• The Journal of Korean Association of Computer Education
• /
• v.10 no.6
• /
• pp.79-89
• /
• 2007

The advent of e-Learning paradigm requires a various type of e-Learning models and systems which are appropriate to support effective teaching-learning process. Accordingly, the teaching-learning system using the Internet and the intelligent tutoring system(ITS) in e-Learning environment has attracted a fair amount of critical attention. However there is a wide gap between infrastructure of a present educational site and the u-learning environment. Therefore, in this paper, an ITS teaching-learning model is proposed and system is developed for a school environment, which is based on a learner's cognitive structure and applies a concept of u-Learning, and then is verified for validity. X-Neuronet, the developed system, offers a method of representing a learner's cognitive structure so as to apply the method for the efficient individualized learning.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.6
• /
• pp.430-439
• /
• 2016

Estimation and analysis of traffic jams plays a vital role in an intelligent transportation system and advances safety in the transportation system as well as mobility and optimization of environmental impact. For these reasons, many researchers currently mainly focus on the brilliant machine learning-based prediction approaches for traffic prediction systems. This paper primarily addresses the analysis and comparison of prediction accuracy between two machine learning algorithms: Naïve Bayes and K-Nearest Neighbor (K-NN). Based on the fact that optimized estimation accuracy of these methods mainly depends on a large amount of recounted data and that they require much time to compute the same function heuristically for each action, we propose an approach that applies multi-threading to these heuristic methods. It is obvious that the greater the amount of historical data, the more processing time is necessary. For a real-time system, operational response time is vital, and the proposed system also focuses on the time complexity cost as well as computational complexity. It is experimentally confirmed that K-NN does much better than Naïve Bayes, not only in prediction accuracy but also in processing time. Multi-threading-based K-NN could compute four times faster than classical K-NN, whereas multi-threading-based Naïve Bayes could process only twice as fast as classical Bayes.

• Journal of Digital Convergence
• /
• v.11 no.11
• /
• pp.693-704
• /
• 2013

The purpose of this study was to analyze the effects of social network service on the collaborative skills, collaborative satisfaction, and interaction within groups in collaborative learning. The group that used KakaoTalk, one of social network service for working on the collaborative task in the course exhibited higher collaborative skills and collaborative satisfaction (p<.05) than the group that did not use KakaoTalk. When analyzing the amount and the content of the messages produced by the group that used KakaoTalk, the amount of messages did not have an impact on the collaborative skills and collaborative satisfaction.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.11
• /
• pp.1482-1484
• /
• 2019

We present a method for transmitting 3D object information in real time in a telepresence system. Three-dimensional object information consists of a large amount of point cloud data, which requires high performance computing power and ultra-wideband network transmission environment to process and transmit such a large amount of data in real time. In this paper, multiple users can transmit object motion and facial expression information in real time even in small network bands by using GANs (Generative Adversarial Networks), a non-supervised learning machine learning algorithm, for real-time transmission of 3D point cloud data. In particular, we propose the creation of an object similar to the original using only the feature information of 3D objects using conditional GANs.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.1
• /
• pp.147-152
• /
• 2020

The bidding program uses statistical analysis method of the collected bidding information and the accumulated bidding results from the public/private sector; however, it is not easy to predict the accurate bidding price by winning the bid method through multiple lottery. Therefore, this paper analyzes the accuracy of the current state data of the electric construction bid from January 2015 to August 2019 acquired from the electric net, which is an electronic bidding site, We use MLP and RNN method, and proposes a technique to predict the bidding amount necessary for the winning bid by predicting the amount between the first and the lowest bidder.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.10
• /
• pp.157-165
• /
• 2021

Recently, studies using deep learning to analyze a large amount of text are being actively conducted. In particular, a pre-trained language model that applies the learning results of a large amount of text to the analysis of a specific domain text is attracting attention. Among various pre-trained language models, BERT(Bidirectional Encoder Representations from Transformers)-based model is the most widely used. Recently, research to improve the performance of analysis is being conducted through further pre-training using BERT's MLM(Masked Language Model). However, the traditional MLM has difficulties in clearly understands the meaning of sentences containing new words such as newly coined words. Therefore, in this study, we newly propose NTM(Newly coined words Target Masking), which performs masking only on new words. As a result of analyzing about 700,000 movie reviews of portal 'N' by applying the proposed methodology, it was confirmed that the proposed NTM showed superior performance in terms of accuracy of sensitivity analysis compared to the existing random masking.

• Journal of Internet of Things and Convergence
• /
• v.9 no.1
• /
• pp.9-17
• /
• 2023

Deep learning with large amount of computations is difficult to implement on micro-sized IoT devices or moblie devices. Recently, lightweight deep learning technologies have been introduced to make sure that deep learning can be implemented even on small devices by reducing the amount of computation of the model. Quantization is one of lightweight techniques that can be efficiently used to reduce the memory and size of the model by expressing parameter values with continuous distribution as discrete values of fixed bits. However, the accuracy of the model is reduced due to discrete value representation in quantization. In this paper, we introduce various quantization techniques to correct the accuracy. We selected APoT and EWGS from existing quantization techniques, and comparatively analyzed the results through experimentations The selected techniques were trained and tested with CIFAR-10 or CIFAR-100 datasets in the ResNet model. We found out problems with them through experimental results analysis and presented directions for future research.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.57-67
• /
• 2021

Recently, multi-modal deep learning techniques that combine heterogeneous data for deep learning analysis have been utilized a lot. In particular, studies on the synthesis of Text to Image that automatically generate images from text are being actively conducted. Deep learning for image synthesis requires a vast amount of data consisting of pairs of images and text describing the image. Therefore, various data augmentation techniques have been devised to generate a large amount of data from small data. A number of text augmentation techniques based on synonym replacement have been proposed so far. However, these techniques have a common limitation in that there is a possibility of generating a incorrect text from the content of an image when replacing the synonym for a noun word. In this study, we propose a text augmentation method to replace words using word hierarchy information for noun words. Additionally, we performed experiments using MSCOCO data in order to evaluate the performance of the proposed methodology.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1707-1720
• /
• 2023

With the increase in satellite time series data, the utility of remote sensing data is growing. In the analysis of time series data, the relative positional accuracy between images has a significant impact on the results, making image registration essential for correction. In recent years, research on image registration has been increasing by applying deep learning, which outperforms existing image registration algorithms. To train deep learning-based registration models, a large number of image pairs are required. Additionally, creating a correlation map between the data of existing deep learning models and applying additional computations to extract registration points is inefficient. To overcome these drawbacks, this study developed a data augmentation technique for training image registration models and applied it to OffsetNet, a registration model that predicts the offset amount itself, to perform image registration for KOMSAT-2, -3, and -3A. The results of the model training showed that OffsetNet accurately predicted the offset amount for the test data, enabling effective registration of the master and slave images.

• Journal of Internet Computing and Services
• /
• v.20 no.6
• /
• pp.65-72
• /
• 2019

Data augmentation is a method that increases the amount of data through various algorithms based on a small amount of sample data. When machine learning and deep learning techniques are used to solve real-world problems, there is often a lack of data sets. The lack of data is at greater risk of underfitting and overfitting, in addition to the poor reflection of the characteristics of the set of data when learning a model. Thus, in this paper, through the layer-wise data augmenting method at each layer of deep neural network, the proposed method produces augmented data that is substantially meaningful and shows that the method presented by the paper through experimentation is effective in the learning of the model by measuring whether the method presented by the paper improves classification accuracy.