• Archives of design research
• /
• v.16 no.4
• /
• pp.443-452
• /
• 2003

This study is to find out the possibility of applying the Blended Learning which combines the advantage of face-to-face classroom instruction and e-Learning to design education. This Blended Loaming Model has five steps such as 'prepare, teach, show, interact, and collaborate'. It is designed by the learning decision points (performance outcomes, content stability and structure, audience size, and so on) and the characteristics of delivery methods(asynchronous, synchronous). This research is based on the learners' satisfaction data of each step. The number of the participants is 27 and a questionnaire with 21 items is administered. Ten items of them are designed with 5-point Likert scales and the rest of them ask learners describe the reason of their selection. The result show that learners are satisfied with the blended learning than the off-line classroom. It is expected that the blended learning can be a substitute of the off-line classroom for the effectiveness of design education.

• Educational Technology International
• /
• v.20 no.2
• /
• pp.223-255
• /
• 2019

The purpose of this study is to draw implications for designing online tools to support monitoring in collaborative learning. For this purpose, eighteen research papers that explored learner dashboards and group awareness tools were analyzed. The driving questions for this analysis related to the information and outcomes that must be monitored, whose performance they represent, and who monitors the extent of learning. The analytical frameworks used for this study included the following: three modes of co-regulation in terms of who regulates whose learning (self-regulation in collaborative learning, other regulation, and socially shared regulation) and four categories of dashboard information to determine which information is monitored (information about preparation, participation, interaction, and achievements). As a result, five design implications for learner dashboards that support monitoring were posited: a) Monitoring tools for collaborative learning should support multiple targets: the individual learner, peers, and the entire group; b) When supporting personal monitoring, information about the individual and peers should be displayed simultaneously to allow direct comparison; c) Information on collaborative learning achievements should be provided in terms of the content of knowledge acquired rather than test scores; d) In addition to information related to interaction between learners, the interaction between learners and learning materials can also be provided; and e) Presentation of the same information to individuals or groups should be variable.

• Journal of KIISE:Software and Applications
• /
• v.34 no.12
• /
• pp.1045-1055
• /
• 2007

Latent topic models are statistical models which automatically captures salient patterns or correlation among features underlying a data collection in a probabilistic way. They are gaining an increased popularity as an effective tool in the application of automatic semantic feature extraction from text corpus, multimedia data analysis including image data, and bioinformatics. Among the important issues for the effectiveness in the application of latent topic models to the massive data set is the efficient learning of the model. The paper proposes an accelerated learning technique for PLSA model, one of the popular latent topic models, by an incremental EM algorithm instead of conventional EM algorithm. The incremental EM algorithm can be characterized by the employment of a series of partial E-steps that are performed on the corresponding subsets of the entire data collection, unlike in the conventional EM algorithm where one batch E-step is done for the whole data set. By the replacement of a single batch E-M step with a series of partial E-steps and M-steps, the inference result for the previous data subset can be directly reflected to the next inference process, which can enhance the learning speed for the entire data set. The algorithm is advantageous also in that it is guaranteed to converge to a local maximum solution and can be easily implemented just with slight modification of the existing algorithm based on the conventional EM. We present the basic application of the incremental EM algorithm to the learning of PLSA and empirically evaluate the acceleration performance with several possible data partitioning methods for the practical application. The experimental results on a real-world news data set show that the proposed approach can accomplish a meaningful enhancement of the convergence rate in the learning of latent topic model. Additionally, we present an interesting result which supports a possible synergistic effect of the combination of incremental EM algorithm with parallel computing.

• Asia pacific journal of information systems
• /
• v.16 no.4
• /
• pp.179-202
• /
• 2006

The objective of this study is to identify the impacts of communication reinforcement on performance of learning in Web-PBL. Communication reinforcement is defined as the combination of information sharing and co-construction. As factors facilitating communication reinforcement, we propose learner's characteristics, task characteristics, and group characteristics. Learner's characteristics are collaboration-orientation, openness, holistic approach, and online community-orientation which reflects e-learning environment. Collaboration-oriented tasks as group projects were developed and given to groups with 5-6 members. The group characteristics are categorized into 'horizontal' and 'vertical', according to the patterns of communication between a group leader and members. To verify empirically the proposed research model, an experimental design was performed to learners who took on-line and off-line courses with group projects. We found important results as follows; First, field dependence has positive impacts on information sharing, and online community-orientation has positive impacts on co-construction. These results correspond with prior studies on relationship between field dependence and collaborative learning. Second, collaboration-oriented task directly impacts on information sharing, and indirectly affects co-construction, This result implicates that information sharing is pre-requisite of co-construction. Third, 'horizontal' was identified as a factor giving positive effects on information sharing and co-construction. This result implies that horizontal communication is very important to facilitate communication reinforcement.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.144-146
• /
• 2021

Idiopathic pulmonary fibrosis (IPF) is one of the most dreadful lung diseases which effects the performance of the lung unpredictably. There is no any authentic natural history discovered yet pertaining to this disease and it has been very difficult for the physicians to diagnosis this disease. With the advent of Artificial intelligent and its related technologies this task has become a little bit easier. The aim of this paper is to develop and to explore the machine learning models for the prediction and diagnosis of this mysterious disease. For our study, we got IPF dataset from Haeundae Paik hospital consisting of 2425 patients. This dataset consists of 502 features. We applied different data preprocessing techniques for data cleaning while making the data fit for the machine learning implementation. After the preprocessing of the data, 18 features were selected for the experiment. In our experiment, we used different machine learning classifiers i.e., Multilayer perceptron (MLP), Support vector machine (SVM), and Random forest (RF). we compared the performance of each classifier. The experimental results showed that MLP outperformed all other compared models with 91.24% accuracy.

• Proceedings of the IEEK Conference
• /
• 2003.07a
• /
• pp.565-568
• /
• 2003

This paper presents a method that can be used to reduce the decoding computational complexity in turbo codes. To reduce the decoding complexity we proposed an adaptive sliding window method which control the learning period of Viterbi sliding window method depending on channel signal to interference ratio (SIR). When received signal to interference ratio (SIR) is relatively high, we can reduce the decoding complexity without a noticeable degradation of BER performance at CDMA cellular system with power control error.

• The Journal of Society for e-Business Studies
• /
• v.25 no.2
• /
• pp.49-63
• /
• 2020

The accurate prediction of box office in the early stage is crucial for film industry to make better managerial decision. With aims to improve the prediction performance, the purpose of this paper is to evaluate the use of machine learning methods. We tested both classification and regression based methods including k-NN, SVM and Random Forest. We first evaluate input variables, which show that reputation-related information generated during the first two-week period after release is significant. Prediction test results show that regression based methods provides lower prediction error, and Random Forest particularly outperforms other machine learning methods. Regression based method has better prediction power when films have small box office earnings. On the other hand, classification based method works better for predicting large box office earnings.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.13 no.3
• /
• pp.105-113
• /
• 2017

Considered as the "new normal" mode of learning, BL has become popular in recent years especially in University education. BL is defined as a learning approach that combines e-learning and face-to-face classroom learning. BL allows for more interactive and reflective learning environment resulting in enhancing learner-directed learning. The adoption of BL in university has made it significant to probe the crucial determinants that would entice instructors and learners to use BL and enhance learning satisfaction. The primary purpose of this study is to investigate the affecting factors of the satisfaction of BL in universities in terms of leaner's aspects. Learner's role is very important in BL, because learner should self-directed study for effective performance and satisfaction in BL environment. Based on prior studies motivation, self-efficacy, and educational expectancy were identified as affecting factors of satisfaction in BL. According to the result of multiple regression, all factors(motivation, self-efficacy, and educational expectancy) were found to be significantly related to the learner's satisfaction in BL. It can provide practical guideline on effective operation strategy for BL in universities.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.109-114
• /
• 2021

GAN(Generative Adversarial Network) is an image generation model, which is composed of a generator network and a discriminator network, and generates an image similar to a real image. Since the image generated by the GAN should be similar to the actual image, a loss function is used to minimize the loss error of the generated image. However, there is a problem that the loss function of GAN degrades the quality of the image by making the learning to generate the image unstable. To solve this problem, this paper analyzes GAN-related studies and proposes an edge GAN(eGAN) using edge detection. As a result of the experiment, the eGAN model has improved performance over the existing GAN model.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.14-19
• /
• 1993

In this paper, we proposed an indirect learning and direct adaptive control schemes using neural networks, i.e., composite adaptive neural control, for a class of continuous nonlinear systems. With the indirect learning method, the neural network learns the nonlinear basis of the system inverse dynamics by a modified backpropagation learning rule. The basis spans the local vector space of inverse dynamics with the direct adaptation method when the indirect learning result is within a prescribed error tolerance, as such this method is closely related to the adaptive control methods. Also hash addressing technique, similar to the CMAC functional architecture, is introduced for partitioning network hidden nodes according to the system states, so global neuro control properties can be organized by the local ones. For uniform stability, the sliding mode control is introduced when the neural network has not sufficiently learned the system dynamics. With proper assumptions on the controlled system, global stability and tracking error convergence proof can be given. The performance of the proposed control scheme is demonstrated with the simulation results of a nonlinear system.