• Journal of Information Processing Systems
• /
• v.18 no.5
• /
• pp.701-710
• /
• 2022

With the development of artificial intelligence technology, various methods have been developed for recognizing objects in images using machine learning. Image segmentation is the most effective among these methods for recognizing objects within an image. Conventionally, image datasets of various classes are trained simultaneously. In situations where several classes require segmentation, all datasets have to be trained thoroughly. Such repeated training results in low training efficiency because most of the classes have already been trained. In addition, the number of classes that appear in the datasets affects training. Some classes appear in datasets in remarkably smaller numbers than others, and hence, the training errors will not be properly reflected when all the classes are trained simultaneously. Therefore, a new method that separates some classes from the dataset is proposed to improve efficiency during training. In addition, the accuracies of the conventional and proposed methods are compared.

• Smart Media Journal
• /
• v.12 no.3
• /
• pp.112-119
• /
• 2023

Shrimp farming has been becoming a new source of income for fishermen in South Korea. It is often necessary for fishers to measure the size of the shrimp for the purpose to understand the growth rate of the shrimp and to determine the amount of food put into the breeding pond. Traditional methods rely on humans, which has huge time and labor costs. This paper proposes a deep learning-based method for calculating the size of shrimps automatically. Firstly, we use fine-tuning techniques to update the Mask RCNN model with our farm data, enabling it to segment shrimps and generate shrimp masks. We then use skeletonizing method and maximum inscribed circle to calculate the length and width of shrimp, respectively. Our method is simple yet effective, and most importantly, it requires a small hardware resource and is easy to deploy to shrimp farms.

• Journal of Korea Multimedia Society
• /
• v.20 no.7
• /
• pp.1102-1112
• /
• 2017

The purpose of this study is to design and application of term project model for Game Math in flipped learning environment. In the term project self study model, students interacts with multi-instruction materials and multi-tutors on flipped learning. We develop a case for game update term project and implement it to a real Game Math classroom. As a result, we show the positive learning experiences focused on effects of technology and human relation through survey.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.15 no.3
• /
• pp.145-152
• /
• 2015

We consider an online selective-sample learning problem for sequence classification, where the goal is to learn a predictive model using a stream of data samples whose class labels can be selectively queried by the algorithm. Given that there is a limit to the total number of queries permitted, the key issue is choosing the most informative and salient samples for their class labels to be queried. Recently, several aggressive selective-sample algorithms have been proposed under a linear model for static (non-sequential) binary classification. We extend the idea to hidden Markov models for multi-class sequence classification by introducing reasonable measures for the novelty and prediction confidence of the incoming sample with respect to the current model, on which the query decision is based. For several sequence classification datasets/tasks in online learning setups, we demonstrate the effectiveness of the proposed approach.

• Archives of design research
• /
• v.15 no.1
• /
• pp.113-122
• /
• 2002

This thesis is focused on online education and proposes a guideline for selecting teaming theories and multimedia representation without difficulty. On the first, consideration of learning theories and analysis of multimedia properties are made, and from these results guidelines are formed. Then they are applied to each 6 types of CAI. Objectivism and constructivism could be used for the basic framework of CAI. The former is suitable for reed, sequential, structural, and passive learning style and the latter is suitable for selectable, unstructural, active, self-controled, learning style. And the quideline for selecting multimedia representation is made out of the properties of media, learners(cognitive model, proficiency, acceptance), and teaming contents. On the basis of guideline obtaining from the previous process, I suggest mosts suitable conditions for each 6 types of CAI available today. Those conditions are consist of learning theories, media selection, levels of learners, and categories and properties of teaming contents.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.1
• /
• pp.208-220
• /
• 2015

This study analyze Online class's current condition in Smart era. And suggest better operation model based on Internet Architecture. This study focuses the condition of e-learning operation model in University online class. Especially, 'Time Check Idea' that using for attendance on e-learning class has some side effects. So this study would applied 'Qualitative Check Idea Concept' on e-learning class. Question Based System, QBS is example model. QBS is leading a Learner's participation in e-class by Making Quiz. These quizs are shared with other students and refer to studing contents. Practically operating Qualitative Concept model QBS on university e-class, we can seek for the effectiveness of Qualitative e-learning model QBS.

• Journal of Digital Convergence
• /
• v.19 no.1
• /
• pp.11-22
• /
• 2021

The COVID-19 pandemic has led to distance learning in primary and secondary school. Little has been known whether home ICTs environment is appropriate for the distance learning. This paper aims to assess the current state of ICTs environment at home for the distance learning of children. Using 2012 and 2019 Korean Media Panel Survey, we investigated the number of smart devices owned by households and found differences in ownership by household characteristics. The results showed that the majority of household owned more than one smart devices per child. However, the difference in the proportion of households with less than one device per child varied depending on whether smartphone was included in smart devices. These results imply that public intervention is needed to prevent educational inequality caused by the home ICTs environment for the distance learning.

• Smart Media Journal
• /
• v.12 no.7
• /
• pp.9-17
• /
• 2023

Plant diseases and pests affect the growth of various plants, so it is very important to identify pests at an early stage. Although many machine learning (ML) models have already been used for the inspection and classification of plant pests, advances in deep learning (DL), a subset of machine learning, have led to many advances in this field of research. In this study, disease and pest inspection of abnormal crops and maturity classification were performed for normal crops using YOLOX detector and MobileNet classifier. Through this method, various plant pest features can be effectively extracted. For the experiment, image datasets of various resolutions related to strawberries, peppers, and tomatoes were prepared and used for plant pest classification. According to the experimental results, it was confirmed that the average test accuracy was 84% and the maturity classification accuracy was 83.91% in images with complex background conditions. This model was able to effectively detect 6 diseases of 3 plants and classify the maturity of each plant in natural conditions.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.36-47
• /
• 2023

Industrial Control System(ICS), which controls facilities at major industrial sites, is increasingly connected to other systems through networks. With this integration and the development of intelligent attacks that can lead to a single external intrusion as a whole system paralysis, the risk and impact of security on industrial control systems are increasing. As a result, research on how to protect and detect cyber attacks is actively underway, and deep learning models in the form of unsupervised learning have achieved a lot, and many abnormal detection technologies based on deep learning are being introduced. In this study, we emphasize the application of preprocessing methodologies to enhance the anomaly detection performance of deep learning models on time series data. The results demonstrate the effectiveness of a Wavelet Transform (WT)-based noise reduction methodology as a preprocessing technique for deep learning-based anomaly detection. Particularly, by incorporating sensor characteristics through clustering, the differential application of the Dual-Tree Complex Wavelet Transform proves to be the most effective approach in improving the detection performance of cyber attacks.

• International Journal of Contents
• /
• v.12 no.2
• /
• pp.49-57
• /
• 2016

This paper aims to explore instructional design of a cyber classroom for secondary students' basic English language competence. A paucity of support for low or under achieving students' English learning exists particularly at the secondary level. In order to bridge the gap, there has been demand for online educational resources considered to be an effective tool in improving students' self-directed learning and motivation. This study employs a comprehensive approach to instructional design for the asynchronous cyber classroom with the underlying premise that different learning theories can be applied in a complementary manner to serve different pedagogical purposes best. Gagné's conditions of learning theory, Bruner's constructivist theory, Carroll's minimalist theory, and Vygotsky's social cognitive development theory serve as the basis for designing instruction and selecting appropriate media. The ADDIE model is used to develop online teaching and learning materials. Twenty-five key grammatical features were selected through the analysis of the national curriculum of English, being grouped into five units. Each feature is covered in one cyber asynchronous class. An Integration Class is given at the end of every five classes for synthesis, where students can practice grammatical features in a communicative context. Related theories, pedagogical practices, and practical web-design strategies for cyber Basic English classes are discussed with suggestions for research, practice and policy to support self-directed learning through a cyber class.