This study combines electroencephalogram (EEG) with virtual reality (VR) technologies to measure the EEG responses of users experiencing changes to architectural elements. We analyze the ratio of alpha to beta waves (RAB) indicators to determine the pre- and poststimulation changes. In our methodology, thirty-three females experience using private rooms in a postpartum care center participated in the experiment. Their brain waves are measured while they are experiencing the VR space of a private room in a postpartum care center. Three architectural elements (i.e., aspect ratio of space, ceiling height, and window ratio) are varied in the VR space. In addition, a self-report questionnaire is administered to examine whether the responses are consistent with the results of the EEG response analysis. As a result, statistically significant differences (p < 0.05) are observed in the changes in the RAB indicator values of the pre- and poststimulation EEG while the subjects are experiencing the VR space where the architectural elements are varied. That is, the effects of the changes to architectural elements on users’ relaxation-arousal responses are statistically verified. Notably, in all the RAB indicator values where significant differences are observed, the poststimulation RAB decreases in comparison to the prestimulus ratios, which is indicative of the arousal response. However, the arousal levels vary across the architectural elements, which implies it would be possible to find out the elements that could induce less arousal response using the proposed method. Moreover, following the experience in the VR space, certain lobes of the brain (F4 and P3 EEG channels) show statistically significant differences in the relaxation-arousal responses. Unlike previous studies, which measured users’ physiological responses to abstract and primordial spatial elements, this study extends the boundaries of the literature by applying the architectural elements applicable to design in practice.

Economic feasibility and cost analysis in the preliminary planning stage of early-phase construction projects have a significant impact on project management and implementation. However, while estimating the construction cost per unit area, the existing approaches do not account for factors other than the area-related information, causing estimation error. Therefore, a construction cost estimation model that can be utilized in the early phase of a construction project is developed in this study based on BIM in the architectural planning stage. Moreover, goodness of fit and accuracy of the model were verified through a validation method considering the BIM design process. The proposed model showed higher accuracy than the conventional models in terms of the floor area. Furthermore, it was possible to confirm the model performance based on the cost estimation accuracy range presented by the AACE. In addition, the developed model can generate estimation results corresponding to Class 1–3, a subsequent construction project stage. The findings of this study emphasize the importance of jointly considering the processes related to construction cost estimation and indicate that parameters other than the floor area need to be considered for construction cost estimation in the early phase of a construction project.

Artificial intelligence presents an optimized alternative by performing problem-solving knowledge and problem-solving processes under specific conditions. This makes it possible to creatively examine various design alternatives under conditions that satisfy the functional requirements of the building. In this study, in order to develop architectural design automation technology using artificial intelligence, the characteristics of an architectural drawings, that is, the architectural elements and the composition of spaces expressed in the drawings, were learned, recognized, and inferred through deep learning. The biggest problem in applying deep learning in the field of architectural design is that the amount of publicly disclosed data is absolutely insufficient and that the publicly disclosed data also haves a wide variety of forms. Using the technology proposed in this study, it is possible to quickly and easily create labeling images of drawings, so it is expected that a large amount of data sets that can be used for deep learning for the automatic recommendation of architectural design or automatic 3D modeling can be obtained. This will be the basis for architectural design technology using artificial intelligence in the future, as it can propose an architectural plan that meets specific circumstances or requirements.

Interactive facades are dynamic in the translation of space in architecture, especially in the aspects of aesthetics, sustainability, adaptation to the environment, and data relay through the medium of light, motion, and embedded technology. The design of interactive facades is complicated and it requires time and effort in the comprehension of the internal functions of the facade from the conceptual stage to occupancy. The existing process of modeling the experimental level of interactive facades through mock-up and prototype models demonstrate a fragmentary outline on which the final development of the interactive façade system is based on. This research aims to analyze the motion aspect of interactive facades design and simplify the conceptual and performance design process through parametric strategies using a multi-hybrid of parametric and simulation tools, such as Rhino Grasshopper, Ladybug, and Daysim, to create interactive facade designs that can verified in a virtual reality environment while generating performance outcomes that can be optimized in a holistic and improved efficient process.