• The Transactions of the Korea Information Processing Society
• /
• v.13 no.9
• /
• pp.429-436
• /
• 2024

As Large Language Models (LLMs) continue to advance, effectively harnessing their potential has become increasingly important. LLMs, trained on vast datasets, are capable of generating text across a wide range of topics, making them useful in applications such as content creation, machine translation, and chatbots. However, they often face challenges in generalization due to gaps in specific or specialized knowledge, and updating these models with the latest information post-training remains a significant hurdle. To address these issues, Retrieval-Augmented Generation (RAG) models have been introduced. These models enhance response generation by retrieving information from continuously updated external databases, thereby reducing the hallucination phenomenon often seen in LLMs while improving efficiency and accuracy. This paper presents the foundational architecture of RAG, reviews recent research trends aimed at enhancing the retrieval capabilities of LLMs through RAG, and discusses evaluation techniques. Additionally, it explores performance optimization and real-world applications of RAG in various industries. Through this analysis, the paper aims to propose future research directions for the continued development of RAG models.

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.114-123
• /
• 2024

This paper proposes AR stone tower content, an experiential content based on wearable augmented reality (AR). Although wearable augmented reality is gaining attention, the acceptance of the technology is still focused on specialized applications such as industrial sites. On the other hand, the proposed AR stone tower content is based on the material of 'stone tower' so that general users can relate to it and easily participate in it, and it is organized to utilize space in a moving environment and find and stack stones based on natural hand gestures. The proposed AR stone tower content was implemented in the HoloLens 2 environment and evaluated by general users through a pilot exhibition in a small art museum. The evaluation results showed that the overall satisfaction with the content averaged 3.85, and the content appropriateness for the stone tower material was very high at 4.15. In particular, users were highly satisfied with content comprehension and sound, but somewhat less satisfied with object recognition, body adaptation, and object control. The above user evaluations confirm the resonance and positive response to the material, but also highlight the difficulties of the average user in experiencing and interacting with the wearable AR environment.

• The KIPS Transactions:PartD
• /
• v.8D no.2
• /
• pp.154-165
• /
• 2001

A number of attempts to develop methods for measuring software effort have been focused on the area of software engineering and many models have also been suggested to estimate the effort of software projects. Almost all current models use algorithmic or statistical mechanisms, but the existing algorithmic effort estimation models have failed to produce accurate estimates. Furthermore, they are unable to reflect the rapidly changing technical environment of software development such as module reuse, 4GL, CASE tool, etc. In addition, these models do not consider the paradigm shift of software engineering and information systems(i.e., Object Oriented system, Client-Server architecture, Internet/Intranet based system etc.). Thus, a new approach to software effort estimation is needed. After reviewing and analyzing the problems of the current estimation models, we have developed a model and a system architecture that will improve estimation performance. In this paper, we have adopted a neural network model to overcome some drawbacks and to increase estimation performance. We will also address the efficient system architecture and estimation procedure by a similar case-based approach and finally suggest the heuristic search method to find the best estimate of target project through empirical experiments. According to our experiment with the optimally parsimonious neural network model the mean error rate was significantly reduced to 14.3%.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_2
• /
• pp.1881-1890
• /
• 2021

Particulate matter (PM) affects the human, ecosystems, and weather. Motorized vehicles and combustion generate fine particulate matter (PM_2.5), which can contain toxic substances and, therefore, requires systematic management. Consequently, it is important to monitor and predict PM_2.5 concentrations, especially in large cities with dense populations and infrastructures. This study aimed to predict PM_2.5 concentrations in large cities using meteorological and chemical variables as well as satellite-based aerosol optical depth. For PM_2.5 concentrations prediction, a random forest (RF) model showing excellent performance in PM concentrations prediction among machine learning models was selected. Based on the performance indicators R², RMSE, MAE, and MAPE with training accuracies of 0.97, 3.09, 2.18, and 13.31 and testing accuracies of 0.82, 6.03, 4.36, and 25.79 for R², RMSE, MAE, and MAPE, respectively. The variables used in this study showed high correlation to PM_2.5 concentrations. Therefore, we conclude that these variables can be used in a random forest model to generate reliable PM_2.5 concentrations predictions, which can then be used to assess the vulnerability of schools to PM_2.5.

• Management & Information Systems Review
• /
• v.38 no.1
• /
• pp.83-101
• /
• 2019

Blockchain is considered as an innovative technology along with Artificial Intelligence, Big Data, and Internet of Things. However, since the inception of the genesis of blockchain technology, the cryptocurrency Bitcoin, the technology is not utilized widely, not let alone disruptive applications. Most of the blockchain research deals with the cryptocurrency, general descriptions of the technology such as trend, outlook of the technology, explanation of component technology, and so on. There are no killer applications like Facebook or Google, of course. Reflecting on the slow adoption by businesses, we wanted know about the current status of the research on blockchain in Korea. The main purpose of this paper is to help business practitioners to identify the application of blockchain to enhance the competitiveness of their organization. To do that, we first use the framework by Iansiti et al (2017) and categorize the blockchain related articles published in Korea according to the framework. This is to provide a benchmark or cases of other organizations' adoption of blockchain technology. Second, based on the value proposition of blockchain applications, we suggest evolutionary paths for adopting them. Third, from the demand pull perspective of technology adoption for innovation, we propose applicable areas where blockchain applications can be introduced. Fourth, we use the value chain model to find out the appropriate domains of blockchain applications in the corporate value chains. And the five competitive forces models is adopted to find ways of lowering the power of forces by incorporating blockchain technology.

• Korean Journal of Medical Ethics
• /
• v.21 no.4
• /
• pp.330-343
• /
• 2018

This article explores some of the ethical issues associated with the fourth industrial revolution and suggests new directions for bioethics education in Korean universities. Some countries have recently developed guidelines and regulations based on the legal and ethical considerations of the benefits and social risks of new technologies associated with the fourth industrial revolution. Foreign universities have also created courses (both classroom and online) that deal with these issues and help to ensure that these new technologies are developed in an ethically appropriate fashion. In South Korea too there have been attempts to enhance bioethics education to meet the changing demands of society. However, bioethics education in Korea remains focused on traditional bioethical topics and largely neglects the ethical issues related to emerging technologies. Furthermore, Korean universities offer no online courses in bioethics and the classroom courses that do exist are generally treated as electives. In order to improve bioethics education in Korean universities, we suggest that (a) new course should be developed for interprofessional education; (b) courses in bioethics should be treated as required subjects gradually; (c) online courses should be prepared, and (d) universities should continually revise course contents in response to the development of new technologies.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.1
• /
• pp.1-8
• /
• 2021

In the political field of news articles, there are polarized and biased characteristics such as conservative and liberal, which is called political bias. We constructed keyword-based dataset to classify bias of news articles. Most embedding researches represent a sentence with sequence of morphemes. In our work, we expect that the number of unknown tokens will be reduced if the sentences are constituted by subwords that are segmented by the language model. We propose a document embedding model with subword tokenization and apply this model to SVM and feedforward neural network structure to classify the political bias. As a result of comparing the performance of the document embedding model with morphological analysis, the document embedding model with subwords showed the highest accuracy at 78.22%. It was confirmed that the number of unknown tokens was reduced by subword tokenization. Using the best performance embedding model in our bias classification task, we extract the keywords based on politicians. The bias of keywords was verified by the average similarity with the vector of politicians from each political tendency.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.12
• /
• pp.569-578
• /
• 2021

Thanks to web development today, we can easily access online news via various media. As much as it is easy to access online news, we often face fake news pretending to be true. As fake news items have become a global problem, fact-checking services are provided domestically, too. However, these are based on expert-based manual detection, and research to provide technologies that automate the detection of fake news is being actively conducted. As for the existing research, detection is made available based on contextual characteristics of an article and the comparison of a title and the main article. However, there is a limit to such an attempt making detection difficult when manipulation precision has become high. Therefore, this study suggests using a verifying article to decide whether a news item is genuine or not to be affected by article manipulation. Also, to improve the precision of fake news detection, the study added a process to summarize a subject article and a verifying article through the summarization model. In order to verify the suggested algorithm, this study conducted verification for summarization method of documents, verification for search method of verification articles, and verification for the precision of fake news detection in the finally suggested algorithm. The algorithm suggested in this study can be helpful to identify the truth of an article before it is applied to media sources and made available online via various media sources.

• Trans-
• /
• v.14
• /
• pp.1-33
• /
• 2023

In the Web 3.0 era, the third generation of web technologies that uses blockchain technology to give creators ownership of data, metaverse is a crucial trend for developing a creator economy. Web 3.0 aims for a value in which content creators are compensated from participation without being dependent on the platform. Blockchain NFT technology is crucial in metaverse, a vital component of Web 3.0, to ensure the ownership of digital assets. Based on the theory that investigates the concept and characteristics of metaverse, this study identifies five features of the metaverse based NFT art ①'Continuity', ②'Presence', ③ 'Concurrency', ④'Economy', ⑤ 'Application of technology'. By focusing on metaverse based NFT art <Hybrid Nature> case study, we analyzed how the concepts and characteristics of the metaverse and NFT art were reflected in the work. This study focuses on the concept of NFT art, which is emerging at the intersection of art, technology and industry, and emphasizes the importance of finding creative, aesthetic, and cultural values rather than the NFT art's potential for financial gain. It is still in its early stage for academic studies to focus on the aesthetic qualities of NFT art. Future academics and researchers can find this study to gain deeper understanding of the traits and artistic, creative aspects of metaverse based NFT art.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_4
• /
• pp.1125-1134
• /
• 2023

Out of the total 17,000 reservoirs in Korea, 13,600 small agricultural reservoirs do not have hydrological measurement facilities, making it difficult to predict water storage volume and appropriate operation. This paper examined univariate and multivariate long short-term memory (LSTM) modeling to predict the storage rate of agricultural reservoirs using remote sensing and artificial intelligence. The univariate LSTM model used only water storage rate as an explanatory variable, and the multivariate LSTM model added n-day accumulative precipitation and date of year (DOY) as explanatory variables. They were trained using eight years data (2013 to 2020) for Idong Reservoir, and the predictions of the daily water storage in 2021 were validated for accuracy assessment. The univariate showed the root-mean square error (RMSE) of 1.04%, 2.52%, and 4.18% for the one, three, and five-day predictions. The multivariate model showed the RMSE 0.98%, 1.95%, and 2.76% for the one, three, and five-day predictions. In addition to the time-series storage rate, DOY and daily and 5-day cumulative precipitation variables were more significant than others for the daily model, which means that the temporal range of the impacts of precipitation on the everyday water storage rate was approximately five days.