• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.2
• /
• pp.65-70
• /
• 2015

In the PCB(Printed Circuit Board) manufacturing industry, the yield is an important management factor because it affects the product cost and quality significantly. In real situation, it is very hard to ensure a high yield in a manufacturing shop because products called chips are made through hundreds of nano-scale manufacturing processes. Therefore, in order to improve the yield, it is necessary to analyze main fault process and equipment that cause low PCB yield. This paper proposes a systematic approach to discover fault-causing processes and equipment by using a logistic regression and a stepwise variable selection procedure. We tested our approach with lot trace records of real work-site. A lot trace record consists of the equipment sequence that the lot passed through and the number of faults for each fault type in the lot. We demonstrated that the test results reflected the real situation of a PCB manufacturing line.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2008.05a
• /
• pp.1985-1990
• /
• 2008

1970년대 이후의 고도경제성장기에 치수대책과 동시에 건설골재로서 하상이 굴착된 하천이 많으며, 국가하천 지정구간외에서는 평균하상고가 1.0m 이상 저하한 하천구간도 많다. 또한 국가하천은 상류의 사방공사나 댐건설에 의한 영향이 복합적으로 하도에 나타나고 있어 하상굴착이 하도특성에 어떤 영향을 미치는가를 실증적(實證的)으로 검증하는 것은 어려운 과제이다. 하천에서의 골재채취는 제방부의 침식에 의한 호안파괴, 하상저하에 따른 교량이나 취수보 등 구조물의 기초 노출이 치수적인 문제를 야기할 뿐만 아니라, 단시간내에 하도의 지형구조를 급격하게 변화시켜 여울 소의 하상구조 교란이나 수중 및 하천변의 서식처 파괴 등으로 하천의 물리적 환경에 큰 영향을 미침으로써 생태계를 교란하거나 파괴하는 결과를 초래하게 된다. 본 연구에서는 골재채취로 인하여 교란된 하천의 복원 및 적응관리 계획수립의 전단계에 필요한 교란평가기법을 개발하기 위하여 황강, 남강 및 감천을 대상으로 하여 대조구간과 교란구간을 선정하고 조사 분석하였다. 하천골재 채취가 없거나 경미한 대조구간에서는 홍수량이 변하지 않으면 terrace 모양의 하안부 재료가 하상재료와 거의 같기 때문에 홍수가 있으면 침식된 원래의 하폭으로 회복되는 방향으로 변하지는 않는 경향이 나타났다. 반면에 골재채취가 많은 경우 큰 홍수시의 저수로부의 수심을 증가시키기 때문에 수충부 등의 최심하상고가 크게 되는 경향이 있었으며, 고수부는 침수되는 빈도와 수심이 감소하기 때문에 토사의 퇴적속도(고수부의 상승속도)의 감소, 퇴적물의 세립화 경향이 나타나서 모래, 실트가 퇴적하지 않는 고수부상에 모래, 실트가 퇴적되는 경우가 있고, 반대로 고수부의 퇴적속도가 상승하는 경우도 있었다. 골재채취로 횡단방향의 평탄화가 초래되어 여울 소의 하상구조가 교란됨과 동시에 구간별로 종단경사가 완만해지며, 대부분 교량부에 하상유지공을 설치해야 할 정도로 하상경사가 급변하는 구간이 다수 조사되었다. 또한 선행연구에서 개발된 하상서식환경, 하상재료, 유속/수심상황, 유사퇴적, 하도흐름상태, 하도개수, 여울출현 빈도, 하안 안정성, 식생피복 및 하반림 등 10개의 교란평가항목을 적용하여 대조구간과 비교 평가하였다.

• The Journal of Bigdata
• /
• v.2 no.2
• /
• pp.1-7
• /
• 2017

Intelligent transportation system (ITS) has been introduced to maximize the efficiency of operation and utilization of the urban traffic facilities and promote the safety and convenience of the users. With the expansion of ITS, various traffic big data such as road traffic situation, traffic volume, public transportation operation status, management situation, and public traffic use status have been increased exponentially. In this paper, we derive structural characteristics of urban traffic according to the vehicle flow by using big data network analysis. DSRC (Dedicated Short Range Communications) data is used to construct the traffic network. The results can help to understand the complex urban traffic characteristics more easily and provide basic research data for urban transportation plan such as road congestion resolution plan, road expansion plan, and bus line/interval plan in a city.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.5
• /
• pp.173-187
• /
• 2018

This paper proposes a computer vision and deep learning-based technique for surveillance camera system for vehicle counting as one part of parking lot management system. We applied the You Only Look Once version 2 (YOLOv2) detector and come up with a deep convolutional neural network (CNN) based on YOLOv2 with a different architecture and two models. The effectiveness of the proposed architecture is illustrated using a publicly available Udacity's self-driving-car datasets. After training and testing, our proposed architecture with new models is able to obtain 64.30% mean average precision which is a better performance compare to the original architecture (YOLOv2) that achieved only 47.89% mean average precision on the detection of car, truck, and pedestrian.

• The KIPS Transactions:PartA
• /
• v.10A no.5
• /
• pp.503-512
• /
• 2003

Recently many applications are being developed as web technologies are evolved rapidly, but the development emthodology and quality improvement speed of the web apllications is not so. The creations of Most web applications have developed depending on the developer's knowledge and experience without a systematic development methodologies. But the web-based application systems require the various developing gechniques and the rich developing methodogies for a design process. This paper applies the UML(Unified Modeling Language) supporting an object-oriented development methodology to the design and implementation of a mobile customer management system. That is, it appliesthe UML to the system modeling based on a story board and a requirement specification at the web development of the similar web applications. Applying UML to this system achieved the analysis and the design of an web application effciently.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2004.11a
• /
• pp.210-215
• /
• 2004

In can occur to many problems on progressing step without close scope definition, interrelation definition between activities, resource plan, and schedule plan on planning step. But it have not closely defined performance system on planning step because of many constraints of domestic construction industry. Therefore this paper intends to discuss a method of calculating optimal cost and duration using Linear Programming that solves maximing or minimizing problems among decision making methodology and Monte Carlo Simulation that decreases to probability errors. With outcoms applying Linear programming and Monte Carlo Simulation for calculating optimal cost and duration, follow as : With outcomes applying Monte Carlo Simulation, it could calculate reliable estimator about project duration through removing various constraints. With outcomes applying Linear programming, it could calculate optimal value about project cost through defining various variables and constraints on many activities.

• Korean Journal of Construction Engineering and Management
• /
• v.16 no.1
• /
• pp.44-51
• /
• 2015

In recent years, the domestic construction business is continuously stagnated caused by housing depression, global financial crisis etc. To overcome these difficulties, the construction companies should reinforce the internal marketing like the service business. However, it is not easy to conduct active internal marketing reinforcement since the companies do not directly receive customers under special situation like construction. Therefore, it is necessary to resolve the urgent issue by selecting order of priority among internal marketing factors. To address this issue, the objective of this study is to analyze the internal marking factors by using Analytic Hierarchy Process. As a result, the first and second factor represents the internal communication and working condition and environment respectively. The findings of this study will contribute to apply the internal marketing into construction industry.

• Spatial Information Research
• /
• v.18 no.4
• /
• pp.13-22
• /
• 2010

For implementing TMDL(Total Maximum Daily Loading) to adopt more effective management of water pollution, water quality modeling is pre-requisite and such modeling requires the extraction of stream centerline. The institutes responsible for the water quality modeling, however, generates the stream centerline with their own criteria and this lead to low accuracy of the extracted centerline as well as different modeling results for the same watershed. Therefore, this study mainly focused on the development of extraction method of the stream centerline. For that, an automated method has been developed through the integration of the centerline extraction method using a maximum inscribed circle with GIS. The result has shown that the newly developed method could enable to represent more details of the stream topography along with enhanced accuracy compared with conventional extraction method. Furthermore, the new method can afford centerline extraction for the island areas which has been the limitation of the conventional method thereby supporting water quality modeling in a detailed level.

• Journal of the Korea Society for Simulation
• /
• v.23 no.3
• /
• pp.19-25
• /
• 2014

Demand forecasting is the basis of management activities including marketing strategy. Especially, the demand of a part is remarkably important in supply chain management (SCM). In the fields of various industries, the part demand usually has the intermittent characteristic. The intermittent characteristic implies a phenomenon that there frequently occurs zero demands. In the intermittent demands, non-zero demands have large variance and their appearances also have stochastic nature. Accordingly, in the intermittent demand forecasting, it is inappropriate to apply the traditional time series models and/or cause-effect methods such as linear regression; they cannot describe the behaviors of intermittent demand. Markov bootstrap method was developed to forecast the intermittent demand. It assumes that first-order autocorrelation and independence of lead time demands. To release the assumption of independent lead time demands, this paper proposes a modified bootstrap method. The method produces the pseudo data having the characteristics of historical data approximately. A numerical example for real data will be provided as a case study.

• International Journal of Highway Engineering
• /
• v.3 no.4 s.10
• /
• pp.137-146
• /
• 2001

Pavement distresses are one of the most important data for pavement management systems. Inspection machines and its related programs have been used for operating tools in PMS developed in advanced countries. In Korea imported machines and programs for the length price ale utilized to get information of pavement condition from the field This study is launched for developing the program which can detect cracks on asphalt pavement due to many drawbacks in current PMS operation such as improper maintenance work and long resting period when it was broken. The focus of this study is to define principles to analyze pavement surface with digital image processing techniques, to test property of pavement images and to suggest an algorithm that reduces noises at test. To test images, the camera attached on the Automatic Road Analyser(ARAN) was used. Through the FFT images, histogram and statistical values of pavement images, it was found that the images had many noises with high-frequency components against general images, and it was difficult to subdivide pavement images into background or crack. Through several testing with various filters for noise reduction a 3X3 median filter was suggested to reduce noises effectively.