• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.7
• /
• pp.928-933
• /
• 2018

Nowadays, gastropathy is a common disease. As endoscopic equipment are developed and used widely, it is possible to provide a large number of endoscopy images. Computer-aided Diagnosis (CADx) systems aim at helping physicians to identify possibly malignant abnormalities more accurately. In this paper, we present a CADx system to detect and classify the abnormalities of gastric lesions which include bleeding, ulcer, neuroendocrine tumor and cancer. We used an Inception module based deep learning model. And we used data augmentation for learning. Our preliminary results demonstrated promising potential for automatically labeled region of interest for endoscopy doctors to focus on abnormal lesions for subsequent targeted biopsy, with Az values of Receiver Operating Characteristic(ROC) curve was 0.83. The proposed CADx system showed reliable performance.

• Journal of Information Technology Services
• /
• v.7 no.4
• /
• pp.21-43
• /
• 2008

This paper develops the research model for the understanding of learner's usage intention in web based collaborative learning(WBCL) system. This model is based on the Davis' Technology Acceptance Model(TAM) and Social Interactivity Theory. Data is collected 225 University students from two different institutions. They were divided into 46 groups and asked to complete an online TOEIC preparation module using WBCL systems over 4 weeks. Data were collected at three points for each participant-before, 3 weeks after, and at the end of the online module. The result show that TAM based Belief factors(Usefulness, Ease of use, Playfulenss) are important determinants of usage intention in WBCL systems. The study also found the external factors of the extended TAM to be subjective norm, leader's enthusiasm in WBCL context.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.1
• /
• pp.49-55
• /
• 2018

In this paper, we propose a design and development of instructional cards to understand the grammar of coding, solving the problems and extending the computational thinking in the robot-driven environment. First, we designed the input/output module of the robot to process the coding grammar through the function analysis of the robot. And we designed the module of command card to learn coding grammar using color sensors. We have proven the validity of the designed instruction card by examining the experts to see if it is suitable for coding grammar learning. Designed robot and command card were developed with 28 cards and sensor robot. After applying the developed robot and command card to the elementary school students, the questionnaire showed that students grow the understanding and confidence of coding. In addition, students showed an increased need for programming learning.

• ETRI Journal
• /
• v.45 no.1
• /
• pp.60-74
• /
• 2023

Integration of the machine learning (ML) technique in all-optical networks can enhance the effectiveness of resource utilization, quality of service assurances, and scalability in optical networks. All-optical multistage interconnection networks (MINs) are implicitly designed to withstand the increasing highvolume traffic demands at data centers. However, the contention resolution mechanism in MINs becomes a bottleneck in handling such data traffic. In this paper, a select list of ML algorithms replaces the traditional electronic signal processing methods used to resolve contention in MIN. The suitability of these algorithms in improving the performance of the entire network is assessed in terms of injection rate, average latency, and latency distribution. Our findings showed that the ML module is recommended for improving the performance of the network. The improved performance and traffic grooming capabilities of the module are also validated by using a hardware testbed.

• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.177-187
• /
• 2023

Semi-supervised learning (SSL) is an effective approach to training models using a small amount of labeled data and a larger amount of unlabeled data. However, many papers in the field use a fixed threshold when applying pseudo-labels without considering the feature-wise differences among images of different classes. In this paper, we propose a SSL method for synthetic aperture radar (SAR) image classification that applies different thresholds for each class instead of using a single fixed threshold for all classes. We propose a threshold learning module into the model, considering the differences in feature distributions among classes, to dynamically learn thresholds for each class. We compare the application of a SSL SAR image classification method using different thresholds and examined the advantages of employing class-specific thresholds.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.10 no.2
• /
• pp.1-9
• /
• 2006

In this paper, we developed professor-assisted learning system including continuously accessible on-off lesson linked module, user designated environment setting module and accumulation of special data, reworking, recycling module.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2001.10a
• /
• pp.321-324
• /
• 2001

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement Beaming is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement loaming is different from supervised teaming in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement loaming algorithms like Q-learning do not require defining or loaming any models of the surrounding environment. Nevertheless it can learn the optimal policy if the agent can visit every state-action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem, we suggest Adaptive Mediation-based Modular Q-Learning(AMMQL) as an improvement of the existing Modular Q-Learning(MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state space effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. This paper introduces the concept of AMMQL and presents details of its application into dynamic positioning of robot soccer agents.

• Fourth Industrial Review
• /
• v.4 no.1
• /
• pp.11-18
• /
• 2024

Purpose: The purpose of this study is to develop a geography class teaching and learning guide that enables learners to realistically explore the characteristics of the world's climate and geographical environment using digital tools. Research design, data and methodology: We review previous research on classes using goal-based scenario learning models, gamification, and digital tools, and explore tools that can be applied to world geography classes. Based on the exploration results, a goal-based scenario learning module is designed and a strategy for promoting educational gamification is established based on the ADDIE instructional design model. Results: The study comprises four sessions. Sessions 1-3 involve performance evaluations using a goal-based scenario learning module. Learners create game characters reflecting geographical characteristics, present results, and proceed with 3D modeling. In Session 4, a gamification class using Google Sites on the CoSpaces metaverse platform will be conducted. Conclusions: The study introduces a goal-based scenario learning model and a gamification class using digital tools to empower learners in exploring geographical diversity and its impact on lifestyles. Utilizing an accessible online platform, the study provides practical measures for integrating digital tools into geography education, addressing the current importance of digital technology in teaching.

• Management & Information Systems Review
• /
• v.2
• /
• pp.311-334
• /
• 1998

By decreasing in CPU price and development of computer assembling technology, personal computer fake a good chance to accelerate its supply. Recently, as being introduced new computing technology so called multi media, teaming assist system which is based on single media such as studying book, cassette tape, video tape, or something else is rapidly being replaced by new assist education system based on multi media in which it is operated by the personal computer. In the computer assist education system, there is an evaluation module which appraise learner's study level into the next study strategy. At the view of this point, this part is very important. In this part, there are some factors like Importance, complexity, or difficulty which commonly include fuzzy factors in our surrounding. But until now, we are still out of the level to handle the evaluation module adequately among the some studies. In this study, we would like to suggest a new module that evaluate learning achievement of ICAI which have a variety of fuzzy environment. We combine Independent fuzzy environment like importance, complexity, difficulty into making total evaluation of learner's achievement. By the result, with expressing by linguistic form, this study can provide the theoretical basis in which we will be able to carry out sentence toward evaluation among elementary school.

• Journal of KIISE:Software and Applications
• /
• v.31 no.8
• /
• pp.1083-1091
• /
• 2004

This paper presents a chunking system employed as a preprocessing module to the parser in a Chinese to Korean machine translation system. The parser can benefit from the dependency information provided by the chunking module. The chunking system was implemented using transformation-based learning technique and an effective interface that conveys the dependency information to the parser was also devised. The module was integrated into the machine translation system and experiments were performed with corpuses collected from Chinese websites. The experimental results show the introduction of chunking module provides noticeable improvements in the parser's performance.