• The Journal of Korean Association of Computer Education
• /
• v.14 no.6
• /
• pp.53-64
• /
• 2011

This paper proposes and evaluates empirically a new recommendation method in order to improve the learning achievement of learners using case-based method. In this paper, we first carried out a survey targeting teachers who work currently in Gyeongbuk area, and constructed learning cases depending on critical factors of learning. We next recommended differentiated learning methods to learners classifying according to learning cases by achievement level through this survey. The students of a middle school took part in the experiment in order to evaluate empirically the proposed learning cases. The students were divided into three groups by their achievement level and three separate learning cases were applied to each group. The weights among learning improvement elements applying to each group were added through the survey result of teachers. The experiment using the proposed case-based recommendation method showed that the learning achievement of learners is improved considerably compared to the previous one.

• English Language & Literature Teaching
• /
• v.17 no.3
• /
• pp.195-212
• /
• 2011

Research studies have shown that phonological awareness focused analogies and anagrams can be used as an effective game-based teaching instruction. However, previous studies used analogies and anagrams as separate instructional tools, especially in EFL-related situations. There has been no vocabulary learning in analogies/anagrams instruction provided, nor has there been usage of an integrated workbook for 'vocabulary learning and analogies/anagrams'. This study examined the effect on learners' vocabulary acquisition scores when a truly phonological awareness integrated 'analogies/anagrams and vocabulary learning' workbook was used as an instructional practice workbook. The results show that the phonological awareness integrated instruction significantly increased learners' vocabulary acquisition scores among 40 college students with minimal or basic level of English proficiency.

• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.858-869
• /
• 2023

As one of the pivotal techniques of image restoration, single-channel blind source separation (SCBSS) is capable of converting a visual-only image into multi-source images. However, image degradation often results from multiple mixing methods. Therefore, this paper introduces an innovative SCBSS algorithm to effectively separate source images from a composite image in various mixed modes. The cornerstone of this approach is a novel triple generative adversarial network (TriGAN), designed based on dual learning principles. The TriGAN redefines the discriminator's function to optimize the separation process. Extensive experiments have demonstrated the algorithm's capability to distinctly separate source images from a composite image in diverse mixed modes and to facilitate effective image restoration. The effectiveness of the proposed method is quantitatively supported by achieving an average peak signal-to-noise ratio exceeding 30 dB, and the average structural similarity index surpassing 0.95 across multiple datasets.

• Journal of Digital Convergence
• /
• v.18 no.7
• /
• pp.307-315
• /
• 2020

This study was conducted to test the effects of core note-based pre-learning on self-determination learning motivation, self-directed learning, and campus life adaptation for undergraduate nursing students. This study used a one group pre-post test design. The participants were 60 nursing students Universities located in C city. Data were collected on two separate occasions before and after the application of the program from August 2018 to November 2018. For data analysis, SPSS/WIN 23.0 program was utilized including pearson correlation coefficients & Paired t-test. This study showed a meaningful positive for self-determination(t=-.52, p<.001), self-directed learning(t=-.2.11, p=.039) and campus life adaptation(t=-2.90, p=.005). The findings suggest the necessity to develop core note-based pre-learning program of various major curriculum of nursing and various instructional strategies for vitalizing Pre-Learning Program.

• Journal of the Korea Computer Industry Society
• /
• v.4 no.10
• /
• pp.673-684
• /
• 2003

In order to understand the concepts of image processing with effect, a learning system with an actual practice is necessary. As most image processing learning materials have some inconvenient respects that it is difficult to understand the processing procedure because they simply show the processed results as figures in the contents, and also, a separate practice tool is needed to operate the source codes because they provide the program source codes as a part in the context. In this paper, in order to solve above inconvenient respects, an image processing learning system that be able to improve the learning effects as accomplishing the theory studying and the actual practice in parallel is proposed. As this system is composed on the bases of java, it is independent to the platforms and it is possible to implement on the Web.

• Journal of Information Processing Systems
• /
• v.10 no.3
• /
• pp.443-458
• /
• 2014

An extreme learning machine (ELM) is a recently proposed learning algorithm for a single-layer feed forward neural network. In this paper we studied the ensemble of ELM by using a bagging algorithm for facial expression recognition (FER). Facial expression analysis is widely used in the behavior interpretation of emotions, for cognitive science, and social interactions. This paper presents a method for FER based on the histogram of orientation gradient (HOG) features using an ELM ensemble. First, the HOG features were extracted from the face image by dividing it into a number of small cells. A bagging algorithm was then used to construct many different bags of training data and each of them was trained by using separate ELMs. To recognize the expression of the input face image, HOG features were fed to each trained ELM and the results were combined by using a majority voting scheme. The ELM ensemble using bagging improves the generalized capability of the network significantly. The two available datasets (JAFFE and CK+) of facial expressions were used to evaluate the performance of the proposed classification system. Even the performance of individual ELM was smaller and the ELM ensemble using a bagging algorithm improved the recognition performance significantly.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.65-70
• /
• 2023

In this paper, we used a deep learning model to detect and segment flame and smoke in real time from fires. To this end, well known U-NET was used to separate and divide the flame and smoke of the fire using multi-class. As a result of learning using the proposed technique, the values of loss error and accuracy are very good at 0.0486 and 0.97996, respectively. The IOU value used in object detection is also very good at 0.849. As a result of predicting fire images that were not used for learning using the learned model, the flame and smoke of fire are well detected and segmented, and smoke color were well distinguished. Proposed method can be used to build fire prediction and detection system.

• Journal of Korean Home Economics Education Association
• /
• v.6 no.2
• /
• pp.147-160
• /
• 1994

The purpose of this study was to review the literatures on designing and developing the CAI program and to develop the middle school students’CAI program for tutorial and instructional game. For these purposes, the learning and instructional theories and the developing phases and strategies for the program were reviewed to design the CAI program. And then the developing unit was selected and the CAI types and the developing direction were set according to the analysis of the CAI programs and related literatures on home economics teaching, The four phases-analysis, design, development, and formative evaluation-were carried out in this study. The results of this study are as following: 1. The CAI porgram was developed on health and food life units. The program contains 12 classes on health and food life in two floppy diskettes. It consisted of total 9,000 lines and 76 frame and takes two hours to study this program. This program could be used in educational computers an could be utilized for unit learing tutorial. It was composed of three parts-unit learning, finding maze, and finding food. In the unit learning part, the learning contents in health and food life units were structured and presented. In finding maze and food part, the basic and the applied problems were presented with game. The characteristics of this program were as followings: (1)This program was able to bring learners’motivation due to the strategies of tutorial and instructional game and they can interestingly learn the program for themselves. (2) The learner could practive the learning contents repeatedly and unit learning while playing the gaming, (3) The learner himself can review and supplement the learning contents without teacher’s help. (4) This program was developed to unit learning on health and food life, on the other hand so far many CAI programs for home economics teaching were developed for studying separate learning units. 2. To effectively utilize this program, the guide book for the student and the teacher was developed. It contained method of using the program, introduction of the program, review of the program, the program objectives, the learning contents, and the keys to progress the program.

• The Mathematical Education
• /
• v.57 no.4
• /
• pp.329-352
• /
• 2018

This study analyzed each process of demand analysis(A), design(D), development(D), implementation(I) and evaluation(E) of the program to support mathematics learning of students with under-achievement of math in high school. To analyze the demand, a survey was conducted on 235 high school math teachers and 334 high school students who were under-achieved in mathematics. To design and develope the program, this study linked middle school math to high school math so that the students with poor math learning could easily participate in mathematics learning. The programs developed in this study were implemented in three high schools, where separate classes were organized and run for students with poor math learning. The evaluation of the programs developed in this study was done in two ways. One was a quantitative evaluation conducted by five experts, and the other was a qualitative evaluation conducted through interviews with teachers and students participating in the program. This study found that students with poor mathematics learning were more motivated to learn, started to do mathematics, and encouraged to be confident when using learning materials that included easy problems and detailed solutions that they could solve themselves. From these results, the following three implications can be derived in developing a program to support students who are experiencing poor mathematics learning in high school. First, we should develop learning materials that link middle school mathematics to high school mathematics so that students can supplement middle school mathematics related to high school mathematics. Second, we need to develop learning materials that include detailed solutions to basic examples and include homogeneous problems that can be solved while looking at the basic example's solution process. Third, we should avoid the challenge of asking students who are under-achieving to respond too openly.

• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.897-905
• /
• 2022

Research for video key frame detection has been actively conducted in the fields of computer vision. Recently with the advances on deep learning techniques, performance of key frame detection has been improved, but the various type of video content and complicated background are still a problem for efficient learning. In this paper, we propose a novel method for key frame detection, witch utilizes contrastive learning and memory bank module. The proposed method trains the feature extracting network based on the difference between neighboring frames and frames from separate videos. Founded on the contrastive learning, the method saves and updates key frames in the memory bank, witch efficiently reduce redundancy from the video. Experimental results on video dataset show the effectiveness of the proposed method for key frame detection.