• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.3
• /
• pp.449-458
• /
• 2023

Many people think that sign language is only for people who are deaf and cannot speak, but of course it is necessary for people who want to talk with them. One of the biggest challenges in ASL(American Sign Language) alphabet recognition is the high inter-class similarities and high intra-class variance. In this paper, we proposed an architecture that can overcome these two problems, which performs similarity learning to reduces inter-class similarities and intra-class variance between images. The proposed architecture consists of the same convolutional neural network with a double configuration that shares parameters (weights and biases) and also applies the Keras API to reduce similarity learning and variance through this pathway. The similarity learning results the use of the dual CNN shows that the accuracy is improved by reducing the similarity and variability between classes by not including the poor results of the two classes.

• Journal of KIISE:Software and Applications
• /
• v.28 no.10
• /
• pp.773-784
• /
• 2001

Since documents on the Web are naturally partitioned into may document database, the efficient information retrieval process requires identifying the document database that are most likely to provide relevant documents to the query and then querying the identified document database. We propose a neural net agent approach to such an efficient information retrieval. First, we present a neural net agent that learns about underlying document database using the relevance feedbacks obtained from many retrieval experiences. For a given query, the neural net agent, which is sufficiently trained on the basis of the BPN learning mechanism, discovers the document database associated with the relevant documents and retrieves those documents effectively. In the experiment, we introduce a neural net agent based information retrieval system and evaluate its performance by comparing experimental results to those of the conventional well-known approaches.

• Proceedings of the Korea Institutes of Information Security and Cryptology Conference
• /
• 2002.11a
• /
• pp.144-146
• /
• 2002

현재 침입탐지 시스템은 인터넷의 확장과 더불어 네트워크 보안을 보장하기 위한 광범위한 수단으로 이용되고 있다. 이러한 탐지 시스템중 신경망의 적용은 분산된 네트워크와 다양한 공격환경하의 오용탐지와 비정상행위 탐지에 좋은 응용이 되고 있다. 본 연구에서는 RBF-신경망을 이용한 침입탐지 시스템이 가지고 있는 단점 중 하나인 학습데이터의 공격과 정상의 비율에 따라 탐지 율의 차이가 큰 것에 착안, 보다 자동화되고 안정된 학습을 위한 데이터 결정 알고리즘을 제안한다.

• Proceedings of The KACE
• /
• 2017.08a
• /
• pp.63-64
• /
• 2017

정보 기술의 끊임없는 발전에 따라 광범위한 분야에서 방대한 양의 데이터가 발생하게 되면서 이를 처리하기 위한 빅 데이터에 대한 연구 및 교육이 활발히 진행되고 있다. 이를 위하여 데이터 분석 및 처리를 위한 고성능의 서버 및 분산 처리를 위한 다수의 컴퓨터가 필요하며 이는, 개인 혹은 저사양의 수업 환경에서 빅 데이터를 학습하는 데에 어려움을 겪게 한다. 때문에 가상 환경에서 원활한 빅 데이터 학습을 위한 클라우드 기반의 시스템이 필요하다. 이에 본 논문에서는, 빅 데이터 처리 기술의 하나인 Spark를 이용한 빅 데이터 플랫폼 구축에 대하여 기술한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10a
• /
• pp.13-15
• /
• 2003

이 연구는 이동 에이전트 시스템에 기반한 가상의 병렬분산 컴퓨팅 환경에서 병렬로 수행되는 인공신경망 시뮬레이터를 구현하는 것을 목적으로 하며, 학습세션 수준에서 병렬로 학습하는 병렬 인공신경망 시뮬레이터의 성능을 대표적인 벤치마크 문제인 NetTalk을 대상으로 평가한 결과, 개발한 시뮬레이터가 상당히 효과적임을 알 수 있다.

• Journal of Advanced Navigation Technology
• /
• v.26 no.4
• /
• pp.226-234
• /
• 2022

With advances in autonomous vehicles and networked control, there is a growing interest in the consensus control of a multi-agents system to control multi-agents with distributed control beyond the control of a single agent. Since consensus control is a distributed control, it is bound to have delay in a practical system. In addition, it is often difficult to have a very accurate mathematical model for a system. Even though a reinforcement learning (RL) method was developed to deal with these issues, it often experiences slow convergence in the presence of large uncertainties. Thus, we propose a slide RL which combines the sliding mode control with RL to be robust to the uncertainties. The structure of a sliding mode control is introduced to the action in RL while an auxiliary sliding variable is included in the state information. Numerical simulation results show that the slide RL provides comparable performance to the model-based consensus control in the presence of unknown time-varying delay and disturbance while outperforming existing state-of-the-art RL-based consensus algorithms.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.147-149
• /
• 1998

본 논문에서는 여러 정보검색 엔진들이 분산되어 있는 환경에서 이 엔진들의 검색 결과를 효과적으로 취합하여 사용자에게 제시하는 컬렉션 융합 방안을 제안하고자 한다. 이 방법은 우선 학습 질의어로 검색된 문서들의 클러스터링 정도를 이용하여 컬렉션에의 신뢰도를 측정하고 새로운 질의어가 입력되었을 때 각 컬렉션에서 검색된 문서의 유사도를 조정하여 융합하는 방법이다. 여기에서 각 컬렉션의 신뢰도는 미리 준비된 학습 질의어와 이 학습 질의어를 입력하여 검색된 문서들 사이의 유사도를 분석하여 측정한다. 이 신뢰도는 새로운 질의어가 입력되었을 때 각 컬렉션마다 문서들을 검색하고 이들 문서들을 어느 정도 신뢰할 것인가를 결정하는데 사용된다. 본 논문에서 제안한 방법은 학습과정에서 사람이 학습시킬 필요가 없는 비지도 학습에 기초하고 있다. 따라서 지금까지 지도 학습에 기초한 컬렉션 융합 방법과는 달리 인터넷과 같이 문서들이 동적으로 변하는 환경에서 쉽게 사용할 수 있다는 장점을 가진다.

• Journal of Korea Multimedia Society
• /
• v.7 no.8
• /
• pp.1131-1144
• /
• 2004

In this paper, we investigate a problem with an e-learning system for e-business environments and introduce the solving method of the problem. To be more accurate, existing Web-hosted and ASP (Application Service Provider)-oriented service model is difficult to cooperate and integrate among the different kinds of systems. So we have produced sharable and reusable learning object, they have extracted a principle from pedagogical designs for units of reuse. We call LIO (Learning Item Object). This modeling makes use of a constructing for XML Web Services. So to speak, units of reuse from pedagogical designs are test tutorial, resource, case example, simulation, problem, test, discovery and discussion and then map introduction, fact, try, quiz, test, link-more, tell-more LIO learning object. These typed LIOs are stored in metadata along with the information for a content location. Each one of LIOs is designed with components and exposed in an interface for XML Web services. These services are module applications, which are used a standard SOAP (Simple Object Access Protocol) and locate any computer over Internet and publish, find and bind to services. This guarantees the interoperation and integration of the different kinds of systems. As a result, the problem of e-learning systems for e-business environments was resolved and then the power of understanding about learning objects based on pedagogical design was increased for learner and instruction designers. And organizations of education hope for particular decreased costs in constructing e-learning systems.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.11
• /
• pp.5658-5671
• /
• 2013

This study was to identify the difference of achievement motivation, self-efficacy, self-directed learning across the learning styles after application of the Problem based learning(PBL) in Nursing students. Descriptive survey was performed from march to june, 2009 at a university in Jeju. The participants were 268 in freshman nursing student and PBL was used during one semester. The data from 242 participants were analysed using IBM SPSS 20.0 The results revealed that most nursing students had converger in learning styles. Achievement motivation and self-efficacy were the greatest scores in accommodator and self-directed learning was the greatest scores in converger. However, Achievement motivation, self-efficacy, and self-directed learning were lowest in diverger. Significant positive correlation was found among achievement motivation, self-efficacy, and self-directed learning each other. There were significant difference in achievement motivation, self-efficacy and self-directed learning across learning styles. More research is needed to determine the effects of PBL in nursing education including many variables.

• The Journal of the Korea Contents Association
• /
• v.17 no.12
• /
• pp.77-91
• /
• 2017

Due to the lack of learning motivation, there is a need to seek ways to facilitate learning incentives because it's causing drop out and maladjustment of university life. This study is to examine whether the ARCS evaluation model developed by Keller (1983) is a valid model for evaluating the motivation level of local university students sample 276(male 116, female 157) in the Republic of Korea. To analyze the data, average statistic, one-way ANOVA and confirmative factor analysis were used. The conclusion of this study is as follows. First, the level of motivation per ARCS factor has demonstrated the highest relevance factor. Second, the level of motivation by the ARCS for the 1st and 3rd graders was appropriate. Differences in 'attention' and 'relevance' have only been observed for each year, and the 1st grade group was found to be larger than the 2nd grade cohort. Third, construct validity and convergent validity were obtained for measuring the level of motivation. The results of the verification of the variables also showed that the AVE and CR were met, and the model fit well was satisfactory. Based on the finding results, discussion and implication for further research were suggested.