• Journal of Korean Tunnelling and Underground Space Association
• /
• v.20 no.4
• /
• pp.701-715
• /
• 2018

A reliability based design approach of the tunnel reinforcement with umbrella arch method was considered to better represent the uncertainties of the weak rock properties around the tunnel. For this, a machine learning approach called an Adaptive Support Vector Machine (ASVM) together with the limit equilibrium method were introduced to minimize the iteration numbers during the classification training of the tunnel stability. The proposed method was compared with the results of typical Monte Carlo simulations. It was concluded that the ASVM was very efficient and accurate to calculate the probability of failure having auxiliary umbrella arches and uncertain material properties of the tunnel. Future work will be concentrated on the refinement of the fast adaptation of the SVM classification so that the minimum number of numerical analyses can be used where the limit solution is not available.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.4
• /
• pp.540-545
• /
• 2007

In this thesis, we introduce and investigate new architectures and comprehensive design methodologies of intelligent dimming converter and evaluate the proposed model and the system through a series of numeric experiments. Electronic ballast enable prolongation of life foy Fluorescent-Lamp and ballast. However, There are no merit in case that user impossible manual control. Therefore in this paper, we put emphasis on the design of electronic ballast based on intelligent dimming converter and the energy saving according to the day-light and the user settings by applying the intelligent model to a fluorescent lamp. Also, we show the superiority of the proposed Intelligent dimming converter through the evaluation of performance with conventional electronic ballast by applying the intelligent model to hardware of systems.

• Korean Journal of Environmental Agriculture
• /
• v.6 no.2
• /
• pp.84-93
• /
• 1987

The water solubilities and vapor pressures of chlorothalonil and Command were measured following the guidelines of the U.S. EPA and OECD. Water solubility of the two compounds is consistent with respective values in the literature. However, the vapor pressures of Chlorothalonil and Command were 5,000 times$(2{\times}10^{-7}\;torr\;at\;25^{\circ}C)$ and 100 times$(<1{\times}10^{-6}\;torr\;at\;45^{\circ}C)$ lower than the literature values, respectively. Courteous use of the vapor pressure values in the handbooks is suggested. With this study, experimental difficulties involved were recognized. Based on the low vapor pressure of Command, the cause of the accidental bleach of non-target plants in the United States might not be attributed to the volatilization of Command, but to the drift during the application of the herbicide. These approaches will be utilized to predict the environmental fate of new chemicals under development, to screen the potential environmental pollutants among chemicals already in use, and to assess measures to minimize the hazards.

• Archives of design research
• /
• v.12 no.2
• /
• pp.89-95
• /
• 1999

Carlo H. Sequin, a computer scientist, became to know a sculpture of subtle space construction which was created by Brent Collins, a sculptor, and introduced it as 'Visual Mathematics' in a journal. Sequin who was able to deduce a basic logic of the construction, has developed a software which can be used for virtual modeling merely by substituting simple numerical values using a computer and supplied it to Collins. The present author who was exposed to their collaboration works through series of their papers published in the journal, Leonardo, introduces the Collins' sculptures and the author's modeling procedures of animation works both of which show many common things in visual characteristics and modeling expansion method. The author investigates the mathematical characteristics which is used as a basic motive of modeling and then supplied as a principal visual characteristics of a material. 'Modeling Development by Principle Expansion,' in which the expansion is developed on the base of space twist as for Collins whereas the space section as for the present author, is introduced in this study. With the same stream of the mutual reaction in 'arts, sciences and technology' which has been stressed with the development of sciences and technology, this modeling technology is suggested as a research theme which has a possiblity of various applications.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.32 no.4_1
• /
• pp.343-351
• /
• 2014

The correlation between regional Walkability Index and their physical socio-economic characteristics has evaluated by the spatial statistical analysis to understand the urban pedestrian environments, where has been emerging the significance, recently. Following to the study, the Walkability Indexes were calculated quantitatively from two administrative districts of Busan and measured Global Local spatial autocorrelation indices. Additionally, the Geographically Weighted Regression model was applied to define the correlation between Walkability Indexes and urban environmental variables. The spatial autocorrelation values and clusters on the Walkability Indexes were derived in statistically significant level. Furthermore, the Geographically Weighted Regression model has been derived more improved inference than the OLS regression model, so as the influence of local level pedestrian environment was identified. The results of this study suggest that the spatial statistical approach can be effective on quantitative assessing the pedestrian environment and navigating their associated factors.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.5
• /
• pp.1013-1018
• /
• 2007

In general, there are many sensors for fuel injection control such as an air flow sensor, an air intake temperature sensor, a cooling water temperature sensor, a throttle position sensor, and a motor position sensor. In this paper, we proposed a method for controlling the amount of fuel consumption in cars using fuzzy control technique by temperature change of an air intake temperature sensor and air-fuel ratio, the ratio of air and fuel mixture. In the proposed method, the amount of fuel injection is controlled by fuzzy membership functions and fuzzy inference rules established for air-fuel ratio, air intake temperature, and final fuel compensation, after computing air-fuel values using each amount of air intake and each amount of fuel injection. We verified that the proposed method is more efficient than conventional methods in fuel injection control from the results of the simulation program.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.9
• /
• pp.19-24
• /
• 2010

The number of automobiles are continuously increasing in Korea since 1990's and it causes frustrating commuting traffic and holyday traffic. Meanwhile, the obsolete traffic signal control system is still under static control based on the aggregated traffic statistics thus it is not sufficiently adaptive in real world traffic situation that changes in real time. Thus, in this paper, we propose an adaptive signal control system using fuzzy control technology that can react to real time traffic situations. The method computes the priority of signal phases based on the number of waiting automobiles and occupying time on intersection using fuzzy membership functions. The phase with highest priority obtains "proceed" signal. Also, the duration of this "proceed" signal is determined based on the ratio of number of waiting automobiles of given phase and total number of waiting automobiles on intersection. In experiment, we show that the proposed fuzzy control system is better than the static control system for all sorts of traffic congestion situations by simulation.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.381-392
• /
• 2021

In this study, we perform deep learning-based object detection analysis on eight types of buildings defined by the digital map topography standard code, leveraging images taken with UAV (Unmanned Aerial Vehicle). Image labeling was done for 509 images taken by UAVs and the YOLO (You Only Look Once) v5 model was applied to proceed with learning and inference. For experiments and analysis, data were analyzed by applying an open source-based analysis platform and algorithm, and as a result of the analysis, building objects were detected with a prediction probability of 88% to 98%. In addition, the learning method and model construction method necessary for the high accuracy of building object detection in the process of constructing and repetitive learning of training data were analyzed, and a method of applying the learned model to other images was sought. Through this study, a model in which high-efficiency deep neural networks and spatial information data are fused will be proposed, and the fusion of spatial information data and deep learning technology will provide a lot of help in improving the efficiency, analysis and prediction of spatial information data construction in the future.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.7
• /
• pp.890-895
• /
• 2021

Recently, the "Act of Serious Disasters, etc" was enacted and institutional and social interest in safety accidents is increasing. In this paper, we analyze statistical data published by government agency on safety accidents that occur in manufacturing sites, and compare various object detection models based on deep learning to build a model to determine dangerous situations to reduce the occurrence of safety accidents. The data-set was directly constructed by collecting images from CCTVs at the manufacturing site, and the YOLO-v4, SSD, CenterNet models were used as training data and evaluation data for learning. As a result, the YOLO-v4 model obtained a value of 81% of mAP. It is meaningful to select a class in an industrial field and directly build a dataset to learn a model, and it is thought that it can be used as an initial research data for a system that determines a risk situation and infers it.

• 한국벤처창업학회:학술대회논문집
• /
• 2022.11a
• /
• pp.105-117
• /
• 2022

본 연구은 군 장병들의 자기결정성에 영향을 미치는 변인을 선정하고 회복탄력성의 매개효과를 알아보고자 한 박사학위논문의 요약본이다. 연구를 위해 전국 육군 8개 부대 장병 898명을 대상으로 자기결정성의 관련 변인을 측정하기 위한 설문을 실시하였다. 설문 결과는 통계분석을 시행하였는데, 매개효과 검증을 위해 독립변인으로 그릿과 주관적 안녕감을, 종속변인으로 자기결정성, 매개변인을 회복탄력성으로 하는 3단계 회기분석을 실시하였다. 연구 결과, 군 장병들의 일반적인 특징에서 성별과 회복탄력성 교육참여 여부는 각 변인에 유의한 차이를 보이지 않았고, 연령은 27세 이상, 계급은 부사관이 모든 변인에서 높은 수치를 보였다. 그릿과 주관적 안녕감의 하위요인들은 자기결정성에 모든 하위요인에 다소 높은 정적 상관관계와 유의한 영향을 미치는 것으로 나타났으며, 그릿과 주관적 안녕감의 하위요인들은 회복탄력성의 모든 하위요인과도 전반적으로 높은 정적 상관관계를 보였고, 전반적으로 유의한 영향을 미치는 것으로 나타났다. 회복탄력성의 하위요인들은 자기결정성의 하위요인 전반에 상관관계를 가졌으며, 부분매개효과를 확인했으나 일부요인은 기준을 충족하지 못하였다. 결론적으로 군 장병들에게 지속적인 관심과 꾸준한 노력을 기울일만한 동기부여가 무엇보다 필요하며, 군 장병들의 성공적인 자기결정력 성장을 위해서는 자율성 증진과 원활한 대인관계 환경 제공을 통한 그릿과 주관적 안녕감의 요인들의 충족이 필요함을 알 수 있었다. 또한 장병들의 회복탄력성 능력 향상을 위한 그릿과 주관적 안녕감 증진은 장병들의 자기결정성 증진에 기여할 주요 수단임을 알 수 있었고, 장병들의 주관적, 긍정적 심리상태와 자신 삶의 만족을 위한 주관적인 능력 증진을 위해서는 그릿 및 주관적 안녕감과 회복탄력성이 주요한 에너지로 활용될 수 있음을 추론할 수 있었다.