• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.8
• /
• pp.958-964
• /
• 2016

In this paper, we propose an i-vector based language recognition system to identify the spoken language of the speaker, which uses multiple discriminative deep neural network (DNN) models analogous to the multi-class support vector machine (SVM) classification system. The proposed model was trained and tested using the i-vectors included in the NIST 2015 i-vector Machine Learning Challenge database, and shown to outperform the conventional language recognition methods such as cosine distance, SVM and softmax NN classifier in open-set experiments.

• The Journal of Information Technology
• /
• v.5 no.2
• /
• pp.95-106
• /
• 2002

This study attempts to construct and manage the distance learning system by focusing on education institutins. However, they lack not only web-based courseware for information literacy but also the contents for the management technology. This study tried to design and implement the web-based courseware by using OCP(Oracle Certified Profession) based on the initial Oracle in distance learning. Learners' individual variations were considered based on problem solving learning. Also, the practical contents that could be applied in the educational field were selected. The learning type web-based courseware, using the technology of ASP, DHTML, JAVAscript, VBA, was designed and implemented into the framework that could be updated easily. The result of the study shows: first of all, this courseware induced a greater understanding of the Oracle language and the student's interests. Secondly, the student's had more control over the process of individual learning and achieved the goal more effectively through immediate feedback, finally, the students could learn wherever they have on-line connections to the web server.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.3C
• /
• pp.257-267
• /
• 2009

This paper presents a training method for neural networks and the employment of MSE (mean scare error) values as the basis of a decision regarding the identity claim of a speaker in a recurrent neural networks based speaker verification system. Recurrent neural networks (RNNs) are employed to capture temporally dynamic characteristics of speech signal. In the process of supervised learning for RNNs, target outputs are automatically generated and the generated target outputs are made to represent the temporal variation of input speech sounds. To increase the capability of discriminating between the true speaker and an impostor, a discriminative training method for RNNs is presented. This paper shows the use and the effectiveness of the MSE value, which is obtained from the Euclidean distance between the target outputs and the outputs of networks for test speech sounds of a speaker, as the basis of speaker verification. In terms of equal error rates, results of experiments, which have been performed using the Korean speech database, show that the proposed speaker verification system exhibits better performance than a conventional hidden Markov model based speaker verification system.

• Journal of Korea Multimedia Society
• /
• v.8 no.5
• /
• pp.707-741
• /
• 2005

In the multimedia streaming technology, the unicast method require additional cost by an increase traffic according to increase a number of users. The multicast method can solve this problem, but it don't have connection and control information of clients. Now, the most routers support only unicast. Also it has a problem with an exchange of service in other ISP. This paper proposes traffic agent system which is applied unicast and P2P(Peer to Peer) for distance video teaming to overcome this problem. The proposed system decrease the traffic of stream server by control agent, and cut down expenses of network. This system is tested under the distance video leaning using JMF and application software.

• Electronics and Telecommunications Trends
• /
• v.20 no.4 s.94
• /
• pp.155-166
• /
• 2005

IT 기술을 이용하여 학습하는 것을 e-러닝이라 한다. 최초의 e-러닝은 DistanceLearning과 Distributed Learning이라는 두 가지 측면만으로도 훌륭한 역할을 하였다. 그러나 최근 정보통신산업의 비약적인 발전에 따라 새로운 e-러닝 서비스에 대한 사용자의 요구가 높아지고 있다. 무선 이동통신기술과 하드웨어기술 등의 발전에 따라 언제 어디서나 양질의 교육에 접근할 수 있고, 멀티미디어 처리기술의 발전에 따라 개인맞춤형 e-러닝 서비스가 필요하다. 이에 따라 본 기고에서는 e-러닝 시스템이라는 측면에서 차세대 e-러닝 서비스를 구상하고자 한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.700-703
• /
• 2003

In recent years, amount of studies on application of wetbased educational system are proceeding in educational field. This study proposes design and implementation for web-based learning system using WMT in order to practise assistance learning between teacher and students on the web. For system design and implementation, this study utilizes Windows 2000 Server and Windows Media Technology. Using WMT, we make teaming materials and put them in web-based educational system. It should be possible to make teaming in accordance with Windows Media Player for a long-distance students. As a result, this study expects to accomplish a web-based learning between teacher and student on the web.

• Journal of Internet Computing and Services
• /
• v.2 no.3
• /
• pp.19-25
• /
• 2001

An educational system using computers was first conceptualized by Dr. Donald Bitzer in the University of Illinois in the late 1950s. Since the PLATO system was developed in 1961, multilateral research were made for the last 30 years. Especially, the development of Internet and Information Technology has contributed to the advancement of the distance education system. This system has greatly changed the existing educational paradigm, As the result, new education system is being realized, This study suggests a distance education system based on ‘push’ technique, which is a means of active information transmission, In this system, the ‘push’ technique is combined with the existing distance education system. Through the combination, learning contents can be provided for learners without connecting the DB on the Internet. In addition, the process of getting new information is real-timed operation. Also, the treatment of item; and the algorithm of level-based item evaluation are devised in consideration of various levels of learners, so that evaluation of items appropriate to the levels of learners can be accomplished.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1998.10a
• /
• pp.133-136
• /
• 1998

Supporting decision-makers involves not only functions of conventional DSS such as problem identification, alternative generation and selection but also education and business processing. The purpose of this paper is to propose Decision-Maker Support System (DMSS) that comprehensively supports decision-makers who should enhance their decision quality. The DMSS consists of three core subsystem: distance learning system, conventional DSS and ERP system.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.3
• /
• pp.698-708
• /
• 1997

To construct distance learing servers and provide their service using the WWW(World Wide Web), it is necessary that we use a real-time processing mehtod rather than the processing after downloading method for multimedia data transmission and their processing.To fulfill such requirements, we developed a real-time processing muduloe for distance education which can process multimedia data in AVI and WAV formats in distrbuted eviroments.We in turn developede a real-time WWW server that can provide real-time services of hypertxt and motion poctures data in temsw of adding the real-time porcessing modute to the MuX framework and intergarting them with WWW. We frnally developed as distance lerming system for real-time interactive chinese character learming, bassed on the results from the pre-vious steps.

• Journal of Astronomy and Space Sciences
• /
• v.41 no.2
• /
• pp.61-78
• /
• 2024

This study developed a real-time spacecraft pose estimation algorithm that combined a deep learning model and the least-squares method. Pose estimation in space is crucial for automatic rendezvous docking and inter-spacecraft communication. Owing to the difficulty in training deep learning models in space, we showed that actual experimental results could be predicted through software simulations on the ground. We integrated deep learning with nonlinear least squares (NLS) to predict the pose from a single spacecraft image in real time. We constructed a virtual environment capable of mass-producing synthetic images to train a deep learning model. This study proposed a method for training a deep learning model using pure synthetic images. Further, a visual-based real-time estimation system suitable for use in a flight testbed was constructed. Consequently, it was verified that the hardware experimental results could be predicted from software simulations with the same environment and relative distance. This study showed that a deep learning model trained using only synthetic images can be sufficiently applied to real images. Thus, this study proposed a real-time pose estimation software for automatic docking and demonstrated that the method constructed with only synthetic data was applicable in space.