Urban Public Space Safety Perception and the Influence of the Built Environment from a Female Perspective: Combining Street View Data and Deep Learning DOI Creative Commons

S. H. Chen,

Sainan Lin, Yao Yao

et al.

Land, Journal Year: 2024, Volume and Issue: 13(12), P. 2108 - 2108

Published: Dec. 5, 2024

Women face disadvantages in urban public spaces due to their physiological characteristics. However, limited attention has been given assessing safety perceptions from a female perspective and identifying the factors that influence these perceptions. Despite advancements machine learning (ML) techniques, efficiently accurately quantifying remains challenge. This study, using Wuhan as case proposes method for ranking street women by combining RankNet with Gist features. Fully Convolutional Network-8s (FCN-8s) was employed extract built environment features, while Ordinary Least Squares (OLS) regression Geographically Weighted Regression (GWR) were used explore relationship between features women’s The results reveal following key findings: (1) perception rankings align its multi-center pattern, significant differences observed central area. (2) Built significantly perceptions, Sky View Factor, Green Index, Roadway Visibility identified most impactful factors. Factor positive effect on whereas other exhibit negative effects. (3) of varies spatially, allowing study area be classified into three types: sky- road-dominant, building-dominant, greenery-dominant regions. Finally, this targeted strategies creating safer more female-friendly spaces.

Language: Английский

Image clustering algorithm and psychological perception in historical building colour rating research: A case study of Guangzhou, China DOI Creative Commons
Tianyi Fan, Xiaoxiang Tang,

Kerun Li

et al.

Frontiers of Architectural Research, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 1, 2025

Language: Английский

Citations

0
Exploration of Strategies for Enhancing the Quality of Urban Space Based on Multi-Source Data Fusion DOI Creative Commons

Silin Yang,

Luyao Xiang, Yu Yan

et al.

Buildings, Journal Year: 2025, Volume and Issue: 15(8), P. 1258 - 1258

Published: April 11, 2025

This article, via empirical studies, investigates the influences of facility accessibility, correlation, and resident satisfaction on urban spatial quality. It is discovered that these three elements are positively correlated with Excellent accessibility rational layout can elevate quality, reflects outcome environmental optimization. On this basis, article puts forward strategies intensifying infrastructure construction, using multi-source data to optimize transportation system, implementing humanistic care promoting community interaction, digital intelligent management city, paying attention cultural aesthetics aim offering theoretical support practical guidance for enhancing facilitating sustainable development improvement residents’ quality life.

Language: Английский

Citations

0
An analysis of spatial vitality distribution and formation mechanisms in historical urban areas based on multi-source big data: A case study of Changsha DOI Creative Commons
Yun Long, Sheng Jiao,

Yan Yu

et al.

Frontiers of Architectural Research, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

Citations

0
The application of artificial intelligence in the revitalization of intangible cultural heritage helps the cultural industry succeed DOI

Qingxiang Zhu,

Xiaobin Liu

Journal of Computational Methods in Sciences and Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: May 2, 2025

The integration of artificial intelligence (AI) in revitalizing intangible cultural heritage (ICH) necessitates solutions to enhance participation and preserve culture, thereby contributing the growth industry. objective this research is design an AI-driven model utilizing Adaptive Donkey Smuggler Algorithm-mutated Malleable Long Short-Term Memory (ADS-MLSTM) network recognition, preservation, revitalization ICH, supporting industry sustainability. Data were collected from multiple ICH archives, including digital representations heritage. This data underwent preprocessing steps such as noise reduction cleaning ensure robustness against diverse ICH. Utilizing Term Frequency-Inverse Document Frequency (TF-IDF) method, features extracted efficiently. ADS MLSTM algorithms proposed ADS-MLSTM demonstrates superior performance, achieving a precision 98.70%, mean squared error (MSE) 0.73, recall 98.27%, F1-score 98.80%, accuracy 99%, root (RMSE) 0.57, further highlighting its effectiveness. incorporation deep learning significantly enhanced model’s effectiveness, leading better results recognizing elements. AI plays essential role recovering assets, particularly through model. By improving recognition fostering user interaction, approaches contribute industry, offering innovative solution for preserving promoting

Language: Английский

Citations

0
Cooperative transportation of an object with a nonholonomic constraint by a swarm robot DOI Creative Commons

Yuto Fukao,

Tatsuro Terakawa, Takahiro Endo

et al.

ROBOMECH Journal, Journal Year: 2025, Volume and Issue: 12(1)

Published: May 24, 2025

Language: Английский

Citations

0
Urban Public Space Safety Perception and the Influence of the Built Environment from a Female Perspective: Combining Street View Data and Deep Learning DOI Creative Commons

S. H. Chen,

Sainan Lin, Yao Yao

et al.

Land, Journal Year: 2024, Volume and Issue: 13(12), P. 2108 - 2108

Published: Dec. 5, 2024

Women face disadvantages in urban public spaces due to their physiological characteristics. However, limited attention has been given assessing safety perceptions from a female perspective and identifying the factors that influence these perceptions. Despite advancements machine learning (ML) techniques, efficiently accurately quantifying remains challenge. This study, using Wuhan as case proposes method for ranking street women by combining RankNet with Gist features. Fully Convolutional Network-8s (FCN-8s) was employed extract built environment features, while Ordinary Least Squares (OLS) regression Geographically Weighted Regression (GWR) were used explore relationship between features women’s The results reveal following key findings: (1) perception rankings align its multi-center pattern, significant differences observed central area. (2) Built significantly perceptions, Sky View Factor, Green Index, Roadway Visibility identified most impactful factors. Factor positive effect on whereas other exhibit negative effects. (3) of varies spatially, allowing study area be classified into three types: sky- road-dominant, building-dominant, greenery-dominant regions. Finally, this targeted strategies creating safer more female-friendly spaces.

Language: Английский

Citations

0