• KIEAE Journal
• /
• 제12권6호
• /
• pp.77-84
• /
• 2012

The current architectural design of unit modular has been based on 2D of CAD program, so unit modular character which needs unit information management, as a dried-member system, has no effect on design process. The purpose of this study is We have developed a suitable BIM design process, according to various works of construction, then tried to contribute to supply and activation of the urban-life-housing based on unit modular. The BIM modeling process based on unit modular has been in order of unit combination with preparing manual classification, and, it has been constructed, at construction site, from housing foundation to roof finish by Bottom-up method. At a manufacturing factory, it has been produced in order of 1) grouping materials and parts, 2) fabricating unit boxes, and 3) interference examination of unit boxes, and each order has been classified as housing structure, architecture, plumbing process separately. At a construction site, the fabrication has been done in order of, like as a real housing construction scenario, 1) RC foundation work 2) unit module job-site-fabrication work, 3) roof truss work, 4) plumbing and HVAC work, and 5) housing interior finish work. After modeling process, the interference examination on each work of construction has finally completed modeling. The Unit modular utilizing BIM modeling can make easy housing maintenance through systematic control with preparing manual of unit module information, and securing accurate and speedy construction information. And it will promote design credibility and create maximum effect of unit modular construction method, such as construction period reduction and upgrade of construction quality, etc., through the computer simulation as real as construction environment in cyber space, and with the interfering examination.

• 대한간호학회지
• /
• 제43권1호
• /
• pp.1-10
• /
• 2013

Purpose: The purpose of this study was to develop a prediction model for the characteristics of older adults with depression using the decision tree method. Methods: A large dataset from the 2008 Korean Elderly Survey was used and data of 14,970 elderly people were analyzed. Target variable was depression and 53 input variables were general characteristics, family & social relationship, economic status, health status, health behavior, functional status, leisure & social activity, quality of life, and living environment. Data were analyzed by decision tree analysis, a data mining technique using SPSS Window 19.0 and Clementine 12.0 programs. Results: The decision trees were classified into five different rules to define the characteristics of older adults with depression. Classification & Regression Tree (C&RT) showed the best prediction with an accuracy of 80.81% among data mining models. Factors in the rules were life satisfaction, nutritional status, daily activity difficulty due to pain, functional limitation for basic or instrumental daily activities, number of chronic diseases and daily activity difficulty due to disease. Conclusion: The different rules classified by the decision tree model in this study should contribute as baseline data for discovering informative knowledge and developing interventions tailored to these individual characteristics.

• 정보보호학회논문지
• /
• 제29권4호
• /
• pp.785-794
• /
• 2019

최근 4차 산업 혁명 기술 중 하나인 딥러닝(Deep Learning) 기술은 보안 분야에서는 탐지하기 어려운 네트워크 데이터의 숨겨진 의미를 식별하고 공격을 예측하는 데 사용되고 있다. 침입탐지에 사용될 딥러닝 알고리즘을 선택하기 전에 데이터의 속성과 품질 분석이 필요하다. 학습에 사용되는 데이터의 오염여부에 따라 탐지 방법에 영향을 주기 때문이다. 따라서 데이터의 특징을 파악하고 특성을 선정해야 한다. 본 논문에서는 네트워크 데이터 셋을 이용하여 악성코드의 단계적 특징을 분석하고 특성을 추출하여 딥러닝 모델을 적용하였을 때 각 특성이 성능에 미치는 영향을 분석하였다. 네트워크 특징에 따른 특성들의 비교에 대한 트래픽 분류 실험을 진행하였으며 선정한 특성을 기반으로 96.52% 정확도를 분류하였다.

• 한국물환경학회지
• /
• 제35권3호
• /
• pp.271-277
• /
• 2019

Korean Trophic State Index ($TSI_{KO}$) was developed in 2006, and was composed of COD ($COD_{Mn}$ based on permanganate method), Chlorophyll a (Chl.a) and total phosphorus (TP). However, $COD_{Mn}$ usually represents only 50-60% of total organic matter in stream or lake water due to low oxidizing power of permanganate. This study investigated the relationship between TOC and $COD_{Mn}$ based on the average data for the whole layer in 81 lakes in Korea, during the period 2013-2017. As a result, $COD_{Mn}$ was found to be 1.54 times more than TOC in 66 of the freshwater lakes and 3 brackish lakes (TOC measured using thermo-oxidation method). TOC was about a quarter of $COD_{Mn}$ in 8 coastal lakes (TOC measured using UV-persulfate oxidation method), and it appeared to be underestimated due to chloride interference. Using the data of 69 lakes with exception of 12 brackish lakes, $TSI_{KO}$(TOC) was developed based on the correlation between TOC and $COD_{Mn}$, while $TSI_{KO}$(COD) was replaced with $TSI_{KO}$(TOC). However, for trophic state assessment of brackish lakes, the $TSI_{KO}$(TOC) can only be utilized in case that TOC is measured through thermo-oxidation method. The determination coefficient of $TSI_{KO}$(Chl) to $TSI_{KO}$(COD) in 66 freshwater lakes and 3 brackish lakes was 0.83, while that to $TSI_{KO}$(TOC) was 0.68. This difference could be attributed to the recalcitrant organic part of TOC.

• International Journal of Computer Science & Network Security
• /
• 제23권3호
• /
• pp.49-56
• /
• 2023

Machine learning methods diversely applied to the Internet of Things (IoT) field have been successful due to the enhancement of computer processing power. They offer an effective way of detecting malicious intrusions in IoT because of their high-level feature extraction capabilities. In this paper, we proposed a novel feature selection method for malicious intrusion detection in IoT by using an evolutionary technique - Genetic Algorithm (GA) and Machine Learning (ML) algorithms. The proposed model is performing the classification of BoT-IoT dataset to evaluate its quality through the training and testing with classifiers. The data is reduced and several preprocessing steps are applied such as: unnecessary information removal, null value checking, label encoding, standard scaling and data balancing. GA has applied over the preprocessed data, to select the most relevant features and maintain model optimization. The selected features from GA are given to ML classifiers such as Logistic Regression (LR) and Support Vector Machine (SVM) and the results are evaluated using performance evaluation measures including recall, precision and f1-score. Two sets of experiments are conducted, and it is concluded that hyperparameter tuning has a significant consequence on the performance of both ML classifiers. Overall, SVM still remained the best model in both cases and overall results increased.

• 한국식생활문화학회지
• /
• 제22권1호
• /
• pp.104-114
• /
• 2007

This research entailed collecting domestic and overseas research papers on technologies for fermentation of Kimchi, which is widely considered the national dish of Korea, creating a technology classification structure and conducting quantitative analysis on each technology component and schematization. Five research papers were published in domestic journals in 1990. Afterwards, the number increased by six to nine papers a year. There was no clear increase after the year 2000, but an average of around 20 papers have been Published every year, indicating that Kimchi research is now becoming widespread. An analysis on researchers entailed determining the percentage of research papers published by the top ten authors. The percentage was 76% in the early-1990s; 63% in the late-1990s; and 52% in the 2000s, indicating that Kimchi has been more and more widely researched and Kimchi research has become professionalized. Universities were found to be leading the research as 52% of researchers belonged to universities. Another 9% were at research institutions. Analysis of technologies showed that domestic research mainly focused on the Kimchi fermentation process and an additive for the development of new Kimchi ingredients and types, preservation and quality improvements. Most of the research papers published overseas dealt with the functions of bacteria strains isolated from Kimchi; and improvements in the Kimchi fermentation and ripening processes. And most of the research papers have been published in a field of microorganism and biotechnology.

• 한국전자거래학회지
• /
• 제25권3호
• /
• pp.1-13
• /
• 2020

기계학습(machine learning)이란 주어진 데이터에 대한 일반화 과정으로부터 특정 문제를 해결할 수 있는 모델(model) 생성 기술을 의미한다. 우수한 성능의 모델을 생성하기 위해서는 양질의 학습데이터와 일반화 과정을 위한 학습 알고리즘이 준비되어야 한다. 성능 개선을 위한 한 가지 방법으로서 앙상블(Ensemble) 기법은 단일 모델(single model)을 생성하기보다 다중 모델을 생성하며, 이는 배깅(Bagging), 부스팅(Boosting), 스태킹(Stacking) 학습 기법을 포함한다. 본 논문은 기존 스태킹 기법을 개선한 다중 스태킹 앙상블(Multiple Stacking Ensemble) 학습 기법을 제안한다. 다중 스태킹 앙상블 기법의 학습 구조는 딥러닝 구조와 유사하고 각 레이어가 스태킹 모델의 조합으로 구성되며 계층의 수를 증가시켜 각 계층의 오분류율을 최소화하여 성능을 개선한다. 4가지 유형의 데이터셋을 이용한 실험을 통해 제안 기법이 기존 기법에 비해 분류 성능이 우수함을 보인다.

• 한국환경복원기술학회지
• /
• 제7권3호
• /
• pp.78-85
• /
• 2004

The non-planned development of the rural area surrounding the Metropolitan area has become a social problem. The land development program until now has an aspect of not combining the spacial plan and the environmental plan. The land use and city development system based on development should change into a form that combines developing the area and conserving the environment. Therefore, this research attempts to compare the results of the overlay analysis and the gravity matrix which are ways to evaluate the value land that has a high environmental conservation value. The research area is the town of Seonggeo-eup, Cheonan City, and the reason for selecting this area is because it is expected to be densely populated as a connected area to the Metropolitan and the development pressure, such as expanding the industrial area, is high due to convenient transportation. The environmental factors used in the research are the relative altitude, incline, age-class, natural degree of the ecology, classification of the land covering and the NDVI, and the research methods used are the overlay analysis of the GIS and the statistical method. The overlay analysis results showed level 1 13.2%, level 2 30.7%, level 3 47.4%, level 4 1.0%, level 5 2.4%, level 6 5.4% and so on. The gravity matrix was classified as level 1 27.0%, level 2 9.3%, level 3 58.2%, level 4 2.4%, level 5 2.3%, level 6 0.9% and so on. These results are more appropriate than current methods for plans that value the environment because the analyzed results of the gravity matrix have a tendency to highly condense the environmentally valuable area. Consequently, if the spacial and environmental plans combine and therefore expand the efficient use of the land in the current state where the nation's concern in environment is getting higher, it is thought that it will contribute highly on the development of the nation's life quality.

• 한국환경복원기술학회지
• /
• 제20권6호
• /
• pp.51-66
• /
• 2017

This study was conducted to develop detailed evaluation indicator as a way for evaluating sustainable urban ecosystem health focused on ecological urban elements from an eco-cultural point of view after the appearance of Eco-cultural City to meet various needs. And this study was also conducted to search for ways to utilize the detailed evaluation indicator like institutionalization. Eco-cultural City was defined as a city where ecological environment and cultural environment coexist and was aimed to derive applicable planning indicators in Korea. For this, FGI was executed, planning indicators were derived, and suitability was examined. The weights were calculated based on the selected indicators through AHP expert survey. After getting the result of FGI, experts reviewed the adequacy of definition from Eco-cultural City and its necessity, and the applicability of planning indicators was examined with evaluation of suitability. As a result of evaluating suitability, it was judged that 41 indicators based on an overall average of 4 areas were relatively high on suitability and also important among sectors. As for the analysis result, the priority order in multistage classification was as followed : harmony between human and environment(B) 0.349, environmental resources(A) 0.266, city environment and quality of culture(C) 0.208, and role division and citizen participation(D) 0.177. In the second level of relative importance, environment protection and infra in the role and citizen participation section was the highest, 0.449, harmonization policy and system in calculating weights was the highest.

• 한방안이비인후피부과학회지
• /
• 제20권3호
• /
• pp.138-146
• /
• 2007

Objective : To observe the trend in clinical study on atopic dermatitis(AD) over the last 3 years in order to develop a study methodology of AD in Oriental Medicine. Methods : Using the Pub med on line site; search terms: atopic dermatitis, field as title/abstract, limitation as published in the last 3 years, only items with links to full text, Humans, Clinical Trial, English. I observed the study contents of all this research and focused on the classification of treatments. I also observed of AD clinical trials registered on a clinical trial site(www.clinicaltrial.gov) on 23rd of June, 2007: study contents, localization and study designs. Results : Through the Pub Med site, I found 169 articles. Classified according to study subject, the studies related to treatment were 114(67.5%); physiology, pathology and prevention 12(7.1%); Diagnosis and Evaluation(7.1%); psychological aspects including quality of life 10(5.9%); diet and management 10(5.9%); epidemiology 7(4.1%); and others 7(4.1%). However, the treatment study of herb-medicine as intervention showed only 1 article. Futhermore, it wasn't based on Oriental Medicine philosophy. In the clinical trial site, there were 31 studies in which patients were recruited or planned for the future. The study on efficacy and safety of the medicine produced 14 trials, 5 comparative trials, 2 phototherapy, 2 diagnosis, 6 physiology and pathology, and 2 epidemiology. The trial institutions were concentrated in U.S.A. Conclusion : I suggest we'd better try to make a good clinical guideline and standardization of diagnosis and herb-medicine in order to develop a clinical study methodology of AD as soon as possible in the future. Even though it 's very hard to find the study methodology, we should aim to achieve positive results and show the evidence of the efficacy and safety of herb-medicine treatment for AD using Oriental Medicine.