• The Journal of the Korea Contents Association
• /
• v.21 no.11
• /
• pp.135-144
• /
• 2021

Recently, data-driven decision-making technology has become a key technology leading the data industry, and machine learning technology for this requires high-quality training datasets. However, real-world data contains missing values for various reasons, which degrades the performance of prediction models learned from the poor training data. Therefore, in order to build a high-performance model from real-world datasets, many studies on automatically imputing missing values in initial training data have been actively conducted. Many of conventional machine learning-based imputation techniques for handling missing data involve very time-consuming and cumbersome work because they are applied only to numeric type of columns or create individual predictive models for each columns. Therefore, this paper proposes a new data imputation technique called 'Denoising Self-Attention Network (DSAN)', which can be applied to mixed-type dataset containing both numerical and categorical columns. DSAN can learn robust feature expression vectors by combining self-attention and denoising techniques, and can automatically interpolate multiple missing variables in parallel through multi-task learning. To verify the validity of the proposed technique, data imputation experiments has been performed after arbitrarily generating missing values for several mixed-type training data. Then we show the validity of the proposed technique by comparing the performance of the binary classification models trained on imputed data together with the errors between the original and imputed values.

• Korean Journal of Construction Engineering and Management
• /
• v.23 no.5
• /
• pp.87-97
• /
• 2022

Although the use of BIM in architectural projects has increased, repetitive modeling tasks and frequent design errors remain as obstacles to the practical application of BIM. In particular, interior finishing elements include the most varied and detailed requirements, and thus requires improving its modelling efficiency and resolving potential design errors. Recently, visual programming-based modules has gained traction as a way to automate a series of repetitive modeling tasks. However, existing approaches do not adequately reflect the practical modeling needs and focus only on replacing siimple, repetitive tasks. This study developed and evaluated the performance of three modules for automatic detailing of walls, floors and ceilings. The three elements were selected by analyzing the man-hours and the number of errors that typically occur when detailing BIM models. The modules were then applied to automatically detail a sample commercial facility BIM model. Results showed that the implementations met the practical modeling requirements identified by actual modelers of an construction management firm.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.211-227
• /
• 2022

Illegal gambling through online gambling sites has become a significant social problem. The development of Internet technology and the spread of smartphones have led to the proliferation of illegal gambling sites, so now illegal online gambling has become accessible to anyone. In order to mitigate its negative effect, the Korean government is trying to detect illegal gambling sites by using self-monitoring agents or reporting systems such as 'Nuricops.' However, it is difficult to detect all illegal sites due to limitations such as a lack of staffing. Accordingly, several scholars have proposed intelligent illegal gambling site detection techniques. Xu et al. (2019) found that fake or illegal websites generally have unique features in the HTML tag structure. It implies that the HTML tag structure can be important for detecting illegal sites. However, prior studies to improve the model's performance by utilizing the HTML tag structure in the illegal site detection model are rare. Against this background, our study aimed to improve the model's performance by utilizing the HTML tag structure and proposes Tag2Vec, a modified version of Doc2Vec, as a methodology to vectorize the HTML tag structure properly. To validate the proposed model, we perform the empirical analysis using a data set consisting of the list of harmful sites from 'The Cheat' and normal sites through Google search. As a result, it was confirmed that the Tag2Vec-based detection model proposed in this study showed better classification accuracy, recall, and F1_Score than the URL-based detection model-a comparative model. The proposed model of this study is expected to be effectively utilized to improve the health of our society through intelligent technology.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.8
• /
• pp.315-324
• /
• 2022

In this paper, we propose KoEPT, a Transformer-based generative model for automatic math word problems solving. A math word problem written in human language which describes everyday situations in a mathematical form. Math word problem solving requires an artificial intelligence model to understand the implied logic within the problem. Therefore, it is being studied variously across the world to improve the language understanding ability of artificial intelligence. In the case of the Korean language, studies so far have mainly attempted to solve problems by classifying them into templates, but there is a limitation in that these techniques are difficult to apply to datasets with high classification difficulty. To solve this problem, this paper used the KoEPT model which uses 'expression' tokens and pointer networks. To measure the performance of this model, the classification difficulty scores of IL, CC, and ALG514, which are existing Korean mathematical sentence problem datasets, were measured, and then the performance of KoEPT was evaluated using 5-fold cross-validation. For the Korean datasets used for evaluation, KoEPT obtained the state-of-the-art(SOTA) performance with 99.1% in CC, which is comparable to the existing SOTA performance, and 89.3% and 80.5% in IL and ALG514, respectively. In addition, as a result of evaluation, KoEPT showed a relatively improved performance for datasets with high classification difficulty. Through an ablation study, we uncovered that the use of the 'expression' tokens and pointer networks contributed to KoEPT's state of being less affected by classification difficulty while obtaining good performance.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.5
• /
• pp.462-469
• /
• 2023

In this study, we propose a method for evaluating the risk of collision between ships to support determination on the risk of collision in a situation in which ships encounter each other and to prevent collision accidents. Because several uncertainties are involved in the navigation of a ship, must be considered when evaluating the risk of collision. We apply the Dempster-Shafer theory to manage this uncertainty and evaluate the collision risk of each target vessel in real time. The distance at the closest point approach (DCPA), time to the closest point approach (TCPA), distance from another vessel, relative bearing, and velocity ratio are used as evaluation factors for ship collision risk. The basic probability assignments (BPAs) calculated by membership functions for each evaluation factor are fused through the combination rule of the Dempster-Shafer theory. As a result of the experiment using automatic identification system (AIS) data collected in situations where ships actually encounter each other, the suitability of evaluation was verified. By evaluating the risk of collision in real time in encounter situations between ships, collision accidents caused by human errora can be prevented. This is expected to be used for vessel traffic service systems and collision avoidance systems for autonomous ships.

• The Magazine of the Society of Air-Conditioning and Refrigerating Engineers of Korea
• /
• v.31 no.7
• /
• pp.53-64
• /
• 2002

$CO_2$ 20세기 초 천연 냉매 $CO_2$는 광범위하게 사용되었지만 프레온계 냉매의 출현으로 1940년경부터 $CO_2$냉매는 사용이 제한되었다. 그러나 반 세기 동안 사라졌던 $CO_2$냉매는 1980년 후반에 노르웨이 과학 기술대학 (NTNU)과 북구 최대 민간연구소 (SINTEF)의 Lorentzen 교수에 의해 $CO_2$천연 냉매 사용을 재고하게 되었다. 프레온계 냉매의 환경적 논쟁이 쟁점이 되면서 천연 냉매 사용을 재고하게 되었다. 특히 비가연성과 비유독성으로 인한 $CO_2$냉매가 주목을 받고 있다. 초월임계 사이클레서의 고압 제어에 대한 새로운 개념은 Lorentzen 교수와 동료 연구원에 의해서 특허로 제안되었다. 이에 대한 상업적 권리를 Norsk Hydro사는 1990년에 얻었고,1990년대 초반에 NTNU/SINTEF의 공동 연구개발 프로그램을 통해 기술 경쟁력과 실현 가능성이 검증되었다. 현재 연구소에서는 최초로 초월임계 $CO_2$사이클을 이용한 상업용 온수 열펌프 시스템, 2003년 시작할 연료전지 전기 자동차에 대한 연구를 수행하고 있다. NTNU/SINTEF에서 개발된 $CO_2$기술은 Hydro-SINTEF 공동 벤처 기업인 Shecco기술회사를 통해 제조업자에게 허가된다. 본 고에서는 NTNU/SINTEF에서 수행하였거나 수 중인 과제들을 중심으로 유럽의 $CO_2$시스템의 결과와 주요 개발 범위를 정리하였으며, 특히 작동유체로서의 $CO_2$냉매의 특징을 간단히 설명하고, 온 수 열 펌프, 자동차용 공조기 및 열 펌프, 상업 냉동기 등이 기술되었다. 그 외 압축기 위주의 요소기술 개발에 관한 내용도 기술되었고, 차세대 기술 경향과 전망에 대해서도 제시되었다. 제시되었다.성균 350$\times$$10^4$ CFU균, 방선균 434$\times$$10^4$ CFU균, 진균 676$\times$$10^4$ CFU균으로 진균의 개체수가 비교적 높게 나타났으며, 비산불지역에서는 호기성균 328$\times$$10^4$ CFU균, 방선균 319$\times$$10^4$ CFU균, 진균 461$\times$$10^4$ CFU균으로 진균의 개체수가 높게 나타났다. 토양미생물은 호기성균, 방선균, 진균 모두 비산불지역 보다 산불지역에서 많이 나타났다. 본 조사지역에서 호기성균은 활엽수림보다 침엽수림에서 많게 나타났으며, 방선균과 진균은 침엽수림보다 활엽수림에서 많이 나타났다.효과와 이를 이용한 자기냉동의 방법 그리고 최근에 이루어진 새로운 진전에 대해 소개하고 공기조화 및 냉동분야에의 적용 가능성을 전망해 보고자 한다.및 도입 등 선주들에게 다양한 선박건조자금을 제공하여 내수기반 확충에도 노력해야 할 것 이다.있었다., 인삼이 성장될 때 부분적인 영양상태의 불충분이나 기후 등에 따른 영향을 받을 수 있기 때문에 앞으로 이에 대한 많은 연구가 이루어져야할 것으로 판단된다.태에도 불구하고 [-wh]의미의 겹의문사는 병렬적 관계의 합성어가 아니라 내부구조를 지니지 않은 단순한 단어(minimal $X^{0}$ elements)로 가정한다. 즉, [+wh] 의미의 겹의문사는 동일한 구성요 소를 지닌 병렬적 합성어([$[W1]_{XO-}$ $[W1]_{XO}$ ]$_{XO}$)로 그리고 [-wh] 의미의 겹의문사는 중복된 발은을 지닌 한 단어로 ([W]$_{XO}$ )

• Journal of the Korea Society for Simulation
• /
• v.32 no.1
• /
• pp.35-44
• /
• 2023

In recent, there are many research cases that analyze trends or research trends with text analysis. When collecting documents by searching for keywords in abbreviations for data analysis, it is necessary to disambiguate abbreviations. In many studies, documents are classified by hand-work reading the data one by one to find the data necessary for the study. Most of the studies to disambiguate abbreviations are studies that clarify the meaning of words and use supervised learning. The previous method to disambiguate abbreviation is not suitable for classification studies of documents looking for research data from abbreviation search documents, and related studies are also insufficient. This paper proposes a method of semi-automatically classifying documents collected by abbreviations by going topic modeling with Non-Negative Matrix Factorization, an unsupervised learning method, in the data pre-processing step. To verify the proposed method, papers were collected from academic DB with the abbreviation 'MSA'. The proposed method found 316 papers related to Micro Services Architecture in 1,401 papers. The document classification accuracy of the proposed method was measured at 92.36%. It is expected that the proposed method can reduce the researcher's time and cost due to hand work.

• Land and Housing Review
• /
• v.14 no.2
• /
• pp.125-135
• /
• 2023

Drones are used in various fields, including land survey, transportation, forestry/agriculture, marine, environment, disaster prevention, water resources, cultural assets, and construction, as their industrial importance and market size have increased. In this study, image data for deep learning was collected using a mavic3 drone capturing images at a shooting altitude was 20 m with ×7 magnification. Swin Transformer and UperNet were employed as the backbone and architecture of the deep learning model. About 800 sheets of labeled data were augmented to increase the amount of data. The learning process encompassed three rounds. The Cross-Entropy loss function was used in the first and second learning; the Tversky loss function was used in the third learning. In the future, when the crack detection model is advanced through convergence with the Internet of Things (IoT) through additional research, it will be possible to detect patching or potholes. In addition, it is expected that real-time detection tasks of drones can quickly secure the detection of pavement maintenance sections.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.219-240
• /
• 2023

Conversational AI which allows users to interact with satisfaction is a long-standing research topic. To develop conversational AI, it is necessary to build training data that reflects real conversations between people, but current Korean datasets are not in question-answer format or use honorifics, making it difficult for users to feel closeness. In this paper, we propose a conversation dataset (KOMUChat) consisting of 30,767 question-answer sentence pairs collected from online communities. The question-answer pairs were collected from post titles and first comments of love and relationship counsel boards used by men and women. In addition, we removed abuse records through automatic and manual cleansing to build high quality dataset. To verify the validity of KOMUChat, we compared and analyzed the result of generative language model learning KOMUChat and benchmark dataset. The results showed that our dataset outperformed the benchmark dataset in terms of answer appropriateness, user satisfaction, and fulfillment of conversational AI goals. The dataset is the largest open-source single turn text data presented so far and it has the significance of building a more friendly Korean dataset by reflecting the text styles of the online community.

• Journal of Ethics
• /
• no.82
• /
• pp.73-125
• /
• 2011

This article aims to search for moral educational implication of J. D. Greene's recent neuro-scientific approaches to deontological ethics. Recently new technique in neuroscience such as fMRI is applied to moral and social psychological concepts or terms, and 'affective primacy' and 'automaticity' principles are highlighted as basic concepts of the new paradigm. When these principles are introduced to ethical theories, it makes rooms of new and different interpretations of them. J. D. Greene et al. claim that deontological moral judgments or theories are just a kind of post hoc rationalization for intuitions or emotions by ways of neuroscientific findings and evolutionary interpretation. For example, Kant's categorical imperative in which a maxim should be universalizable to be as a principle, might be a product of moral intuition. Firstly this article tries to search for intellectual backgrounds of the social intuitionalism where Greens' thought originates. Secondly, this article tries to collect and summarize his arguments about moral dilemma responses, personal-impersonal dilemma catergorizing hypothesis, fMRI data interpretations by ways of evolutionary theory, cultural and social psychological theories, application to deontological and consequential theories, and his suggestion that deontological ethics shoud be rejected as a normative ethical thought and consequentialism be a promising theory etc. Thirdly, this tries to analyse and critically exam those aspects and argumentation, especially from viewpoints of the ethicists whose various strategies seek to defeat Greene's claims. Fourthly, this article criticizes that his arguments make a few critical mistakes in methodology and data interpretation. Last, this article seeks to find its implications for moral education in korea, in which in spite of incomplete argumentation of his neuroscientific approach to morality, neuroethics needs to be introduced as a new approach and educational content, and critical materials as well.