• The Journal of the Korea Contents Association
• /
• v.20 no.11
• /
• pp.422-434
• /
• 2020

This study aims to analyze the types of college admission that should be strengthened or reflected in universities and to suggest the direction of entrance examination by identifying the actual implementation of the literature-science integrated 2015 revised national curriculum. In order to do so, in-depth interviews on the current state were executed to five curriculum experts. As a result of the interview, it was found that the introduction and adoption of clear admission types look into the inner side of high school life are necessary. Also, it is required to establish specific criteria for student selection expand in-depth interviews related to learning activities in high school, strengthen evaluation competence of admission staffs and recruit more evaluation personnel. In addition, in order to revitalize the 2015 revised curriculum, it is necessary to evaluate how many subjects, especially in career-related subjects, students have taken in order to expand the school record-focused system. For this, it is required to extract evaluation elements and criteria of universities that can grasp continuous and active role performance, and to design a typical design that can objectively judge them. This study can contribute to the settlement of the selection process that can revitalize public education. And it is expected that the selection of the talents desired by the university will be used as a possible basic data.

• Journal of Korean Society for Quality Management
• /
• v.51 no.4
• /
• pp.573-588
• /
• 2023

Purpose: This study presents a research approach that utilizes deep reinforcement learning to construct optimal portfolios based on the business cycle for stocks and other assets. The objective is to develop effective investment strategies that adapt to the varying returns of assets in accordance with the business cycle. Methods: In this study, a diverse set of time series data, including stocks, is collected and utilized to train a deep reinforcement learning model. The proposed approach optimizes asset allocation based on the business cycle, particularly by gathering data for different states such as prosperity, recession, depression, and recovery and constructing portfolios optimized for each phase. Results: Experimental results confirm the effectiveness of the proposed deep reinforcement learning-based approach in constructing optimal portfolios tailored to the business cycle. The utility of optimizing portfolio investment strategies for each phase of the business cycle is demonstrated. Conclusion: This paper contributes to the construction of optimal portfolios based on the business cycle using a deep reinforcement learning approach, providing investors with effective investment strategies that simultaneously seek stability and profitability. As a result, investors can adopt stable and profitable investment strategies that adapt to business cycle volatility.

• Journal of Internet of Things and Convergence
• /
• v.8 no.4
• /
• pp.49-55
• /
• 2022

This study aimed to examine the meaning of adult learners' experience in which they performed a convergence program for the self-confidence improvement of disabled persons with brain lesion who were daycare center users. For the goal, the study collected data through a 5-session profound interview with those disabled persons and then through this author's observation. This study analyzed all the data and, as a result, categorized three significant themes that best represented the above mentioned meaning, which are 'tension of beginning', 'joy of being in company with others' and 'I as the present being'. With those meaningful themes taken into serious consideration. Finally, this study suggested that field programs for social welfare practice in better connection with adult learners' major should be researched and developed.

• The Journal of Korea Robotics Society
• /
• v.15 no.4
• /
• pp.398-403
• /
• 2020

Robot's throwing control is difficult to accurately calculate because of air resistance and rotational inertia, etc. This complexity can be solved by using machine learning. Reinforcement learning using reward function puts limit on adapting to new environment for robots. Therefore, this paper applied deep reinforcement learning using neural network without reward function. Throwing is evaluated as a success or failure. AI network learns by taking the target position and control policy as input and yielding the evaluation as output. Then, the task is carried out by predicting the success probability according to the target location and control policy and searching the policy with the highest probability. Repeating this task can result in performance improvements as data accumulates. And this model can even predict tasks that were not previously attempted which means it is an universally applicable learning model for any new environment. According to the data results from 520 experiments, this learning model guarantees 75% success rate.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1267-1270
• /
• 2021

In this paper, we propose a distributed routing algorithm for mobile ad hoc networks (MANET) where mobile devices can be utilized as relays for communication between remote source-destination nodes. The objective of the proposed algorithm is to minimize the end-to-end communication delay caused by transmission failure with deep channel fading. In each hop, the node needs to select the next relaying node by considering a tradeoff relationship between the link stability and forward link distance. Based on such feature, we formulate the problem with partially observable Markov decision process (MDP) and apply deep reinforcement learning to derive effective routing strategy for the formulated MDP. Simulation results show that the proposed algorithm outperforms other baseline schemes in terms of the average end-to-end delay.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.406-409
• /
• 2023

With the explosion of information, recommendation algorithms are becoming increasingly important in providing people with appropriate content, enhancing their online experience. In this paper, we propose a recommender system using advanced deep reinforcement learning(DRL) techniques. This method is more adaptive and integrative than traditional methods. We selected the MovieLens dataset and employed the precision metric to assess the effectiveness of our algorithm. The result of our implementation outperforms other baseline techniques, delivering better results for Top-N item recommendations.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.633-642
• /
• 2021

This study explores the online learning experiences of Chinese foreign students in Korea by using the CQR process and method. To gather data, researchers conducted online, in-depth interviews with 15 Chinese university students in Korea who were enrolled in the spring and fall semesters in 2020. After compiling the research, the data were segmented into four domains and 13 categories, with 36 subcategories identified from among foreign students' online learning experiences. The results show that Chinese students perceived the convenience of online classes and personalized learning as its strength, but considered lowered motivation and lack of concentration as weaknesses. Also, they experienced an increase in the amount of learning, spending more time studying online, using personal learning strategies, and getting help from friends and the university's online learning system. Moreover, they experienced difficulties related to class notifications, guidance, and interactions with the instructors. Foreign students studying in Korea need their instructor's facilitation in order to understand and participate in online classes, reinforcing a student's self-directed learning ability, and need appropriate guidance and support in terms of the online class environment.

• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.55-64
• /
• 2019

In this study, we introduce trends in neural-network-based deep learning research applied to dialogue systems. Recently, end-to-end trainable goal-oriented dialogue systems using long short-term memory, sequence-to-sequence models, among others, have been studied to overcome the difficulties of domain adaptation and error recognition and recovery in traditional pipeline goal-oriented dialogue systems. In addition, some research has been conducted on applying reinforcement learning to end-to-end trainable goal-oriented dialogue systems to learn dialogue strategies that do not appear in training corpora. Recent neural network models for end-to-end trainable chit-chat systems have been improved using dialogue context as well as personal and topic information to produce a more natural human conversation. Unlike previous studies that have applied different approaches to goal-oriented dialogue systems and chit-chat systems respectively, recent studies have attempted to apply end-to-end trainable approaches based on deep neural networks in common to them. Acquiring dialogue corpora for training is now necessary. Therefore, future research will focus on easily and cheaply acquiring dialogue corpora and training with small annotated dialogue corpora and/or large raw dialogues.

• Journal of the Korean Institute of Gas
• /
• v.27 no.2
• /
• pp.49-56
• /
• 2023

As AI (Artificial Intelligence)-related technologies are highly developed due to the 4th industrial revolution, cases of applying AI in various fields are increasing. The main reason is that there are practical limits to direct processing and analysis of exponentially increasing data as information and communication technology develops, and the risk of human error can be reduced by applying new technologies. In this study, after collecting the data received from the 'remote potential measurement terminal (T/B, Test Box)' and the output of the 'remote rectifier' at that time, AI was trained. AI learning data was obtained through data augmentation through regression analysis of the initially collected data, and the learning model applied the value-based Q-Learning model among deep reinforcement learning (DRL) algorithms. did The AI that has completed data learning is put into the actual city gas supply area, and based on the received remote T/B data, it is verified that the AI responds appropriately, and through this, AI can be used as a suitable means for electricity management in the future. want to verify.

• Journal of the Korean association of regional geographers
• /
• v.22 no.2
• /
• pp.397-410
• /
• 2016

Although industrial complexes have played as an engine of the Korean economy for the last 40 years, the majority of industrial complexes shows limitations to the continuous growth such as a lack of innovation capabilities and social capital, conceived as a key to transforming into clusters of innovation. To overcome those problems, the Korean government embarked on the cluster policy from the mid 2000's, focusing on promoting the endogenous development capabilities of individual industrial complexes. Drawing upon the in-depth case study of the Gumi IT cluster, one of the representative large-scale industrial complexes in Korea, the authors conclude that the cluster policy has contributed to making the Gumi IT cluster enhance the capabilities of endogenous development through the facilitation of self-organizing learning communities within the cluster.