• Korean Journal of Construction Engineering and Management
• /
• v.13 no.3
• /
• pp.43-55
• /
• 2012

A methodology for BIM Quality Assurance in the construction industry is becoming increasingly an important issue to determine the reliability of BIM. However, the quality assurance of BIM is currently limited to check 3D models, such as clash detection and space layout while verification methods for disciplinary BIM results from structural engineering, mechanical engineering, and estimation do not exist yet. Particularly, in the BIM-based estimation mathematical equations to take off quantities are not clearly exposed so that the results are not quite accepted at practices. With the concept of reliability engineering defined in the manufacturing industry to improve reliability of outcomes of BIM-based quantity take-off, impacting factors that affect reliability of BIM-based quantity take-off were derived. It was found that the factors also include the modeling method and the features of a BIM tool. Therefore, this research aims to propose modeling and verification methods to improve reliability of BIM-based quantity take-off through the pilot test that was performed with commercial BIM tools and IFC-based BIM data.

• Journal of KIBIM
• /
• v.6 no.3
• /
• pp.49-56
• /
• 2016

As project opportunities for the Architecture, Engineering and Construction (AEC) industry have grown more complex and larger, the utilization of Building Information Modeling (BIM) technologies for three-dimensional (3D) design and simulation practices has been increasing significantly; the typical applications of the BIM technologies include clash detection and design alternative based on 3D planning, which have been expanded over to the technology of construction management in the AEC industry for virtual design and construction. As for now, commercial BIM software has been operated under a single-user environment, which is why initial costs for its introduction are very high. Cloud computing, one of the most promising next-generation Internet technologies, enables simple Internet devices to use services and resources provided with BIM software. Recently in Korea, studies to link between BIM and cloud computing technologies have been directed toward saving costs to build BIM-related infrastructure, and providing various BIM services for small- and medium-sized enterprises (SMEs). This study addressed development of the usage metering functions of BIM software under cloud computing architecture in order to archive and use BIM data and create an optimal revenue structure so that the BIM services may grow spontaneously, considering a demand for cloud resources. For the reason, we surveyed relevant cases, and then analyzed needs and requirements from AEC industry. Based on the relevant cases, customizing for cloud BIM and design for the development was performed. We also surveyed any related-law to support cloud computing-based BIM service. Finally, we proposed herein how to optimally design and develop the usage metering functions of cloud BIM software.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.59-68
• /
• 2021

As artificial intelligence(AI) technologies, which have made rapid growth recently, began to be applied to the marine environment such as ships, there have been active researches on the application of CNN-based models specialized for digital videos. In E-Navigation service, which is combined with various technologies to detect floating objects of clash risk to reduce human errors and prevent fires inside ships, real-time processing is of huge importance. More functions added, however, mean a need for high-performance processes, which raises prices and poses a cost burden on shipowners. This study thus set out to propose a method capable of processing information at a high rate while maintaining the accuracy by applying Quantization techniques of a deep learning model. First, videos were pre-processed fit for the detection of floating matters in the sea to ensure the efficient transmission of video data to the deep learning entry. Secondly, the quantization technique, one of lightweight techniques for a deep learning model, was applied to reduce the usage rate of memory and increase the processing speed. Finally, the proposed deep learning model to which video pre-processing and quantization were applied was applied to various embedded boards to measure its accuracy and processing speed and test its performance. The proposed method was able to reduce the usage of memory capacity four times and improve the processing speed about four to five times while maintaining the old accuracy of recognition.