Interpretable spatial machine learning for understanding spatial heterogeneity in factors affecting street theft crime DOI
Han Yue, Jianguo Chen

Applied Geography, Journal Year: 2024, Volume and Issue: 175, P. 103503 - 103503

Published: Dec. 27, 2024

Language: Английский

Revealing the differences in bicycle theft and motorcycle theft: spatial patterns and contributing factors DOI Creative Commons
Lin Liu, Heng Liu,

Dongping Long

et al.

Humanities and Social Sciences Communications, Journal Year: 2025, Volume and Issue: 12(1)

Published: Feb. 9, 2025

Language: Английский

Citations

0
Perception of urban street visual color environment based on the CEP-KASS framework DOI
Ningjun Chen, Lei Wang, Tao Xu

et al.

Landscape and Urban Planning, Journal Year: 2025, Volume and Issue: 259, P. 105359 - 105359

Published: April 9, 2025

Language: Английский

Citations

0
Mapping the Impact of Spontaneous Streetscape Features on Social Sensing in the Old City of Quanzhou, China: Based on Multisource Data and Machine Learning DOI Creative Commons
Keran Li,

Yan Lin

Buildings, Journal Year: 2025, Volume and Issue: 15(9), P. 1522 - 1522

Published: May 1, 2025

Streetscapes in old urban areas are not only an important carrier to show regional economies and city style, but also closely correlate residents’ everyday life the hustle bustle which they live. Nevertheless, previous studies have either focused on a few examples with low-throughput surveys or lacked specific consideration of spontaneous features data-driven explorations. Furthermore, impact streetscape diversified social sensing has rarely been examined. This paper combined mobile collection street view images (SVIs) machine learning algorithm calculate eight types elements integrated two online platforms (Dianping Sina Weibo) map distribution economic vitality media perception, respectively. Then, through comparing multiple regression models, impacts characteristics were revealed. The results include following aspects: (1) overall, certain similarity both dimensions Quanzhou, significant clustering transitional trends strong spatial heterogeneity; (2) specifically, can be divided into three categories, given differentiated roles significantly positive, negative, polarizing results. For example, proper use open-interface storefronts, ads, banners is consistent common suggestions, while excessive pursuit interface diversity cultural may bring ambiguous effect. provides transferable analytical framework for mixed regeneration potentially inspire related decisionmakers adopt more refined low-cost approach enhance sustainability.

Language: Английский

Citations

0
Comparing effectiveness of point of interest data and land use data in theft crime modelling: A case study in Beijing DOI

Jiajia Feng,

Yuebing Liang, Hao Qi

et al.

Land Use Policy, Journal Year: 2024, Volume and Issue: 147, P. 107357 - 107357

Published: Sept. 17, 2024

Language: Английский

Citations

0
Exploring the Complex Association Between Urban Built Environment, Sociodemographic Characteristics and Crime: Evidence from Washington, D.C. DOI Creative Commons
Kaixin Liu,

Longhao Zhang,

Shangen Tsou

et al.

Land, Journal Year: 2024, Volume and Issue: 13(11), P. 1886 - 1886

Published: Nov. 11, 2024

The urban built environment and sociodemographic characteristics have complex relationships with crime. However, previous studies had limitations such as generalizing green space types, functionality, characteristics. Given these, this study aimed to explore the relationship between them using more detailed indicators. utilized Google Street View points of interest depict environment. Building on work that segmented natural artificial elements in streetscape images, further distinguished trees, bush, grass. Additionally, it incorporated data from Data Analysis Visualization Unit DC Office Planning reflect a broader range individual Weighted least squares regression Pearson correlation analysis were used test environment, sociodemographic, crime, respectively. Some key findings are follows. (1) Trees, bushes, grass all reduce (2) Urban functionality is hard curb crime by enhancing informal public surveillance. (3) Among variables, walking commute rate variable most strongly positively correlated (4) Family play an important role suppressing This examined comprehensive indicators affecting favor safer cities.

Language: Английский

Citations

0
Interpretable spatial machine learning for understanding spatial heterogeneity in factors affecting street theft crime DOI
Han Yue, Jianguo Chen

Applied Geography, Journal Year: 2024, Volume and Issue: 175, P. 103503 - 103503

Published: Dec. 27, 2024

Language: Английский

Citations

0