• The Journal of the Acoustical Society of Korea
• /
• v.14 no.5
• /
• pp.74-82
• /
• 1995

This paper is study on the voice dialing using HMM and post processing of the connected digits. HMM algorithm is widely used in the speech recognition with a good result. But, the maximum likelihood estimation of HMM(Hidden Markov Model) training in the speech recognition does not lead to values which maximize recognition rate. To solve the problem, we applied the post processing to segmental K-means procedure are in the recognition experiment. Korea connected digits are influenced by the prolongation more than English connected digits. To decrease the segmentation error in the level building algorithm some word models which can be produced by the prolongation are added. Some rules for the added models are applied to the recognition result and it is updated. The recognition system was implemented with DSP board having a TMS320C30 processor and IBM PC. The reference patterns were made by 3 male speakers in the noisy laboratory. The recognition experiment was performed for 21 sort of telephone number, 252 data. The recognition rate was $6\%$ in the speaker dependent, and $80.5\%$ in the speaker independent recognition test.

• Journal of the Korean Chemical Society
• /
• v.61 no.6
• /
• pp.369-377
• /
• 2017

The purpose of this study was to investigate high school students' perceptions on chemistry subjects: reasons for choosing chemistry, learning volume and content difficulty, interests, teaching/learning methods, preferable classes etc. A total of 1,087 students who took chemistry subjects at 126 high schools by proportional stratified sampling were voluntarily participated in the survey. The main reasons the students chose chemistry subjects were interests and interests in chemistry, foundation to science, relevance to college majors, and so on. Students recognized that the learning volume and content difficulty as normal level was about 60%. Reasons why chemistry was difficult was that, although there was a difference in degree, chemistry was difficult in itself and had too much things to memorize. In the case of interests in chemistry subjects, students of 43.9% of Chemistry I and 52.0% of Chemistry II recognized the level as normal. The reason why not interested in chemistry subjects was that it was the nature of chemistry contents, or students had neither interests and enjoyment of chemistry nor foundation for chemistry. Classes were mostly lectures but the students preferred mainly experimental activities, or explanation with real-life examples or science stories. The frequency of experimental activities was found to be 1 to 5 times per semester, or not experimented. Research and efforts will be necessary to improve classes and environments for students' experimental activities.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.750-753
• /
• 2005

Internet service, a part of our life, requires the changes not only of environment in our life but also of people's sense of value. It also requires a quick change in the spear of education activities without exception. It brought a lot of changes into educational methods, our recognition on education, and various kinds of educational tools and environment. The introduction of WBI (Web Based Instruction) is one of the most important thing. This study have applied WBI to Industrial high school education to improve its quality and accomplish its effective teaching-learning. That is, we have applied CNC(Computerized Numerical Control) and Processing learning to machining center learning and have given students chances and various learning materials so that they could contact with new information. We aimed at testing and studying some effects on the improvements of learning accomplishment and motive in this study.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2006.11a
• /
• pp.11-14
• /
• 2006

최근 정보통신 기술의 급속한 발전으로 소형 이동형 단말기를 이용한 각종 스포츠 경기 시청이 두드러지게 증가하고 있다. 그럼에도 불구하고 이동형 단말기를 통해 제공되는 영상은 일반 TV나 HDTV용으로 제작되어 소형 이동형 단말기의 사용자가 화면을 통해 스포츠 경기의 상황을 인식하는데 많은 불편함을 주고 있다. 특히, 경기 진행 시간이나 점수를 포함하는 점수상자(scoreboard)는 경기의 상황을 파악하는데 매우 중요한 역할을 하나, 소형 이동형 단말기의 작은 화면에서는 점수상자의 내용을 정확히 인식하기가 쉽지 않다. 이에 본 논문은 많은 사람들이 즐겨보는 축구 경기에 대하여 짧은 학습 기간을 갖는 효율적인 점수상자 추출 방법을 제안하고자 한다. 제안하는 알고리즘은 전수상자와 주변 환경의 밝기 정보를 이용한 점수상자 경계 좌표 추출, 학습을 통한 최적의 경계 좌표 결정, 전수상자 영역 추출 및 확대의 세 단계로 구성된다. 제안하는 알고리즘은 점수상자가 없는 프레임에서도 몇 프레임 앞서 표시된 점수상자의 저장을 통해 디스플레이가 가능하도록 하였다. 다양한 축구경기 비디오에 대한 실험을 통해 제안된 알고리즘이 소형 이동형 단말기 상에서 점수상자를 추출하고 이를 사용자가 쉽게 인식할 수 있도록 확대하여 디스플레이 하는 좋은 해결책임을 보이고자 한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.11a
• /
• pp.127-128
• /
• 2010

본 논문에서는 CCTV 감시 영상에서 취득한 얼굴 이미지를 이용하여, 범죄자 감시목록에 등록된 범죄 용의자를 탐지 식별하는 시스템을 설계 및 구현하였다. 특히 본 논문에서 제안한 SVDD와 SRC를 혼합한 계층적 구조의 범죄 용의자 식별 모듈은 다음과 같은 특성을 갖는다: 1) 먼저 SVDD를 이용하여 범죄 용의자만을 빠르게 인식함으로써, 일반인에 대한 불필요한 범죄자 식별 연산을 수행하지 않는다; 2) 다양한 식별 성능을 저해하는 환경에서도 이미 강인한 성능이 검증된 SRC를 범죄 용의자 식별과정에 적용함으로써 안정적이고 정확한 식별 시스템을 보장한다; 3) 동일 생체 특정의 반복적 사용을 통한 다수결 투표전략을 취함으로써 시스템의 신뢰도를 보장한다; 4) 점증적 갱신의 학습 능력으로 인하여 범죄 용의자 감시목록 데이터베이스의 변화에도 능동적으로 적응한다 실제 KUFD(Korea University Face Database)를 자체 제작하고 캠퍼스 내에서 CCTV 환경의 얼굴 인식 기반 범죄 용의자 탐지 및 식별 시스템 환경을 모의 구축하여 실험적으로 제안된 시스템의 성능을 검증한다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.2
• /
• pp.120-126
• /
• 2009

In order to reduce the noise quantity in a conversation under the noisy environment it is necessary for the signal processing system to process adaptively according to the noise quantity in order to enhance the performance. Therefore this paper presents a recognition method for noise quantity by linear predictive coefficient using a three layered neural network, which is trained using three kinds of speech that is degraded by various background noises. The performance of the proposed method for the noise quantity was evaluated based on the recognition rates for various noises. In the experiment, the average values of the recognition results were 98.4% or more for such noise using Aurora2 database.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.4 s.36
• /
• pp.47-56
• /
• 2005

With the development of wearable(ubiquitous) computers, those traditional interfaces between human and computers gradually become uncomfortable to use, which directly leads to a requirement for new one. In this paper, we study on a new interface in which computers try to recognize the gesture of human through a digital camera. Because the method of recognizing hand gesture through camera is affected by the surrounding environment such as lighting and so on, the detector should be a little sensitive. Recently, Viola's detector shows a favorable result in face detection. where Adaboost learning algorithm is used with the Haar features from the integral image. We apply this method to hand area detection and carry out comparative experiments with the classic method using skin color. Experimental results show Viola's detector is more robust than the detection method using skin color in the environment that degradation may occur by surroundings like effect of lighting.

• The Journal of Korean Association of Computer Education
• /
• v.19 no.6
• /
• pp.33-44
• /
• 2016

In this study, learning preferences of the informatics gifted participating in on-line programming practice has been investigated and the tutoring strategy based on learning styles was developed and verified its effectiveness. On-line programming learning is the environment in which learning is done through interaction with a tutor. For determination of the students' learning styles, Grasha-Reichmann's learning style was utilized. Key elements, learning activity and feedback, of tutoring strategy were derived based on learning style and developed on-line programming learning tutoring strategy. To verify the effectiveness, six-class period of learning C-language of 173 middle and high school students based on learning styles was applied for 12 weeks. As a result, the experiment group applied with a tutoring strategy based on the learning style showed significant improvements in terms of satisfaction and achievement than the control group.

• Proceedings of the KIEE Conference
• /
• 2008.09a
• /
• pp.255-257
• /
• 2008

초고속 전기정보의 전송 시대와 U-정보전자시대에 응용하는 최신 정보기기와 의료기기 및 군사정보의 실시간 전송을 위하여 많은 실시간 알고리즘과 모델링의 연구가 필수적이다. 또한 원격지에 많은 전기 및 전력정보를 비선형적 특성이 있는 환경하에서도 정보의 오차가 없이 실시간으로 전송하는 기술은 현대 정보사회에서 해결해야 할 매우 중요한 요소중에 하나이다. 이러한 내용으로 수행되어지는 신경회로망을 이용한 실시간 모델링을 제안하고자 한다. 이와 관련한 일반적인 방법으로 역전파 학습 알고리즘을 들 수 있다. 파라미터에도 덜 민감하며, 특히 온라인으로 인식과 제어가 가능하도록 수렴속도를 향상 시켜야하는 새로운 모델의 필요성이 요구된다. 본 연구에서는 기존의 신경회로망이 가지고 있는 여러 단점들을 개선하고자 새로운 학습 알고리즘과 새로운 구조의 신경회로망을 제시한다. 또한 제시한 알고리즘을 이용하여 불규칙적 시스템 모델망과 다양한 센서 모델링 등에 연결하여 다양한 실험을 수행하여 그 결과를 보여 실시간 특성을 갖는 것을 입증해 보였다.

• Journal of The Korean Association For Science Education
• /
• v.29 no.5
• /
• pp.552-563
• /
• 2009

The purpose of this study is to investigate the students' perception of the learning support system of Korea Science Academy and to propose improvements to it. The impact of the science learning support system on 129 gifted students in Korea Science Academy (KSA) was estimated by using Likert-type items and the multiple-choice method approach for more comprehensive evaluation. The results of our investigation are as follows: First, the learning support system of KSA appears globally useful to the students. The list of educational usefulness to the students comprises, in the decreasing order of utility, classroom work, Internet, lab activities, reading rooms, library, research meetings and clubs, academic advisors (AA), SAF (Science Academy Fair), e-learning system, and finally colloquia by invited lecturers. Second, what the gifted students hope for in the realm of learning support from KSA are learning guides by subject teachers, presentation skill program, the constructions of on/off-line learning communities, etc. It seems that the results of this study would be helpful in improving the learning support system, and will provide useful information for planning the direction of future science-gifted education programs at the high-school level.