Search results

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.

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).

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).

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.

Accurate documentation of damaged or destroyed historical buildings to protect cultural heritage has been on the agenda of architecture for many years. In that sense, this study uses machine learning (ML) to predict missing/damaged parts of historical buildings within the scope of early ottoman tombs.

This study uses conditional generative adversarial networks (cGANs), a subset of ML to predict missing/damaged parts of historical buildings within the scope of early Ottoman tombs. This paper discusses that using GAN as a ML framework is an efficient method for estimating missing/damaged parts of historical buildings. The study uses the plan drawings of nearly 200 historical buildings, which were prepared one by one as a data set for the ML process.

The study contributes to the field by (1) generating a mixed methodological framework, (2) validating the effectiveness of the proposed framework in the restitution of historical buildings and (3) assessing the contextual dependency of the generated data. The paper provides insights into how ML can be used in the conservation of architectural heritage. It suggests that using a comprehensive data set in the process can be highly effective in getting successful results. The findings of the research will be a reference for new studies on the conservation of cultural heritage with ML and will make a significant contribution to the literature.

A reliable outcome has been obtained concerning the interpretation of documented data and the generation of missing data at the macro level. The framework is remarkably effective when it comes to the identification and re-generation of missing architectural components like walls, domes, windows, doors, etc. on a macro level without details. On the other hand, the proposed methodological framework is not ready for advanced steps of restitution since every case of architectural heritage is very detailed and unique. Therefore, the proposed framework for re-generation of missing components of heritage buildings is limited by the basic geometrical form which means the architectural details of the mentioned components including ornaments, materials, identification of construction layers, etc. are not covered.

The generic literature as to ML models used in architecture mostly constitutes design exploration and floor plan/urban layout generation. More specific studies in the conservation of architectural heritage by using ML mostly focus on architectural component recognition over 3D point cloud data (1) or superficial damage detection of heritage buildings (2). However, we propose a mixed methodological framework for the interpretation of documented architectural data and the regeneration of missing parts of historical buildings. In addition, the methodology and the results of this paper constitute a guide for further research on ML and consequently contribute to architects in the early phases of restitution.

It is important to provide building performance feedback to the designer as early as possible in the design process. However, many aspects of building performance are significantly affected by the design of the building’s technical systems (e.g., heating, airconditioning), which are typically configured in detail only in the later stages of design. The challenge is thus to find a method to use detailed simulation tools even during the early stages of design when values for many of the variables for the building’s technical systems are not yet available. In this paper, we demonstrate how this problem can be partially solved by use of differential representation for building and technical system, homology‐based automatic mapping of relevant information from the building to the technical system representation, and generative design agents which, with a minimal user‐input, can design and model the technical system. We conclude the paper with illustrative examples of detailed performance analysis of complex buildings and their heating, ventilation, and air‐conditioning systems, performed in early stages of design.

This research aims to develop an automated and optimization algorithms (OAs)-integrated 4D building information modeling (BIM) approach and a prototype and enable construction managers and practitioners to estimate the time of compound elements in building projects using the resource specification technique.

A 4D BIM estimation process was first developed by applying the resource specification and geometric information from the BIM model. A suite of OA including particle swarm optimization, ant colony, differential evolution and genetic algorithm were developed and compared in order to facilitate and automate the estimation process. The developed processes and porotypes were linked and integrated.

The OA-based automated 4D BIM estimation prototype was developed and validated through a real-life construction project. Different OAs were applied and compared, and the genetic algorithm was found as the best performing one. The prototype was successfully linked with BIM timeliner application. By using this approach, the start and finish dates of all object-based activities are developed, and the project completion time is automatically estimated.

Unlike conventional construction estimation methods which need various tools and are error prone and time-consuming, the developed method bypasses the existing time estimation tools and provides the integrated and automated process with BIM and machine learning algorithms. Furthermore, this approach integrates 4D BIM applications into construction design procedures, connected with OA automation.

Computer‐based models for the automatic generation of facility layouts have been shown to provide significant benefits to the industrial community for the planning and development of facilities. In a manufacturing environment, layouts are often needed for the manufacture, storage and shipment of specific product types within specific time periods. This is especially true in metal fabrication plants, as the dynamic nature of product storage and manufacture dictates the need for effective layout generation to achieve cost reductions. The system described in this paper integrates raw material storage, inventory management, scheduling and rack system design with facility layout development for the most satisfactory dynamic response. The research addressed in this paper has resulted in the development of a computer‐based model that focuses on the concept of integrating the domains of plant layout, material handling and warehousing in terms of raising overall effectiveness.

Open-plan office environments are considered to offer workplace productivity benefits because of the opportunities that they create for interaction and knowledge exchange, but more recent research has highlighted noise, distraction and loss of privacy as significant productivity penalties with this office layout. This study aims to investigate if the purported productivity benefits of open plan outweigh the potential productivity penalties.

Previous research suggests that office environments are experienced differently according to the gender and age of the occupier across both open-plan and enclosed configurations. Empirical research undertaken with office occupiers in the Middle East (N = 220) led to evaluations to establish the impact different offices had on perceived productivity. Factor analysis was used to establish five underlying components of office productivity. The five factors are subsequently used as the basis for comparison between office occupiers based on age, gender and office type.

This research shows that benefits and penalties to workplace productivity are experienced equally across open-plan and enclosed office environments. The greatest impact on perceived workplace productivity however was availability of a variety of physical layouts, control over interaction and the “downtime” offered by social interaction points. Male occupiers and those from younger generations were also found to consider the office environment to have more of a negative impact on their perceived workplace productivity compared to female and older occupiers.

The originality of this paper is that it develops the concept of profiling office occupiers with the aim of better matching office provision. This paper aims to establish different occupier profiles based on age, gender and office type. Data analysis techniques such as factor analysis and t-test analysis identify the need for different spaces so that occupiers can choose the most appropriate space to best undertake a particular work task. In addition, it emphasises the value that occupiers place on “downtime” leading to the need for appropriate social space.

The home page design of a digital news website is a key factor in determining its attractiveness to readers. This study aims to propose an approach to manage the frequent adjustment of the dynamic layout of the news content on the website home page in a real-time environment to increase its attractiveness to readers.

This paper shows that this news website layout design problem can be modeled as an optimization problem based on the information of news contents that change within a multiple-period planning horizon similar to the dynamic facility layout problem. A hybrid genetic algorithm-based approach integrated with local search heuristic methods is also proposed to improve the solution.

This paper finds that the DPLP model is effective in modeling the changing layout of a digital news website. The problem can solved in a timely manner using the proposed hybrid genetic algorithm.

This paper was based on hypothetical data and on the assumption of equal section size. Actual data would help fine-tune the application of the dynamic facility layout model. As well the algorithm could be enhanced for unequal size sections.

The model should help online newspapers apply sophisticated algorithms to optimize the layout of news websites dynamically in a timely manner.

News websites are increasingly the desired medium to consume news. So it has an important role in educating society. Thus optimizing and improving the process will help in this regard.

To the best of the authors’ knowledge, this paper is the first one to apply the DPLP model to the digital newspaper website dynamic design problem.

This paper aims to propose an innovative building information modelling (BIM)-based framework for multi-objective and dynamic temporary construction site layout design (SLD), which uses a hybrid approach of systematic layout planning (SLP) and mathematical modelling.

The hybrid approach, which follows a step-by-step process for site layout planning, is designed to facilitate both qualitative and quantitative data collection and processing. BIM platform is usedto facilitate the determination of the required quantitative data, while the qualitative data are generated through knowledge-based rules.

The multi-objective layout model represents two important aspects: layout cost and adjacency score. The result shows that the model meets construction managers’ requirements in not only saving cost but also assuring the preferences of temporary facility relationships. This implies that the integration of SLP and mathematical layout modelling is an appropriate approach to deliver practical multi-objective SLD solutions.

The proposed framework is expected to serve as a solution, for practical application, which takes the advantage of technologies in data collection and processing. Besides, this paper demonstrates, by using numerical experimentation and applying Microsoft Excel Solver for site layout optimisation, how to reduce the complexity in mathematical programming for construction managers.

The original contribution of this paper is the attempt of developing a framework in which all data used for the site layout modelling are collected and processed using a systematic approach, instead of being predetermined, as in many previous studies.

A plant layout in the context of manufacturing facilities design consists of the production areas, manufacturing support areas and personnel areas. In facilities design, plant layout has been determined to be one of the most important elements in the effectiveness of systematic manufacturing operability. This paper describes the development of a split departmental plant layout generation system (LAYSPLIT) in the domain of facilities design to develop layouts that will minimize the material handling costs. The plant layout generation system consists of a data acquisition module, a pair‐wise departmental exchange module, a layout development module, and a graphical representation module. The approach used to develop the system using a split departmental method, and the characteristics of the system are outlined. The advantages of the developed system in terms of facilitating effective operations and increasing productivity in manufacturing environments are discussed. The results obtained from LAYSPLIT are compared with that produced by the MCRAFT system and discussed.

In this study, a novel framework based on deep learning models is presented to assess energy and environmental performance of a given building space layout, facilitating the decision-making process at the early-stage design.

A methodology using an image-based deep learning model called pix2pix is proposed to predict the overall daylight, energy and ventilation performance of a given residential building space layout. The proposed methodology is then evaluated by being applied to 300 sample apartment units in Tehran, Iran. Four pix2pix models were trained to predict illuminance, spatial daylight autonomy (sDA), primary energy intensity and ventilation maps. The simulation results were considered ground truth.

The results showed an average structural similarity index measure (SSIM) of 0.86 and 0.81 for the predicted illuminance and sDA maps, respectively, and an average score of 88% for the predicted primary energy intensity and ventilation representative maps, each of which is outputted within three seconds.

The proposed framework in this study helps upskilling the design professionals involved with the architecture, engineering and construction (AEC) industry through engaging artificial intelligence in human–computer interactions. The specific novelties of this research are: first, evaluating indoor environmental metrics (daylight and ventilation) alongside the energy performance of space layouts using pix2pix model, second, widening the assessment scope to a group of spaces forming an apartment layout at five different floors and third, incorporating the impact of building context on the intended objectives.