Revealing connectivity in residential Architecture: An algorithmic approach to extracting adjacency matrices from floor plans
In today's world, various approaches and parameters exist for designing a plan and determining its spatial, placement. Hence, various modes for identifying crucial locations can be explored when an architectural plan is designed in different dimensions. While designing all these modes takes con...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2024-04-01
|
| Series: | Frontiers of Architectural Research |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2095263523000924 |
| _version_ | 1827318607443394560 |
|---|---|
| author | Mohammad Amin Moradi Omid Mohammadrashidi Navid Niazkar Morteza Rahbar |
| author_facet | Mohammad Amin Moradi Omid Mohammadrashidi Navid Niazkar Morteza Rahbar |
| author_sort | Mohammad Amin Moradi |
| collection | DOAJ |
| description | In today's world, various approaches and parameters exist for designing a plan and determining its spatial, placement. Hence, various modes for identifying crucial locations can be explored when an architectural plan is designed in different dimensions. While designing all these modes takes considerable time, there are numerous potential applications for artificial intelligence (AI) in this domain. This study aims to compute and use an adjacency matrix to generate architectural residential plans. Additionally, it develops a plan generation algorithm in Rhinoceros software, utilizing the Grasshopper plugin to create a dataset of architectural plans. In the following step, the data was entered into a neural network to identify the architectural plan's type, furniture, icons, and use of spaces, which was achieved using YOLOv4, EfficientDet, YOLOv5, DetectoRS, and RetinaNet. The algorithm's execution, testing, and training were conducted using Darknet and PyTorch. The research dataset comprises 12,000 plans, with 70% employed in the training phase and 30% in the testing phase. The network was appropriately trained practically and precisely in relation to an average precision (AP) resulting of 91.50%. After detecting the types of space use, the main research algorithm has been designed and coded, which includes determining the adjacency matrix of architectural plan spaces in seven stages. All research processes were conducted in Python, including dataset preparation, network object detection, and adjacency matrix algorithm design. Finally, the adjacency matrix is given to the input of the proposed plan generator network, which consequently, based on the resulting adjacency, obtains different placement modes for spaces and furniture. |
| first_indexed | 2024-04-25T00:04:56Z |
| format | Article |
| id | doaj.art-876724b2cb2a45e099e61f94234dba2e |
| institution | Directory Open Access Journal |
| issn | 2095-2635 |
| language | English |
| last_indexed | 2024-04-25T00:04:56Z |
| publishDate | 2024-04-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Frontiers of Architectural Research |
| spelling | doaj.art-876724b2cb2a45e099e61f94234dba2e2024-03-14T06:14:26ZengKeAi Communications Co., Ltd.Frontiers of Architectural Research2095-26352024-04-01132370386Revealing connectivity in residential Architecture: An algorithmic approach to extracting adjacency matrices from floor plansMohammad Amin Moradi0Omid Mohammadrashidi1Navid Niazkar2Morteza Rahbar3School of Architecture and Engineering, University College of Rouzbahan, Mazandaran, IranSchool of Architecture, Islamic Azad University, SafaDasht Campus, Tehran, IranA. James Clark School of Engineering, University of Maryland, College Park, MD, USASchool of Architecture and Environmental Design, Iran University of Science and Technology, Tehran, Iran; Corresponding author.In today's world, various approaches and parameters exist for designing a plan and determining its spatial, placement. Hence, various modes for identifying crucial locations can be explored when an architectural plan is designed in different dimensions. While designing all these modes takes considerable time, there are numerous potential applications for artificial intelligence (AI) in this domain. This study aims to compute and use an adjacency matrix to generate architectural residential plans. Additionally, it develops a plan generation algorithm in Rhinoceros software, utilizing the Grasshopper plugin to create a dataset of architectural plans. In the following step, the data was entered into a neural network to identify the architectural plan's type, furniture, icons, and use of spaces, which was achieved using YOLOv4, EfficientDet, YOLOv5, DetectoRS, and RetinaNet. The algorithm's execution, testing, and training were conducted using Darknet and PyTorch. The research dataset comprises 12,000 plans, with 70% employed in the training phase and 30% in the testing phase. The network was appropriately trained practically and precisely in relation to an average precision (AP) resulting of 91.50%. After detecting the types of space use, the main research algorithm has been designed and coded, which includes determining the adjacency matrix of architectural plan spaces in seven stages. All research processes were conducted in Python, including dataset preparation, network object detection, and adjacency matrix algorithm design. Finally, the adjacency matrix is given to the input of the proposed plan generator network, which consequently, based on the resulting adjacency, obtains different placement modes for spaces and furniture.http://www.sciencedirect.com/science/article/pii/S2095263523000924Algorithm designAdjacency matrixGenerate floor planDetection plan |
| spellingShingle | Mohammad Amin Moradi Omid Mohammadrashidi Navid Niazkar Morteza Rahbar Revealing connectivity in residential Architecture: An algorithmic approach to extracting adjacency matrices from floor plans Frontiers of Architectural Research Algorithm design Adjacency matrix Generate floor plan Detection plan |
| title | Revealing connectivity in residential Architecture: An algorithmic approach to extracting adjacency matrices from floor plans |
| title_full | Revealing connectivity in residential Architecture: An algorithmic approach to extracting adjacency matrices from floor plans |
| title_fullStr | Revealing connectivity in residential Architecture: An algorithmic approach to extracting adjacency matrices from floor plans |
| title_full_unstemmed | Revealing connectivity in residential Architecture: An algorithmic approach to extracting adjacency matrices from floor plans |
| title_short | Revealing connectivity in residential Architecture: An algorithmic approach to extracting adjacency matrices from floor plans |
| title_sort | revealing connectivity in residential architecture an algorithmic approach to extracting adjacency matrices from floor plans |
| topic | Algorithm design Adjacency matrix Generate floor plan Detection plan |
| url | http://www.sciencedirect.com/science/article/pii/S2095263523000924 |
| work_keys_str_mv | AT mohammadaminmoradi revealingconnectivityinresidentialarchitectureanalgorithmicapproachtoextractingadjacencymatricesfromfloorplans AT omidmohammadrashidi revealingconnectivityinresidentialarchitectureanalgorithmicapproachtoextractingadjacencymatricesfromfloorplans AT navidniazkar revealingconnectivityinresidentialarchitectureanalgorithmicapproachtoextractingadjacencymatricesfromfloorplans AT mortezarahbar revealingconnectivityinresidentialarchitectureanalgorithmicapproachtoextractingadjacencymatricesfromfloorplans |