Skip to main content
Kent Academic Repository

Feature Extraction and K-means Clustering Approach to Explore Important Features of Urban Identity

Chang, Mei-Chih, Buš, Peter, Schmitt, Gerhard (2018) Feature Extraction and K-means Clustering Approach to Explore Important Features of Urban Identity. In: Proceedings of the 16th IEEE International Conference on Machine Learning and Applications (ICMLA 2017). . pp. 1139-1144. IEEE ISBN 978-1-5386-1419-8. E-ISBN 978-1-5386-1418-1. (doi:10.1109/ICMLA.2017.00015) (KAR id:68960)

PDF Author's Accepted Manuscript
Language: English
Download this file
[thumbnail of 082607991(1).pdf]
Request a format suitable for use with assistive technology e.g. a screenreader
PDF Publisher pdf
Language: English

Restricted to Repository staff only
Contact us about this Publication
[thumbnail of 082607991.pdf]
Official URL:


Public spaces play an important role in theprocesses of formation, generation and change of urban identity.Under present day conditions, the identities of cities are rapidlydeteriorating and vanishing. Therefore, the importance of urbandesign, which is a means of designing urban spaces and theirphysical and social aspects, is ever growing. This paper proposesa novel methodology by using Principle Component Analysis(PCA) and K-means clustering approach to find importantfeatures of the urban identity from public space. K. Lynch`s work and Space Syntax theory are reconstructed and integratedwith POI (Points of Interest) to quantify the quality of the publicspace. A case study of Zürich city is used to test of theseredefinitions and features of urban identity. The results showthat PCA and K-means clustering approach can identify theurban identity and explore important features. This strategycould help to improve planning and design processes andgeneration of new urban patterns with more appropriate featuresand qualities.

Item Type: Conference or workshop item (Proceeding)
DOI/Identification number: 10.1109/ICMLA.2017.00015
Additional information: Unmapped bibliographic data: LA - en [Field not mapped to EPrints] SE - 1139 [Field not mapped to EPrints]
Uncontrolled keywords: Urban identity, Space syntax, k-means clustering, Feature extraction
Subjects: N Visual Arts > NA Architecture
Divisions: Divisions > Division of Arts and Humanities > Kent School of Architecture and Planning
Depositing User: Peter Bus
Date Deposited: 06 Sep 2018 10:19 UTC
Last Modified: 04 Jul 2023 13:01 UTC
Resource URI: (The current URI for this page, for reference purposes)

University of Kent Author Information

  • Depositors only (login required):

Total unique views for this document in KAR since July 2020. For more details click on the image.