• 한국컴퓨터산업학회논문지
• /
• 제6권5호
• /
• pp.791-800
• /
• 2005

본 논문에서 ASP 프로그래밍 능력 향상을 위한 교육용 컨텐츠를 개발하였다. 여기서 개발된 교육용 컨텐츠는 구성주의에 바탕을 둔 교수 학습 모델의 하나인 인지적 도제 모델을 적용하였다. 특히, 본 컨텐츠를 통해서 학습자는 멀티미디어로 만들어진 교육용 동영상을 통해 학습할 수 있고, 실제 실습 환경과 유사하게 실행되는 동영상의 예제에 따라 프로그래밍을 실습할 수 있으며, 주어진 과제를 해결함으로써 스스로 이해 수준을 파악할 수 있다. 따라서 이 교육용 컨텐츠는 학습자 스스로가 프로그래밍 실습에 흥미를 가지고 학습을 유도하도록 개발하였으므로 학습 효과를 기대할 수 있다.

• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.235-238
• /
• 2019

In real world object detection is an active research topic for understanding different objects from images. There are different models presented in past and had significant results. In this paper we are presenting vehicle logo detection using previous object detection models such as You only look once (YOLO) and Faster Region-based CNN (F-RCNN). Both the front and rear view of the vehicles were used for training and testing the proposed method. Along with deep learning an image pre-processing algorithm called perspective transformation is proposed for all the test images. Using perspective transformation, the top view images were transformed into front view images. This algorithm has higher detection rate as compared to raw images. Furthermore, YOLO model has better result as compare to F-RCNN model.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 1999년도 제11회 한글 및 한국어 정보처리 학술대회 및 제1회 형태소 분석기 및 품사태거 평가 워크숍
• /
• pp.151-156
• /
• 1999

텍스트로부터 명사를 추출하기 위해서 다양한 기법이 이용될 수 있는데, 본 논문에서는 학습 데이터를 이용하여 생성한 규칙과 사전을 이용하는 단순한 모델을 통해 명사를 효과적으로 추출할 수 있는 기법에 대하여 기술한다. 사용한 모델은 기본적으로 명사, 어미, 술어 사전을 사용하고 있으며 명사 추정은 학습 데이터를 통해 생성한 규칙을 통해 이루어진다. 제안한 방법은 복잡한 언어학적 분석 없이 명사 추정이 가능하며, 복합명사 사전을 이용하지 않고 복합 명사를 추정할 수 있는 장점을 지니고 있다. 또한, 명사추정의 주 요소인 규칙이나 사전 등록어의 추가, 갱신 등이 용이하며, 필요한 경우에는 특정 분야의 텍스트 분석을 위한 새로운 사전의 추가가 가능하다. 제안한 방법을 이용해 "제1회 형태소 분석기 및 품사 태거 평가대회(MATEC '99')"의 명사 추출기 분야에 참가하였으며, 본 논문에서는 성능평가 결과를 제시하고 평가결과에 대한 분석을 기술하고 있다. 또한, 현재의 평가기준 중에서 적합하지 않은 부분을 규정하고 이를 기준으로 삼아 자체적으로 재평가한 평가결과를 제시하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.920-924
• /
• 2005

This paper presents adaptive learning data of evolvable neural networks (ENNs) for time series prediction of nonlinear dynamic systems. ENNs are a special class of neural networks that adopt the concept of biological evolution as a mechanism of adaptation or learning. ENNs can adapt to an environment as well as changes in the environment. ENNs used in this paper are L-system and DNA coding based ENNs. The ENNs adopt the evolution of simultaneous network architecture and weights using indirect encoding. In general just previous data are used for training the predictor that predicts future data. However the characteristics of data and appropriate size of learning data are usually unknown. Therefore we propose adaptive change of learning data size to predict the future data effectively. In order to verify the effectiveness of our scheme, we apply it to chaotic time series predictions of Mackey-Glass data.

• The Journal of the Acoustical Society of Korea
• /
• 제22권2E호
• /
• pp.62-68
• /
• 2003

This paper addresses a novel noise-compensation scheme to solve the mismatch problem between training and testing condition for the automatic speech recognition (ASR) system, specifically in car environment. The conventional spectral subtraction schemes rely on the signal-to-noise ratio (SNR) such that attenuation is imposed on that part of the spectrum that appears to have low SNR, and accentuation is made on that part of high SNR. However, these schemes are based on the postulation that the power spectrum of noise is in general at the lower level in magnitude than that of speech. Therefore, while such postulation is adequate for high SNR environment, it is grossly inadequate for low SNR scenarios such as that of car environment. This paper proposes an efficient spectral subtraction scheme focused specifically to low SNR noisy environment by extracting harmonics distinctively in speech spectrum. Representative experiments confirm the superior performance of the proposed method over conventional methods. The experiments are conducted using car noise-corrupted utterances of Aurora2 corpus.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 B
• /
• pp.933-935
• /
• 1999

In this paper, we present model predictive control scheme based on neural network to control discrete-time chaotic systems. We use a feedforward neural network as nonlinear prediction model. The training algorithm used is an adaptive backpropagation algorithm that tunes the connection weights. And control signal is obtained by using gradient descent (GD), some kind of LMS method. We identify that the system identification results through model prediction control have a great effect on control performance. Finally, simulation results show that the proposed control algorithm performs much better than the conventional controller.

• 한국컴퓨터정보학회논문지
• /
• 제23권3호
• /
• pp.79-84
• /
• 2018

The government developed National Competency Standards and expands field friendly education for innovation of industrial field based education training. NCS is the national level of standards that the government systemized knowledge, skills and attitudes required to work in industrial fields by each industry and each level. This study was intended to research NCS education contents of an introduction of dental hygienics, which is a basic major subject among subjects of dental hygiene course, to present learning goals accordingly, and to be used as a basic resource of NCS field oriented classes of dental hygienists through the comparison before and after. In case of the dental hygiene course, dental hygienists are performing important core tasks as clinicians at dental offices. Therefore, such comprehensive and professional performance abilities as scaling, oral prophylaxis and oral health education are required at the fields. The education process and education contents for this should be researched continuously.

• 한국컴퓨터정보학회논문지
• /
• 제23권3호
• /
• pp.107-115
• /
• 2018

This study aimed to explore the effect of college students' self-leadership and entrepreneurship on employment competency and identify the moderating effect of nationality. To this end, the validity of data collected from 450 college students attending a four-year university in Seoul was tested using structural equation modeling and AMOS statistical software. The study showed the following results. First, self-leadership was found to have a significant effect on entrepreneurship. Second, entrepreneurship was found to have a significantly positive effect on employment competency. Third, it was found that nationality exerted a partial effect on the relationship of self-leadership and entrepreneurship to employment competency. Based on these findings, this study indicated that developing college student's employment competency through self-leadership and entrepreneurship training according to their nationality can help resolve the severe employment crisis in the age of the fourth industry.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2017년도 제55차 동계학술대회논문집 25권1호
• /
• pp.155-156
• /
• 2017

본 논문에서는 블리자드 회사에서 제작한 게임 중 하나인 오버워치(Overwatch)에서 게임의 간접정보를 학습하여 플레이어에게 유리한 영웅 캐릭터를 추천해주는 인공신경망 기반 영웅 캐릭터 추천 방법을 제안한다. 오버워치에서 게임 맵별로 적군 캐릭터와 아군 캐릭터가 선정되었을 때 플레이어가 어떤 영웅캐릭터를 선정하면 승률에 좋은지를 알기가 어렵다. 본 논문에서는 플레이어의 영웅캐릭터 선정을 도와주기위하여 오버워치 게임의 간접정보를 기반으로 학습데이터를 만들어 인공신경망을 학습한 후 학습한 인공신경망을 이용하여 영웅캐릭터를 추천한다. 실험결과 인공신경망이 추천하는 영웅캐릭터가 적절한 캐릭터임을 확인하였다.

• 한국시뮬레이션학회논문지
• /
• 제8권4호
• /
• pp.89-107
• /
• 1999

There are many issues in computer simulation such as verifying model code, validating models, understanding the dynamics of systems and training the personnel. The developers of simulation tool have been interested in the animation since it can help solve the problems related to the above listed issues. In practice, animation is one of the popular method for displaying the simulation output for solving these problems. Trying to display all the graphic objects representing the dynamics of the models being simulated, however, causes the distraction of focus, which results in solving the above listed problems difficult. The redundant graphic objects also Increase the computer computation overhead. This paper presents a hierarchical animation environment in which the users can have better focus on the dynamics of system components. In hierarchical animation environment the users can observe the dynamics of system by selectively choosing the hierarchical level and components with in a level of the hierarchically structured model. Especially when the model is large and complex the selection of observation level is needed. The design approach of the hierarchical animator is based on the DEVS(Discrete Event system Specification) formalism which is theoretically well grounded means of expressing modular and hierarchical models.