 샘플들을 가장 잘 분리할 수 있는 최적의 초평면을 구하고, 이 초평면을 이용해 Positive샘플에서 VectorBoost의 판단율을 향상시키는 방법을 제안한다. 이러한 방법을 적용했을 때 Positive샘플들의 오판단율이 감소하는 효과를 보였으며, 불필요한 연산의 감소로 약 30%의 속도향상을 얻을 수 있었다.