Pollen sensing using AI
Pollen sensing using AI
Hay fever affects around 15% population, with different species affecting people in different ways. Therefore, we want to be able to monitor pollen in real-time. One way to achieve this is to use lensless sensing. We use neural networks to categorise pollen grains from their scattering patterns and use neural networks to transform the scattering patterns into images of the pollen grains. We also use neural networks to transform images of dehydrated pollen grains into images of hydrated pollen grains to aid in understanding their initial state and potentially their environment. We also explore pollen grain morphology using latent space to try to understand their evolution.
Grant-Jacob, James A.
c5d144d8-3c43-4195-8e80-edd96bfda91b
Grant-Jacob, James A.
c5d144d8-3c43-4195-8e80-edd96bfda91b
Grant-Jacob, James A.
(2024)
Pollen sensing using AI.
AI@FEPS Lightning Talks & Networking, University of Southampton, Southampton, United Kingdom.
(In Press)
Record type:
Conference or Workshop Item
(Other)
Abstract
Hay fever affects around 15% population, with different species affecting people in different ways. Therefore, we want to be able to monitor pollen in real-time. One way to achieve this is to use lensless sensing. We use neural networks to categorise pollen grains from their scattering patterns and use neural networks to transform the scattering patterns into images of the pollen grains. We also use neural networks to transform images of dehydrated pollen grains into images of hydrated pollen grains to aid in understanding their initial state and potentially their environment. We also explore pollen grain morphology using latent space to try to understand their evolution.
This record has no associated files available for download.
More information
Accepted/In Press date: 13 June 2024
Venue - Dates:
AI@FEPS Lightning Talks & Networking, University of Southampton, Southampton, United Kingdom, 2024-06-13
Identifiers
Local EPrints ID: 491519
URI: http://eprints.soton.ac.uk/id/eprint/491519
PURE UUID: 9e9af343-77fd-49a8-8724-b7558788e2ee
Catalogue record
Date deposited: 25 Jun 2024 16:58
Last modified: 26 Jun 2024 01:43
Export record
Contributors
Author:
James A. Grant-Jacob
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics