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 20 of 17537

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

_id	ef83
authors	Liu, A.M.M.
year	1999
title	Residential satisfaction in housing estates: a Hong Kong perspective
source	Automation in Construction 8 (4) (1999) pp. 511-524
summary	Post-occupancy evaluation (POE) has been developed to address the problem of acquiring feedback from the occupants who are, arguably, in the best position to provide information for a future design database. This paper presents a study of the factors (on both physical and social levels), which influence residential satisfaction of a sample of occupants in a chosen residential area in Hong Kong; factor analysis and multiple regression were carried out on the data. A comparison is also made of the perceived factors of dissatisfaction amongst the public and private housing occupants. It is suggested that a wider systematic coverage of the subject through investigative and diagnostic POE should be carried out in Hong Kong.
series	journal paper
more	http://www.elsevier.com/locate/autcon
last changed	2003/05/15 21:22

_id	caadria2018_103
id	caadria2018_103
authors	Liu, Chang, Zhang, Xu and Nagakura, Takehiko
year	2018
title	PanoFrame: A Lightweight Panoramic Video Editing Tool for Storytelling with Spatial Content
source	T. Fukuda, W. Huang, P. Janssen, K. Crolla, S. Alhadidi (eds.), Learning, Adapting and Prototyping - Proceedings of the 23rd CAADRIA Conference - Volume 2, Tsinghua University, Beijing, China, 17-19 May 2018, pp. 567-576
doi	https://doi.org/10.52842/conf.caadria.2018.2.567
summary	As low-cost panoramic cameras become prevalent among non-professional consumers, an easy-to-use panoramic video editing tool is required for emerging storytellers. This paper proposes a lightweight online panoramic video editing tool for storytelling and explores a method of interpreting the same spatial content from different perspectives with panoramic videos. We conducted three experiments using different groups of participants to test how people create, understand, and interact with a panoramic video story in the proposed tool. The results reveal that this tool enables storytellers to work collaboratively and create multiple narratives from a panoramic video, and the generated panoramic video narratives are also more attractive to audiences than the raw video. This tool has the potential to be an ever-growing crowdsourcing community with a database of multiple narratives and creates opportunities for designers to record, learn about and present architectural and urban space from multiple perspectives.
keywords	Storytelling; panoramic video; spatial content; multiple perspective narrative; crowdsourcing
series	CAADRIA
email
last changed	2022/06/07 07:59

_id	ecaade2017_067
id	ecaade2017_067
authors	Liu, Chenjun, Wang, Tsung-Hsien, Meagher, Mark and Peng, Chengzhi
year	2017
title	Feather-inspired social media data processing for generating developable surfaces: Prototyping an affective architecture - Prototyping an affective architecture
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 1, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 181-190
doi	https://doi.org/10.52842/conf.ecaade.2017.1.181
summary	This paper presents the development of an interactive installation intended as a prototype of experimental affective architecture connected with social media data processing. Social moods and emotions are now spread more widely and faster than ever before due to pervasive uses of social media platforms. We explore how data processing of users' expressions and sharing of moods/emotions through social media can become a source of influences on shaping the form and behaviour of interactive architecture. The interactive prototyping method includes (1) a feather-inspired data-to-shape rule system together with the ShapeOp Library for generating strips as developable surfaces, (2) a physical computing platform built with Arduino micro-processor and shape memory alloy springs for actuation, and (3) physical model-making. As a prototype of social media aware affective architecture, an interactive installation design is proposed for a campus space where the actuation of the strip installation is linked to data processing of Twitter messages collated from users on campus. We reflect on the prototyping methodology and the implications of an architecture affected by people's expression of moods/emotions through social media.
keywords	social media data processing; developable surfaces; interactive prototyping; shape memory alloy; elastic morphing; ShapeOp
series	eCAADe
email
last changed	2022/06/07 07:59

_id	caadria2020_023
id	caadria2020_023
authors	Liu, Chenjun
year	2020
title	Double Loops Parametric Design of Surface Steel Structure Based on Performance and Fabrication
source	D. Holzer, W. Nakapan, A. Globa, I. Koh (eds.), RE: Anthropocene, Design in the Age of Humans - Proceedings of the 25th CAADRIA Conference - Volume 1, Chulalongkorn University, Bangkok, Thailand, 5-6 August 2020, pp. 23-33
doi	https://doi.org/10.52842/conf.caadria.2020.1.023
summary	In intelligent epoch, automatic parameter design systems reduce the requirements of the skills needed to create objects. The creator only needs to select the most perceptual primitive form to automatically generate the data system that iterates to the most efficient solution. In this paper, a method of combining performance driven optimization with parametric design is proposed. The iterative evolution is under the control of performance loop and fabrication loop, which makes all the data provided by parametric design in a practical project available for exploring structural analysis and digital prefabrication. Related to the case of surface steel structure, parametric optimization is not limited to a set of shape types or design problems, it would be based on the generality and built-in characteristics of parametric modelling environment in the most convenient and flexible way. (Rolvink et al. 2010)And the given parameters would be fed back on geometric structure, performance indicators, and design variables, so that designers can easily and effectively coordinate and try different solutions. The system transforms the generated data into machine language so that the process including design, analysis, manufacturing, and construction can maintain the orthogonal persistence of the data.
keywords	parametric design; component prefabrication; curved steel structure; performance driven
series	CAADRIA
email
last changed	2022/06/07 07:59

_id	caadria2009_092
id	caadria2009_092
authors	Liu, Chun-Hung; Chang-Franw Lee
year	2009
title	The Design of a Mobile Navigation System Based on QR Codes for Historic Buildings
source	Proceedings of the 14th International Conference on Computer Aided Architectural Design Research in Asia / Yunlin (Taiwan) 22-25 April 2009, pp. 103-112
doi	https://doi.org/10.52842/conf.caadria.2009.103
summary	Due to the rapid development of mobile and compact electronic devices such as PDAs and smart phones, designers and developers now have to consider user mobility and the dynamic context of use in the design of interactive systems. In this study, literatures associated with mobile navigation systems in museums and historic buildings are first reviewed in order to understand the features, advantages, and drawbacks of current mobile navigation technology. The feasibility of applying QR codes in the navigation of historic buildings is then discussed, and the mobile navigation principles mentioned in previous literatures are applied in our proposed system. A number of common problems are encountered in the navigation of local historic buildings or museums. Visitors (1) cannot understand what makes an exhibited item a work of art; (2) do not know where to start or how to get started; (3) feel rushed by guides during the guided tour; and (4) find that the audio guide is not clear enough. Managers of historic buildings or museums are generally concerned about (1) the high cost of constructing a mobile navigation environment; (2) possible damage to devices; and (3) the cost of device maintenance. This study attempts to solve the above issues by constructing an affordable digital navigation environment that enables users to clearly understand each exhibited item and its location.
keywords	Mobile navigation; QR code; historic buildings
series	CAADRIA
email
last changed	2022/06/07 07:59

_id	4e6e
authors	Liu, Clive K. and Eastman, Charles M.
year	1981
title	Object Grammars : Language for the Generation of Masonry Designs
source	20 p. ; ill April, 1981. includes bibliography.
summary	Bricks, one of the oldest manufactured building materials, are used extensively in construction. Usually they are built into wall assemblies. In this paper, the construction of traditional masonry designs are investigated. Object grammars are defined for the recursive generation of the 3 dimensional wall designs. Also, the uses of object grammars are discussed
keywords	shape grammars, objects, synthesis, assemblies, architecture, applications
series	CADline
email
last changed	2003/06/02 13:58

_id	c327
authors	Liu, Clive K.
year	1981
title	A Graphic Processor for Computer-Aided Engineering Drawing
source	October, 1981. 7 p
summary	A drafting system whose purpose of is to provide an advanced tool for teaching engineering drawing and as a production tool for designers who regularly produce engineering drawings is described. The graphic processor is part of the system, which incorporates a set of operations that produce and manipulate graphic entities and that require graphic entities as operands. This paper examines the issues of constructing such a processor. Representations are proposed for 2D graphic objects, including points, line segments and segments generated by conic sections; which are predefined data types in the system. The geometric primitive operators take these objects as arguments and produce other graphic objects, and allow users to build up various construction operators and drawings with the same flexibility and generality allowed in, say, descriptive geometry. These operators, which are functions, can be combined as macro expressions that executed by the processor. This environment allows users to define their own macros for various tasks
keywords	CAD, drafting, education, tools
series	CADline
last changed	2003/06/02 13:58

_id	8c95
authors	Liu, Clive K.
year	1984
title	Drawings as Models for Design: A Computer Drawing System to Build Models Supporting Design Process through Abstractions
source	Carnegie Mellon University, Pittsburgh
summary	A general design process can be characterized by the sequence of defining various abstract objects used to represent the artifact. For example, designers use various abstractions (dclined as abstrnct objects), such as graphs, polygons, etc., to represent the artifact. As design evolves, these abstract objects will be transformed into a definition (eg. of a building) detailed enough to allow manufacturing and to determine that the result will perform as desired. This thesis is concerned with providing a computer drawing system that could support various abstractions in the design process and allow various representations of the design to be processed and interpreted. A precise drawing contains not only the shape information, but also conveys many topological and geometric relations that its elements must hold to correspond to the arbfact in reality. For many operations during design, one wants these type of relations to be maintained. Other than the drawing being an iconic model, these relations are the semantics of the drawing and, if embedded in the drawing, imbue it with many characteristics of a symbolic model. Current CAD systems have no or limited mechanisms for embedding such relations in a drawing. It is my intent to demonstrate that drawings, especially for shape (both topologV and geometry) information, can be defined as various abstract objects during design process. Therefore, drawings are used as models to represent the artifact. When a model is manipulated, relations defined in the model are maintained.
series	thesis:PhD
last changed	2003/02/12 22:37

_id	acadia19_404
id	acadia19_404
authors	Liu, Henan; Liao, Longtai; Srivastava, Akshay
year	2019
title	AN ANONYMOUS COMPOSITION
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. 404-411
doi	https://doi.org/10.52842/conf.acadia.2019.404
summary	Within the context of continuous technology transformations, the way scientists and designers process data is changing dramatically from simplification and explicit defined rules to searching and retrieving. Ideally, such a trending method can eliminate issues including deviation and ambiguity with the help of hypothetically unlimited computational power. To process data in this manner, artificial intelligence is necessary and needs to be integrated into the design process. An experiment of a design process that consists of a generative model, a data library, and a machine learning system (GAN) is introduced to demonstrate its effectiveness. The methodology is further evaluated by comparing its output with its input targets, which proves the possibility of employing machine learning systems to aggressively process data and automate the design process. Further improvement of such methodology, including judging criteria and possible applications, and the sensibility of the machine is also discussed at the end.
keywords	Machine Learning, Automation, Variables, Data Processing, Sensibility, Generative Design
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:59

_id	caadria2007_165
id	caadria2007_165
authors	Liu, Huai-Wie; Ji-Hyun Lee
year	2007
title	Personal Assistant: Autonomous Agents Base on Multi-Agent System among Different Industrial Design Stakeholders
source	CAADRIA 2007 [Proceedings of the 12th International Conference on Computer Aided Architectural Design Research in Asia] Nanjing (China) 19-21 April 2007
doi	https://doi.org/10.52842/conf.caadria.2007.x.f2e
summary	To deal with complex communication problems, requires both a web-based collaborative system and a multi-agent system (MAS) integrated with knowledge management architecture. Agents have been acknowledged as a promising approach through the metaphor that an agent can act as a personal assistant. In this paper we proposes an approach to develop personal assistant agents, each of which can represent a different stakeholder and load different domain knowledge inside. To demonstrate our proposed concepts, we focus on a prototype system for notebook design for the company ASUS, a leading notebook manufacturer based in Taiwan.
series	CAADRIA
email
last changed	2022/06/07 07:50

_id	91ea
authors	Liu, J.
year	1997
title	Quality prediction for concrete manufacturing
source	Automation in Construction 5 (6) (1997) pp. 491-499
summary	The problem of extracting information from several sources of information is a very important issue in intelligent systems. In the field of manufacturing concrete--one of the most common construction materials--in Hong Kong, this problem is quite common. There is no direct formulation of concrete mix for specified properties, and all of the mixes are designed by experience and subject to quality inconsistency due to many possible mixing variations. This paper describes an application of neural network techniques to the acquisition of qualitative knowledge during the production of concrete. It shows the capabilities of the developed model for the analysis and representation of production data and prediction of the quality of concrete under different mixing formulations. The simulation results indicate that the neural network's prediction is generally superior to those of conventional methods which often require time-consuming trial mixes for verifying the specified properties before mass production for use.
series	journal paper
more	http://www.elsevier.com/locate/autcon
last changed	2003/05/15 21:22

_id	caadria2024_272
id	caadria2024_272
authors	Liu, Jiaxin, Huang, Xiaoran and Yan, Hongming
year	2024
title	Exploring Visual Factors Influencing Women’s Perceived Insecurity in Metro Stations and Adjacent Built Environments: A Case Study of Milan, Italy
source	Nicole Gardner, Christiane M. Herr, Likai Wang, Hirano Toshiki, Sumbul Ahmad Khan (eds.), ACCELERATED DESIGN - Proceedings of the 29th CAADRIA Conference, Singapore, 20-26 April 2024, Volume 2, pp. 385–394
doi	https://doi.org/10.52842/conf.caadria.2024.2.385
summary	Prior research has established a direct correlation between women's perceived insecurity in public spaces and the design of the surrounding built environment. However, limited attention has been given to investigating how the built environment influences women's security perceptions within metro systems. This study introduces a novel methodology to analyze the impact of visual factors on the entire walking experience within commuter cores, covering both the station and surrounding areas in Milan Metro Line 1. Both Street View Imagery (SVI) and manual photography are employed for semantic segmentation analysis, followed by expert auditing and machine learning for evaluation. Finally, the study constructs regression models to analyze the relationship between the area ratio of visual factors and women’s perceptions. The results demonstrate that certain factors, such as wider platforms and sidewalks, can positively influence women's safety perceptions in the surrounding and interior spaces, respectively. The models could be used to dissect Milan's other metro stations and their surroundings, offering insights applicable to other metro lines. Moreover, the methodology presents serves as a framework for investigating analogous concerns in diverse cities and delving into the experiences of other marginal groups.
keywords	metro station, perceived insecurity, women perception, Google Street View, built environment, deep learning, inclusive city
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	caadria2018_306
id	caadria2018_306
authors	Liu, Jie, Ma, Hongtao, Tang, Ning, Xu, Weiguo and Luo, Dan
year	2018
title	Kinetair: Interactive Stairs with Multiple Functions
source	T. Fukuda, W. Huang, P. Janssen, K. Crolla, S. Alhadidi (eds.), Learning, Adapting and Prototyping - Proceedings of the 23rd CAADRIA Conference - Volume 2, Tsinghua University, Beijing, China, 17-19 May 2018, pp. 369-378
doi	https://doi.org/10.52842/conf.caadria.2018.2.369
summary	Kinetair is an interactive stairs prototype which could change its appearance according to the surrounding conditions, providing a diversity of functions, such as stairs, exhibition walls, furniture and so on. This research is based on the Interactive Architecture theory, integrating with digital fabrication technology. This paper will illustrate the origin of the concept, the concept development process, the fabrication process and the various possible application of Kinetair. This experiment evokes us to rethink the fundamental meanings of the architecture components in a brand new perspective, and stimulates designers to explore the new features of conventional constructions with cutting-edge technologies.
keywords	interactive stairs; stair design; kinetic structure; dynamic design; adaptive form
series	CAADRIA
email
last changed	2022/06/07 07:59

_id	caadria2021_396
id	caadria2021_396
authors	Liu, Jie, Wang, Yuechen and Zhu, Ning
year	2021
title	Cycling Virtual Tour - A Remote Online Travel System Based On Interactive Technologies And Its User Experience Evaluation
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 2, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 243-252
doi	https://doi.org/10.52842/conf.caadria.2021.2.243
summary	Virtual reality has been widely adopted into various fields of human life. It is entering the world of tourism to remote places. This paper proposes a brand-new interaction design system for remote online virtual tourism based on bicycle riding behavior and projection mapping technologies. Through the user experience evaluation experiments of this system, the research found that this interactive system can effectively improve the realism and sense of the presence of the virtual environment. It can also enhance the delectation and satisfaction of the virtual tour. At the same time, this system can reduce the simulator syndrome which plays as a common problem in the traditional virtual tour experience.
keywords	interaction design; immersive environment; virtual tour; user experience
series	CAADRIA
email
last changed	2022/06/07 07:59

_id	caadria2019_227
id	caadria2019_227
authors	Liu, Jie, Xu, Weiguo, Chang, Jiahui, Ma, Hongtao and Xu, Qingqing
year	2019
title	Flipped - An Interactive Installation Working as Social Catalyst for Social Anxiety Disorder Students
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. 515-524
doi	https://doi.org/10.52842/conf.caadria.2019.1.515
summary	This research attempts to use an architectural design approach to increase the opportunities to participate in social activities and the chances to establish friendship for social anxiety disorder students. By analyzing the cause and treatment of social anxiety disorder, we propose an entertaining, therapeutic interactive installation named Flipped which working as a social catalyst for social anxiety disorder students. In order to build the installation space intelligent and friendly, a variety of advanced technologies have been embedded into the design. The paper will detail the development of the design concept, the technical implementation of the construction, and the problems encountered during the experience activities.
keywords	Interactive Installation; Social Anxiety Disorder; Therapeutic Interactive Environment; Social Catalyst
series	CAADRIA
email
last changed	2022/06/07 07:59

_id	ecaade2021_223
id	ecaade2021_223
authors	Liu, Jie
year	2021
title	From Physiology to Architecture - The methodology for interactive architecture behavior design
source	Stojakovic, V and Tepavcevic, B (eds.), Towards a new, configurable architecture - Proceedings of the 39th eCAADe Conference - Volume 1, University of Novi Sad, Novi Sad, Serbia, 8-10 September 2021, pp. 195-204
doi	https://doi.org/10.52842/conf.ecaade.2021.1.195
summary	Interactive architectural design is a booming topic in current architectural research, which requires thinking about how to realize buildings provide various spatial services according to users' needs. In the human-building interaction (HBI) design, the architectural behavior design plays as one of the most relevant and essential parts of architectural space design. HBI design requires the establishment of a standard behavioral language system for architecture and people. Therefore, this paper proposes that the design of architectural behavior can mimic human behavior at the physiological level, thus making it easier for people to understand the behavior of architecture. The paper systematically analyzes the design methods and design routes to build muscular and glandular systems for architecture through some case studies.
keywords	interactive architecture; human-building interaction; design methodology
series	eCAADe
email
last changed	2022/06/07 07:59

_id	ijac202119103
id	ijac202119103
authors	Liu, Jingyang; Yi-Chin Lee, and Daniel Cardoso Llach
year	2021
title	Computational design and fabrication of highly customizable architectural space frames: Making a flat-cut Weaire-Phelan structure
source	International Journal of Architectural Computing 2021, Vol. 19 - no. 1, 37–49
summary	This paper documents a computational approach to the design, fabrication, and assembly of customizable space structures built entirely out of flat-cut interlocking elements without the need of nodes, fasteners, cement, or glue. Following a Research by Design (RbD) methodology, we establish a framework comprising geometric and parametric modeling, structural analysis, and digital fabrication stages to examine the following research question: how might the modularity of a construction kit be combined with the plasticity of parametric descriptions to facilitate the design and fabrication of flat-cut space structures? We find that an adaptive joint design that resolves local deformations at the node and element levels can facilitate the construction of flat-cut space structures by making modular components responsive to local geometric, material, and mechanical demands. The research centers on the design and construction of an architecture-scale installation based on the Weaire-Phelan structure—an aperiodic space-filling geometric structure that approximates the geometry of foam—entirely out of flat-cut interlocking elements. Documenting the process in technical detail, as well as some limitations, the paper contributes to recent efforts to develop digital materials suitable for architectural applications. In addition, it contributes to extend the formal and architectural possibilities of flat-cut space structure design by facilitating “bottom-up” design explorations in concert with the structure’s tectonic resolution.
keywords	Computational design, generative fabrication, construction kit
series	journal
email
last changed	2021/06/03 23:29

_id	caadria2023_114
id	caadria2023_114
authors	Liu, Mengxuan, Yang, Chunxia and Fan, Zhaoxiang
year	2023
title	Behaviour Simulation Optimization Based on the Influence of Microclimate on Crowd Perception – A Case Study of Urban Waterfront Public Space
source	Immanuel Koh, Dagmar Reinhardt, Mohammed Makki, Mona Khakhar, Nic Bao (eds.), HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference, Ahmedabad, 18-24 March 2023, pp. 19–28
doi	https://doi.org/10.52842/conf.caadria.2023.2.019
summary	The outdoor behaviour is usually influenced by space and environment. Previous studies on behaviour simulation of outdoor space always focused on the influence of two-dimensional space, but did not take the microclimate perceived into account. However, the microclimate of outdoor public spaces has a strong influence on the activities, which makes the subsequent behaviour simulation results unable to fit well with the reality. Therefore, this research attempts to integrate the influence of space and microclimate perception of crowd into behaviour simulation system. Firstly, we explored the laws of behaviour in terms of seasons, weekdays/weekends, and time slices. Secondly, the multiple linear regression equations of the influence of space and microclimate on behaviour were established. In addition, combining the laws and models with the social force model, a behaviour simulation model in public space under the joint influence of microclimate and space was established. Finally, a comprehensive workflow combining microclimate simulation and behaviour simulation was proposed. The research promoted the application and development of behaviour simulation technology from strong-purpose behaviours to weak-purpose and non-purpose behaviours. Moreover, starting from human behaviour and perception, it provides support for the optimization of urban public space from the bottom up.
keywords	Behaviour Simulation, Microclimate Perception, Outdoor Activities, Public Space
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	caadria2024_382
id	caadria2024_382
authors	Liu, Mengxuan, Yang, Chunxia and Fan, Zhaoxiang
year	2024
title	Prediction, Simulation and Evaluation of Stay Behavior in Public Space Integrated With Microclimate
source	Nicole Gardner, Christiane M. Herr, Likai Wang, Hirano Toshiki, Sumbul Ahmad Khan (eds.), ACCELERATED DESIGN - Proceedings of the 29th CAADRIA Conference, Singapore, 20-26 April 2024, Volume 2, pp. 129–138
doi	https://doi.org/10.52842/conf.caadria.2024.2.129
summary	As "users", individuals directly influence the use of space through their choices and decisions, ultimately determining the vitality of the space. Among these behaviours, stay behaviour significantly contributes to the dominance of space vitality due to its longer occupancy. Therefore, this study focuses on the stay behaviour in public spaces, with a specific emphasis on the choice and decision-making related to seating facilities. The study introduces a neural network model to analyse the influence weights of space and microclimate factors on the preferences of individuals. These weights are then integrated into a social force model to achieve the simulation and visualization of stay behaviour in public spaces. Building upon the results of behaviour simulation, the study evaluates the current utilization of seating facilities in existing public spaces. The original contribution of this study proposes a comprehensive workflow for the simulation of stay behaviour, encompassing "model construction - visualization - evaluation analysis - optimization." The aim is to provide insights for the quantitative analysis and rapid design of urban spatial environments.
keywords	Public Space Analysis, Outdoor Activities, Behaviour simulation, Behaviour Prediction, Microclimate Perception
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	caadria2022_238
id	caadria2022_238
authors	Liu, Nuozhi and Koh, Immanuel
year	2022
title	Machine-Reading Places & Spaces: Generative Probabilistic Modelling of Urban Thematic Zones & Contexts
source	Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 465-474
doi	https://doi.org/10.52842/conf.caadria.2022.1.465
summary	In this paper, a "place" is conceptualised as a composition of dynamic socioeconomic activities and collective perceptions. We apply generative probabilistic modelling to explore urban contextual semantics. By analogy to sorting documents into different topics, this research retrieves data embedding for each urban regions and classify them with thematic zones. Using Singapore as a case study, topic modelling is applied to retrieve perceptual and functional thematic zones from Instagram and TripAdvisor respectively. A subsequent analysis shows strong correlations among certain regions with functional and perceptual consistency. In addition, with our proposed uniqueness and diversity indices, a strong negative correlation at 0.82 is found, suggesting that a region could be more unique if the functions tend to be dominated by certain types of functional and perceptual thematic zones.
keywords	Machine Learning, Natural Language Processing, Generative Probabilistic Models, Urban Data Modelling, Thematic Zones, Topic Modelling, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

For more results click below: