Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

An artificial neural network approach for glomerular activity pattern prediction using the graph kernel method and

Zu Soh¹, Toshio Tsuji, Noboru Takiguchi

¹Department of System Cybernetics, Graduate School of Engineering, Hiroshima University, Kagamiyama, Higashihiroshima, Japan. sozu@bsys.hiroshima-u.ac.jp

Chemical Senses

|February 24, 2011

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Machine learning-based analysis of the relationship between brain lesion sites and swallowing and cognitive functions in stroke patients.

Scientific reports·2026

Same author

Manual and automated assessments of general movements in neonates are associated with early autism risk at 18 months.

Scientific reports·2026

Same author

Rapid Biodegradation Assessment of Biomass Plastics Using Closed Recirculating Aquaculture Systems: A Novel Approach for Environmental Sustainability.

Marine biotechnology (New York, N.Y.)·2025

Same author

Assessing the acute effect of compression socks on improving arterial compliance in young volunteers.

Heliyon·2025

Same author

Risk of autism spectrum disorder at 18 months of age is associated with prenatal level of polychlorinated biphenyls exposure in a Japanese birth cohort.

Scientific reports·2024

Same author

Cognitive screening test for rehabilitation using spatiotemporal data extracted from a digital trail making test part-A.

Heliyon·2024

This study introduces a neural network model to predict olfactory glomerular activity from odorant molecular structures. The model demonstrates moderate to high correlation, aiding in understanding odor perception.

Area of Science:

Computational neuroscience
Cheminformatics
Machine learning

Background:

The olfactory system processes odorant molecules to elicit specific neural responses.
Predicting olfactory responses from molecular structure is crucial for understanding odor perception and designing new scents.

Purpose of the Study:

To develop a neural network model for predicting olfactory glomerular activity based on odorant molecular structure.
To evaluate the model's ability to quantify structural similarities and predict glomerular activity patterns.

Main Methods:

Utilizing a graph kernel method to represent odorant molecules and quantify structural similarities.
Employing an artificial neural network to convert molecular structures into predicted glomerular activity using Gaussian mixture functions.

Related Experiment Videos

Developing a learning algorithm for model parameter adjustment using odorant-glomerular activity data pairs.

Main Results:

The model established a correlation of 0.3-0.9 between odorant structure similarity and glomerular activity similarity.
Simulations showed the model possesses prediction ability, with predicted glomerular activity patterns correlating with measured patterns at a middle to high level on average.
The model was tested on a dataset comprising 363 odorants.

Conclusions:

The proposed neural network model shows promise for predicting olfactory glomerular activity from molecular structure.
This approach can contribute to the evaluation of odor qualities and advance the field of computational olfaction.
Further development could enhance the accuracy and applicability of the model in odor research.