• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.494-496
• /
• 2024

현재 소프트웨어 산업에서 자연어 요구사항의 정확한 분석 연구는 활발히 진행되고 있다. 그러나, 문법적인 분석만을 통해 해석하는 것이 일반적이다. 본 연구는 요구공학과 언어학 그리고 카툰 공학을 접목을 제안한다. 이를 위해서, 1) 언어학적 관점에는 촘스키의 구문 구조 분석 이론과 필모어의 의미역 이론을 결합하여 문법적, 의미적 분석을 수행한다. 2) 요구공학 관점에서는 요구사항 분석으로 상태 모델 속성 추출 및 접목한다. 3) 카툰 공학에서는 3D 이미지 생성한다. 또한, 해결 못했던 동사와 형용사에 대해 분석하여 범위를 확장한다. 즉 언어학적 분석을 바탕으로 UML 상태 다이어그램을 추출하고, 이를 3D 상태 이미지 생성한다. 본 연구는 AI 기술(Text to Image)에 소프트웨어 공학적 방법에서의 절차적인 공정과 재사용 적용함으로써, AI 내부 작동 원리에 대해 체계적으로 연구하고자 한다.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.31 no.1
• /
• pp.1-8
• /
• 2018

The purpose of this study is to implement modeling by applying the parametric technique to the atypical trusses of rigid retractable large space structures. The retractable large space structure requires a lot of time and skill in modeling nonlinear shapes or generating, interpreting, and reviewing many models by alternative. To solve these problems, we introduce firstly parametric modeling tool, secondly, we analyze the connection of atypical three-dimensional trusses of a rigid retractable large-space structure, and finally model it as parametric components of the developed trusses. Therefore, it is a future study to make effective modeling of the openable roof by developing the components that can realize the modeling of the truss classified by the opening and closing method, respectively.

• The Journal of Society for e-Business Studies
• /
• v.21 no.2
• /
• pp.151-161
• /
• 2016

In the era of the Web 2.0, characterized by the openness, sharing and participation, it is easy for internet users to produce and share the data. The amount of the unstructured data which occupies most of the digital world's data has increased exponentially. One of the kinds of the unstructured data called personal online product reviews is necessary for both the company that produces those products and the potential customers who are interested in those products. In order to extract useful information from lots of scattered review data, the process of collecting data, storing, preprocessing, analyzing, and drawing a conclusion is needed. Therefore we introduce the text-mining methodology for applying the natural language process technology to the text format data like product review in order to carry out extracting structured data by using R programming. Also, we introduce the data-mining to derive the purpose-specific customized information from the structured review information drawn by the text-mining.

• Journal of Advanced Navigation Technology
• /
• v.15 no.6
• /
• pp.1053-1058
• /
• 2011

In this paper, we propose a concatenated single antenna diversity system to assure the data transmission reliability between flight type air nodes which move according to their atypical orbit, then analyze its performance. The proposed system achieve a diversity gain using single antenna and a coding gain from convolutional code simultaneously. Simulation result about the bit error rate(BER) of the proposed system shows that its BER performance is about 9.5dB greater than convolutional code at $10^{-4}$ and about 14dB greater than space time block code at $10^{-3}$ which has a full diversity gain. In addition, compared with space time trellis code with diversity gain and coding gain, the proposed system shows the better 4dB at a BER of $10^{-5}$. Therefore, it is necessary that concatenated single antenna diversity should be adopted to the reliable data transmission of flight type air nodes.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.5
• /
• pp.23-34
• /
• 2004

In this paper we propose a feature point tracking algorithm using optical flow under non-prior taming active feature model (NPT-AFM). The proposed algorithm mainly focuses on analysis non-rigid objects[1], and provides real-time, robust tracking by NPT-AFM. NPT-AFM algorithm can be divided into two steps: (i) localization of an object-of-interest and (ii) prediction and correction of the object position by utilizing the inter-frame information. The localization step was realized by using a modified Shi-Tomasi's feature tracking algoriam[2] after motion-based segmentation. In the prediction-correction step, given feature points are continuously tracked by using optical flow method[3] and if a feature point cannot be properly tracked, temporal and spatial prediction schemes can be employed for that point until it becomes uncovered again. Feature points inside an object are estimated instead of its shape boundary, and are updated an element of the training set for AFH Experimental results, show that the proposed NPT-AFM-based algerian can robustly track non-rigid objects in real-time.

• Polymer(Korea)
• /
• v.24 no.1
• /
• pp.133-139
• /
• 2000

Poly(ethylene glycol) with number-average molecular weight (M$_{n}$) of 200 (PEG 200) or 400 (PEG 400) was reacted with various linking agents (CH$_2$Cl$_2$, CH$_2$Br$_2$, CH$_2$I$_2$, Br(CH$_2$)$_3$Br) in the presence of alkali to form of oxyalkylene linked chains. Molecular weights of copolymers were controlled using feed mole ratio of alkali/CH$_2$C1$_2$/PEG. The M$_{n}$ of the polymers measured by end group analysis and that measured by GPC agreed well. Molecuglar weights of polyether copolymers obtained from PEG 200 and PEG 400 were about 500~8500 and 1000~2000, respectively. Polyether copolymers prepared from PEG 400 showed melting points of around 1$0^{\circ}C$. Glass transition temperatures of the copolymers were around -75$^{\circ}C$ and the crystallinity was about 0~25%. The polyether copolymers prepared from PEG 200 had no crystallinity below the M$_{n}$ of 2500. 2500.

• Journal of Digital Contents Society
• /
• v.18 no.2
• /
• pp.339-346
• /
• 2017

There is increasing interest in text analysis based on unstructured data such as articles and comments, questions and answers. This is because they can be used to identify, evaluate, predict, and recommend features from unstructured text data, which is the opinion of people. The same holds true for TEL, where the MOOC service has evolved to automate debating, questioning and answering services based on the teaching-learning support system in order to generate question topics and to automatically classify the topics relevant to new questions based on question and answer data accumulated in the system. Therefore, in this study, we propose topic modeling using LDA to automatically classify new query topics. The proposed method enables the generation of a dictionary of question topics and the automatic classification of topics relevant to new questions. Experimentation showed high automatic classification of over 0.7 in some queries. The more new queries were included in the various topics, the better the automatic classification results.

• Smart Media Journal
• /
• v.11 no.5
• /
• pp.63-74
• /
• 2022

Initial public offering (IPO) has a legal framework for investor protection, and because there are various quantitative evaluation factors, objective analysis is possible, and various studies have been conducted. In addition, crowdfunding also has several devices to prevent indiscriminate funding as the legal system for investor protection. On the other hand, the blockchain-based cryptocurrency white paper (ICO), which has recently been in the spotlight, has ambiguous legal means and standards to protect investors and lacks quantitative evaluation methods to evaluate ICOs objectively. Therefore, this study collects online-published ICO white papers to detect fraud in ICOs, performs ICO fraud predictions based on BERT, a text embedding technique, and compares them with existing Random Forest machine learning techniques, and shows the possibility on fraud detection. Finally, this study is expected to contribute to the study of ICO fraud detection based on quantitative methods by presenting the possibility of using a quantitative approach using unstructured data to identify frauds in ICOs.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.05a
• /
• pp.91-92
• /
• 2023

With the development of technology, interest in the implementation of free-form buildings is increasing, and research on producing free-form panels is being conducted accordingly. Since free-form buildings are curved and consist of geometric shapes, there are many problems with the production technology of free-form panels that implement them. Due to the inability to reuse molds, the cost of disposal of construction waste and waste of manpower for assembly increase the construction period and construction cost. To improve these limitations, a 3D printed concrete nozzle for FCP production was developed. However, this technology is not quantitatively extruded according to the shape of the panel, and there is a problem that residues are generated. Therefore, an free-form panel extrusion experiment was conducted to analyze the limitations of existing nozzles and to analyze the requirements for the development of new concrete extrusion nozzles. Existing nozzles were unable to be quantitatively extruded, resulting in errors. Due to the weak pressure of the screw and the inability to adjust the internal pressure, detailed extrusion speed control was impossible, and residue generation in the opening and closing device seemed to be the cause. Therefore, a pump capable of quantitative concrete pressure transfer and a pressure control device for easy extrusion of concrete are required. In addition, it is judged that it is necessary to develop an opening and closing device and an extrusion device that do not generate residues. The results of this study are expected to provide information for FCP production and production and to be a basic study of technologies necessary for the production of free-form building panels.

• The Korean Journal of Applied Statistics
• /
• v.37 no.2
• /
• pp.119-138
• /
• 2024

Text indicators are increasingly valuable in economic forecasting, but are often hindered by noise and high dimensionality. This study aims to explore post-processing techniques, specifically noise filtering and dimensionality reduction, to normalize text indicators and enhance their utility through empirical analysis. Predictive target variables for the empirical analysis include monthly leading index cyclical variations, BSI (business survey index) All industry sales performance, BSI All industry sales outlook, as well as quarterly real GDP SA (seasonally adjusted) growth rate and real GDP YoY (year-on-year) growth rate. This study explores the Hodrick and Prescott filter, which is widely used in econometrics for noise filtering, and employs sufficient dimension reduction, a nonparametric dimensionality reduction methodology, in conjunction with unstructured text data. The analysis results reveal that noise filtering of text indicators significantly improves predictive accuracy for both monthly and quarterly variables, particularly when the dataset is large. Moreover, this study demonstrated that applying dimensionality reduction further enhances predictive performance. These findings imply that post-processing techniques, such as noise filtering and dimensionality reduction, are crucial for enhancing the utility of text indicators and can contribute to improving the accuracy of economic forecasts.