CN 11-5366/S     ISSN 1673-1530
"Landscape Architecture is more than a journal."
Guo H G, Zhang M H, Wan B Y, Hong X C. A Machine Learning-Based Research on the Influence of Street Environment Colors on the Elderly’s Perception of Pleasure[J]. Landscape Architecture, 2025, 32(8): 1-9.
Citation: Guo H G, Zhang M H, Wan B Y, Hong X C. A Machine Learning-Based Research on the Influence of Street Environment Colors on the Elderly’s Perception of Pleasure[J]. Landscape Architecture, 2025, 32(8): 1-9.

A Machine Learning-Based Research on the Influence of Street Environment Colors on the Elderly’s Perception of Pleasure

  • Objective Streets serve as critical spaces for the elderly’s daily activities, offering environments for essential activities such as walking, social interaction, and physical exercise. These urban environments are not only integral to the elderly’s physical health but also have a significant impact on their mental health, thereby enhancing their quality of life and fostering a sense of community. Designing street environments that specifically address the health needs of the elderly is crucial for advancing the national strategies of “Proactive Response to Population Aging” and “Healthy China”. While existing research has demonstrated the general impact of environmental factors on mental health, there remains a notable gap in understanding the specific mechanisms through which street environment colors influence the elderly’s perception of pleasure. Environmental colors, as key visual elements, have the capacity to evoke various emotional responses, including calmness, vibrancy, or discomfort. This research aims to bridge this gap by systematically examining the relationship between street environment colors and the elderly’s perception of pleasure. The research identifies and analyzes five critical color variables — hue, saturation, brightness (value), color harmony, and color complexity — focusing on their nonlinear relationships and interactive effects on the elderly’s perception of pleasure.
    Methods Fuzhou City, a rapidly aging urban area located in southeastern China, is selected as an example for this research. A total of 11,000 high-quality streetscape images are collected from 5,500 sampling points along major roads and residential streets, with a focus on roads at or above the tertiary level within the research area. The perception of pleasure of elderly participants is assessed through a field survey conducted in January 2024, in which participants are asked to evaluate paired street images based on their subjective emotional responses. These subjective assessments are subsequently converted into numerical scores on perception of pleasure using the TrueSkill algorithm, a Bayesian probabilistic method that ensures reliable results even in the context of subjective evaluations. The streetscape images are processed using semantic segmentation techniques to extract color variables, with the analysis centered on the nonlinear relationships and interactions between street environment colors and the elderly’s perception of pleasure. The dependent variable involved in the analysis is the elderly’s perception of pleasure, while the independent variables include the built environment, street environment colors, and socio-economic factors such as age, gender, income, and education. To examine the nonlinear effects and interactions among these variables, a random forest model us employed.
    Results The research yields several significant findings. First, it is revealed that color brightness (value) has the most substantial negative effect on the elderly’s perception of pleasure. High levels of brightness are associated with visual discomfort, particularly due to age-related visual impairments such as reduced light sensitivity and slower adaptation to lighting changes. In contrast, color harmony and color complexity have positive effects and can enhancing the perception of pleasure by creating visually engaging, aesthetically balanced environments. Second, the relationship between street environment colors and the elderly’s perception of pleasure exhibits nonlinear patterns, including U-shaped, S-shaped, and exponential curves. Specifically, moderate levels of brightness (value) are found to positively influence the perception of pleasure, while extremely high or low brightness levels have a detrimental impact. Similarly, saturation shows a positive effect up to a certain threshold, beyond which its influence plateaus. These findings highlight the importance of carefully calibrating color variables to stay within optimal ranges that maximize the emotional benefits for the elderly. Third, the research identifies complex interactions between color variables, with some combinations having synergistic effects that enhance the perception of pleasure, while others demonstrating antagonistic effects. For example, moderate levels of color complexity, when combined with high saturation, may produce the most positive emotional outcomes, as this combination provides visual stimulation without overwhelming the viewer. On the other hand, excessive brightness combined with low color harmony may weaken emotional outcomes, creating visually discordant or overly stimulating environments.
    Conclusion This research underscores the pivotal role that street environment colors play in influencing the elderly’s perception of pleasure, contributing significantly to the field of urban design and planning. The research’s findings provide actionable insights for urban planners and designers to optimize street color schemes in ways that enhance the mental health of the elderly. In particular, the research recommends moderating color brightness levels to prevent visual fatigue and discomfort while prioritizing color harmony and moderate complexity to foster positive emotional responses. Furthermore, hues that align with the elderly’s preferences, such as green and yellow-green tones, should be incorporated to promote a calming and relaxing atmosphere. These design strategies are in alignment with the national strategies of “Healthy China” and “Proactive Response to Population Aging”, as they contribute to the creation of urban spaces that support active and healthy aging. By integrating advanced techniques, such as machine learning and big data analytics, into environmental design, this research expands the understanding of how street colors influence the elderly’s perception of pleasure. Additionally, the identification of nonlinear and interactive effects offers a nuanced perspective on how targeted environmental design interventions can be implemented to improve the quality of life for aging populations. This research lays the foundation for future research and practical applications in the design of elderly-friendly urban spaces, providing a framework for optimizing street color schemes to meet the emotional and physical needs of the elderly.
  • loading

Catalog

    Turn off MathJax
    Article Contents

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return