• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2005.05a
• /
• pp.193-206
• /
• 2005

This paper considers a new flow-shop scheduling problem where a different WIP (work-in-process) state has different weight on the duration time. For the two machine case, the recognition version is NP-Complete in the strong sense. Several special cases are solved by different polynomial time algorithms. Finally, we develop a heuristic and provide an upper-bound on relative error which is tight in limit.

• Proceedings of the Korean Society for Bio-Environment Control Conference
• /
• 1994.05a
• /
• pp.98-101
• /
• 1994

표고는 다른 농산물에 비하여 품질등급을 결정하는 외관 특징들이 갓의 전후면에 걸쳐 복잡하게 분포하고 있어 자동 선별장치를 구현하기 위해서는 갓의 전후면 인식과 아울러 외관특징을 검출해야 한다. 특히 건조 표고의 경우 갓 바깥으로 튀어나온 꼭지부의 존재 여부 및 상태가 갓의 크기, 모양 및 후면 내피의 말린 정도를 검색하는 데 큰 영향을 미친다. (중략)

• Proceedings of the PSK Conference
• /
• 2002.10a
• /
• pp.161-162
• /
• 2002

Field of enantioseparations represents one of the actual topics of chemistry. Significant, in some cases dramatic differences in a desired activity as well as in toxic properties of enantiomers of chiral drugs, food additives, agrochemicals, cosmetic products, etc. represents a driving force in this field. The enantiomers of all chiral bioactive compounds have to be isolated and to be tested. Besides the ethical or environmental reasons for developing single enantiomers, it may be a real therapeutic benefit and in some cases, it has been used as a strategy for extending patent life. (omitted)

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.51-55
• /
• 1998

한국통신이 개발하여 현재 700-3000번으로 서비스되고 있는 음성 인식 증권정보시스템을 소개하고, 음성인식 성능을 향상시키기 위한 한국통신의 연구현황을 기술하고자 한다. 현재 운용중에 있는 서비스 시스템은 120명이 동시에 사용할 수 있는 시스템이며 S/W 와 H/W를 분리시켜 S/W의 버전을 갱신하더라고 H/W의 변경이 최소화 되도록 설계되었다. 현재 고려하고 있는 성능 향상 방법은 연속음성 인식 기술을 이용하여 고립단어 인식을 시도하는 것과 거절기능 구현 및 tied-state에 의한 문맥종속 음소를 구하는 것이다. 또한 연속 HMM 모델 방식으로의 변경도 연구중에 있다.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.372-374
• /
• 1998

온라인 문자 인식을 위해 시도된 여러 방법 중 은닉 마르코프 모델(HMM)이 우수한 성능을 보이고 있다. 영숫자 인식은 물론 한글 인식에 있어서도 HMM은 최근 널리 사용되고 있는데, HMM을 이용해서 모델링 할 때 해결해야 할 문제 중의 하나는 HMM의 구조를 어떻게 최적화 하느냐이다. 본 논문에서는 HMM을 이용한 온라인 한글 인식 시스템에서 HMM의 최적화를 통해 인식률을 향상시키고자 한다. 특히 HMM의 상태(state)수를 어떻게 정할 것인가에 초점을 맞춰, 실험을 통해 최적의 HMM 상태 수를 찾고자 한다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1098-1101
• /
• 1993

The purpose of this work is to build a fuzzy model of a batch culture for a process control. The process is highly nonlinear system with large delay. This paper presents two methods of modeling the process behavior. One is a method of recognizing them by fuzzy rules that are contracted by the pattern analysis in consideration of skilled operators' way. The other is a method of predicting them by approximate linear models and fuzzy rules by statistic analysis.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1995.10b
• /
• pp.52-58
• /
• 1995

A shared-weight neural network that performed classification based on the features extracted with the fuzzy morphological operation is introduced. Learning rules for the structuring elements, degree of membership, and weighting factors are also precisely described. In application to handwritten digit recognition problem, the fuzzy morphological shared-weight neural network produced the results which are comparable to the state-of-art for this problem.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1353-1355
• /
• 1996

This paper presents classification of high impedance fault pattern using linear prediction coefficients. A feature of neutral phase current is extracted by the linear predictive coding. This feature is classified into faults by a multilayer perceptron neural network. Neural network successfully classifies test data into three faults and one normal state.

• Proceedings of the KIEE Conference
• /
• 2004.05a
• /
• pp.114-116
• /
• 2004

Biometrics consist of technologies that support automatic identification or verification of identity based on behavioral or physical traits. Biometrics can authenticate identities since they measure unique individual characteristics including fingerprints, hand geometry, iris, hand vascular patterns and facial characteristics. we review the state of the hand vascular patterns identification technology and compare other competitive authentication technologies such as cryptography, electronic signature and PKI.

• Proceedings of the KIEE Conference
• /
• 2004.05a
• /
• pp.117-119
• /
• 2004

Biometrics are best defined as measurable physiological and behavioral characteristics that can be utilized to verify the identity of an individual. Biometric technologies will continue to improve, becoming even more accurate and reliable as technology evolves. In this paper, we review the state of the hand vascular patterns identification technology and analyse the opportunities and threats of the technology in the markets.