TU Darmstadt / ULB / TUprints

Unsupervised Clustering Pipeline to Obtain Diversified Light Spectra for Subject Studies and Correlation Analyses

Klir, Stefan ; Fathia, Reda ; Babilon, Sebastian ; Benkner, Simon ; Khanh, Tran Quoc (2022):
Unsupervised Clustering Pipeline to Obtain Diversified Light Spectra for Subject Studies and Correlation Analyses. (Publisher's Version)
In: Applied Sciences, 11 (19), MDPI, e-ISSN 2076-3417,
DOI: 10.26083/tuprints-00021256,
[Article]

[img] Text
applsci-11-09062-v2.pdf
Copyright Information: CC BY 4.0 International - Creative Commons, Attribution.

Download (7MB)
Item Type: Article
Origin: Secondary publication via sponsored Golden Open Access
Status: Publisher's Version
Title: Unsupervised Clustering Pipeline to Obtain Diversified Light Spectra for Subject Studies and Correlation Analyses
Language: English
Abstract:

Featured Application: Selection of most diverse light spectra from a larger set of possible candidates to be used in subject studies or for machine learning to find correlations between photometric and other parameters such as psychological, physiological, or preference-based outcome measures.

Abstract: Current subject studies and data-driven approaches in lighting research often use manually selected light spectra, which usually exhibit a large bias due to the applied selection criteria. This paper, therefore, presents a novel approach to minimize this bias by using a data-driven framework for selecting the most diverse candidates from a given larger set of possible light spectra. The spectral information per wavelength is first reduced by applying a convolutional autoencoder. The relevant features are then selected based on Laplacian Scores and transformed to a two-dimensional embedded space for subsequent clustering. The low dimensional embedding, from which the required diversity follows, is done with respect to the locality of the features. In a second step, photometric parameters are considered and a second clustering is performed. As a result of this algorithmic pipeline, the most diverse selection of light spectra complying with a given set of relevant photometric parameters can be extracted and used for further experiments or applications.

Journal or Publication Title: Applied Sciences
Volume of the journal: 11
Issue Number: 19
Place of Publication: Darmstadt
Publisher: MDPI
Collation: 18 Seiten
Classification DDC: 600 Technik, Medizin, angewandte Wissenschaften > 600 Technik
Divisions: 18 Department of Electrical Engineering and Information Technology > Adaptive Lighting Systems and Visual Processing
Date Deposited: 06 May 2022 12:04
Last Modified: 23 Aug 2022 11:41
DOI: 10.26083/tuprints-00021256
Corresponding Links:
URN: urn:nbn:de:tuda-tuprints-212563
Additional Information:

This article belongs to the Special Issue Machine Learning and Signal Processing for IOT Applications

Keywords: light clustering; diversified light spectra; spectral embedding; light selection; spectral feature selection

URI: https://tuprints.ulb.tu-darmstadt.de/id/eprint/21256
PPN: 494614714
Export:
Actions (login required)
View Item View Item