• Proceedings of the Acoustical Society of Korea Conference
• /
• 1996.10a
• /
• pp.76-79
• /
• 1996

본 논무에서는 한국어 음소를 대상으로 Kohonen 이 제안한 LVQ2 방법의 결저을 보완한 MLVQ2 방법으로 인식실험을 행하고 MLVQ2 알고리즘의 유효성을 검토하고자 한다. 인식실험을 위한 음성자료는 ETRI 611단어로부터 추출한 49음소를 사용하였다. 그리고 인식실험에 있어서는 먼저 파열음을 대상으로 학습회수, 표준패턴의 수, 샘플수에 따른 인식률의 변화를 조사하였으며, 이 결과 표준패턴의 수 15개, 학습회수 10회 이하, 샘플 수 3000 개일 경우가 가장 좋은 인식률을 보였다. 이 결과를 참고로 음소군별 인식실험 결과 모음 69.11%, 파열음 74.69%, 마찰음 및 파찰음 86.31%비음 및 유음 74.51%의 평균 인식률을 얻었다. 또한 , 한국어 49음소 전음소에 대한 인식실험 결과 71.2%의 인식률 얻어 MLVQ2의 유효성을 확인하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1998.06a
• /
• pp.111-114
• /
• 1998

음성을 인식하기 위해서는 주어진 음성을 미리 정한 기준 음성과 비교하여 가장 유사한 것을 갖는 과정을 거치게 된다. 같은 단어라도 화자에 따라서 발음 속도, 음의 강약이 틀리므로 화자 독립 음성 인식을 위해서는 여러 화자가 발음한 음성을 기준 음성으로 사용하여 인식 성능을 향상시킬 수 있다. 그러나 화자 수를 증가시켜도 인식 성능의 향상에는 한계를 보이고 있다. 이러한 문제점은 현재 음성에서 추출되는 피춰가 인식에 필요한 정보를 충분히 포함하지 않는 것과 인식 알고리즘의 효율성 등에서 원인을 찾을 수 있다. 본 논문에서는 남자 10명과 여자 10명이 발음한 한국어 숫자음을 인식 대상으로 하여 멜켑스트럼을 추출하고 DTW에 의해 인식을 수행하여 피춰 추출의 관점에서 화자 수 증가에 따른 인식률의 변화와 그 한계에 대해서 분석한다.

• Journal of Korea Game Society
• /
• v.3 no.2
• /
• pp.19-23
• /
• 2003

컴퓨터 기술의 발전에 따라서 게임분야 역시 다양한 첨단 기술이 적용되고 있다. 예를 들면 강력한 3D가속 기능을 가진 비디오카드, 5.1 채널 사운드, 포스피드백 지원 입력 장치, 운전대, 적외선 센서, 음성 감지기 등이 게임의 입출력 인터페이스로서 이용되고 있다. 전형적인 방법 이외에도 광학방식이나 휴대용 게임기에 대한 플레이 방식에 대한 연구도 활발하다. 최근에는 비디오 게임기에도 사람의 동작을 인식하여 게임의 입력으로 받아들이는 기술이 상용화되기도 하였다. 본 논문에서는 이런 발전 방향을 고려하여 차세대 게임 인터페이스의 방식으로서 사용될 수 있는 사람의 표정 인식을 통한 인터페이스 구현을 위한 접근 방법들에 대하여 고찰을 하고자 한다. 사람의 표정을 입력으로 사용하는 게임은 심리적인 변화를 게임에 적용시킬 수 있으며, 유아나 장애자들이 게임을 플레이하기 위한 수단으로도 유용하게 사용될 수 있다. 영상을 통한 자동 얼굴 인식 및 분석 기술은 다양한 응용분야에 적용될 수 있는 관계로 많은 연구가 진행되어 왔다. 얼굴 인식은 동영상이나 정지영상과 같은 영상의 형태, 해상도, 조명의 정도 등에 따른 요소에 의하여 인식률이나 인식의 목적이 달라진다. 게임플레이어의 표정인식을 위해서는 얼굴의 정확한 인식 방법을 필요로 하며, 이를 위한 비교적 최근의 연구 동향을 살펴보고자 한다.

• Journal of Christian Education in Korea
• /
• v.71
• /
• pp.23-59
• /
• 2022

This paper explored the effect of digital epistemology on Christian education. The media of an era determines the type and form of the epistemology of that era, which in turn has a decisive influence on the direction of Christian education in that era. Therefore, it consists of three parts. First, an investigation on the relationship between media and epistemology, second, an investigation on digital epistemology, and third, an investigation on the effect of digital epistemology on Christian education. In this paper, first, from the perspective of McLuhan's media theory, it was discovered that media go beyond simply expanding the our senses and change our perception through creating a new environment and way of life. This paper could characterize digital epistemology in the following four ways through comparison with the traditional epistemology of the print media era: namely "from linguistic to omnisensory epistemology", "from causality to relational epistemology", "from historical to post-historical thinking", and "from interpretive to performative epistemology". In addition, it examined the effects of that digital epistemology on Christian education. Through this study, it found that digital media can act both positively and negatively on the essence of Christian education. Therefore, the task of Christian education in the digital age is to make it a positive function rather than a dysfunctional one, and an opportunity rather than a challenge.

• 한국과학기술학회:학술대회논문집
• /
• 2002.12a
• /
• pp.99-116
• /
• 2002

• LP가스
• /
• s.105
• /
• pp.35-42
• /
• 2006

산업체 시설, 공략대상 급부상...LPG업계 인식 변화 선결돼야 안전관리자.검사체계 현실맞게 바꿔야 변화없이 LPG공급 통한 수익 기대 금물

• Journal of Korean Home Economics Education Association
• /
• v.19 no.1 s.43
• /
• pp.65-79
• /
• 2007

The purpose of this study was to test the effects of practical reasoning home economics instruction on middle school students' views of home economics. Thomas(1986) categorized six alternative views of home economics as education for women, manual training, application of science, household management, family development, and an intervention. This study carried a quasi-experiment research with an independent variable of types of instruction and a dependent variable of views of home economics. The experiment was carried with the sample of 137 8th grade students in Gwangju area for ten class hours. Paired t-test was performed to examine the pretest-posttest differences of each experiment group and comparison group. The results showed that practical reasoning instruction improved level of the view of home economics as an intervention, and decreased level of the view of home economics as manual training. From the results of this study, conclusion can be made that practical reasoning home economics instruction is effective in changing to the appropriate views of home economics. Also it is expected that current Korean home economics textbook can lead to the views of home economics as household management and as family development.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.9
• /
• pp.345-350
• /
• 2018

This study is an algorithm for detecting vein pattern features important for finger vein recognition. The feature detection algorithm is important because it greatly affects recognition results in pattern recognition. The recognition rate is degraded because the reference is changed according to the finger position change. In addition, the image obtained by irradiating the finger with infrared light is difficult to separate the image background and the blood vessel pattern, and the detection time is increased because the image preprocessing process is performed. For this purpose, the presented algorithm can be performed without image preprocessing, and the detection time can be reduced. SWDA (Down Slope Trace Waveform) algorithm is applied to the finger vein images to detect the fingertip position and vein pattern. Because of the low infrared transmittance, relatively dark vein images can be detected with minimal detection error. In addition, the fingertip position can be used as a reference in the classification stage to compensate the decrease in the recognition rate. If we apply algorithms proposed to various recognition fields such as palm and wrist, it is expected that it will contribute to improvement of biometric feature detection accuracy and reduction of recognition performance time.

• Korean Journal of Cognitive Science
• /
• v.18 no.3
• /
• pp.255-284
• /
• 2007

This study explored the ESL college learners' perceptions on integrating reading and writing in the context of the reading-to-write composition classroom. Using the panel survey (N=60) that repeatedly measured the same set of individuals at three different times during a semester, this study examined whether students' perceptions on reading-writing integrations were reshaped over the course of classroom practices. The survey instrument was developed to assess the perception scores from less integrative continua to more integrative continua on a 5-point Likert scale. A two-factor ANOVA with repeated measures was performed to evaluate mean differences across the perception groups and over the three treatment times. The results do not demonstrate a significant treatment effect, suggesting that L2 learners' integrative perceptions were stable over the course of the semester. The dynamics in the perception changes differed widely across the perception groups. This result provides insights into understanding students' reading-writing practices and thus into instructional practices applicable to the classrooms. The present study argues for 12 learners' perceptions on integrating reading and writing as a key construct to understand their literacy practices involved in the composing process.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.5
• /
• pp.783-788
• /
• 2002

Recently, research and developmental direction of communication system is concurrent adopting voice data and face image in speaking to provide more higher recognition rate then in the case of only voice data. Therefore, we present a method of lipreading in speech image sequence by using the 3-D facial shape model. The method use a feature information of the face image such as the opening-level of lip, the movement of jaw, and the projection height of lip. At first, we adjust the 3-D face model to speeching face Image sequence. Then, to get a feature information we compute variance quantity from adjusted 3-D shape model of image sequence and use the variance quality of the adjusted 3-D model as recognition parameters. We use the intensity inclination values which obtaining from the variance in 3-D feature points as the separation of recognition units from the sequential image. After then, we use discrete HMM algorithm at recognition process, depending on multiple observation sequence which considers the variance of 3-D feature point fully. As a result of recognition experiment with the 8 Korean vowels and 2 Korean consonants, we have about 80% of recognition rate for the plosives md vowels.