• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06d
• /
• pp.72-75
• /
• 1998

본 논문에서는 숫자음 인식시스템의 인식률 향상을 위한 연구로서 4연속 숫자음을 대상으로 연음 현상 및 경음화 현상등과 같은 음성학적 특징을 고려하여 숫자음에 강건한 모델을 작성하는 방법을 제안하고 인식실험을 통하여 그 유효성을 확인하고자 한다. 이를 위하여 음성자료로서는 국어공학센터(KLE)에서 채록한 4연속 숫자음을 사용하며 인식의 기본단위로서 음향학적 특징을 고려한 19개의 연속분포 HMM을 유사음소 단위(Phoneme Like Units ; PLUS) 로 사용한다. 또한 , 인식실험에 있어서는 기존의 방법으로 모델을 작성한 경우와 연음 현상과 경음화 현상 등과 같은 음성학적 특징을 고려하여 모델을 작성한 경우에 대해서 유한상태 오토마타(finite State Automata ; FSA)에 의한 구문제어를 통한 OPDP(One Pass Dynamic Programming)법으로 인식실험을 수행하여 그 결과를 비교 검토하였다. 그 결과, 기존이 방법의 경우 64.6%, 음성학적 특징을 고려한 경우 68.6%의 인식률을 보여, 음성학적 특징을 고려한 경우가 4.0% 향상된 인식률을 얻어 제안한 방법의 유효성을 확인하였다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.179-182
• /
• 2000

본 논문은 전화음성 서비스 시스템의 핵심 기술인 멀티채널 음성인식 시스템의 구현에 대해서 기술하고자 한다. 구현한 시스템은 전화망 인터페이스 모듈, 음성입력 모듈, 음성인식 모듈, 및 서비스 제어모듈로 구성되어 있다. 전화망 인터페이스 모듈은 전화망을 이용한 교환기와의 호 처리 및 이벤트 처리를 담당하며, 전화망 접속카드와 밀접한 관계를 가지고 있다. 음성입력 및 인식 모들은 호 접속이 이루어진 채널로부터 음성을 입력받아 단어인식 기능을 수행하는 부분으로서 멀티 채널을 수용할 수 있는 구조로 설계되어 있다. 음성인식 모델은 문맥 종속형 CHMM 모델이며, 각각의 HMM 모델은 3-state, skip path 로 구성되어 있다. 음성인식 모듈내의 함수들은 모두 re-entrant 하도록 구성함으로써 멀티 채별이 가능하며, 각각의 채널은 모두 독립적인 메모리 공간에서 동작하도록 되어있다. 이와 같은 멀티채널 전화음성인식 시스템은 Dialogic보드를 이용하여 Windows NT에서 동작하도록 구현하였다. 실험결과, 구현된 시스템은 실시간으로 상용서비스가 가능한 인식율을 보였으며 원활한 멀티채널 지원이 가능하였다.

• Annual Conference on Human and Language Technology
• /
• 1993.10a
• /
• pp.101-110
• /
• 1993

본 논문에서는 연속분포 hidden Markov 모델을 이용한 화자독립 연속 음성 인식 시스템에 관해 기술한다. 연속분포 모델은 평균과 분산 벡터로 구성되며 음성신호를 직접 모델링하여 양자화 왜곡이 없어진다. 특징벡터는 filter bank 계수 및 그 1, 2차 미분계수를 사용하여 음성신호의 동적 특성을 반영하였다. Segmental K-means 알고리즘을 이용하여 학습하였으며, 연속어 인식에서 가장 문제가 되는 조음화 현상으로 인한 인식률 저하를 막기 위해 앞뒤의 음소를 고려해 주는 triphone을 인식단위로 사용하였다. Search 알고리즘으로는 시간 면에서 효율이 좋은 one-pass search 알고리즘을 사용하였다. 성능 평가를 위한 화자 독립 인식 실험에서 문법이 없을 경우 83%, finite state network율 적용한 경우에는 94%의 인식률을 나타내었다.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.1
• /
• pp.485-492
• /
• 2018

In this paper, we propose facial expression recognition using CNN (Convolutional Neural Network), one of the deep learning technologies. The proposed structure has general classification performance for any environment or subject. For this purpose, we collect a variety of databases and organize the database into six expression classes such as 'expressionless', 'happy', 'sad', 'angry', 'surprised' and 'disgusted'. Pre-processing and data augmentation techniques are applied to improve training efficiency and classification performance. In the existing CNN structure, the optimal structure that best expresses the features of six facial expressions is found by adjusting the number of feature maps of the convolutional layer and the number of nodes of fully-connected layer. The experimental results show good classification performance compared to the state-of-the-arts in experiments of the cross validation and the cross database. Also, compared to other conventional models, it is confirmed that the proposed structure is superior in classification performance with less execution time.

• Proceedings of the KIPE Conference
• /
• 2001.07a
• /
• pp.301-304
• /
• 2001

In this paper, a method which can detect tracking caused by the insulation deterioration of conduct wiring, is proposed. The computer which take experiment data is learned by neural network algorithm, which has recently been used for the load recognition. The proposed method in our study can be applied to the development of several measuring equipments such as hot-line insulation tester, car earth tester for the detection of tracking under hot-line state.

• The Korean Journal of Pain
• /
• v.25 no.2
• /
• pp.75-80
• /
• 2012

Hypnosis is an altered state of consciousness that comprises of heightened absorption in focal attention, dissociation of peripheral awareness, and enhanced responsiveness to social cues. Hypnosis has a long tradition of effectiveness in controlling somatic symptoms, such as pain. Pain, the most common symptom in clinical practice, is a multi-dimensional experience, which includes sensory-discriminative, affective-emotional, cognitive and behavioral components. There is a growing recognition for hypnosis and related techniques in pain management. Psychological approaches to pain control, such as hypnosis, can be highly effective analgesics, but are underused in Korea. In this article, we would like to review the basic concepts of hypnosis, the mechanism, and the outcome data of the analgesic effects of hypnosis, and also, its limitations.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.1
• /
• pp.358-362
• /
• 2013

RFID reader platform with self-diagnosis function studied in this paper has an automatic state recognition function, a report function, and an automatic upgrade function. Also, since it uses frequency operation policy in multiple reader environments, it will be frequently used in the large operation environment and multi-readers environment. Therefore, the technology can meet the demands not only in the domestic RFID market, but in the global market.

• Journal of Navigation and Port Research
• /
• v.32 no.2
• /
• pp.127-132
• /
• 2008

The safety degree of navigation for collision avoidance is closely related with the combination between mariner's behavior and navigational environment. The condition of navigational environment is mainly decided by navigable waters, ship traffic, rule of road, sea state, weather and so on. Especially, the condition of navigable waters and ship traffic in navigational environment are ones of the important factors to attain safe navigation when mariners are underway and crossing, head on or overtaking situation. Thus this paper is to analyze the characteristics of mariner's behavior for collision avoidance caused by ship traffic and navigable waters by analyzing the contents of questionnaire and the results of international collaborative research. As a result, it can be concluded that the density of ship traffic and the area of navigable waters affect mariner's ship handling for collision avoidance.

• Current Optics and Photonics
• /
• v.3 no.5
• /
• pp.390-400
• /
• 2019

Encrypted images obtained through double random phase-encoding (DRPE) occupy considerable storage space. We propose efficient compression schemes to reduce the size of the encrypted data. In the proposed schemes, two state-of-art compression methods of JPEG and JP2K are applied to the quantized encrypted phase images obtained by combining the DRPE algorithm with the virtual photon counting imaging technique. We compute the nonlinear cross-correlation between the registered reference images and the compressed input images to verify the performance of the compression of double random phase-encoded images. We show quantitatively through experiments that considerable compression of the encrypted image data can be achieved while security and authentication factors are completely preserved.

• Journal of the Korea Safety Management & Science
• /
• v.19 no.4
• /
• pp.53-62
• /
• 2017

It has come to attention that a risk-assessing organization, that will benchmark a company's safety department, is imperative, following an increase in large-scale SOC-business project, construction of higher-raised buildings, development of underground space; all that have increase accident rates. Having faced problems that arise in firms that demand diversity, complexity and instantaneity, the purpose of the thesis is to arrive at efficient and practical problem-solving means. In order to solve the problems that would surface theoretically during an actual risk assessment, the state of the operation systems of the top five national construction firms having a hazard rate of 0.25 times less than the average rate have been analyzed, while a hierarchal recognition research of the employees who not only function at the operating level but are the practice subjects of a firm, has also been conducted, bringing the main text.