이진국 교수

Abstract This paper discusses an approach to augmented virtual reality (AVR) and 360-degree spatial visualization. The approach involves locating stereoscopic three-dimensional virtual objects into a real off-site panorama, supporting spatial remodel design decision-making through realistic comparisons. Previous studies have shown that in the design process, end-user engagement promotes the quality and satisfaction of design solutions. Immersive media such as virtual reality (VR) and augmented r

This paper describes an approach for identifying and appending interior design style information stochastically with reference images and a deep-learning model. In the field of interior design, design style is a useful concept and has played an important role in helping people understand and communicate interior design. Previous studies have focused on how the interior design style categories can be defined. On the other hand, this paper focuses on how stochastically recognizing the design style

Abstract This paper describes an approach to extracting a predicate-argument structure (PAS) in building design rule sentences using natural language processing (NLP) and deep learning models. For the computer to reason about the compliance of building design, design rules represented by natural language must be converted into a computer-readable format. The rule interpretation and translation processes are challenging tasks because of the vagueness and ambiguity of natural language. Many studie

This paper presents an approach for defining high-level implementable methods to improve their low-level rule-checking procedures. This is part of an effort to develop challenging building information modeling (BIM)-enabled applications for building permits through automated code compliance checking. The main approach described here aims to alleviate the time-consuming and error-prone tasks of translating natural language into explicitly defined rules. An explicit expression of design requiremen

Abstract This study introduces a novel approach to architectural visualization using generative artificial intelligence (AI), particularly emphasizing text-to-image technology, to remarkably improve the visualization process right from the initial design phase within the architecture, engineering, and construction industry. By creating more than 10 000 images incorporating an architect’s personal style and characteristics into a residential house model, the effectiveness of base AI models. Furth

Room temperature ionic liquids have been used as electrolytes to investigate the performance and the characteristics in dye-sensitized solar cells (DSSCs). We focused on quasi-solid state electrolyte using ionic liquids, which are non-volatile liquids having relatively high conductivities. We studied the performance of the DSSC device with different anion or cation structures of ionic liquids. The power conversion efficiency of the DSSC device using [EMIm]+[PF6]− under 100 mA/cm2 is achieved up

As a subset standard for domain-specific building information modeling (BIM) data exchanges, a model view definition (MVD) has been developed under the Industry Foundation Class (IFC) schema. When a MVD is constructed, specific domains have employed numerous concepts that entail modularized definitions for entities, attributes, relationships, and properties to avoid redundancy in data exchange requirements. Few underlying frameworks, however, assist in either the reliable development of MVDs or