• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.24 no.6
• /
• pp.1-13
• /
• 2021

This study was performed to investigate the ecosystem service patterns in relation to climate change acceleration utilizing big data analysis. This study aimed to use big data analysis as one of the network of views to identify convergent thinking in two fields: climate change and ecosystem service. The keywords were analysed to ascertain if there were any differences in the perceiving problems, policy direction, climate change implications, and regional differences. In addition, we examined the research keywords of each continent, the centre of ecosystem service research, and the topics to be referred to in domestic research. The results of the analysis are as follows: First, the keyword centrality of climate change is similar to the detailed indicators of The Intergovernmental Science-Policy Platform on Biodiversity and Ecosystem Services (IPBES) regulations, content, and non-material ecosystem services. Second, the cross-analysis of terms in two journals showed a difference in value-oriented point; the Ecosystem Service Journal identified green infrastructure as having economic value, whereas the Climate Change Journal perceives water, forest, carbon, and biodiversity as management topics. The Climate Change Journal, but not the former, focuses on future predictions. Third, the analysis of the research topics according to continents showed that water and soil are closely related to the economy, and thus, play an important role in policy formulation. This disparity is due to differences in each continent's environmental characteristics, as well as economic and policy issues. This fact can be used to refer to the direction of research on ecosystem services in Korea. Consistent with the recent trend of expanding research regarding the impacts of climate change, it is necessary to study strategies to scientifically predict and respond to the negative effects of climate change.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• Land and Housing Review
• /
• v.13 no.1
• /
• pp.67-84
• /
• 2022

This study aims to investigate the value of greenbelts exploring how they can be linked with green infrastructure networks. This research interprets the results of geographical information system (GIS) analysis differently from a conventional approach. The findings of the research are four-fold based on the analysis of the Daejeon Metropolitan Area. First, the most controversial greenbelts are laid on Yuseong-gu because the relaxation of the greenbelts for new housing development has caused outstanding issues since the early 2000s. Decisions on further relaxation or restoration of the greenbelts, which will provide a new direction for the establishment of green infrastructure networks, should be made through accurate environmental assessments. Second, the connected north-south corridors of large cities will affect the greenbelts not only in Daejeon, but also in the entire Chungcheong Provinces, and surrounding local municipalities, which should be considered for the revision of the greenbelt policy. Third, it is expected to experience growing development pressures towards neighboring municipalities due to the ongoing strict greenbelt policy. Among them, the most likely areas are Sejong City to the north and Nonsan to the south, requiring policy measures. Fourth, the value of green infrastructure should be added to current evaluation criteria rather than a binary approach - relaxing or preserving the greenbelts - to be holistically integrated with a metropolitan plan.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.318-331
• /
• 2022

With the recent development of hardware computing devices and software based frameworks, machine tasks using deep learning networks are expected to be utilized in various industrial fields and personal IoT devices. However, in order to overcome the limitations of high cost device for utilizing the deep learning network and that the user may not receive the results requested when only the machine task results are transmitted from the server, Collaborative Intelligence (CI) proposed the transmission of feature maps as a solution. In this paper, an efficient compression method for feature maps with vast data sizes to support the CI paradigm was analyzed and presented through experiments. This method increases redundancy by applying feature map reordering to improve compression efficiency in traditional video codecs, and proposes a feature map method that improves compression efficiency and maintains the performance of machine tasks by simultaneously utilizing image compression format and video compression format. As a result of the experiment, the proposed method shows 14.29% gain in BD-rate of BPP and mAP compared to the feature compression anchor of MPEG-VCM.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.3
• /
• pp.53-61
• /
• 2022

Recent years have drawn a great attention to generation MZ and Metaverse, due to 4th industrial revolution and the development of digital environment that blurs the boundary between reality and virtual reality. Generation MZ approaches the information very differently from the existing generations and uses distinguished communication methods. In terms of learning, they have different motivations, types, skills and build relationships differently. Meanwhile, Metaverse is drawing a great attention as a teaching method that fits traits of gen MZ. Thus, the current research aimed to investigate how to increase the use of Metaverse in Educational Technology. Specifically, this research examined the antecedents of popularity of Gather Town, a platform of Metaverse. Big data of news articles have been collected and analyzed using the Bigkinds system provided by Korea Press Foundation. The analysis revealed, first, a rapid increasing trend of media exposure of Gather Town since July 2021. This suggests a greater utilization of Gather Town in the field of education after the COVID-19 pandemic. Second, Word Association Analysis and Word Cloud Analysis showed high weights on education related words such as 'remote', 'university', and 'freshman', while words like 'Metaverse', 'Metaverse platform', 'Covid19', and 'Avatar' were also emphasized. Third, Network Analysis extracted 'COVID19', 'Avatar', 'University student', 'career', 'YouTube' as keywords. The findings also suggest potential value of Gather Town as an educational tool under COVID19 pandemic. Therefore, this research will contribute to the application and utilization of Gather Town in the field of education.

• Journal of the Korean earth science society
• /
• v.43 no.1
• /
• pp.165-175
• /
• 2022

Earthquakes have occurred owing to movements on a fault since several billion years ago. Research on the relationship between earthquakes and groundwater began in the 1960s in the United States, but related works, including hydrogeochemistry research, only began in the 2010s in South Korea. In this study, domestic studies on the relationship between earthquakes and groundwater until 2021 were collected from the Web of Science and characterized by subject area (groundwater level, hydrogeochemistry, combination of the two, and others). The results showed that the number of published articles per year was positively correlated with the 2011 Tohoku earthquake, 2016 Gyeongju earthquake, and 2017 Pohang earthquake, with the maximum numbers observed in 2011, 2018, 2019, and 2020. Most studies on the relationship between earthquakes and groundwater level addressed groundwater level fluctuations in the duration of the subject earthquake, with little consideration of the precursors. Groundwater level monitoring data, as well as hydrogeochemical information and microbial communities, may contribute to a more detailed understanding of groundwater flow and chemical reactions in bedrock caused by earthquakes. Therefore, the establishment of a national groundwater monitoring network for seismic monitoring and prediction is required.

• The Journal of Society for e-Business Studies
• /
• v.27 no.1
• /
• pp.15-28
• /
• 2022

Due to recent expansion of online market such as clothing, utilizing customer review has become a major marketing measure. User review has been used as a tool of analyzing sentiment of customers. Sentiment analysis can be largely classified with machine learning-based and lexicon-based method. Machine learning-based method is a learning classification model referring review and labels. As research of sentiment analysis has been developed, multi-modal models learned by images and video data in reviews has been studied. Characteristics of words in reviews are differentiated depending on products' and customers' categories. In this paper, sentiment is analyzed via considering review data and metadata of products and users. Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), Self Attention-based Multi-head Attention models and Bidirectional Encoder Representation from Transformer (BERT) are used in this study. Same Multi-Layer Perceptron (MLP) model is used upon every products information. This paper suggests a multi-modal sentiment analysis model that simultaneously considers user reviews and product meta-information.

• Journal of Ginseng Research
• /
• v.46 no.2
• /
• pp.255-265
• /
• 2022

Background: Ginsenoside Rb1, a bioactive component isolated from the Panax ginseng, acts as a remedy to prevent myocardial injury. However, it is obscure whether the cardioprotective functions of Rb1 are related to the regulation of endogenous metabolites, and its potential molecular mechanism still needs further clarification, especially from a comprehensive metabolomics profiling perspective. Methods: The mice model of acute myocardial ischemia (AMI) and oxygen glucose deprivation (OGD)-induced cardiomyocytes injury were applied to explore the protective effect and mechanism of Rb1. Meanwhile, the comprehensive metabolomics profiling was conducted by high-performance liquid chromatography and quadrupole time-of-flight mass spectrometry (HPLC-Q/TOF-MS) and a tandem liquid chromatography and mass spectrometry (LC-MS). Results: Rb1 treatment profoundly reduced the infarct size and attenuated myocardial injury. The metabolic network map of 65 differential endogenous metabolites was constructed and provided a new inspiration for the treatment of AMI by Rb1, which was mainly associated with mitophagy. In vivo and in vitro experiments, Rb1 was found to improve mitochondrial morphology, mitochondrial function and promote mitophagy. Interestingly, the mitophagy inhibitor partly attenuated the cardioprotective effect of Rb1. Additionally, Rb1 markedly facilitated the phosphorylation of AMP-activated protein kinase α (AMPKα), and AMPK inhibition partially weakened the role of Rb1 in promoting mitophagy. Conclusions: Ginsenoside Rb1 protects acute myocardial ischemia injury through promoting mitophagy via AMPKα phosphorylation, which might lay the foundation for the further application of Rb1 in cardiovascular diseases.

• Journal of the Society of Disaster Information
• /
• v.17 no.4
• /
• pp.848-863
• /
• 2021

Purpose: On August 16, 2021, the Taliban established the Taliban regime after conquering capital Kabul of the Afghan by using the strong alliance of international terrorist organizations. The Taliban carried out terrorism targeting the Korean people, including the kidnapping of Kim Seon-il in 2004, the abduction of a member of the Saemmul Church in 2007, and the attack on Korean Provincial Reconstruction Team in 2009. Therefore, this research has shown the possibility of Taliban terrorism in Korea. Method: Based on the statistical data on terrorism that occurred in Afghanistan, Taliban's various terrorist activities such as tactics, strategies, and weapons are examined. Consequently, the target facilities and the type of terrorist attacks are analyzed. Result: The Taliban are targeting the Afghan government as their main target of attack, and IS and the Taliban differ in their selection of targets for terrorism. Conclusion: From the result of this research, we recommend Korea need to reinforce the counter terrorism system in soft targets. Because If the Taliban, which has seized control of Afghanistan, and IS, which has established a worldwide terrorism network, cooperate to threaten domestic multi-use facilities with bombing, the Republic of Korea may face a terrorist crisis with insufficient resources and counter-terrorism related countermeasures.

• The Journal of the Korea Contents Association
• /
• v.22 no.4
• /
• pp.222-230
• /
• 2022

Recently, Korea's cultural content industry is developing, and behind the growing recognition around the world is the real-time sharing service of global network users due to the development of science and technology. In particular, in the case of YouTube, its propagation power is fast and powerful in that everyone, not limited users, can become potential video providers. As more than 80% of mobile phone users are using YouTube in Korea, YouTube's information means that psychological factors of users are reflected. For example, information such as the number of video views, likes, and comments of a channel with a specific personality shows a measure of the channel's personality interest. This is highly related to the fact that information such as the frequency of keyword search on portal sites is closely related to the stock market economically and psychologically. Therefore, in this study, YouTube information from a representative entertainment company is collected through a crawling algorithm and analyzed for the causal relationship with major variables related to stock prices. This study is considered meaningful in that it conducted research by combining cultural content, IT, and financial fields in accordance with the era of the fourth industry.