Finding Main Streets: Applying Machine Learning to Urban Design Planning
نویسنده
چکیده
In the urban design realm careful consideration of connecting architectural form and socioeconomic function is a compelling issue. City planners and architects spend a significant amount of their time on collecting and integrating data from various information sources. Rapid growth of Geographic Information Systems (GIS) made it possible to map and display laboriously collected data, but these tools are limited by lack of sophisticated data analysis and inference capability. In this project we explored possibilities of how A.I. techniques can boost the performance of urban design planning by providing large scale data analysis and inference capability. Not to mention general benefits of automated process such as speed and labor cost, statistical analysis can also provide theoretical justification for designers which is not typically available in the case of manual efforts. As a proof of concept experiment we implemented an application of active learning that identifies a certain type of urban setting, Main Streets, based on their complicated spatial and semantic relationships over building geometry. The preliminary results show that active learning algorithm can effectively learn a classifier with relatively small number of training examples.
منابع مشابه
Learning from Main Streets A Machine Learning Approach Identifying Neighborhood Commercial Districts
In this paper we explore possibilities for using Artificial Intelligence techniques to boost the performance of urban design tools by providing large scale data analysis and inference capability. As a proof of concept experiment we showcase a novel application that learns to identify a certain type of urban setting, Main Streets, based on architectural and socioeconomic features of its vicinity...
متن کاملA Review of Relationship between Environmental Quality and Citizen’s Behavioral Patterns in Public Spaces (Case Study: Mashhad Kouhsangi and Qaranei Streets)
Purpose of this article is to introduce different approaches in reviewing the mutual relationship between the built environment and citizen’s behavioral patterns in public spaces with applying analytical and comparative methods by using a questionnaire, a sample of 200 members of the audience in two streets of Mashhad, Kouhsangi and Qaranei, by using two tests of the ordinal logistic regression...
متن کاملExpanding Walkability in Tehran’s Historic Downtown Case Study: Streets Leading to the Imam Khomeini Square (Maidan-e Tup-khana)
This research explores the correlation between ‘walkability’ and the ‘sense of place’ in Tehran’s streets, particularly streets leading to the Imam Khomeini square (Maidan-e Tup-khana) at the heart of historic downtown. The goal is to evaluate the walkability through a measurable method in order to prioritize strategies to enhance various aspects of the historic districts. After reviewing the e...
متن کاملDemocratic Urban Streets Design Guideline Codifications (Based on Qualitative Democratic Urban Spaces Design Norms)
متن کامل
Organizing the Urban Landscape with Emphasis on Legibility, Using Visual Preference Technique (V.P.T) (Case Study: Khayyam Street of Qazvin)
Urban landscapes form the main parts of the city. One of these spaces is urban streets, in whichsocial interactions and urban vitality reach its maximum quality and quantity. One of the principles and properties ofurban landscape design is its intelligibility. A viewer who takes a look at an intelligible city and knows it can attract newemotional manifestations of city without damaging its orig...
متن کامل