Cumincad : CUMINCAD Papers : Search Results

CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design
supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures

PDF papers
References

Hits 1 to 15 of 15

Reformat results as: short short into frame detailed detailed into frame

_id	acadia21_70
id	acadia21_70
authors	McAndrew, Claire; Jaschke, Clara; Retsin, Gilles; Saey, Kevin; Claypool, Mollie; Parissi, Danaë
year	2021
title	House Block
doi	https://doi.org/10.52842/conf.acadia.2021.070
source	ACADIA 2021: Realignments: Toward Critical Computation [Proceedings of the 41st Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 979-8-986-08056-7]. Online and Global. 3-6 November 2021. edited by B. Bogosian, K. Dörfler, B. Farahi, J. Garcia del Castillo y López, J. Grant, V. Noel, S. Parascho, and J. Scott. 70-75.
summary	House Block was a temporary housing prototype in East London, UK from April to May 2021. The project constituted the most recent in a series of experiments developing Automated Architecture (AUAR) Labs’ discrete framework for housing production, one which repositions the architect as curator of a system and enables participants to engage with active agency. Recognizing that there is a knowledge gap to be addressed for this reconfiguration of practices to take form, this project centred on making automation and its potential for local communities tangible. This sits within broader calls advocating for a more material alignment of inclusive design with makers and 21st Century making in practice (see, for example, Luck 2018). House Block was designed and built using AUAR’s discrete housing system consisting of a kit of parts, known as Block Type A. Each block was CNC milled from a single sheet of plywood, assembled by hand, and then post-tensioned on site. Constructed from 270 identical blocks, there are no predefined geometric types or hierarchy between parts. The discrete enables an open-ended, adaptive system where each block can be used as a column, floor slab, wall, or stair—allowing for disconnection, reconfiguration, and reassembly (Retsin 2019). The democratisation of design and production that defines the discrete creates points for alternative value systems to enter, for critical realignments in architectural production.
series	ACADIA
type	project
email
last changed	2023/10/22 12:06

_id	acadia21_340
id	acadia21_340
authors	Zhang, Yu; Tatarintseva, Liz; Clewlow, Tom; Clark, Ed; Botsford, Gianni; Shea, Kristina
year	2021
title	Mortarless Compressed Earth Block Dwellings
doi	https://doi.org/10.52842/conf.acadia.2021.340
source	ACADIA 2021: Realignments: Toward Critical Computation [Proceedings of the 41st Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 979-8-986-08056-7]. Online and Global. 3-6 November 2021. edited by B. Bogosian, K. Dörfler, B. Farahi, J. Garcia del Castillo y López, J. Grant, V. Noel, S. Parascho, and J. Scott. 340-345.
summary	This project develops a template design and an adaptive fabrication process for sustainable Compressed Earth Block (CEB) dwellings for low-income countries. Most existing projects (Wilton et al. 2019; WASP 2021) on sustainable dwellings involve high-tech equipment or skilled workers on-site. This project integrates digital technologies into the design and fabrication processes to reduce these requirements and make the design compatible with conventional construction methods that are actively adopted in low-income countries using minimum infrastructure, skilled labor, and investment.
series	ACADIA
type	project
email
last changed	2023/10/22 12:06

_id	acadia20_136p
id	acadia20_136p
authors	López Lobato, Déborah; Charbel, Hadin
year	2020
title	Foll(i)cle
source	ACADIA 2020: Distributed Proximities / Volume II: Projects [Proceedings of the 40th Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-95253-6]. Online and Global. 24-30 October 2020. edited by M. Yablonina, A. Marcus, S. Doyle, M. del Campo, V. Ago, B. Slocum. 136-141
summary	In the early months of 2019, air pollution in Bangkok reached a record high, bringing national and international attention to the air quality in the South East Asian cosmopolitan. Although applications such as real-time pollution maps provide an environmental reading from the exterior, such information reveals the ‘here and now,’ where its record is inevitably lost through the ‘refreshing’ process of the live update and does not take increment and accumulation as factors to consider. The project was conceived around understanding the human body as precisely that medium that resists classification as either an interior or exterior environment that inherently performs as an impressionable record of its surroundings. Can a city’s toxicity be read through its living constituents? Can the living bodies that dwell, navigate, breathe, and process habitable environments be accessed? Can architecture retain a degree of independence while also performing as a beacon for the collective? Along this line of questioning, it was found that human hair can be transformed from a material that is effortlessly and continuously grown, cut, stylized, and discarded, and instead be intercepted and used in the production of public information gathering. Foll(i)cle is a collective being made of discarded human hair. Performing as a parliament for collectivity embedded with a protocol; the hairy pavilion invites the public in and presents them with a device at the center that hosts all the necessary equipment and information for anonymously and voluntarily providing hair samples for heavy metal analysis, the data of which is used in making a publically accessible toxi-cartography. Although humans are the primary subject for this study, the results suggest that extending the methodology to non-humans could prove useful in reading urban toxicity through various life forms.
series	ACADIA
type	project
email
last changed	2021/10/26 08:03

_id	acadia21_76
id	acadia21_76
authors	Smith, Rebecca
year	2021
title	Passive Listening and Evidence Collection
doi	https://doi.org/10.52842/conf.acadia.2021.076
source	ACADIA 2021: Realignments: Toward Critical Computation [Proceedings of the 41st Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 979-8-986-08056-7]. Online and Global. 3-6 November 2021. edited by B. Bogosian, K. Dörfler, B. Farahi, J. Garcia del Castillo y López, J. Grant, V. Noel, S. Parascho, and J. Scott. 76-81.
summary	In this paper, I present the commercial, urban-scale gunshot detection system ShotSpotter in contrast with a range of ecological sensing examples which monitor animal vocalizations. Gunshot detection sensors are used to alert law enforcement that a gunshot has occurred and to collect evidence. They are intertwined with processes of criminalization, in which the individual, rather than the collective, is targeted for punishment. Ecological sensors are used as a “passive” practice of information gathering which seeks to understand the health of a given ecosystem through monitoring population demographics, and to document the collective harms of anthropogenic change (Stowell and Sueur 2020). In both examples, the ability of sensing infrastructures to “join up and speed up” (Gabrys 2019, 1) is increasing with the use of machine learning to identify patterns and objects: a new form of expertise through which the differential agendas of these systems are implemented and made visible. I trace the differential agendas of these systems as they manifest through varied components: the spatial distribution of hardware in the existing urban environment and / or landscape; the software and other informational processes that organize and translate the data; the visualization of acoustical sensing data; the commercial factors surrounding the production of material components; and the apps, platforms, and other forms of media through which information is made available to different stakeholders. I take an interpretive and qualitative approach to the analysis of these systems as cultural artifacts (Winner 1980), to demonstrate how the political and social stakes of the technology are embedded throughout them.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	acadia19_40
id	acadia19_40
authors	Garcia del Castillo y López, Jose Luis
year	2019
title	Robot Ex Machina
doi	https://doi.org/10.52842/conf.acadia.2019.040
source	ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-59179-7] (The University of Texas at Austin School of Architecture, Austin, Texas 21-26 October, 2019) pp. 40-49
summary	Industrial robotic arms are increasingly present in digital fabrication workflows due to their robustness, degrees of freedom, and potentially large scale. However, the range of possibilities they provide is limited by their typical software control paradigms, specifically offline programming. This model requires all the robotic instructions to be pre-defined before execution, a possibility only affordable in highly predictable environments. But in the context of architecture, design and art, it can hardly accommodate more complex forms of control, such as responding to material feedback, adapting to changing conditions on a construction site, or on-the-fly decision-making. We present Robot Ex Machina, an open-source computational framework of software tools for real-time robot programming and control. The contribution of this framework is a paradigm shift in robot programming models, systematically providing a platform to enable real-time interaction and control of mechanical actuators. Furthermore, it fosters programming styles that are reactive to, rather than prescriptive about, the state of the robot. We argue that this model is, compared to traditional offline programming, beneficial for creative individuals, as its concurrent nature and immediate feedback provide a deeper and richer set of possibilities, facilitates experimentation, flow of thought, and creative inquiry. In this paper, we introduce the framework, and discuss the unifying model around which all its tools are designed. Three case studies are presented, showcasing how the framework provides richer interaction models and novel outcomes in digital making. We conclude by discussing current limitations of the model and future work.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:51

_id	acadia19_576
id	acadia19_576
authors	García del Castillo y López, Jose Luis; Bechthold, Martin; Seibold, Zach; Mhatre, Saurabh; Alhadidi, Suleiman
year	2019
title	Janus Printing
doi	https://doi.org/10.52842/conf.acadia.2019.576
source	ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-59179-7] (The University of Texas at Austin School of Architecture, Austin, Texas 21-26 October, 2019) pp. 576-585
summary	The benefits of additive manufacturing technologies for the production of customized construction elements has been well documented for several decades. Multi-material additive manufacturing (MM-AM) enhances these capacities by introducing region-specific characteristics to printed objects. Several examples of the production of multi-material assemblies, including functionally-graded materials (FGMs) exist at the architectural scale, but none are known for ceramics. Factors limiting the development and application of this production method include the cost and complexity of existing MM-AM machinery, and the lack of a suitable computational workflow for the production of MM-AM ceramics, which often relies on a continuous linear toolpath. We present a method for the MM-AM of paste-based ceramics that allows for unique material expressions with relatively simple end-effector design. By borrowing methods of co-extrusion found in other industries and incorporating a 4th axis of motion into the printing process, we demonstrate a precisely controlled MM-AM deposition strategy for paste-based ceramics. We present a computational workflow for the generation of toolpaths, and describe full-body tiles and 3D artifacts that can be produced using this method. Future process refinements include the introduction of more precise control of material gradation and refinements to material composition for increased element functionality.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:51

_id	ecaadesigradi2019_393
id	ecaadesigradi2019_393
authors	Wendell, Augustus, Ozludil, Burcak and López-Salas, Estefanía
year	2019
title	Calculating Movement - An Agent Based Modeling System for Historical Studies
doi	https://doi.org/10.52842/conf.ecaade.2019.1.541
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 541-550
summary	Simulating human movement and actions in historical spaces/landscapes is a complex task. It requires not only the recreation of spaces that no longer exist, but more challenging the recovery of actions performed in the past. These actions can provide insights into important aspects such as how people inhabited, used, perceived, lived, sensed, and shaped these spaces. This research aims to show a framework to approach studying human movement, using an Agent Based Modeling (ABM) system. Our ABM tool has methods for creating, managing, and choreographing the movement of agents through 3D models. A number of iterative tests, both agent-to-agent and agent-to-model, enable the system to produce scholarly quantitative data in historical spaces. We highlight the use of this system through two case studies, one at an architectural scale and the other at landscape scale.
keywords	Agent Based Modeling; Art and Architectural History; Simulation
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:58

_id	caadria2019_117
id	caadria2019_117
authors	Deniz Kiraz, Leyla and Kocaturk, Tuba
year	2019
title	Integrating User-Behaviour as Performance Criteria in Conceptual Parametric Design
doi	https://doi.org/10.52842/conf.caadria.2019.1.215
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 1, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 215-224
summary	Prediction of user behaviour has always been problematic in architectural design. Several methods have already been developed and explored to model human behaviour in architecture. However, the majority of these methods are implemented during post-design evaluation where the insights obtained can only be implemented in a limited capacity. There is an apparent gap and opportunity, in current research and practice, to embed behaviour simulations directly into the conceptual design process. The proposed paper (research) aims to fill this gap. This paper will report on the results of a recently completed research exploring the integration process of Agent Based Modelling into the conceptual design process, using a parametric design approach. The research resulted in the development of a methodological framework for the integration of behavioural parameters into the explorative stages of the early design process. This paper also offers a categorisation and critical evaluation of existing Agent Based Modelling applications in current research and practice, which leads to the formulation of possible pathways for future implementation.
keywords	Performance Based Design; Generative Design; Behaviour Modelling; Agent Based Modelling; Parametric Design
series	CAADRIA
email
last changed	2022/06/07 07:55

_id	ecaade2020_138
id	ecaade2020_138
authors	Patel, Sayjel Vijay, Tchakerian, Raffi, Lemos Morais, Renata, Zhang, Jie and Cropper, Simon
year	2020
title	The Emoting City - Designing feeling and artificial empathy in mediated environments
doi	https://doi.org/10.52842/conf.ecaade.2020.2.261
source	Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 2, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 261-270
summary	This paper presents a theoretical blueprint for implementing artificial empathy into the built environment. Transdisciplinary design principles have oriented the creation of a new model for autonomous environments integrating psychology, architecture, digital media, affective computing and interactive UX design. 'The Emoting City', an interactive installation presented at the 2019 Shenzhen Bi-City Biennale of Urbanism/Architecture, is presented as a first step to explore how to engage AI-driven sensing by integrating human perception, cognition and behaviour in a real-world scenario. The approach described encompasses two main elements: embedded cyberception and responsive surfaces. Its human-AI interface enables new modes of blended interaction that are conducive to self-empathy and insight. It brings forth a new proposition for the development of sensing systems that go beyond social robotics into the field of artificial empathy. The installation innovates in the design of seamless affective computing that combines 'alloplastic' and 'autoplastic' architectures. We believe that our research signals the emergence of a potential revolution in responsive environments, offering a glimpse into the possibility of designing intelligent spaces with the ability to sense, inform and respond to human emotional states in ways that promote personal, cultural and social evolution.
keywords	Artificial Intelligence; Responsive Architecture; Affective Computation; Human-AI Interfaces; Artificial Empathy
series	eCAADe
email
last changed	2022/06/07 07:59

_id	sigradi2023_39
id	sigradi2023_39
authors	Borges, Marina, Karantino, Lucas and Gorges, Diego
year	2023
title	Walkability: Digital Parametric Process for Analyzing and Evaluating Walkability Criteria in Peripheral Central Regions of Belo Horizonte
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 397–408
summary	According to one of the Sustainable Development Goals (UN, 2018), it is important for cities to be inclusive, safe, resilient, and sustainable. Therefore, it is necessary to value pedestrians and consequently active mobility, giving priority to the concepts of the Transportation Oriented Development (TOD) methodology. Although the Master Plan (BELO HORIZONTE, 2019) proposes that areas located in regional centralities are enhancing active mobility, can residents actually benefit from these resources at a walkable distance to access basic services? Thus, the aim of this research is to utilize digital technologies to visualize, analyze, and assess pedestrians' access conditions to commerce and basic services, identifying areas lacking infrastructure. The goal is for the model to serve as a reference for the development of public policies. To achieve this, metadata was used for parametric modeling to study walkability in the peripheral region of the city of Belo Horizonte.
keywords	Walkability, Urban Data Analysis, Urban Design, Parametric Urbanism, Algorithmic Logic
series	SIGraDi
email
last changed	2024/03/08 14:07

_id	ecaadesigradi2019_016
id	ecaadesigradi2019_016
authors	Eloy, Sara, Dias, Luís, Ourique, Lázaro and Sales Dias, Miguel
year	2019
title	Home Mobility Hazards Detected via Object Recognition in Augmented Reality
doi	https://doi.org/10.52842/conf.ecaade.2019.2.415
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 2, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 415-422
summary	We present an Environmental Analysis and Safety Advisor system capable of identify the environmental barriers and hazards found in the homes of elderly people. This augmented reality tool runs on a portable computing device and can be used by informal and formal caregivers without specific knowledge of Accessible Design, to evaluate the safeness of an elderly home environment, ensuring that potential fall hazards are detected and corrected. The system recognizes specific indoor elements of the house (e.g. arm-chair, bed, chair), and then computes and analyses their mutual distances in the environment so that a warning of hazard is emitted in case of need (e.g. loose cable, not enough space to pass a wheelchair). In this context, we implemented object recognition at the category level of miniature versions of real sized furniture and the determination of the distance between neighboring objects, signaling if it is below a certain threshold value. Environmental Analysis tool can then recognize furniture and measure the distance between two furniture elements enabling the system to pop up an alert sign if the space left does not guarantee good accessibility.
keywords	augmented reality; computer vision; object category recognition; ambient assisted living
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:55

_id	ecaadesigradi2019_100
id	ecaadesigradi2019_100
authors	Henriques, Gonçalo Castro, Bueno, Ernesto, Lenz, Daniel and Sardenberg, Victor
year	2019
title	Generative Systems:Intertwining Physical, Digital and Biological Processes, a case study
doi	https://doi.org/10.52842/conf.ecaade.2019.1.025
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 25-34
summary	The fourth Industrial Revolution is characterised by the computational fusion of physical, digital and biological systems. Increasing information in terms of size, speed and scope exponentially. This fusion requires improved, if not new, tools and methods to deal with complexity and information processing. By opening Generative Systems to interact with the context, we believe that they can develop solutions that are more adequate for our time. This research began with a literature review about generative systems and their application to solve problems. We then selected the tools, Cellular Automata, L-Systems, Genetic Algorithms and Shape Grammar, and thought about how to translate these original mathematical tools to specific design situations. We tested the application of these tools and methods in a workshop, implementing recursive loops to open these techniques to interference. Analysing the empirical results made us revise our design thinking, relying on the study of complexity to understand how these techniques can be more context-aware, so we can make design evolve. Finally, we present a comparative framework analyses that interlaces techniques and methods, so in the future we can merge physical, digital and biological information.
keywords	generative systems; design thinking; complexity; context interaction; recursion
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:49

_id	sigradi2023_416
id	sigradi2023_416
authors	Machado Fagundes, Cristian Vinicius, Miotto Bruscato, Léia, Paiva Ponzio, Angelica and Chornobai, Sara Regiane
year	2023
title	Parametric environment for internalization and classification of models generated by the Shap-E tool
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 1689–1698
summary	Computing has been increasingly employed in design environments, primarily to perform calculations and logical decisions faster than humans could, enabling tasks that would be impossible or too time-consuming to execute manually. Various studies highlight the use of digital tools and technologies in diverse methods, such as parametric modeling and evolutionary algorithms, for exploring and optimizing alternatives in architecture, design, and engineering (Martino, 2015; Fagundes, 2019). Currently, there is a growing emergence of intelligent models that increasingly integrate computers into the design process. Demonstrating great potential for initial ideation, artificial intelligence (AI) models like Shap-E (Nichol et al., 2023) by OpenAI stand out. Although this model falls short of state-of-the-art sample quality, it is among the most efficient orders of magnitude for generating three-dimensional models through AI interfaces, offering practical balance for certain use cases. Thus, aiming to explore this gap, the presented study proposes an innovative design agency framework by employing Shap-E connected with parametric modeling in the design process. The generation tool has shown promising results; through generations of synthetic views conditioned by text captions, its final output is a mesh. However, due to the lack of topological information in models generated by Shap-E, we propose to fill this gap by transferring data to a parametric three-dimensional surface modeling environment. Consequently, this interaction's use aims to enable the transformation of the mesh into quantifiable surfaces, subject to collection and optimization of dimensional data of objects. Moreover, this work seeks to enable the creation of artificial databases through formal categorization of parameterized outputs using the K-means algorithm. For this purpose, the study methodologically orients itself in a four-step exploratory experimental process: (1) creation of models generated by Shap-E in a pressing manner; (2) use of parametric modeling to internalize models into the Grasshopper environment; (3) generation of optimized alternatives using the evolutionary algorithm (Biomorpher); (4) and classification of models using the K-means algorithm. Thus, the presented study proposes, through an environment of internalization and classification of models generated by the Shap-E tool, to contribute to the construction of a new design agency methodology in the decision-making process of design. So far, this research has resulted in the generation and classification of a diverse set of three-dimensional shapes. These shapes are grouped for potential applications in machine learning, in addition to providing insights for the refinement and detailed exploration of forms.
keywords	Shap-E, Parametric Design, Evolutionary Algorithm, Synthetic Database, Artificial Intelligence
series	SIGraDi
email
last changed	2024/03/08 14:09

_id	sigradi2023_234
id	sigradi2023_234
authors	Santos, Ítalo, Andrade, Max, Zanchettin, Cleber and Rolim, Adriana
year	2023
title	Machine learning applied in the evaluation of airport projects in Brazil based on BIM models
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 875–887
summary	In a country with continental dimensions like Brazil, air transport plays a strategic role in the development of the country. In recent years, initiatives have been promoted to boost the development of air transport, among which the BIM BR strategy stands out, instituted by decree n-9.983 (2019), decree n-10.306 (2020) and more recently, the publication of the airport design manual (SAC, 2021). In this context, this work presents partial results of a doctoral research based on the Design Science Research (DSR) method for the application of Machine Learning (ML) techniques in the Artificial Intelligence (AI) subarea, aiming to support SAC airport project analysts in the phase of project evaluation. Based on a set of training and test data corresponding to airport projects, two ML algorithms were trained. Preliminary results indicate that the use of ML algorithms enables a new scenario to be explored by teams of airport design analysts in Brazil.
keywords	Airports, Artificial intelligence, BIM, Evaluation, Machine learning.
series	SIGraDi
email
last changed	2024/03/08 14:07

_id	ecaadesigradi2019_171
id	ecaadesigradi2019_171
authors	Uzun, Can and Çolako?lu, Meryem Birgül
year	2019
title	Architectural Drawing Recognition - A case study for training the learning algorithm with architectural plan and section drawing images
doi	https://doi.org/10.52842/conf.ecaade.2019.2.029
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 2, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 29-34
summary	This paper aims to develop a case study for training an algorithm to recognize architectural drawings. In order to succeed that, the algorithm is trained with labeled pixel-based, architectural drawing (plan and section) dataset. During the training process, transfer learning (pre-training model) is applied. The supervised learning and convolutional neural network are utilized. After certain iterations, the algorithm builds awareness and can classify pixel-based plan and section drawings. When the algorithm is shown a section that is not produced with conventional drawing technic but through hybrid technics, it could predict the drawing class correctly with %80 of accuracy. On the other hand, some of the algorithm prediction is misoriented. We examined this prediction problem in the discussion section. The results illustrate that neural networks are successful in training algorithms to recognize and classify pixel-based architectural drawings. But for a highly accurate algorithm prediction, the dataset of the drawing images must be ordered, according to sample resolution, sample size and sample coherence for the dataset.
keywords	Classification Algorithm; Pixel-Based Architectural Drawing Recognition; Plan; Section
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:57

No more hits.