Inferring socio-economic, transport and environmental inequalities using both street network and urban image features

Stephen Law; Kimon Krenz; Alan Penn

Inferring socio-economic, transport and environmental inequalities using both street network and urban image features

Stephen Law, Kimon Krenz, Alan Penn

Architecture

Research output: Contribution to conference › Poster › peer-review

18 Downloads (Pure)

Abstract

Machine learning methods have achieved human-level accuracies in many computer vision and natural language processing tasks. These techniques
have led to advances in not only medical imaging, gaming and robotics but also in urban analytics. Previous research [1] has begun to apply these learning methods to estimate socio-economic indicators using urban imagery. However, limited research studied how different urban form data can be combined to improve its performance. The aims of this research is to test and explore the efficacy on combining three sources of urban data to make inferences on socio-economic, transport and environmental indicators for the case study of Greater London, UK.

Original language	English
Pages	P321
Number of pages	1
Publication status	Published - 8 Apr 2022
Event	XXVIII International Seminar on Urban Form - "Urban Form and the Sustainable and Prosperous City" - University of Strathclyde, Glasgow, United Kingdom Duration: 29 Jun 2021 → 3 Jul 2021

Conference

Conference	XXVIII International Seminar on Urban Form - "Urban Form and the Sustainable and Prosperous City"
Abbreviated title	ISUF
Country/Territory	United Kingdom
City	Glasgow
Period	29/06/21 → 3/07/21

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 15 Life on Land

Keywords

machine learning
socioeconomic analysis
UK cities

Access to Document

Law-etal-ISUF-2021-Inferring-socioeconomic-transport-and-environmental-inequalities-using-both-street-network-and-urban-image-featuresFinal published version, 922 KBLicence: CC BY 4.0

Cite this

@conference{90a486cd61a54efd8e81eec32b042779,

title = "Inferring socio-economic, transport and environmental inequalities using both street network and urban image features",

abstract = "Machine learning methods have achieved human-level accuracies in many computer vision and natural language processing tasks. These techniques have led to advances in not only medical imaging, gaming and robotics but also in urban analytics. Previous research [1] has begun to apply these learning methods to estimate socio-economic indicators using urban imagery. However, limited research studied how different urban form data can be combined to improve its performance. The aims of this research is to test and explore the efficacy on combining three sources of urban data to make inferences on socio-economic, transport and environmental indicators for the case study of Greater London, UK.",

keywords = "machine learning, socioeconomic analysis, UK cities",

author = "Stephen Law and Kimon Krenz and Alan Penn",

year = "2022",

month = apr,

day = "8",

language = "English",

pages = "P321",

note = "XXVIII International Seminar on Urban Form - {"}Urban Form and the Sustainable and Prosperous City{"}, ISUF ; Conference date: 29-06-2021 Through 03-07-2021",

}

Inferring socio-economic, transport and environmental inequalities using both street network and urban image features. / Law, Stephen; Krenz, Kimon; Penn, Alan.
2022. P321 Poster session presented at XXVIII International Seminar on Urban Form - "Urban Form and the Sustainable and Prosperous City", Glasgow, United Kingdom.

Research output: Contribution to conference › Poster › peer-review

TY - CONF

T1 - Inferring socio-economic, transport and environmental inequalities using both street network and urban image features

AU - Law, Stephen

AU - Krenz, Kimon

AU - Penn, Alan

PY - 2022/4/8

Y1 - 2022/4/8

N2 - Machine learning methods have achieved human-level accuracies in many computer vision and natural language processing tasks. These techniques have led to advances in not only medical imaging, gaming and robotics but also in urban analytics. Previous research [1] has begun to apply these learning methods to estimate socio-economic indicators using urban imagery. However, limited research studied how different urban form data can be combined to improve its performance. The aims of this research is to test and explore the efficacy on combining three sources of urban data to make inferences on socio-economic, transport and environmental indicators for the case study of Greater London, UK.

AB - Machine learning methods have achieved human-level accuracies in many computer vision and natural language processing tasks. These techniques have led to advances in not only medical imaging, gaming and robotics but also in urban analytics. Previous research [1] has begun to apply these learning methods to estimate socio-economic indicators using urban imagery. However, limited research studied how different urban form data can be combined to improve its performance. The aims of this research is to test and explore the efficacy on combining three sources of urban data to make inferences on socio-economic, transport and environmental indicators for the case study of Greater London, UK.

KW - machine learning

KW - socioeconomic analysis

KW - UK cities

UR - https://doi.org/10.17868/80146

M3 - Poster

SP - P321

T2 - XXVIII International Seminar on Urban Form - "Urban Form and the Sustainable and Prosperous City"

Y2 - 29 June 2021 through 3 July 2021

ER -

Inferring socio-economic, transport and environmental inequalities using both street network and urban image features

Abstract

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

ISUF Annual Conference Proceedings of the XXVIII International Seminar on Urban Form: "Urban Form and the Sustainable and Prosperous City"

Cite this