• 한국콘텐츠학회논문지
• /
• 제21권9호
• /
• pp.543-556
• /
• 2021

본 연구는 현장에서 수어통역 서비스를 제공하는 수어통역사와 청각장애인통역사 그리고 수어통역서비스를 이용하는 농인들을 대상으로 초점집단면접을 실시하여 현 수어통역사 자격제도에 대한 구체적인 인식을 알아보고 이를 통해 수어통역사 자격제도 운영의 개선점을 살펴보고자 하였다. 주제분석 결과 각 그룹별로 세 개의 상위범주가 도출되었고 이를 다시 종합한 결과 '수어통역 역량과 전문성을 공인받을 수 있는 자격제도로의 변화'와 '한국수어와 농문화에 기초한 자격제도로의 개선'으로 정리되었다. 이상의 연구결과를 토대로 '수어통역사 자격시험 관리 운영을 전담하는 상설 기관 신설', '수어통역의 전문성 및 수준과 경력이 반영된 자격제도로 개편', '모든 시험 문제와 시험의 과정을 수어 중심으로 진행', '농인이 주체가 되는 시스템', '수어통역사와 청각 장애인통역사를 위한 윤리강령 제정'을 제언하였다.

• 한국지역사회생활과학회지
• /
• 제23권1호
• /
• pp.41-50
• /
• 2012

This study was performed to understand the depression of children with hearing impairment with relation to their mothers' nurturing attitude and sign language level. The subjects were 131 hearing impaired children aged from 9 to 16 years and their mothers, who had no hearing impairments. The children's depression was assessed by CDI(Kovacs 1983) adapted by Cho and Lee(1990), and the maternal attitude was measured through the instrument developed by Oh and Lee(1982) and revised by Lim(1987). The results were as follows. First, the girls' depression was higher than the boys', and children in a dormitory type of school showed higher depression than those in a general type of school. Second, children's depression did not show differences according to mother-child communication methods but differed according to mothers' sign language level. Children whose mothers had high level of sign language showed the highest depression and those whose mothers had beginning level of sign language showed the lowest depression. And mothers' affective, goal- achieving and rational attitude were negatively related with children's depression. Third, the depression of hearing impairment children was influenced mainly by the maternal affective attitude, and the next order was the type of school the children attend.

• 스마트미디어저널
• /
• 제12권1호
• /
• pp.32-46
• /
• 2023

Natural Language Processing (NLP) has grown tremendously in recent years. Typically, bilingual, and multilingual translation models have been deployed widely in machine translation and gained vast attention from the research community. On the contrary, few studies have focused on translating between spoken and sign languages, especially non-English languages. Prior works on Sign Language Translation (SLT) have shown that a mid-level sign gloss representation enhances translation performance. Therefore, this study presents a new large-scale Korean sign language dataset, the Museum-Commentary Korean Sign Gloss (MCKSG) dataset, including 3828 pairs of Korean sentences and their corresponding sign glosses used in Museum-Commentary contexts. In addition, we propose a translation framework based on self-supervised learning, where the pretext task is a text-to-text from a Korean sentence to its back-translation versions, then the pre-trained network will be fine-tuned on the MCKSG dataset. Using self-supervised learning help to overcome the drawback of a shortage of sign language data. Through experimental results, our proposed model outperforms a baseline BERT model by 6.22%.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1319-1323
• /
• 2004

In this paper, a problem of Thai sign language recognition using a neural network is considered. The paper addresses the problem in classifying certain signs conveying quantitative meaning, e.g., large or small. By treating those signs corresponding to different quantities as derived from different classes, the recognition error rate of the standard multi-layer Perceptron increases if the precision in recognizing different quantities is increased. This is due the fact that, to increase the quantitative recognition precision of those signs, the number of (increasingly similar) classes must also be increased. This leads to an increase in false classification. The problem is due to misinterpreting the amount of quantity the quantitative signs convey. In this paper, instead of treating those signs conveying quantitative attribute of the same quantity type (such as 'size' or 'amount') as derived from different classes, here they are considered instances of the same class. Those signs of the same quantity type are then further divided into different subclasses according to the level of quantity each sign is associated with. By using this two-level classification, false classification among main gesture classes is made independent to the level of precision needed in recognizing different quantitative levels. Moreover, precision of quantitative level classification can be made higher during the recognition phase, as compared to that used in the training phase. A standard multi-layer Perceptron with a back propagation learning algorithm was adapted in the study to implement this two-level classification of quantitative gesture signs. Experimental results obtained using an electronic glove measurement of hand postures are included.

• 한국멀티미디어학회논문지
• /
• 제25권9호
• /
• pp.1257-1265
• /
• 2022

Recognition of sign language is challenging due to the occlusion of hands, accuracy of hand gestures, and high computational costs. In recent years, deep learning techniques have made significant advances in this field. Although these methods are larger and more complex, they cannot manage long-term sequential data and lack the ability to capture useful information through efficient information processing with faster convergence. In order to overcome these challenges, we propose a word-level sign language recognition (SLR) system that combines a real-time human pose detection library with the minimized version of the gated recurrent unit (GRU) model. Each gate unit is optimized by discarding the depth-weighted reset gate in GRU cells and considering only current input. Furthermore, we use sigmoid rather than hyperbolic tangent activation in standard GRUs due to performance loss associated with the former in deeper networks. Experimental results demonstrate that our pose-based optimized GRU (Pose-OGRU) outperforms the standard GRU model in terms of prediction accuracy, convergency, and information processing capability.

• 한국연극학
• /
• 제52호
• /
• pp.271-317
• /
• 2014

This essay studied the acting theories of Diderot, Delsarte, Meyerhold, and Artaud to know the historical formation of 'sign acting' and its theoretical and aesthetic appropriateness. The sign acting so far discussed shows the repetitive patterns of idea as follows. The sign acting (1) emphasizes the physical expression such as gesture and movement, (2) assumes that the physical expression functions as a sign evoking special emotion and thought, (3) thus recommends the imitation of the outer sign, (4) uses a tableau for the effective reception of outer sign, (5) aims for the spectator oriented aesthetics as it stresses the result of outer sign rather than the creative process of a role, (6) assumes that the emotional reaction or the intellectual understanding springs from the physical experience, (7) thus emphasizes the physical language rather than speech, (8) can attain the appropriateness of physical language by the recent theories of cognitive science. Besides having such commonness, the sign acting also reveals the individual differences. For instance, the intended sign for Diderot and Delsarte was the sign of emotion, for Meyerhold the stylized sign of circus and acrobatics, and for Artaud the spiritual sign. If Diderot and Meyerhold demands the cool consciousness for the correct sign acting, Artaud's sign acting tends to pursue the state of trance. And if Diderot, Delsarte, and Meyerhold think the sign acting on the level of sensory appeal, Artaud insists that the sign acting should dismantle the spectator's sense. As such the discussion of sign acting shows both recurrent ideas and new visions, forming an unity out of diversity. Perhaps the sign acting is a matter of practice before we consider it as a theory. It is not only supposed to have been existed practically since ancient theatre, but also used by actors consciously and unconsciously in expressing certain emotion and thought. We need to study the sign acting more academically, considering its long history and aesthetic potentials. In fact the sign acting has been an essential element of acting, in spite of bad reputation judging it as a banal and worn-out style. It is true that the sign acting, in the worst case, could produce a stereotypical expression. It was this aspect of sign acting that caused a fierce negative reaction of the realists who sought the natural expression based upon psychological truth. Of course the sign acting has a serious problem when it stays banal and artificial. But we need to see this issue from a different perspective. What is the natural expression of emotion? How is it free from the learned way of expression? In some respect, we use, in reality, a learned expression of emotion that could be accepted socially. For instance, when we attend a funeral, we use the outer sign of mourning gestures learned socially. If a semiotic expression pervades various aspects of our life, the acting, being the representation of life, seems not to be free from codified expression. The sign acting could be used consciously and unconsciously in all kinds of acting.

• 한국간호교육학회지
• /
• 제12권2호
• /
• pp.143-150
• /
• 2006

Purpose: The purposes of this study were to identify the actual conditions and needs of the health care utilization and health information in deafs. Methods: Forty-one deaf volunteers were interviewed by suwha nursing students. The semi-structured interviews were conducted in sign language at homes and community centers. The instrument developed by researchers consisted of 22 items including demographic information, health care utilization, and open-ended questions. Data were analyzed using content analysis, frequency and percentage. Results: The most discomfort problems were communication difficulty and expression of symptom. The deaf people wanted to learn about diseases and symptoms. The deaf wanted to get information about cancer. Conclusions: Further studies focusing on educational intervention are needed to increase the knowledge level on disease of deaf. The sign language translators are needed to help communication for deaf in health care facilities.

• 한국사회복지학
• /
• 제45권
• /
• pp.315-340
• /
• 2001

The purpose of study is to examine the effects of family support on the life satisfaction of elderly with disabilities and provide a ground necessary to improve it. Research was conducted on 167 elderly with hearing, visual and physical disabilities aged over 60 who were living in Seoul and Pusan. Telephone survey, sign language and interview, in accordance with types of disability, were adopted to collect data effectively. That is telephone survey was used for elderly with visual impairment whereas face-to-face interview for physical impairment and sign language for hearing impairment by volunteers. Collected data were analyzed, using hierarchical regression analysis. This study utilized two different models, direct effect model and buffering effect of social support in order to examine the effects of familial support on the life satisfaction of elderly with disabilities. Research findings suggest that the level of life satisfaction appeared to be low in general among elderly with disabilities and emotional family support exerted a positive effect on life satisfaction. In addition, it is empirically supported that emotional family support buffered the negative effect of economic limitations on life satisfaction. In other words, the effects of economic limitations as stress factor decreased with the increase in the frequency of emotional support, however, the level of life satisfaction decreased at a mercy of the stress factor of economic limitations with the decrease in the frequency of emotional support. Finally, this paper attempted to provide some alternatives to effectively improve life satisfaction among elderly with disabilities based on empirical findings.

• 한국전자거래학회지
• /
• 제12권4호
• /
• pp.127-144
• /
• 2007

본 논문에서는 RFID 미들웨어와 이에 연결된 정보 서비스(Information Service), 네임 서비스(Object Name Service), 상위 애플리케이션을 위한 웹 서비스 등을 통합적으로 관리하기 위한 보안 관리기를 기술한다. 또한 분산된 RFID 시스템의 개체에 대한 접근제어를 확립하기 위해 기존의 사용 제어 모델과 SAML의 assertion을 확장하여 싱글사인온(Single-Sign On)을 구현하였다. 본 논문에서 제시한 RFID 보안 기술은 미들웨어에 포함되어 RFID 정보보호에 기여하고 향후 유비쿼터스 센서 네트워크 분야에서도 동일하게 적용될 수 있을 것이다.

• ETRI Journal
• /
• 제45권6호
• /
• pp.1022-1034
• /
• 2023

In this study, the impact of varying lighting conditions on recognition and decision-making was considered. The luminosity approach was presented to increase gesture recognition performance under varied lighting. An efficient framework was proposed for sensor-based sign language gesture identification, including picture acquisition, preparing data, obtaining features, and recognition. The depth images were collected using multiple Microsoft Kinect devices, and data were acquired by varying resolutions to demonstrate the idea. A case study was designed to attain acceptable accuracy in gesture recognition under variant lighting. Using American Sign Language (ASL), the dataset was created and analyzed under various lighting conditions. In ASL-based images, significant feature points were selected using the scale-invariant feature transformation (SIFT). Finally, an artificial neural network (ANN) classified hand gestures using specified characteristics for validation. The suggested method was successful across a variety of illumination conditions and different image sizes. The total effectiveness of NN architecture was shown by the 97.6% recognition accuracy rate of 26 alphabets dataset with just a 2.4% error rate.