• 한국컴퓨터정보학회논문지
• /
• 제23권11호
• /
• pp.25-30
• /
• 2018

Pattern classification system is often an important component of intelligent systems. In this paper, we present a pattern classification system consisted of the feature selection module, knowledge base construction module and decision module. We introduce a feature impact evaluation selection method based on fuzzy cluster analysis considering computational approach and generalization capability of given data characteristics. A fuzzy neural network, OFUN-NET based on unsupervised learning data mining technique produces knowledge base for representative clusters. 240 blemish pattern images are prepared and applied to the proposed system. Experimental results show the feasibility of the proposed classification system as an automating defect inspection tool.

• 스마트미디어저널
• /
• 제10권3호
• /
• pp.9-22
• /
• 2021

Basically, machine learning models use input data to produce results. Sometimes, the input data is too complicated for the models to learn useful patterns. Therefore, feature engineering is a crucial data preprocessing step for constructing a proper feature set to improve the performance of such models. One of the most efficient methods for automating feature engineering is the autoencoder, which transforms the data from its original space into a latent space. However certain factors, including the datasets, the machine learning models, and the number of dimensions of the latent space (denoted by k), should be carefully considered when using the autoencoder. In this study, we design a framework to compare two data preprocessing approaches: with and without autoencoder and to observe the impact of these factors on autoencoder. We then conduct experiments using autoencoders with classifiers on popular datasets. The empirical results provide a perspective regarding the best suited autoencoder for these factors.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2019년도 추계 학술논문 발표대회
• /
• pp.112-113
• /
• 2019

In this study, development of 3D software for automated formwork design was conducted to achieve optimization and reduction of labor for temporary work. Through the literature review, the current technical level was identified and the required functions of 3D software for automated formwork design were derived. The 3D software should be developed with the aim of automating 3D design, improving construction quality and utilizing the Internet of Things. As a preliminary step to develop 3D software, the prototype demo version was developed to implement 3D design automation function, which confirm the possibility of 3D software development.

• 토지주택연구
• /
• 제11권4호
• /
• pp.99-104
• /
• 2020

This paper presents the recent research developments identified through a review of literature on the application of artificial intelligence in developing automated designs of fire protection facilities. The literature review covered research related to image recognition and applicable neural networks. Firstly, it was found that convolutional neural network (CNN) may be applied to the development of automating the design of fire protection facilities. It requires a high level of object detection accuracy necessitating the classification of each object making up the image. Secondly, to ensure accurate object detection and building information, the data need to be pulled from architectural drawings. Thirdly, by applying image recognition and classification, this can be done by extracting wall and surface information using dimension lines and pixels. All combined, the current review of literature strongly indicates that it is possible to develop automated designs for fire protection utilizing artificial intelligence.

• 한국기계가공학회지
• /
• 제19권10호
• /
• pp.74-80
• /
• 2020

Crawler-type hydraulic devices facilitate forward and backward driving of construction equipment by converting power into mechanical energy. The existing hydraulic device performance test process is time- and labor-intensive. This study aims to improve efficiency and productivity by automating the hydraulic device production performance test processes, which have been separately conducted so far. We also used SolidWorksⓇ, a 3D modeling program, and ANSYSⓇ, a structural analysis tool, for structural analysis and to verify the suitability of fixing pins required for connecting a hydraulic device to performance test equipment. Our results that employing an automated hydraulic device performance test process improves efficiency.

• 한국BIM학회 논문집
• /
• 제9권4호
• /
• pp.21-30
• /
• 2019

Many studies on BIM-based design, construction and operation have already been conducted on roads, railways, etc., but BIM research in the ports and harbors is still lacking. This research develops BIM Library and Technical contents focused on practical usability of ports and harbors infrastructure. We have developed technical content by applying various User Interfaces and workflows, considering the characteristics of ports and harbors design. In order to examine the practical utility of the developed library and contents, we tried modeling the breakwater using these. As a result, we confirmed that collaboration of BIM library and technical contents could significantly improve the productivity of BIM design by increasing library usage and automating repetitive tasks.

• 대한임베디드공학회논문지
• /
• 제15권6호
• /
• pp.307-316
• /
• 2020

Machine learning model data is highly affected by performance. preprocessing is needed to enable analysis of various types of data, such as letters, numbers, and special characters. This paper proposes a development environment that aims to process categorical and continuous data according to the type of missing values in stage 1, implementing the function of selecting the best performing algorithm in stage 2 and automating the process of checking model performance in stage 3. Using this model, machine learning models can be created without prior knowledge of data preprocessing.

• International Journal of Computer Science & Network Security
• /
• 제22권6호
• /
• pp.83-90
• /
• 2022

Traditional Cloud Computing would be unable to safely host IoT data due to its high latency as the number of IoT sensors and physical devices accommodated on the Internet grows by the day. Because of the difficulty of processing all IoT large data on Cloud facilities, there hasn't been enough research done on automating the security of all components in the IoT-Cloud ecosystem that deal with big data and real-time jobs. It's difficult, for example, to build an automatic, secure data transfer from the IoT layer to the cloud layer, which incorporates a large number of scattered devices. Addressing this issue this article presents an intelligent algorithm that deals with enhancing security aspects in IoT cloud ecosystem using butterfly optimization algorithm.

• 국제학술발표논문집
• /
• The 2th International Conference on Construction Engineering and Project Management
• /
• pp.239-248
• /
• 2007

In the highly competitive construction industry, a slight inaccuracy of estimation can easily cause the loss of a project. Erroneous experience-based cost estimates or allocations of on-site supervisory manpower often offset the profit gained from the project and may jeopardize the management processes. To counter these types of problems, we develop a model using mathematical analysis and case-based reasoning to automate the allocation of on-site supervisory manpower and estimate construction site costs. The method is founded upon laborious data collection processes and analysis by matching statistical assumptions, and is applicable to construction projects. In the modeling the costs and allocation of on-site supervisory manpower are quantified for both owners and contractors before initiating or bidding on the projects. The findings confirm that the degree of variation of the model predictions has an accuracy rate at 88.47%. Single-site construction projects can be accurately predicted and the assignment of supervisory manpower feasibly automated.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2011년도 춘계학술발표대회
• /
• pp.1606-1607
• /
• 2011

온라인상에서 흥미 있는 고객을 상호 매칭시키는 알고리즘은 취업 시스템, 결혼 중매 시스템, 비행기표 구매 시스템 등에 적용가능한 주요 기능을 담당한다. 일반적으로 조건검색의 단방향과 양쪽 사용자의 의사를 모두 고려하는 양방향 방법이 있다. 양방향 방식에서 기존에는 사용자가 자신의 흥미를 직접 입력하였으나, 이는 상대 사용자가 입력을 하지 않거나 서비스 초기에 사용자가 적을 경우 사용자가 사용의 흥미를 잃을 위험이 있다. 본 연구는 퍼지 알고리즘을 이용하여 시스템이 사용자의 흥미를 자동으로 계산하도록 하였으며, 매칭유예 알고리즘으로 명명하였다. 매칭유예 알고리즘의 적용 효과를 측정하기 위해 취업사이트에 적용하여 사용자 만족도를 조사하였다. 도입 효과 분석 결과 취업 활동동기를 부여하는 긍정적인 효과가 있는 것으로 보였다.