• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.1
• /
• pp.17-28
• /
• 2019

In the financial investment management strategy, the distributed investment selecting and combining various financial assets is called portfolio management theory. In recent years, the blockchain based financial assets, such as cryptocurrencies, have been traded on several well-known exchanges, and an efficient portfolio management approach is required in order for investors to steadily raise their return on investment in cryptocurrencies. On the other hand, deep learning has shown remarkable results in various fields, and research on application of deep reinforcement learning algorithm to portfolio management has begun. In this paper, we propose an efficient financial portfolio investment management method based on Asynchronous Advantage Actor-Critic (A3C), which is a representative asynchronous reinforcement learning algorithm. In addition, since the conventional cross-entropy function can not be applied to portfolio management, we propose a proper method where the existing cross-entropy is modified to fit the portfolio investment method. Finally, we compare the proposed A3C model with the existing reinforcement learning based cryptography portfolio investment algorithm, and prove that the performance of the proposed A3C model is better than the existing one.

• Journal of The Korean Association For Science Education
• /
• v.38 no.6
• /
• pp.825-838
• /
• 2018

The purpose of this study is to develop a survey tool of scientific character for elementary student which connects science education and character education effectively by figuring out traits of elementary students' character being presented in teaching and learning context of elementary school science. For this, we adapted the theocratical model from the previous research which defined scientific character as the competencies being able to practice in concrete teaching and learning context of science. Based on this model, we developed the survey tool as 'Scientific Character Inventory for Elementary Student' to assess elementary students' scientific character as the competences to practice the virtues being pursued in the context of elementary school science and verified its reliability and validity. As a result of an exploratory and confirmatory factor analysis, we confirmed all the items could be summarized into 28 items and eight constructs such as scientific problem-solving, self-management, self-reflection, communication, interpersonal skill, community participation, global citizenship, and environmental ethics awareness. We found that minimum reliability coefficient of constructs was over than 0.5 and reliability coefficient of the total items was 0.878. And also, there was modest relationship between each construct and the total score of scientific character. These results show that the developed survey tool can be useful in evaluating the effectiveness of science character education. This study is meaningful in that it systematically reveals constructs of scientific character which can be raised in concrete context of science teaching and learning so as to suggest the survey tool to assess this.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.17 no.3
• /
• pp.63-83
• /
• 2021

The appearance of education is also rapidly changing in social changes represented by social networks. And the development of information and communication technology is also having a widespread effect on the education field. In the era of untact caused by Covid-19, education through smart learning is having a greater effect on students as well as adult learners more quickly and broadly. In addition, smart learning is not just limited to learning content, but is developing into personalized, convergence, and intelligent. The purpose of this study is to identify the factors of ARCS motivation theory that can determine the learning motivation of smart learning users, and to empirically study the casual relationship between these factors on education achievement through practical value and hedonic value. Specifically, I would like to examine how the independent variables ARCS motivation factors (attention, relevance, confidence, and satisfaction) affect learners' education achievement through the parameters of practical value and hedonic value. To this end, a research model was presented that applied the main variables of attention, relevance, confidence, and satisfaction, which are four elements of ARCS motivation theory, a specific and systematic motivational strategy to induce and maintain learners' motivation. In order to empirically verify the research model of this study, a survey was carried out on learners with experience using smart learning. As a result of the study, first attention was found to have a positive effect on the hedonic value. Second, relevance was found to have a positive effect on the hedonic value. Third, it was found that confidence did not have a positive effect on the practical value and the hedonic value. Forth, satisfaction was found to have a positive effect on the practical value and the hedonic value. Fifth, practical value was found to have a positive effect on the education achievement. Sixth, hedonic value was found to have a positive effect on the education achievement. Through this, it can be seen that the intrinsic motivation of learners using smart learning affects the education achievement of users through intrinsic and extrinsic value. A variety of smart learning that combines advanced IT technologies such as AI and big data can contribute to improving learners' education achievement more effectively and efficiently. Furthermore, it can contribute a lot to social development.

• Journal of Digital Convergence
• /
• v.19 no.4
• /
• pp.217-225
• /
• 2021

This study aimed to provide implications required to establish a content strategy by examining the influencing factors affecting the acceptance of curation services for 320 OTT users, and the main results are as follows. First, innovativeness was found to have a positive effect on performance expectations. Second, innovativeness was found to have a positive impact on the effort expectation. Third, performance expectation had a positive effect on the intention to use continuously. Fourth, it was shown that the effort expectation had a positive effect on the intention to use continuously. Fifth, social influence was found to have no significant effect on the intention to use continuously. Sixth, it was found that the facilitating conditions did not significantly affect the intention to use continuously. The above results can be assessed as the higher the OTT users perceive the performance and effort expectations of the curation service, the higher their intention to continue using them. This study is meaningful in that it verified the factors affecting the intention to use the OTT curation service and expanded the UTAUT model.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.1-27
• /
• 2021

The entire tourism industry is being hit hard by the COVID-19 as a global pandemic. Accommodation sharing services such as Airbnb, which have recently expanded due to the spread of the sharing economy, are particularly affected by the pandemic because transactions are made based on trust and communication between consumer and supplier. As the pandemic situation changes individuals' perceptions and behavior of travel, strategies for the recovery of the tourism industry have been discussed. However, since most studies present macro strategies in terms of traditional lodging providers and the government, there is a significant lack of discussion on differentiated pandemic response strategies considering the peculiarity of the sharing economy centered on peer-to-peer transactions. This study discusses the marketing strategy for individual hosts of Airbnb during COVID-19. We empirically analyze the effect of changes in listing descriptions posted by the Airbnb hosts on listing performance after COVID-19 was outbroken. We extract nine aspects described in the listing descriptions using the Attention-Based Aspect Extraction model, which is a deep learning-based aspect extraction method. We model the effect of aspect changes on listing performance after the COVID-19 by observing the frequency of each aspect appeared in the text. In addition, we compare those effects across the types of Airbnb listing. Through this, this study presents an idea for a pandemic crisis response strategy that individual service providers of accommodation sharing services can take depending on the listing type.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.15 no.2
• /
• pp.23-36
• /
• 2005

The main obstacle hindering the wide deployment of identity-based cryptosystem is that the entity responsible for creating the private key has too much power. As a result, private keys are no longer private. One obvious solution to this problem is to apply the threshold technique. However, this increases the authentication computation, and communication cost during the key issuing phase. In this paper, we propose a new effi ient model for issuing multiple private keys in identity-based encryption schemes based on the Weil pairing that also alleviates the key escrow problem. In our system, the private key of a user is divided into two components, KGK (Key Description Key) and KUD(Key Usage Desscriptor), which are issued separately by different parties. The KGK is issued in a threshold manner by KIC (Key Issuing Center), whereas the KW is issued by a single authority called KUM (Key Usage Manager). Changing KW results in a different private key. As a result, a user can efficiently obtain a new private key by interacting with KUM. We can also adapt Gentry's time-slot based private key revocation approach to our scheme more efficiently than others. We also show the security of the system and its efficiency by analyzing the existing systems.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.91-98
• /
• 2021

Today's information and communication technology is rapidly developing, the security of IT infrastructure is becoming more important, and at the same time, cyber attacks of various forms are becoming more advanced and sophisticated like intelligent persistent attacks (Advanced Persistent Threat). Early defense or prediction of increasingly sophisticated cyber attacks is extremely important, and in many cases, the analysis of network-based intrusion detection systems (NIDS) related data alone cannot prevent rapidly changing cyber attacks. Therefore, we are currently using data generated by intrusion detection systems to protect against cyber attacks described above through Host-based Intrusion Detection System (HIDS) data analysis. In this paper, we conducted a comparative study on machine learning algorithms using LID-DS (Leipzig Intrusion Detection-Data Set) host-based intrusion detection data including thread information, metadata, and buffer data missing from previously used data sets. The algorithms used were Decision Tree, Naive Bayes, MLP (Multi-Layer Perceptron), Logistic Regression, LSTM (Long Short-Term Memory model), and RNN (Recurrent Neural Network). Accuracy, accuracy, recall, F1-Score indicators and error rates were measured for evaluation. As a result, the LSTM algorithm had the highest accuracy.

• Journal of Hospice and Palliative Care
• /
• v.24 no.4
• /
• pp.204-213
• /
• 2021

Purpose: At the end of life, communication is a key factor for good care. However, in clinical practice, it is difficult to adequately discuss end-of-life care. In order to understand and analyze how decision-making related to life-sustaining treatment (LST) is performed, the shared decision-making (SDM) behaviors of physicians were investigated. Methods: A questionnaire was designed after reviewing the literature on attitudes toward SDM or decision-making related to LST. A final item was added after consulting experts. The survey was completed by internal medicine residents and hematologists/medical oncologists who treat terminal cancer patients. Results: In total, 202 respondents completed the questionnaire, and 88.6% said that the decision to continue or end LST is usually a result of SDM since they believed that sufficient explanation is provided to patients and caregivers, patients and caregivers make their own decisions according to their values, and there is sufficient time for patients and caregivers to make a decision. Expected satisfaction with the decision-making process was the highest for caregivers (57.4%), followed by physicians (49.5%) and patients (41.1%). In total, 38.1% of respondents said that SDM was adequately practiced when making decisions related to LST. The most common reason for inadequate SDM was time pressure (89.6%). Conclusion: Although most physicians answered that they practiced SDM when making decisions regarding LST, satisfactory SDM is rarely practiced in the clinical field. A model for the proper implementation of SDM is needed, and additional studies must be conducted to develop an SDM model in collaboration with other academic organizations.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.7
• /
• pp.233-240
• /
• 2022

Most of the recent AI researches has focused on developing AI models. However, recently, artificial intelligence research has gradually changed from model-centric to data-centric, and the importance of learning data is getting a lot of attention based on this trend. However, it takes a lot of time and effort because the preparation of learning data takes up a significant part of the entire process, and the generation of labeling data also differs depending on the purpose of development. Therefore, it is need to develop a tool with various labeling functions to solve the existing unmetneeds. In this paper, we describe a labeling system for creating precise and fast labeling data of medical images. To implement this, a semi-automatic method using Back Projection, Grabcut techniques and an automatic method predicted through a machine learning model were implemented. We not only showed the advantage of running time for the generation of labeling data of the proposed system, but also showed superiority through comparative evaluation of accuracy. In addition, by analyzing the image data set of about 1,000 patients, meaningful diagnostic indexes were presented for men and women in the diagnosis of sarcopenia.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.2
• /
• pp.1-10
• /
• 2021

The purpose of this study is to explore a significant HPWS(High Performance Work System) model for the entertainment industry. HPWS is one of the most studied themes for managing human resources as well as a set of practices to elicit employees' commitment to an organization. Recently, the entertainment industry is growing rapidly, but it is difficult for entertainment firms to retain a stable profit unlike the manufacturing industry. This is because the performance of entertainment business tends to rely heavily on the capabilities and synergy of human resources. In order to suggest a systematic way to manage these, this research identified an effective HPWS model for entertainment business and provides a competitive advantage to entertainment firms, using ANP(Analytic Network Process). ANP is a multicriteria decision making technique that allows dependences and feedbacks among decision elements in the hierarchical or network structures in a holistic manner. The pairwise comparison data that prioritized the criteria of HPWS was collected from 28 team leaders in entertainment firms. According to our results, the most critical factor for HPWS in entertainment business is "employee involvement in decision-making." The sub-factors such as "open communication," "distributive decision-making," and "performance-driven reward" have a greater effect. These findings could provide implications for entertainment firms to determine which practices should be taken into account to accomplish HPWS.