Papers by Aydan Aghabayli
UMinho Editora eBooks, May 3, 2022
Dissertação de Mestrado Integrado em Arquitetura, com a especialização em Arquitetura apresentada... more Dissertação de Mestrado Integrado em Arquitetura, com a especialização em Arquitetura apresentada na Faculdade de Arquitetura da Universidade de Lisboa para obtenção do grau de Mestre.Portugal e o Azerbaijão tiveram uma forte influência islâmica no passado. Mesmo hoje em dia, podemos experimentar sinais desse património cultural e do impacto tangível e intangível em ambos os países. É perceptível em muitas áreas da mesma forma na arquitetura. Em Portugal, apesar de muitos exemplos de influência da herança islâmica terem sido perdidos ou destruídos, ainda existem em algumas cidades em particular um notável legado de arquitectura e ornamentação. Por outro lado, a situação no Azerbaijão é ligeiramente diferente devido ao fato de que a maioria da população do Azerbaijão é muçulmana. Portanto, ainda existem muitos exemplos vivos de motivos geométricos islâmicos na arquitetura e, eventualmente, uma tradição viva. A presente dissertação é parte de um projeto de pesquisa em andamento intitu...
4º congresso português de ‘Building Information Modelling’ vol. 2 - ptBIM, May 3, 2022
Digitalisation is among prominent concepts in the AEC industry within the scope of Construction 4... more Digitalisation is among prominent concepts in the AEC industry within the scope of Construction 4.0. Effective data management is essential to enable the digitalisation of construction. Converting raw data into knowledge requires the ability to convert data into information by making sense of it in a particular context. Only then information can be converted into knowledge by both humans and machines. As such, this work adopts a learning perspective for machines to learn from data stored in Building Information Modelling (BIM) Models, the modern information management repositories in the sector. This study suggests that BIM Models represent an opportunity to explore large data sets which can improve the industry’s knowledge management and performance. Machine Learning (ML) is a scientific domain including several computational techniques which open new horizons in the learning process, to the extent of finding patterns that are sometimes difficult to be discovered by the human eye and that could insightfully challenge the current construct of AEC. The methodology of the dissertation included a literature review and a case study. A literature review of state-of-the-art applications of ML on BIM or ML to spatial design was performed. It has been observed a lack of extensive works on application ML to spatial design through BIM models. This gap was considered a research opportunity, leading to the development of a case study that intended to test a proposed framework of ML application to BIM models. The steps of implementation of the case study included: (i) extracting data from BIM models; (ii) modifying, filtering and merging the data; (iii) training and testing ML model. Convolutional Neural Network and Graph Neural Network algorithms were used for this case study. As a final output of the application, the automatic labelling of the spaces was idealised. The study concludes that the application of ML from BIM models requires meeting specific criteria, which are yet proven to be a challenge in the context of the sector. Firstly, Machine Learning needs a large amount of input data to operate. Secondly, the data also needs to be appropriately collected, filtered and stored. Thirdly, the data shall be converted into information to facilitate the learning process. In the case study presented, the Space Syntax technique was identified as a linking tool to convert BIM models data into information to be processed by ML algorithms. Notwithstanding the expected hurdles to be overcome in AEC, this study suggests that BIM models, along with the introduction of adequate interoperability measures, can change the paradigm of the industry. The ability to manipulate large amounts of information can facilitate insight and challenge the current mechanisms of information and knowledge management in the industry.
BIM (Building Information Modelling) is a prominent intelligent technology based on a modelling p... more BIM (Building Information Modelling) is a prominent intelligent technology based on a modelling process that facilitates collaboration, design and managing the project during the whole lifecycle. The model can include information on the digital description of every aspect of the built asset [1]. BIM is a complex system that requires careful planning throughout every building design phase and managing stage.
öz sürətli yayılmasının başlangıcında memarlıq simasına sahib deyildi. Dini yaymaq üçün yeni əraz... more öz sürətli yayılmasının başlangıcında memarlıq simasına sahib deyildi. Dini yaymaq üçün yeni ərazilər işğal edən İslam mədəniyyəti yerli mədəniyyətlərin, yaşam tərzlərinin təsirinə məruz qalırdı və əsas etibarilə onlardan istifadə edirdi. Nümunə olaraq günümüzə gəlib çıxan ən qədim məscid olan Qüdsdə yerləşən Qübbətus-Səhranın strukturuna baxmaq yetər və bunun müasir məscidlərdən fərqləndiyini görərik.
Thesis Chapters by Aydan Aghabayli
BIM A+ master's dissertation, 2021
Digitalisation is among prominent concepts in the AEC industry within the scope of Construction 4... more Digitalisation is among prominent concepts in the AEC industry within the scope of Construction 4.0. Effective data management is essential to enable the digitalisation of construction. Converting raw data into knowledge requires the ability to convert data into information by making sense of it in a particular context. Only then information can be converted into knowledge by both humans and machines. As such, this work adopts a learning perspective for machines to learn from data stored in Building Information Modelling (BIM) Models, the modern information management repositories in the sector.
This study suggests that BIM Models represent an opportunity to explore large data sets which can improve the industry’s knowledge management and performance. Machine Learning (ML) is a scientific domain including several computational techniques which open new horizons in the learning process, to the extent of finding patterns that are sometimes difficult to be discovered by the human eye and that could insightfully challenge the current construct of AEC.
The methodology of the dissertation included a literature review and a case study. A literature review of state-of-the-art applications of ML on BIM or ML to spatial design was performed. It has been observed a lack of extensive works on application ML to spatial design through BIM models. This gap was considered a research opportunity, leading to the development of a case study that intended to test a proposed framework of ML application to BIM models. The steps of implementation of the case study included: (i) extracting data from BIM models; (ii) modifying, filtering and merging the data; (iii) training and testing ML model. Convolutional Neural Network and Graph Neural Network algorithms were used for this case study. As a final output of the application, the automatic labelling of the spaces was idealised.
The study concludes that the application of ML from BIM models requires meeting specific criteria, which are yet proven to be a challenge in the context of the sector. Firstly, Machine Learning needs a large amount of input data to operate. Secondly, the data also needs to be appropriately collected, filtered and stored. Thirdly, the data shall be converted into information to facilitate the learning process. In the case study presented, the Space Syntax technique was identified as a linking tool to convert BIM models data into information to be processed by ML algorithms.
Notwithstanding the expected hurdles to be overcome in AEC, this study suggests that BIM models, along with the introduction of adequate interoperability measures, can change the paradigm of the industry. The ability to manipulate large amounts of information can facilitate insight and challenge the current mechanisms of information and knowledge management in the industry.
Portugal and Azerbaijan had a strong Islamic influence in the past. Even nowadays, we can experie... more Portugal and Azerbaijan had a strong Islamic influence in the past. Even nowadays, we can experience signs of this cultural heritage, and the tangible and intangible impact in both countries. It is noticeable in many areas likewise in architecture.
In Portugal, despite many examples of Islamic heritage influence have been lost or destroyed, there still are in some particular cities a remarkable architecture and ornamentation legacy. On the other hand, the situation in Azerbaijan is slightly different due to the fact that the majority of Azerbaijan’s population is Muslim. Therefore, there are still many living examples of Islamic geometric motifs in architecture and eventually, a living tradition.
The present dissertation is part of an ongoing research project entitled “Biomimetics and Digital Morphogenesis” enrolled at the CIAUD Research Centre of the Faculty of Architecture of the University of Lisbon.
The main focus of this work will be given to girih - a particular geometric pattern used in Islamic decoration, which can be found in a wide area from Portugal to Azerbaijan. The geometric patterns in Portugal were used mainly in “azulejos”, "alfarge" and some stucco works, while in Azerbaijan, they are employed in different manners of designing mainly stone decorations and glass decorations on "shebeke" (an art of creating windows consisting of colorful glass and small wooden details attached without glue or nail using).
Nevertheless, all of the decorative elements deployed use a range of symmetries that have now been classified as belonging to distinct mathematical groups. But the subtlety and beauty of the designs are unparalleled in modern mathematical thinking and design.
Thus, our goal is to try to establish a relationship between the survey examples of Islamic geometric patterns in Portugal and Azerbaijan; to assemble a parallel between those decorative elements in both countries; and try to establish if there are some connections, similarities and the levels of correspondence.
Uploads
Papers by Aydan Aghabayli
Thesis Chapters by Aydan Aghabayli
This study suggests that BIM Models represent an opportunity to explore large data sets which can improve the industry’s knowledge management and performance. Machine Learning (ML) is a scientific domain including several computational techniques which open new horizons in the learning process, to the extent of finding patterns that are sometimes difficult to be discovered by the human eye and that could insightfully challenge the current construct of AEC.
The methodology of the dissertation included a literature review and a case study. A literature review of state-of-the-art applications of ML on BIM or ML to spatial design was performed. It has been observed a lack of extensive works on application ML to spatial design through BIM models. This gap was considered a research opportunity, leading to the development of a case study that intended to test a proposed framework of ML application to BIM models. The steps of implementation of the case study included: (i) extracting data from BIM models; (ii) modifying, filtering and merging the data; (iii) training and testing ML model. Convolutional Neural Network and Graph Neural Network algorithms were used for this case study. As a final output of the application, the automatic labelling of the spaces was idealised.
The study concludes that the application of ML from BIM models requires meeting specific criteria, which are yet proven to be a challenge in the context of the sector. Firstly, Machine Learning needs a large amount of input data to operate. Secondly, the data also needs to be appropriately collected, filtered and stored. Thirdly, the data shall be converted into information to facilitate the learning process. In the case study presented, the Space Syntax technique was identified as a linking tool to convert BIM models data into information to be processed by ML algorithms.
Notwithstanding the expected hurdles to be overcome in AEC, this study suggests that BIM models, along with the introduction of adequate interoperability measures, can change the paradigm of the industry. The ability to manipulate large amounts of information can facilitate insight and challenge the current mechanisms of information and knowledge management in the industry.
In Portugal, despite many examples of Islamic heritage influence have been lost or destroyed, there still are in some particular cities a remarkable architecture and ornamentation legacy. On the other hand, the situation in Azerbaijan is slightly different due to the fact that the majority of Azerbaijan’s population is Muslim. Therefore, there are still many living examples of Islamic geometric motifs in architecture and eventually, a living tradition.
The present dissertation is part of an ongoing research project entitled “Biomimetics and Digital Morphogenesis” enrolled at the CIAUD Research Centre of the Faculty of Architecture of the University of Lisbon.
The main focus of this work will be given to girih - a particular geometric pattern used in Islamic decoration, which can be found in a wide area from Portugal to Azerbaijan. The geometric patterns in Portugal were used mainly in “azulejos”, "alfarge" and some stucco works, while in Azerbaijan, they are employed in different manners of designing mainly stone decorations and glass decorations on "shebeke" (an art of creating windows consisting of colorful glass and small wooden details attached without glue or nail using).
Nevertheless, all of the decorative elements deployed use a range of symmetries that have now been classified as belonging to distinct mathematical groups. But the subtlety and beauty of the designs are unparalleled in modern mathematical thinking and design.
Thus, our goal is to try to establish a relationship between the survey examples of Islamic geometric patterns in Portugal and Azerbaijan; to assemble a parallel between those decorative elements in both countries; and try to establish if there are some connections, similarities and the levels of correspondence.
This study suggests that BIM Models represent an opportunity to explore large data sets which can improve the industry’s knowledge management and performance. Machine Learning (ML) is a scientific domain including several computational techniques which open new horizons in the learning process, to the extent of finding patterns that are sometimes difficult to be discovered by the human eye and that could insightfully challenge the current construct of AEC.
The methodology of the dissertation included a literature review and a case study. A literature review of state-of-the-art applications of ML on BIM or ML to spatial design was performed. It has been observed a lack of extensive works on application ML to spatial design through BIM models. This gap was considered a research opportunity, leading to the development of a case study that intended to test a proposed framework of ML application to BIM models. The steps of implementation of the case study included: (i) extracting data from BIM models; (ii) modifying, filtering and merging the data; (iii) training and testing ML model. Convolutional Neural Network and Graph Neural Network algorithms were used for this case study. As a final output of the application, the automatic labelling of the spaces was idealised.
The study concludes that the application of ML from BIM models requires meeting specific criteria, which are yet proven to be a challenge in the context of the sector. Firstly, Machine Learning needs a large amount of input data to operate. Secondly, the data also needs to be appropriately collected, filtered and stored. Thirdly, the data shall be converted into information to facilitate the learning process. In the case study presented, the Space Syntax technique was identified as a linking tool to convert BIM models data into information to be processed by ML algorithms.
Notwithstanding the expected hurdles to be overcome in AEC, this study suggests that BIM models, along with the introduction of adequate interoperability measures, can change the paradigm of the industry. The ability to manipulate large amounts of information can facilitate insight and challenge the current mechanisms of information and knowledge management in the industry.
In Portugal, despite many examples of Islamic heritage influence have been lost or destroyed, there still are in some particular cities a remarkable architecture and ornamentation legacy. On the other hand, the situation in Azerbaijan is slightly different due to the fact that the majority of Azerbaijan’s population is Muslim. Therefore, there are still many living examples of Islamic geometric motifs in architecture and eventually, a living tradition.
The present dissertation is part of an ongoing research project entitled “Biomimetics and Digital Morphogenesis” enrolled at the CIAUD Research Centre of the Faculty of Architecture of the University of Lisbon.
The main focus of this work will be given to girih - a particular geometric pattern used in Islamic decoration, which can be found in a wide area from Portugal to Azerbaijan. The geometric patterns in Portugal were used mainly in “azulejos”, "alfarge" and some stucco works, while in Azerbaijan, they are employed in different manners of designing mainly stone decorations and glass decorations on "shebeke" (an art of creating windows consisting of colorful glass and small wooden details attached without glue or nail using).
Nevertheless, all of the decorative elements deployed use a range of symmetries that have now been classified as belonging to distinct mathematical groups. But the subtlety and beauty of the designs are unparalleled in modern mathematical thinking and design.
Thus, our goal is to try to establish a relationship between the survey examples of Islamic geometric patterns in Portugal and Azerbaijan; to assemble a parallel between those decorative elements in both countries; and try to establish if there are some connections, similarities and the levels of correspondence.