EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Perceptual metrics for odorants: Learning from non-expert similarity feedback using machine learning

Priyadarshini Kumari iD, Tarek Besold, Michael Spranger

PLOS ONE · 2023

DOI: 10.1371/journal.pone.0291767 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, 2023. Verfasst von Priyadarshini Kumari und 2 weiteren Autor:innen. Beteiligte Einrichtung: Sony AI, Sunnyvale, California, United States of America. Hauptthemen laut MEDLINE: Odorants, Olfactory Perception. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Defining perceptual similarity metrics for odorant comparisons is crucial to understanding the mechanism of olfactory perception. Current methods in olfaction rely on molecular physicochemical features or discrete verbal descriptors (floral, burnt, etc.) to approximate perceptual (dis)similarity between odorants. However, structural or verbal descriptors alone are limited in modeling complex nuances of odor perception. While structural features inadequately characterize odor perception, language-based discrete descriptors lack the granularity needed to model a continuous perception space. We introduce data-driven approaches to perceptual metrics learning (PMeL) based on two key insights: a) by combining physicochemical features with the user’s perceptual feedback, we can leverage both structural and perceptual attributes of odors to define dissimilarity, and b) instead of discrete labels, user’s perceptual feedback can be gathered as relative similarity comparisons, such as “Does molecule-A smell more like molecule-B, or molecule-C?” These triplet comparisons are easier even for non-experts users and offer a more effective representation of the continuous perception space. Experimental results on several defined tasks show the effectiveness of our approach in evaluating perceptual dissimilarity between odorants. Finally, we investigate how closely our model, trained on non-expert feedback, aligns with the expert’s similarity judgments. Our effort aims to reduce reliance on expert annotations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

OdorantsOlfactory PerceptionFeedbackSmellMachine Learning

Autor:innen und Institutionen

  • Sony AI, Sunnyvale, California, United States of America.
  • Sony AI, Barcelona, Spain.
  • Sony AI, Tokyo, Japan.

ORCID-Profile: Priyadarshini Kumari

Zitieren

APA

Kumari, P., Besold, T., & Spranger, M. (2023). Perceptual metrics for odorants: Learning from non-expert similarity feedback using machine learning. PLOS ONE. https://doi.org/10.1371/journal.pone.0291767

Vancouver

Kumari P, Besold T, Spranger M. Perceptual metrics for odorants: Learning from non-expert similarity feedback using machine learning. PLOS ONE. 2023. doi:10.1371/journal.pone.0291767

BibTeX
@article{Kumari2023,
  author = {Kumari, Priyadarshini and Besold, Tarek and Spranger, Michael},
  title = {Perceptual metrics for odorants: Learning from non-expert similarity feedback using machine learning},
  journal = {PLOS ONE},
  year = {2023},
  doi = {10.1371/journal.pone.0291767}
}
Kostenlos starten →