Jiayi Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jiayi Zhao has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Chang Liu
College of Landscape Architecture and Art, Fujian Agriculture and Forestry University, Fuzhou, China
2 shared publications - Yongrong Zheng
College of Landscape Architecture and Art, Fujian Agriculture and Forestry University, Fuzhou 350002, China
2 shared publications - Yuhan Liu
College of Landscape Architecture and Art, Fujian Agriculture and Forestry University, Fuzhou 350002, China
2 shared publications - Nuo Xu
College of Landscape Architecture and Art, Fujian Agriculture and Forestry University, 15 Shangxiadian Rd., Fuzhou 350002, China
1 shared publication - Siren Lan
College of Landscape Architecture and Art, Fujian Agriculture and Forestry University, Fuzhou 350002, China
1 shared publication - Songjun He
College of Landscape Architecture and Art, Fujian Agriculture and Forestry University, Fuzhou 350002, China
1 shared publication
Latest Publications
- Open Access
- 18 November 2024
- Published by MDPI AG in Sustainability
- Vol. 16 (22) , 10038
Optimizing Perceived Jogging Supportiveness for Enhanced Sustainable Greenway Design Based on Computer Vision: Implications of the Nonlinear Influence of Perceptual and Physical Characteristics
Active transportation and lifestyles are important components of a sustainable city. Greenways play a crucial role in providing conducive environments for jogging. To investigate the influence of micro-scale characteristics on perceived jogging supportiveness (PJS), 230 video clips of greenways within Fuzhou City were collected as samples. PJS was evaluated using a Likert scale, perceptual characteristics were assessed through a semantic difference scale, and physical characteristics were computed via semantic segmentation. By employing SHAP values and dependence plots within an XGBoost framework, the findings reveal the following: (1) Regarding perceptual characteristics, continuity, culture, and facility affordance exhibit the highest relative importance to PJS (|SHAP| ≥ 0.1). Continuity, naturalness, and vitality generally have positive impacts on PJS, while disturbance is negative. Facility affordance, scale, culture, openness, and brightness demonstrate more complex nonlinear influences that suggest optimal value ranges. (2) Concerning physical characteristics, fences, motor vehicles, and surface material are deemed most influential (|SHAP| ≥ 0.1). The presence of fences, walls, and construction generally negatively affect PJS, while excessive openness is also unfavorable. Comfortable road surfaces are associated with higher levels of PJS. Natural elements and the presence of people and vehicles have promoting effects up to certain thresholds, but beyond that point, they exert opposite influences. Finally, suggestions for designing greenways that encourage jogging are proposed. This study provides practical references for optimizing greenway design to promote active transportation and lifestyles, reinforcing the contribution of green infrastructure to public health in sustainable cities.
- 18 November 2024
- Published by MDPI AG in Sustainability
- Vol. 16 (22) , 10038
Open AccessOptimizing Perceived Jogging Supportiveness for Enhanced Sustainable Greenway Design Based on Computer Vision: Implications of the Nonlinear Influence of Perceptual and Physical Characteristics
Active transportation and lifestyles are important components of a sustainable city. Greenways play a crucial role in providing conducive environments for jogging. To investigate the influence of micro-scale characteristics on perceived jogging supportiveness (PJS), 230 video clips of greenways within Fuzhou City were collected as samples. PJS was evaluated using a Likert scale, perceptual characteristics were assessed through a semantic difference scale, and physical characteristics were computed via semantic segmentation. By employing SHAP values and dependence plots within an XGBoost framework, the findings reveal the following: (1) Regarding perceptual characteristics, continuity, culture, and facility affordance exhibit the highest relative importance to PJS (|SHAP| ≥ 0.1). Continuity, naturalness, and vitality generally have positive impacts on PJS, while disturbance is negative. Facility affordance, scale, culture, openness, and brightness demonstrate more complex nonlinear influences that suggest optimal value ranges. (2) Concerning physical characteristics, fences, motor vehicles, and surface material are deemed most influential (|SHAP| ≥ 0.1). The presence of fences, walls, and construction generally negatively affect PJS, while excessive openness is also unfavorable. Comfortable road surfaces are associated with higher levels of PJS. Natural elements and the presence of people and vehicles have promoting effects up to certain thresholds, but beyond that point, they exert opposite influences. Finally, suggestions for designing greenways that encourage jogging are proposed. This study provides practical references for optimizing greenway design to promote active transportation and lifestyles, reinforcing the contribution of green infrastructure to public health in sustainable cities.
- Open Access
Modeling the Effect of Greenways’ Multilevel Visual Characteristics on Thermal Perception in Summer Based on Bayesian Network and Computer Vision
The aim of this study is to reveal the effects of multilevel visual characteristics of greenways on thermal perception in hot and humid regions during summer and to explore the potential of visual design to enhance psychological thermal comfort. Data on light (L), color (C), plant richness (PR), space openness (SO), scenic view (SV), thermal sensation (TS), and thermal preference (TP) were collected through questionnaires (n = 546). Computer vision technology was applied to measure the green view index (GVI), sky view index (SVI), paving index (PI), spatial enclosure (SE), and water index (WI). Using the hill climbing algorithm in R to construct a Bayesian network, model validation results indicated prediction accuracies of 0.799 for TS and 0.838 for TP. The results showed that: (1) SE, WI, and SV significantly positively influence TS, while L significantly negatively influences TS (R2 = 0.6805, p-value < 0.05); (2) WI, TS, and SV significantly positively influence TP (R2 = 0.759, p-value < 0.05).
Open AccessModeling the Effect of Greenways’ Multilevel Visual Characteristics on Thermal Perception in Summer Based on Bayesian Network and Computer Vision
The aim of this study is to reveal the effects of multilevel visual characteristics of greenways on thermal perception in hot and humid regions during summer and to explore the potential of visual design to enhance psychological thermal comfort. Data on light (L), color (C), plant richness (PR), space openness (SO), scenic view (SV), thermal sensation (TS), and thermal preference (TP) were collected through questionnaires (n = 546). Computer vision technology was applied to measure the green view index (GVI), sky view index (SVI), paving index (PI), spatial enclosure (SE), and water index (WI). Using the hill climbing algorithm in R to construct a Bayesian network, model validation results indicated prediction accuracies of 0.799 for TS and 0.838 for TP. The results showed that: (1) SE, WI, and SV significantly positively influence TS, while L significantly negatively influences TS (R2 = 0.6805, p-value < 0.05); (2) WI, TS, and SV significantly positively influence TP (R2 = 0.759, p-value < 0.05).