Research on the Influence of Lighting Environment Indicators in Clothing Stores Based on Machine Learning on Atmosphere Perception
WANG Shouyi
XIONG Ye
FENG Hua
MA Haoran
Abstract：Study the influence patterns of the lighting environment on atmosphere perception in personalized clothing stores,and propose corresponding lighting environment optimization suggestions based on different clothing styles.This study takes 665 clothing stores across four clothing styles as research subjects.Data were collected through both objective and subjective surveys,and were processed and analyzed using variance analysis,CRITIC weighting,and other methods.AN XGBoost regression algorithm was used to establish a lighting environment atmosphere perception prediction model.The SHAP method was employed to interpret the contribution,correlation,and influencing patterns of lighting environment indicators on atmosphere perception.The atmosphere created by the lighting environment in clothing stores can be evaluated through three atmosphere perception dimensions:comfort,liveliness,and transcendence.Horizontal illuminance is the key variable affecting comfort and is negatively correlated with it;the accent lighting coefficient is the key variable affecting liveliness and is positively correlated with it;and color temperature is the key variable affecting transcendence and is positively correlated with it.
Keywords：clothing storelighting environmentatmosphere perceptionXGBoostSHAP
Publication Date：2024-08-28
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：10( 125-134 )