• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.139-152
• /
• 2022

Engineering's work area for plants is a technical area that directly affects productivity, performance, and quality throughout the lifecycle from planning, design, construction, operation and disposal. Using the different types of data that occur to make decisions is important not only in the subsequent process but also in terms of cyclical cost reduction. However, there is a lack of systems to manage and analyze these integrated data. In this paper, we developed a knowledge base-based plant engineering analysis platform that can manage and utilize data. The platform provides a knowledge base that preprocesses previously collected engineering data, and provides analysis and visualization to use it as reference data in AI models. Users can perform data analysis through the use of prior technology and accumulated knowledge through the platform and use visualization in decision-support and systematically manage construction that relied only on experience.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.72-74
• /
• 2022

The National Science and Technology Knowledge Information Service (NTIS) provides information on national R&D projects. Project information consists of meta-information such as 'project name', 'project performance institution', 'research manager name', and text explaining projects such as 'research goal', 'research content', and 'expected effect'. There is a problem that it takes a lot of time to find the desired project information by checking all of the "research goals" or "research contents" in the list of results of searching for 1 million project information. To solve this problem, this paper proposes a project information summary system that summarizes the parts consisting of long texts within the national R&D project information. By analyzing the linguistic characteristics of the Korean language, a preprocessor was built and a project information summary model based on natural language processing technology was developed to process preprocessed text information. Through this, project information composed of long sentences is provided in a compressed and summarized form, which will help users to easily and quickly infer the overall content with the summary information alone.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.110-110
• /
• 2022

본 연구는 자율운항 선박의 원격 고장 진단 기법 개발의 일부로 수행되었다. 특히, 엔진 연료 계통 장비로부터 계측된 시계열 데이터로부터 상태 진단을 위한 알고리즘 구현 결과를 제시하였다. 엔진 연료 펌프와 청정기를 가진 육상 실험 장비로부터 진동 시계열 데이터 계측하였으며, 이상 감지, 고장 분류 및 고장 예측이 가능한 심층 학습(Deep Learning) 및 기계 학습(Machine Learning) 알고리즘을 구현하였다. 육상 실험 장비에 고장 유형 별로 인위적인 고장을 발생시켜 특징적인 진동 신호를 계측하여, 인공 지능 학습에 이용하였다. 계측된 신호 데이터는 선행 발생한 사건의 신호가 후행 사건에 영향을 미치는 특성을 가지고 있으므로, 시계열에 내포된 고장 상태는 시간 간의 선후 종속성을 반영할 수 있는 학습 알고리즘을 제시하였다. 고장 사건의 시간 종속성을 반영할 수 있도록 순환(Recurrent) 계열의 RNN(Recurrent Neural Networks), LSTM(Long Short-Term Memory models)의 모델과 합성곱 연산 (Convolution Neural Network)을 기반으로 하는 Conv1D 모델을 적용하여 예측 정확성을 비교하였다. 특히, 합성곱 계열의 RNN LSTM 모델이 고차원의 순차적 자연어 언어 처리에 장점을 보이는 모델임을 착안하여, 신호의 시간 종속성을 학습에 반영할 수 있는 합성곱 계열의 Conv1 알고리즘을 고장 예측에 사용하였다. 또한 기계 학습 모델의 효율성을 감안하여 XGBoost를 추가로 적용하여 고장 예측을 시도하였다. 최종적으로 연료 펌프와 청정기의 진동 신호로부터 Conv1D 모델과 XGBoost 모델의 고장 예측 성능 결과를 비교하였다

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.648-653
• /
• 2023

관계 추출 태스크는 주어진 텍스트로부터 두 개체 간의 적절한 관계를 추론하는 작업이며, 지식 베이스 구축 및 질의응답과 같은 응용 태스크의 기반이 된다. 최근 자연어처리 분야 전반에서 생성형 거대 언어모델의 내재 지식을 활용하여 뛰어난 성능을 성취하면서, 대표적인 정보 추출 태스크인 관계 추출에서 역시 이를 적극적으로 활용 가능한 방안에 대한 탐구가 필요하다. 특히, 실 세계의 추론 환경과의 유사성에서 기인하는 저자원 특히, 제로샷 환경에서의 관계 추출 연구의 중요성에 기반하여, 효과적인 프롬프팅 기법의 적용이 유의미함을 많은 기존 연구에서 증명해왔다. 따라서, 본 연구는 한국어 관계 추출 분야에서 거대 언어모델에 다각적인 프롬프팅 기법을 활용하여 제로샷 환경에서의 추론에 관한 비교 연구를 진행함으로써, 추후 한국어 관계 추출을 위한 최적의 거대 언어모델 프롬프팅 기법 심화 연구의 기반을 제공하고자 한다. 특히, 상식 추론 등의 도전적인 타 태스크에서 큰 성능 개선을 보인 사고의 연쇄(Chain-of-Thought) 및 자가 개선(Self-Refine)을 포함한 세 가지 프롬프팅 기법을 한국어 관계 추출에 도입하여 양적/질적으로 비교 분석을 제공한다. 실험 결과에 따르면, 사고의 연쇄 및 자가 개선 기법 보다 일반적인 태스크 지시 등이 포함된 프롬프팅이 정량적으로 가장 좋은 제로샷 성능을 보인다. 그러나, 이는 두 방법의 한계를 지적하는 것이 아닌, 한국어 관계 추출 태스크에의 최적화의 필요성을 암시한다고 해석 가능하며, 추후 이러한 방법론들을 발전시키는 여러 실험적 연구에 의해 개선될 것으로 판단된다.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.509-515
• /
• 2023

Despite the continued development of alternative energies, fuel consumption is increasing. In particular, the price of gasoline fluctuates greatly according to fluctuations in international oil prices. Gas stations adjust their gasoline inventory to respond to gasoline price fluctuations. In this study, news datasets is used to analyze the gasoline consumption patterns through fluctuations of the gasoline inventory. First, collecting news datasets with web crawling. Second, summarizing news datasets using KoBART, which summarizes the Korean text datasets. Finally, preprocessing and deriving the fluctuations factors through N-Gram Language Model and TF-IDF. Through this study, it is possible to analyze and predict gasoline consumption patterns.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.55-65
• /
• 2023

In this paper, we apply KeyBERT(Keyword extraction with Bidirectional Encoder Representations of Transformers) algorithm-driven topic extraction and topic frequency analysis to deep learning and reinforcement learning research to discover the rapidly changing trends in them. First, we crawled abstracts of research papers on deep learning and reinforcement learning, and temporally divided them into two groups. After pre-processing the crawled data, we extracted topics using KeyBERT algorithm, and then analyzed the extracted topics in terms of topic occurrence frequency. This analysis reveals that there are distinct trends in research work of all analyzed algorithms and applications, and we can clearly tell which topics are gaining more interest. The analysis also proves the effectiveness of the utilized topic extraction and topic frequency analysis in research trend analysis, and this trend analysis scheme is expected to be used for research trend analysis in other research fields. In addition, the analysis can provide insight into how deep learning will evolve in the near future, and provide guidance for select research topics and methodologies by informing researchers of research topics and methodologies which are recently attracting attention.

• The Korean Journal of Applied Statistics
• /
• v.36 no.5
• /
• pp.489-499
• /
• 2023

As sharing of analyst reports became widely available, reports generated by analysts have become a useful tool to reduce difference in financial information between market participants. The quantitative information of analyst reports has been used in many ways to predict stock returns. However, there are relatively few domestic studies on the prediction power of text information in analyst reports to predict stock returns. We test stock return predictability of text in analyst reports by creating variables representing the TONE from the text. To overcome the limitation of the linear-model-assumption-based approach, we use the random-forest-based F-test.

• Smart Media Journal
• /
• v.12 no.9
• /
• pp.19-27
• /
• 2023

Since morphemes are the smallest unit of meaning in Korean, it is necessary to develop an accurate morphemes analyzer to improve the performance of the Korean language model. However, most existing analyzers present morpheme analysis results by learning word unit tokens as input values. However, since Korean words are consist of postpositions and affixes that are attached to the root, even if they have the same root, the meaning tends to change due to the postpositions or affixes. Therefore, learning morphemes using word unit tokens can lead to misclassification of postposition or affixes. In this paper, we use morpheme-level tokens to grasp the inherent meaning in Korean sentences and propose a morpheme analyzer based on a sequence generation method using Transformer. In addition, a user dictionary is constructed based on corpus data to solve the out - of-vocabulary problem. During the experiment, the morpheme and morpheme tags printed by each morpheme analyzer were compared with the correct answer data, and the experiment proved that the morpheme analyzer presented in this paper performed better than the existing morpheme analyzer.

• Information Systems Review
• /
• v.23 no.4
• /
• pp.127-146
• /
• 2021

Fake news isexpanded and reproduced rapidly regardless of their authenticity by the characteristics of modern society, called the information age. Assuming that 1% of all news are fake news, the amount of economic costs is reported to about 30 trillion Korean won. This shows that the fake news isvery important social and economic issue. Therefore, this study aims to develop an automated detection model to quickly and accurately verify the authenticity of the news. To this end, this study crawled the news data whose authenticity is verified, and developed fake news prediction models using word embedding (Word2Vec, Fasttext) and deep learning algorithms (LSTM, BiLSTM). Experimental results show that the prediction model using BiLSTM with Word2Vec achieved the best accuracy of 84%.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.2
• /
• pp.229-244
• /
• 2024

Recently, supply chain attacks against nuclear facilities such as "Evil PLC" are increasing due to the application of digital technology in nuclear power plants such as the APR1400 reactor. Nuclear supply chain security requires a asset management system that can systematically manage a large number of providers due to the nature of the industry. However, due to the nature of the control system, there is a problem of inconsistent management of attribute information due to the long lifecycle of software assets. In addition, due to the availability of the operational technology, the introduction of automated configuration management is insufficient, and limitations such as input errors exist. This study proposes a systematic asset management system using SBOM(Software Bill Of Materials) and an improvement for input errors using natural language processing techniques.