A Research on the Relationship between Indoor Environment and Learning Efficiency based on Symbolic Regression

Xuebing Ba ； Fengnan Wang ； Yonghui Wang ； Xueying Zhang

《International Journal of Social Science and Education Research》 5卷8期 (2022/08) Pp. 234-241

https://doi.org/10.6918/IJOSSER.202208_5(8).0034

摘要

The research of the learning environment has become an important part of education, because indicating how the learning environment affects learning efficiency has great significance. This research focuses on the indoor environment in summer, and aims to figure out which environmental factors have substantial influences on learning efficiency. The indoor air data and questionnaire data were collected in summer, and the nonlinear relationship between environmental factors and learning efficiency was identified by applying the automatic data mining function of symbolic regression. A model of this relationship was also established. In this paper, three major conclusions were made: (1) In the summer indoor environment, the temperature and carbon dioxide concentration are primary influential factors, especially the temperature; (2) The optimal temperature of the indoor environment is about 25°C, and the lighting condition also has a certain effect on learning efficiency; (3) The higher the carbon dioxide concentration, the lower the learning efficiency.

關鍵字

Symbolic regression ； Learning efficiency ； Learning environment

參考文獻

H. Kim, T. Hong, J. Kim, et al. A psychophysiological effect of indoor thermal condition on college students' learning performance through EEG measurement. Building and Environment, Vol.184(2020), 107223.

C. Jung, J. Awad.: Improving the IAQ for Learning Efficiency with Indoor Plants in University Classrooms in Ajman, United Arab Emirates. Buildings, Vol.11 (2021) No. 7, p. 289.

N. Norazman, A. Ani, NH Ja€Afar, et al. Indoor Lighting in Classroom Environment Influences on Students€ Learning Per-formance. The Journal of Social Sciences Research, (2018) No.6 , p. 986-990.

M.G. Pizon, E.F. Sagrado: Forecasting Disease Burden In Philippines: A Symbolic Regression Analysis. arXiv e-prints, (2021). Information on: https://doi.org/10.48550/arXiv.2105.04813

H. Wang, G. Dong, J. Chen. Application of genetic programming in the identification of tool wear. Engineering Computations, (2021) Information on:. https://doi.org/10.1108/EC-08-2020-0470