Conference Editor
Jianshun Zhang; Edward Bogucz; Cliff Davidson; Elizabeth Krietmeyer
Keywords:
Classroom lighting; Visual comfort; Lighting energy efficiency; Subjective evaluation experiment; C-SVM
Location
Syracuse, NY
Event Website
http://ibpc2018.org/
Start Date
26-9-2018 10:30 AM
End Date
26-9-2018 12:00 PM
Description
Considering the quality of the classroom light-environment will directly affect students' eye health and learning efficiency, it is a problem to be solved that how to evaluate the visual comfort levels of the classroom light-environment and save lighting energy on the premise of necessary visual comfort. Aiming at these problems above, this study restored the classroom scene through adjustable full-size light-environment simulation laboratory, in which 135 subjects participated in the visual comfort evaluation experiment of the indoor light-environment. After features (illuminance and correlated color temperature) and labels (comfort levels) preprocessed ,we trained and visualized the visual comfort classification models of desktop reading and blackboard reading using the algorithms of C-Support Vector Machine (C-SVM). Through the contour map and the scatter diagram, we get the classification boundary of different comfort levels and the relationship between visual comfort and lighting parameters, which has guiding significance to classroom lighting design and evaluation.
Recommended Citation
Dang, Rui; Wang, Qingchen; Bu, Yanhui; and Liu, Gang, "Application of C-SVM Classification Algorithm to the Lighting Visual Comfort of University Classrooms" (2018). International Building Physics Conference 2018. 1.
DOI
https://doi.org/10.14305/ibpc.2018.hf-4.01
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.
Application of C-SVM Classification Algorithm to the Lighting Visual Comfort of University Classrooms
Syracuse, NY
Considering the quality of the classroom light-environment will directly affect students' eye health and learning efficiency, it is a problem to be solved that how to evaluate the visual comfort levels of the classroom light-environment and save lighting energy on the premise of necessary visual comfort. Aiming at these problems above, this study restored the classroom scene through adjustable full-size light-environment simulation laboratory, in which 135 subjects participated in the visual comfort evaluation experiment of the indoor light-environment. After features (illuminance and correlated color temperature) and labels (comfort levels) preprocessed ,we trained and visualized the visual comfort classification models of desktop reading and blackboard reading using the algorithms of C-Support Vector Machine (C-SVM). Through the contour map and the scatter diagram, we get the classification boundary of different comfort levels and the relationship between visual comfort and lighting parameters, which has guiding significance to classroom lighting design and evaluation.
https://surface.syr.edu/ibpc/2018/HF4/1
Comments
If you are experiencing accessibility issues with this item, please contact the Accessibility and Inclusion Librarian through lib-accessibility@syr.edu with your name, SU NetID, the SURFACE link, title of record, and author & and reason for request.