Deep learning surrogate models for spatial and visual connectivity

Abstract

Spatial and visual connectivity are important metrics when developing workplace layouts. Calculating those metrics in real time can be difficult, depending on the size of the floor plan being analysed and the resolution of the analyses. This article investigates the possibility of considerably speeding up the outcomes of such computationally intensive simulations by using machine learning to create models capable of identifying the spatial and visual connectivity potential of a space. To that end, we present the entire process of investigating different machine learning models and a pipeline for training them on such task, from the incorporation of a bespoke spatial and visual connectivity analysis engine through a distributed computation pipeline, to the process of synthesizing training data and evaluating the performance of different neural networks.

Generative Layout Modeling using Constraint Graphs

“…Topological statistics S t are specialized to measure the topology of a layout graph [35,55]: Alignment statistics S a measure alignment between all pairs of elements:…”

How do we choose the appropriate deep learning method for our case? A systematic literature review

“…Downloading and finding out more about the packages offered by eclipse can visit https://www.eclipse.org/downloads/packages/release/kepler/sr1/eclipse-ide-java-developers. Tarabishy et al (2020) The outcomes of the entire analysis of the various ML models and the pathways for training ML in various tasks have been quite encouraging to show the potential expansion of ML systems into a number of analyses that require floor plans as input in particular analytical environments like glare, which seems to be a recurring issue in the sector architecture. Deep learning used is a system that is able to and the ability to face the entrepreneurial environment.…”

“…DL includes both supervised and unsupervised architecture Saleem and Chishti (2021a) including there are several algorithms used in several problem solving implementations presented in this review article such as Convolutional Neural Network (CNN) (Kumari et al 2021;Hao et al 2021;Dimililer et al 2021a;Saha et al 2021;Singaravel et al 2019;Bai et al 2020;Tong et al 2020;Hong et al 2020;Sharma and Mir 2020;Lei et al 2020;Maleki et al 2020;Gomez-Fernandez et al 2020;Iqbal and Qureshi 2020;Peddireddy et al 2020;Neb et al 2020;Yamaguchi et al 2019;Tarabishy et al 2020;Gomez-Donoso et al 2017;Qi et al 2017;Qsi et al 2016;Su et al 2015;Maturana and Scherer 2015;Ji et al 2013;Z. Zhang et al 2018;Kumari et al 2021;Z.…”

Self-Organizing Floor Plans

“…Thirdly, computer scientists have found that applications of certain models and algorithms can be tested against a real-case scenario (for example, the design and construction of a building). An example of this is the work that Tarabishy and his colleagues have done on the use of "deep learning surrogate models for spatial and visual connectivity" (Tarabishy et al, 2020). In this, they use a number of ML methods to reduce the computational time needed to simulate the spatial and visual connectivity of a given office space.…”