• Journal of Oral Medicine and Pain
• /
• v.8 no.1
• /
• pp.61-67
• /
• 1983

Authors observed a corpse which is died from "Charring", caused by air disaster, for the purpose of individual identification. This is an identifide case of the charred corpse due to the fire while landing of KAL 747 Jumbo(HL 7445) at Kimpo airport Nov.1980. It was referred to author in the state of carbonization by high degree of heat-as unknown body entirely. But teeth condition and treated condition were well preserved under mouth closing and by the comparative examination of antermortem dental records, dental radiographs, the individual identification was simply accomplished. Therefore, it brought repeatedly a recognition of the practical effectiveness of dental identification and importance or dental records.

• Journal of Korean Society for Quality Management
• /
• v.36 no.2
• /
• pp.67-84
• /
• 2008

Given the industry's unprecedented attention and dedication of resources to voice recognition, this paper introduces and explores a novel idea generation technique whereby ideas are captured directly through verbalization rather than forcing group members to type ideas. A group simulator was used to measure the idea generation performance of individuals who input ideas verbally or via typing in the context of nominal and interacting groups. The results clearly indicate that verbal input represents a more desirable mechanism in a computer-mediated idea generation environment. Liberating group members from the keyboard produces remarkable performance gains. Verbalizing ideas helps individuals focus on analytical thinking and leverage group member ideas, ultimately facilitating the creation of ideas pools that are vastly superior in terms of quantity and quality. These effects were found across nominal and interacting groups. The implications of these results for future research and the design of technologies are discussed.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2003.02a
• /
• pp.209-214
• /
• 2003

바이오 센서는 생물학적 인식 반응(Biological recognition reaction)이나 생물 촉매 공정(Bio-catalytic process)을 측정 가능한 전기적 신호로 변환시켜주는 적절한 변환기(Transducer)와 같은 생물학적 인식요소로 이루어진 감지 장치를 의미한다. 1962년 효소를 이용한 Glucose 전극봉의 개발이후 이 분야에 대한 수많은 연구와 기기의 개발이 진행되어왔다. 분석도구로써 바이오 센서는 효소, 항체, 수용체, 세포, 조직 등과 같은 생물학적 인식 요소들에 광범위하게 적용 가능하다는 장점이 있는 반면, 위에 열거한 생물학적 인식 요소들의 불안정성으로 인해 신뢰성이 유지되지 못하는 단점을 동시에 지니고 있다. (중략)

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.7
• /
• pp.1380-1385
• /
• 2009

This paper was studied about the aging judgment method by ultraviolet rays image to happen in electric power equipment using ultraviolet rays camera. We established the aging judgment method as follows; 20% within of risk factor of insulation state of electrical facility that ultraviolet rays image does not show is "good or recognition". 30$^{\sim}$50% within of risk factor is "check", 50$^{\sim}$60% within of risk factor is "inspection" and 60% above of risk factor is "replacement". This method will be utilized for the inspection about electrical facilities.

• ETRI Journal
• /
• v.32 no.5
• /
• pp.795-800
• /
• 2010

Embedding a large vocabulary speech recognition system in mobile devices requires a reduced acoustic model obtained by eliminating redundant model parameters. In conventional optimization methods based on the minimum description length (MDL) criterion, a binary Gaussian tree is built at each state of a hidden Markov model by iteratively finding and merging similar mixture components. An optimal subset of the tree nodes is then selected to generate a downsized acoustic model. To obtain a better binary Gaussian tree by improving the process of finding the most similar Gaussian components, this paper proposes a new distance measure that exploits the difference in likelihood values for cases before and after two components are combined. The mixture weight of Gaussian components is also introduced in the component merging step. Experimental results show that the proposed method outperforms MDL-based optimization using either a Kullback-Leibler (KL) divergence or weighted KL divergence measure. The proposed method could also reduce the acoustic model size by 50% with less than a 1.5% increase in error rate compared to a baseline system.

• Journal of Dairy Science and Biotechnology
• /
• v.24 no.1
• /
• pp.29-42
• /
• 2006

Recent trend of consumers' for health give rise to the interest in health and functional foods. Functional yogurt is a primary item in USA, EU, and Japan that are leaders in health and functional food industry and its market is going to be enlarged. Also in Korea, functional yogurt has been recognized as health food by consumers. Concept of functional yogurt is various by health of intestine, stomach, and liver, and lowering blood pressure in Korean market. However, functional yogurt is not registered as health and functional foods in Health/Functional Food Act of Korea. Under these circumstances, the results of trustable and scientific research on the efficacy of functional yogurt should be accumulated to obtain the consumers' solid recognition of functional yogurt as health and functional food.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06e
• /
• pp.369-372
• /
• 1998

본 논문은 어휘독립(Vocabulary-Independent) 환경에서 별도의 훈련과정 없이 인식대상 어휘를 추가 및 변경할 수 있는 가변어휘(Variable Vocabulary) 음성인식에 관한 연구를 다룬다. 가변어휘 인식은 처음에 대용량 음성 데이터베이스(DB)로 음소모델을 훈련하고 인식대상 어휘가 결정되면 발음사전에 의거하여 음소모델을 연결함으로써 별도의 훈련과정 없이 인식대상 어휘를 변경 및 추가할 수 있다. 문맥 종속형(Context-Dependent) 음소 모델인 triphone을 사용하여 인식실험을 하였고, 인식성능의 비교를 위해 어휘종속 모델을 별도로 구성하여 인식실험을 하였다. Unseen triphone 문제와 훈련 DB의 부족으로 인한 모델 파라메터의 신뢰성 저하를 방지하기 위해 state-tying 방법 중 음성학적 지식에 기반을 둔 tree-based clustering(TBC) 기법[1]을 도입하였다. Mel Frequency Cepstrum Coefficient(MFCC)와 대수에너지에 기반을 둔 3 가지 음성특징 벡터를 사용하여 인식 실험을 병행하였고, 연속 확률분포를 가지는 Hidden Markov Model(HMM) 기반의 고립단어 인식시스템을 구현하였다. 인식 실험에는 22 개 부서명 DB[3]를 사용하였다. 실험결과 어휘독립 환경에서 최고 98.4%의 인식률이 얻어졌으며, 어휘종속 환경에서의 인식률 99.7%에 근접한 성능을 보였다.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.11a
• /
• pp.693-696
• /
• 2006

Global optimization is a method for finding more reliable models in various fields, such as financial engineering, pattern recognition, process optimization. In this study, we compare and analyze the performance of the state-of-the-art global optimization techniques, which include Genetic Algorithm (DE,SCGA), Simulated Annealing (ASA, DSSA, SAHPS), Tabu & Direct Search (DTS, DIRECT), Deterministic (MCS, SNOBIT), and Trust-Region algorithm. The test functions for the experiments are Benchmark problems in Hedar & Fukushima (2004), which are evaluated with respect to efficiency and accuracy. Through the experiment, we analyse the computational complexity of the methods and finally discuss the pros and cons of them.

• Journal of Computing Science and Engineering
• /
• v.11 no.4
• /
• pp.130-141
• /
• 2017

Feature selection is one of the most challenging problems of pattern recognition and data mining. In this paper, a feature selection algorithm based on an improved version of binary differential evolution is proposed. The method simultaneously optimizes two feature selection criteria, namely, set approximation accuracy of rough set theory and relational algebra based derived score, in order to select the most relevant feature subset from an entire feature set. Superiority of the proposed method over other state-of-the-art methods is confirmed by experimental results, which is conducted over seven publicly available benchmark datasets of different characteristics such as a low number of objects with a high number of features, and a high number of objects with a low number of features.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.16-18
• /
• 1997

The adhesion of stimulated and unstimulated platelet to fibrinogen requires the receptor binding site of GPIIb/IIIa. These recognition sites are existed in the Au chain(RGDS at positions 572-575 and RGDF at 95-98) and the carboxyterminal $\gamma$ chain (HHLGGAKQAGDV at 400-411) of fibrinogen. The unstimulated platelet does not adhered on the fragment E-coated surface containing RGDF sequence. In this study, we developed RGDF-immobilized surface to detect the functional state of platelet. RGDF-immobilized surface was prepared on the glass using photolithographic technology. Platelet adhesion to petide(RGDF)-immobilized surface was observed by the fluorescence microscope using mepacrine.