• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.823-830
• /
• 2022

The risk of project execution increases due to the enlargement and complexity of Engineering, Procurement, and Construction (EPC) plant projects. In the fourth industrial revolution era, there is an increasing need to utilize a large amount of data generated during project execution. The design is a key element for the success of the EPC plant project. Although the design cost is about 5% of the total EPC project cost, it is a critical process that affects the entire subsequent process, such as construction, installation, and operation & maintenance (O&M). This study aims to develop a system using machine-learning (ML) techniques to predict risks and support decision-making based on big data generated in an EPC project's design and construction stages. As a result, three main modules were developed: (M1) the design cost estimation module, (M2) the design error check module, and (M3) the change order forecasting module. M1 estimated design cost based on project data such as contract amount, construction period, total design cost, and man-hour (M/H). M2 and M3 are applications for predicting the severity of schedule delay and cost over-run due to design errors and change orders through unstructured text data extracted from engineering documents. A validation test was performed through a case study to verify the model applied to each module. It is expected to improve the risk response capability of EPC contractors in the design and construction stage through this study.

• 한국콘텐츠학회논문지
• /
• 제21권2호
• /
• pp.121-129
• /
• 2021

본 연구에서는 데이터마이닝(Data Mining) 기법 중 하나인 연관관계분석(Association Rule Mining)을 적용하여 위험화물 선별모델을 구축함으로써 관세위험을 최소화하고자 한다. 이를 위해 관세청 수입신고서 빅데이터를 활용하여 연관관계분석 알고리즘인 어프라이어리 알고리즘(Apriori Algorithm)을 적용하고 공급망 간의 위험정도를 계산한다. 대규모의 수입신고 데이터로부터 해외공급자와 수입업체 간의 세율관련(과세가격, 품목, 중수량 등), 원산지표시 위반 등에 관련한 적발결과 관한 규칙셋(Rule Set)과 이 규칙들의 신뢰도(Confidence)을 확보하여 우범공급망 간의 거래패턴을 예측할 수 있는 선별모델을 구축한다. 총 2년 6개월 치의 수입신고 데이터를 활용하여 5-겹 교차검증(5-fold cross validation)을 수행한 결과 16.6%의 Precision과 33.8%의 Recall을 보였다. 이는 빈도기반 방법보다 Precision 기준 약 3.4배 Recall 기준 약 1.5배 높은 결과이다. 이로써 논문에서 제안하고 있는 방법이 관세위험을 줄일 수 있는 효과적인 방법임을 확인하였다.

• Asian Journal for Public Opinion Research
• /
• 제5권4호
• /
• pp.266-284
• /
• 2018

This paper adopts the big data research method, and draws 491 data from the Tianya Forum about the Simultaneous Renting and Purchasing policy of Guangzhou. The qualitative analysis software Nvivo11 is used to cluster the main questions about the Simultaneous Renting and Purchasing policy in the forum. The 36 high-frequency word frequencies are obtained through text clustering. Through rooted theory analysis, the main driving factors for summarizing people's doubts are 9 main categories, 3 core categories, and the model of driving factors for online forums is established. The study finds that resource factors are the most key factor, economic factors are the important drivers, and policy guiding factors are sub-important drivers.

• International journal of advanced smart convergence
• /
• 제5권4호
• /
• pp.32-39
• /
• 2016

Machine learning is a field of artificial intelligence (AI), and a technology that collects, forecasts, and analyzes securities data is developed upon machine learning. The difference between using machine learning and not using machine learning is that machine learning-seems similar to big data-studies and collects data by itself which big data cannot do. Machine learning can be utilized, for example, to recognize a certain pattern of an object and find a criminal or a vehicle used in a crime. To achieve similar intelligent tasks, data must be more effectively collected than before. In this paper, we propose a method of effectively collecting data.

• Communications for Statistical Applications and Methods
• /
• 제26권5호
• /
• pp.497-506
• /
• 2019

Forecasting the U.S. employment level is made using machine learning methods of the artificial neural network: deep neural network, long short term memory (LSTM), gated recurrent unit (GRU). We consider the big data of the federal reserve economic data among which 105 important macroeconomic variables chosen by McCracken and Ng (Journal of Business and Economic Statistics, 34, 574-589, 2016) are considered as predictors. We investigate the influence of the two statistical issues of the dimension reduction and time series differencing on the machine learning forecast. An out-of-sample forecast comparison shows that (LSTM, GRU) with differencing performs better than the autoregressive model and the dimension reduction improves long-term forecasts and some short-term forecasts.

• 한국산학기술학회논문지
• /
• 제19권5호
• /
• pp.480-488
• /
• 2018

정보통신 기술의 발전으로 농업분야에서도 다량의 데이터로부터 가치 있는 정보를 생성하고 그 활용을 위해 빅데이터 기술을 적용하는 연구가 활발히 진행되고 있다. 농업에서 재배 가능한 작물과 품종은 기온, 강수량, 일조시간 등의 자연환경의 영향에 따라 결정된다. 본 논문은 마늘의 생육과정과 일별로 측정되는 기상변수를 활용하여 농작물 생산에 영향을 미치는 기상기후 요인을 도출하고 마늘을 대상으로 단위면적당 생산량 예측(단수) 모형을 도출하였다. 기상변수는 마늘의 생육단계를 고려하여 빅데이터 분석 기법을 이용하였다. 탐색적 자료 분석과정에서는 통계청, 농촌진흥청, 농촌경제연구원으로부터 생산량, 도매시장 반입량, 생육 데이터 등 다양한 농산물 생산 데이터를 제공받아 활용하였다. 또한 기상청으로부터 AWS, ASOS, 특보현황 등 다양한 기상관측 데이터를 수집하여 활용하였다. 상관관계 분석 과정은 변수선택, 후보모형 도출, 모형진단, 시나리오 예측 등을 통해 도출한 모형의 모형 적합도와 생산량 예측력을 비교하여 마늘생산단수예측 모형을 설계하였다. 수많은 기상요인 변수는 요인분석을 이용하여 차원을 감소시키고 설명변수로 선정하였다. 이 방법을 이용함으로써 회귀분석에서 발생할 수 있는 다중공선성과 낮은 자유도의 문제를 효과적으로 통제할 수 있었으며 회귀분석의 적합도와 예측력을 높일 수 있었다.

• 디지털산업정보학회논문지
• /
• 제13권3호
• /
• pp.133-147
• /
• 2017

This study aims to investigate the effect of personality traits (Big5) of local government officials on job exhaustion. First, we examine the correlation between personal characteristics of individual employees and self-efficacy and the correlation between factors of civil servants' personality characteristics and job stress. Also, it was confirmed whether self-efficacy had a significant effect on job exhaustion and whether job stress had a significant effect on job exhaustion. In order to empirically study this research model, we held a survey based on the employees of Gangnam-gu, Seoul. The main results of this study are as follows : First, it was confirmed that sincerity among personality characteristics affects positive self-efficacy and neuroticism affects negative self-efficacy. However, it was confirmed that extroversion, affinity, and openness were not correlated with self-efficacy. Second, neuroticism has a positive influence on job stress and openness has a negative effect on job stress. However, there was no correlation between extroversion, affinity, sincerity and job stress. Third, the relationship between self-efficacy and job exhaustion turned out to give a negative effect. Finally, job stress was positively influenced by job exhaustion. Therefore, it is necessary to apply the study on personality characteristics (Big5), job stress, and job exhaustion, which have been studied based on service industries, to local government officials. The purpose of this study is to suggest job training for enhancing personality traits that can help reduce the job burden of local government officials.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.423-427
• /
• 2003

In this paper, it is to development of brake system with ABS function for aircraft. The test of brake system is required before applying on aircraft. The real-time dynamic simulator with 5-D.O.F. aircraft dynamic model is developed for braking performance test of ABS (Anti-skid Brake System) control h/w with anti-skid brake functions. The dynamic simulator is real-time interface system that is composed of dynamic simulation parts, master control parts, digital and analog in/out interface parts, and user interface parts. The 5-D.O.F. aircraft dynamic model is composed of a big contour and a little contour by simulation s/w. The big contour represents the interactions of forces in airframe, nose and main landing gear, and engines on the center of gravity. The little contour represents interactions of wheel, braking units, hydraulic units and a control unit. ABS control h/w unit with ABS control algorithm is also developed and is tested with simulator under the some conditions of gripping coefficient. We have known that ABS control h/w unit on wet or snowy runway as well as dry runway very well protects wheel skid.

• 한국컴퓨터정보학회논문지
• /
• 제28권9호
• /
• pp.17-25
• /
• 2023

본 논문에서는 매개변수가 더 적고, 빠르게 추정 가능한 MobileViT 기반 모델을 통해 사람 자세 추정 과업을 수행할 수 있는 모델을 제안한다. 기반 모델은 합성곱 신경망의 특징과 Vision Transformer의 특징이 결합한 구조를 통해 경량화된 성능을 입증한다. 본 연구에서 주요 매커니즘이 되는 Transformer는 그 기반의 모델들이 컴퓨터 비전 분야에서도 합성곱 신경망 기반의 모델들 대비 더 나은 성능을 보이며, 영향력이 커지게 되었다. 이는 사람 자세 추정 과업에서도 동일한 상황이며, Vision Transformer기반의 ViTPose가 COCO, OCHuman, MPII 등 사람 자세 추정 벤치마크에서 모두 최고 성능을 지키고 있는 것이 그 적절한 예시이다. 하지만 Vision Transformer는 매개변수의 수가 많고 상대적으로 많은 연산량을 요구하는 무거운 모델 구조를 가지고 있기 때문에, 학습에 있어 사용자에게 많은 비용을 야기시킨다. 이에 기반 모델은 Vision Transformer가 많은 계산량을 요구하는 부족한 Inductive Bias 계산 문제를 합성곱 신경망 구조를 통한 Local Representation으로 극복하였다. 최종적으로, 제안 모델은 MS COCO 사람 자세 추정 벤치마크에서 제공하는 Validation Set으로 ViTPose 대비 각각 5분의 1과 9분의 1만큼의 3.28GFLOPs, 972만 매개변수를 나타내었고, 69.4 Mean Average Precision을 달성하여 상대적으로 우수한 성능을 보였다.

• Asia pacific journal of information systems
• /
• 제23권3호
• /
• pp.25-53
• /
• 2013

This study analyzes the effect of Computer Aided Innovation (CAI) to improve R&D Capabilities empirically. Survey was distributed by e-mail and Google Docs, targeting CTO of 235 SMEs. 142 surveys were returned back (rate of return 60.4%) from companies. Survey results from 119 companies (83.8%) which are effective samples except no-response, insincere response, estimated value, etc. were used for statistics analysis. Companies with less than 50billion KRW sales of entire researched companies occupy 76.5% in terms of sample traits. Companies with less than 300 employees occupy 83.2%. In terms of the type of company business Partners (called 'partners with big companies' hereunder) who work with big companies for business occupy 68.1%. SMEs based on their own business (called 'independent small companies') appear to occupy 31.9%. The present status of holding IT system according to traits of company business was classified into partners with big companies versus independent SMEs. The present status of ERP is 18.5% to 34.5%. QMS is 11.8% to 9.2%. And PLM (Product Life-cycle Management) is 6.7% to 2.5%. The holding of 3D CAD is 47.1% to 21%. IT system-holding and its application of independent SMEs seemed very vulnerable, compared with partner companies of big companies. This study is comprised of IT infra and IT Utilization as CAI capacity factors which are independent variables. factors of R&D capabilities which are independent variables are organization capability, process capability, HR capability, technology-accumulating capability, and internal/external collaboration capability. The highest average value of variables was 4.24 in organization capability 2. The lowest average value was 3.01 in IT infra which makes users access to data and information in other areas and use them with ease when required during new product development. It seems that the inferior environment of IT infra of general SMEs is reflected in CAI itself. In order to review the validity used to measure variables, Factors have been analyzed. 7 factors which have over 1.0 pure value of their dependent and independent variables were extracted. These factors appear to explain 71.167% in total of total variances. From the result of factor analysis about measurable variables in this study, reliability of each item was checked by Cronbach's Alpha coefficient. All measurable factors at least over 0.611 seemed to acquire reliability. Next, correlation has been done to explain certain phenomenon by correlation analysis between variables. As R&D capabilities factors which are arranged as dependent variables, organization capability, process capability, HR capability, technology-accumulating capability, and internal/external collaboration capability turned out that they acquire significant correlation at 99% reliability level in all variables of IT infra and IT Utilization which are independent variables. In addition, correlation coefficient between each factor is less than 0.8, which proves that the validity of this study judgement has been acquired. The pair with the highest coefficient had 0.628 for IT utilization and technology-accumulating capability. Regression model which can estimate independent variables was used in this study under the hypothesis that there is linear relation between independent variables and dependent variables so as to identify CAI capability's impact factors on R&D. The total explanations of IT infra among CAI capability for independent variables such as organization capability, process capability, human resources capability, technology-accumulating capability, and collaboration capability are 10.3%, 7%, 11.9%, 30.9%, and 10.5% respectively. IT Utilization exposes comprehensively low explanatory capability with 12.4%, 5.9%, 11.1%, 38.9%, and 13.4% for organization capability, process capability, human resources capability, technology-accumulating capability, and collaboration capability respectively. However, both factors of independent variables expose very high explanatory capability relatively for technology-accumulating capability among independent variable. Regression formula which is comprised of independent variables and dependent variables are all significant (P<0.005). The suitability of regression model seems high. When the results of test for dependent variables and independent variables are estimated, the hypothesis of 10 different factors appeared all significant in regression analysis model coefficient (P<0.01) which is estimated to affect in the hypothesis. As a result of liner regression analysis between two independent variables drawn by influence factor analysis for R&D capability and R&D capability. IT infra and IT Utilization which are CAI capability factors has positive correlation to organization capability, process capability, human resources capability, technology-accumulating capability, and collaboration capability with inside and outside which are dependent variables, R&D capability factors. It was identified as a significant factor which affects R&D capability. However, considering adjustable variables, a big gap is found, compared to entire company. First of all, in case of partner companies with big companies, in IT infra as CAI capability, organization capability, process capability, human resources capability, and technology capability out of R&D capacities seems to have positive correlation. However, collaboration capability appeared insignificance. IT utilization which is a CAI capability factor seemed to have positive relation to organization capability, process capability, human resources capability, and internal/external collaboration capability just as those of entire companies. Next, by analyzing independent types of SMEs as an adjustable variable, very different results were found from those of entire companies or partner companies with big companies. First of all, all factors in IT infra except technology-accumulating capability were rejected. IT utilization was rejected except technology-accumulating capability and collaboration capability. Comprehending the above adjustable variables, the following results were drawn in this study. First, in case of big companies or partner companies with big companies, IT infra and IT utilization affect improving R&D Capabilities positively. It was because most of big companies encourage innovation by using IT utilization and IT infra building over certain level to their partner companies. Second, in all companies, IT infra and IT utilization as CAI capability affect improving technology-accumulating capability positively at least as R&D capability factor. The most of factor explanation is low at around 10%. However, technology-accumulating capability is rather high around 25.6% to 38.4%. It was found that CAI capability contributes to technology-accumulating capability highly. Companies shouldn't consider IT infra and IT utilization as a simple product developing tool in R&D section. However, they have to consider to use them as a management innovating strategy tool which proceeds entire-company management innovation centered in new product development. Not only the improvement of technology-accumulating capability in department of R&D. Centered in new product development, it has to be used as original management innovative strategy which proceeds entire company management innovation. It suggests that it can be a method to improve technology-accumulating capability in R&D section and Dynamic capability to acquire sustainable competitive advantage.