• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.3
• /
• pp.186-199
• /
• 2013

We pose pattern classification as a density estimation problem where we consider mixtures of generative models under partially labeled data setups. Unlike traditional approaches that estimate density everywhere in data space, we focus on the density along the decision boundary that can yield more discriminative models with superior classification performance. We extend our earlier work on the recursive estimation method for discriminative mixture models to semi-supervised learning setups where some of the data points lack class labels. Our model exploits the mixture structure in the functional gradient framework: it searches for the base mixture component model in a greedy fashion, maximizing the conditional class likelihoods for the labeled data and at the same time minimizing the uncertainty of class label prediction for unlabeled data points. The objective can be effectively imposed as individual mixture component learning on weighted data, hence our mixture learning typically becomes highly efficient for popular base generative models like Gaussians or hidden Markov models. Moreover, apart from the expectation-maximization algorithm, the proposed recursive estimation has several advantages including the lack of need for a pre-determined mixture order and robustness to the choice of initial parameters. We demonstrate the benefits of the proposed approach on a comprehensive set of evaluations consisting of diverse time-series classification problems in semi-supervised scenarios.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.27 no.1
• /
• pp.75-94
• /
• 2002

The development of Information technologies huts contributed on-line training as one of important education methods. On-line training In firms, which is similar to e-learning or virtual education, provides trainees with more education opportunities in diverse ways. It has developed a range of innovative services with an one-stop solution of education within the electronic sector. Also under the on-line training environment, trainees can undertake customized training packages at anytime and any places. Moreover, information technology allows both the trainers and other trainees to be decoupled in any of the elements of time, place, and space. Two research questions are investigated : what are the determinants affecting the on-line training effectiveness and how those variables effect the two aspects of training effectiveness: learning performance and transfer performance. Based on the previous literature conducted on the traditional training environment, the determinants of training effectiveness are derived. light hypotheses are developed based on literature reviews and tested by questionnaires survey data. The collected data have been analyzed by LISREL. It is found that the relationship between individual, organizational and on-line sloe design variables and training effectiveness (learning and transfer) are significant. The contribution and limitations of this research are also discussed tilth future studies.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2726-2728
• /
• 2001

This paper describes an optimal synthesis method of binary neural network(BNN) for an approximation problem of a circular region using a newly proposed learning algorithm[7] Our object is to minimize the number of connections and neurons in hidden layer by using a Newly Expanded and Truncated Learning Algorithm(NETLA) for the multilayer BNN. The synthesis method in the NETLA is based on the extension principle of Expanded and Truncated Learning(ETL) and is based on Expanded Sum of Product (ESP) as one of the boolean expression techniques. And it has an ability to optimize the given BNN in the binary space without any iterative training as the conventional Error Back Propagation(EBP) algorithm[6] If all the true and false patterns are only given, the connection weights and the threshold values can be immediately determined by an optimal synthesis method of the NETLA without any tedious learning. Futhermore, the number of the required neurons in hidden layer can be reduced and the fast learning of BNN can be realized. The superiority of this NETLA to other algorithms was proved by the approximation problem of one circular region.

• Journal of Korea Multimedia Society
• /
• v.12 no.12
• /
• pp.1819-1826
• /
• 2009

To enhance the automatic performance of existing predicting and planning algorithms that require a predefined probability of the states' transition, this paper proposes a multiple sequence generation system. When interacting with unknown environments, a virtual agent needs to decide which action or action order can result in a good state and determine the transition probability based on the current state and the action taken. We describe a sequential behavior generation method motivated from the change in the agent's state in order to help the virtual agent learn how to adapt to unknown environments. In a sequence learning process, the sensed states are grouped by a set of proposed motivation filters in order to reduce the learning computation of the large state space. In order to accomplish a goal with a high payoff, the learning agent makes a decision based on the observation of states' transitions. The proposed multiple sequence behaviors generation system increases the complexity and heightens the automatic planning of the virtual agent for interacting with the dynamic unknown environment. This model was tested in a virtual library to elucidate the process of the system.

• Smart Media Journal
• /
• v.7 no.4
• /
• pp.24-29
• /
• 2018

Text analysis technique for natural language processing in deep learning represents words in vector form through word embedding. In this paper, we propose a method of constructing a document vector and classifying it into spam and normal text message, using word embedding and deep learning method. Automatic spacing applied in the preprocessing process ensures that words with similar context are adjacently represented in vector space. Additionally, the intentional word formation errors with non-alphabetic or extraordinary characters are designed to avoid being blocked by spam message filter. Two embedding algorithms, CBOW and skip grams, are used to produce the sentence vector and the performance and the accuracy of deep learning based spam filter model are measured by comparing to those of SVM Light.

• International Journal of Advanced Culture Technology
• /
• v.12 no.3
• /
• pp.419-426
• /
• 2024

Due to the government's announcement of the 2025 policy mandating coding education, there is a growing need for effective coding learning methods in elementary education. However, there are few methods available that can easily help younger students understand coding. While text-based coding and visual block coding methods exist, they have limitations. To address these issues, we propose a block coding learning platform that combines virtual reality (VR) technology with gamification elements. The traditional two dimensional (2D) block coding methods have some limitations, so this platform aims to overcome these by providing an environment where learners can intuitively understand and experience coding in a three dimensional (3D) virtual space. The primary goal is to enhance immersive, learner-centered experiences and improve creative problem-solving skills and computational thinking. This study proposes an experimental approach to demonstrate the effectiveness of a learning platform that combines VR technology with block coding. Furthermore, we expect that the VR-based platform will significantly contribute to improving the quality of education and promoting self-directed learning among students.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.6
• /
• pp.287-292
• /
• 2010

The flow gradually into the Information age to the Information age has changed, leading to the development of computer and communication technology was very important for the value. Of these the most used in computer communication using the Internet, and this proportion accounts for the development of the Internet, the information was established as a means of interaction. In this paper, to improve these problems without the constraints of time and space to allow two-way interactions using web based learning system to enable Computer Architecture were learning. Learn how Computer Architecture using Camtasia the learner, without limitation of time and place of the browser through the Internet to enable real-time learning and assessment appropriate to individual learners and teaching - learning process in conjunction with individual learners can be self-directed learning will play a role in that.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.4
• /
• pp.60-68
• /
• 1994

In this paper we propose a new Hybrid learning rule applied to multilayer feedforward neural networks, which is constructed by combining Hebbian learning rule that is a good feature extractor and Back-Propagation(BP) learning rule that is an excellent classifier. Unlike the BP rule used in multi-layer perceptron(MLP), the proposed Hybrid learning rule is used for uptate of all connection weights except for output connection weigths becase the Hebbian learning in output layer does not guarantee learning convergence. To evaluate the performance, the proposed hybrid rule is applied to classifier problems in two dimensional space and shows better performance than the one applied only by the BP rule. In terms of learning speed the proposed rule converges faster than the conventional BP. For example, the learning of the proposed Hybrid can be done in 2/10 of the iterations that are required for BP, while the recognition rate of the proposed Hybrid is improved by about $0.778\%$ at the peak.

• Journal of the Korea Convergence Society
• /
• v.11 no.8
• /
• pp.139-145
• /
• 2020

Due to the rapid development of computer technology, online learning using ICT technology is already quickly settling in our lives. Music education was conducted mainly in an offline-based environment, but research is being conducted to switch to online because there is no time and space constraint of online education and interactive education led by learners is possible. In this study, we propose design and implement an adaptive learning system to enable adaptive learning online among music education. This system has the following advantages. First, by providing an LMS-based platform, one can solve the social education problem corresponding to economic and geographical factors. Second, both objective learning feedback provided automatically by the online adaptive harmony learning system and teaching feedback. Third, learners can be provided with recommended answers to given harmony exercises. The adaptive online learning system of harmony will lead professors and learners to effectively teach and study.

• Journal of the Korean association of regional geographers
• /
• v.14 no.6
• /
• pp.752-766
• /
• 2008

For all the region is the basic unit of geographical learning and the grounds of human activities, regional learning can't possible be carried out at the class. Because there are very few regional learning materials that are applicable to class and can be expanded to geographical basic concept. This paper aims to regulate the construction principles of regional learning and select the contents of regional learning. Firstly, the six basic concepts of geographical education be made a selection of the construction principles of regional learning: human-environment, location, region, interaction, change, scale. And then, I suggest the upper five subject that be based on the results of systematical geography. Those are the necessity and method of regional apprehension, the physical environment and the regional human-life, the resource and industrial activities. the regional life-space's formation and change, and the changing world and region. And I propose the subdivided the mid and the lower subject that be reflected the learner's need and the social demand, and could be experienced the results of geography and the everyday life. For the best regional learning, these subjects can be combined one or more in various scale.