Poisonous Mushroom Detection Using Graph Neural Networks

This study delves into the use of Graph Neural Networks (GNNs) for the classification of poisonous and edible mushrooms based on image data, aiming to address the limitations of manual identification methods. Three GNN architectures, Graph Convolutional Network (GCN), GraphSAGE, and Graph Isomorphis...

Full description

Saved in:

Bibliographic Details
Published in:	2023 5th International Conference on Advancements in Computing (ICAC) pp. 328 - 333
Main Authors:	Pathirana, D.P.C.H, Rajapaksha, R.M.T.U., Rathnayake, H.M. Samadhi Chathuranga, Sirisena, Kosala, Samarathunga, Udara
Format:	Conference Proceeding
Language:	English
Published:	IEEE 07-12-2023
Subjects:	Biology Computer architecture Convolutional neural networks Deep Learning Graph neural networks Image Processing Mushroom classification Poisonous Mushroom Detection Toxicology
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	This study delves into the use of Graph Neural Networks (GNNs) for the classification of poisonous and edible mushrooms based on image data, aiming to address the limitations of manual identification methods. Three GNN architectures, Graph Convolutional Network (GCN), GraphSAGE, and Graph Isomorphism Network (GIN), are examined, with a comparison of the Adam and Stochastic Gradient Descent (SGD) optimizers within each. The results underscore GNNs' effectiveness in discerning toxic mushrooms by capturing nuanced pixel relationships, offering a valuable contribution to the fields of biology and toxicology, with practical implications for mushroom toxicity prevention.
ISSN:	2837-5424
DOI:	10.1109/ICAC60630.2023.10417353