Purpose This study aims to present a twofold machine learning (ML) model, namely, EDU-AI, and its implementation in educational buildings. The specific focus is on classroom layout design, which is investigated regarding implementation of ML in the early phases of design. Design/methodology/approach This study introduces the framework of the EDU-AI, which adopts generative adversarial networks (GAN) architecture and Pix2Pix method. The processes of data collection, data set preparation, training, validation and evaluation for the proposed model are presented. The ML model is trained over two coupled data sets of classroom layouts extracted from a typical school project database of the Ministry of National Education of the Republic of Turkey and validated with foreign classroom boundaries. The generated classroom layouts are objectively evaluated through the structural similarity method (SSIM). Findings The implementation of EDU-AI generates classroom layouts despite the use of a small data set. Objective evaluations show that EDU-AI can provide satisfactory outputs for given classroom boundaries regardless of shape complexity (reserved for validation and newly synthesized). Originality/value EDU-AI specifically contributes to the automation of classroom layout generation using ML-based algorithms. EDU-AI’s two-step framework enables the generation of zoning for any given classroom boundary and furnishing for the previously generated zone. EDU-AI can also be used in the early design phase of school projects in other countries. It can be adapted to the architectural typologies involving footprint, zoning and furnishing relations.
Owing to factors such as high living standards and digitalization, energy use is growing. However, the proportion of renewable energy sources is also rising in all energy consumption. Given this use of renewable energy, global warming and environmental issues are still rising. Fossil-based energy species are more polluting and resource-stricken than others. Studies on environmental pollution show that fossil-based energies are the most important pollutants. Fossil-based energy source is still the most consumed type of energy. Besides, the renewable energy sources’ consumption is very low. Therefore, it is important to increase the use of renewable energy, which creates cleaner and less emissions. Buildings should have the right clean energy use incentives. The needs such as heating, refrigeration, and lighting can be met by renewable energy. This research aims to explore and demonstrate how renewable energy can profit when fulfilling public building functions. Through using both conventional methods and creative methods together, the rate of use of renewable resources such as solar, wind, and geothermal resources in buildings can be increased. Therefore, major contributions to reducing the environmental issues caused by energy consumption can be made.
Tall buildings have the ability to produce wind energy, having been exposed to relatively high airflow speeds at a far distance from ground levels. However, with the introduction of wind energy into urban areas, there are many concerns. These include especially environmental noise impacts since the wind turbines will be located in dense urban areas where tall buildings are mostly located. Therefore, this increasing use of wind energy in the built environment has led to the publication of up-to-date regulations that limit noise levels for wind farms in many European countries. At this point, the following three aspects should be considered for noise emission: the noise source, the distance from the source, and the sound pressure level of the noise source. The choice of wind turbines for urban environments should, therefore, be compatible with low noise levels. In addition, careful positioning of turbines is also important (avoid locations where wind conditions are unfavorable, avoid sensitive places, i.e. areas at which noise levels must be low). It was necessary to calculate the noise in strong winds because the noise from a wind turbine rises with wind velocity. For the measurement of noise emitted from the wind turbine, two potential solutions were proposed until now; either it could be measured in a wind tunnel or it could be measured in the natural wind outside. However, in the early design stage, these types of measurement methods are mostly not preferable due to high financial requirements and long measurement processes. Hence, in this study, wind turbine noise is simulated via software. A case study of a tall mixed-use tower is chosen and the environmental noise distribution due to the wind turbine located on the roof of the tower is simulated. The results may provide an important guideline for architects looking for an acoustically comfortable way to integrate wind turbines into their buildings in the early design stage.
Estimating indoor airflow characteristics of natural ventilation systems is very significant in the early design stage. It's clear that for the early steps of design, existing numerical and experimental analysis methods are very time consuming and they require in depth knowledge of Fluid Dynamics. These methods are not efficient especially in the case that the building form changes dynamically. Besides, both wind tunnel testing and Computational Fluid Dynamics simulations are not efficient when it comes to taking output in real-time. Due to all of these reasons, a need for a fast and robust method occurs. Particle-based algorithms are efficient methods for this type of analyses however they have not been used in architectural aerodynamics. At this point, a very powerful method which doesn't require mesh (control volume) is developed. In this study, the details of the developed algorithm and the output of it are given. The algorithm was assessed in three case studies of natural ventilation systems. As a result, it is seen that the developed algorithm can be a guide in building-wind interaction analysis for architects in the early design stage. However, in our paper, we do not only present case studies, but also an analysis methodology from architectural and engineering perspectives. This is significant because the methodology and the results of this paper constitute a guide for further researches on natural ventilation with a new method and consequently contribute to improved wind quality of indoor spaces.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.