Critical Analysis of Machine Learning and Deep Learning Models for Mushroom Classification

Neogi, Akashdip (2024) Critical Analysis of Machine Learning and Deep Learning Models for Mushroom Classification. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration Manual) Download (5MB) | Preview

Abstract

Accurate mushroom classification is crucial to prevent the consumption of toxic species. This study compares machine learning and deep learning models, including Random Forest, MobileNetv2m ResNet50, ResNet101, VGG16 and custom CNNs, for classifying edible and poisonous mushrooms. MobileNetV2 had achieved the highest accuracy of (82.14%), followed by ResNet50 (75%), while traditional methods underperformed. The findings emphasize the effectiveness of deep learning, particularly with transfer learning and hyperparameter optimization. Practical applications include real-time identification tools for foragers and researchers. Despite limitations such as a small dataset, this research provides a strong foundation for future work on more diverse datasets and multi-modal approaches, advancing sage mushroom classifications.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Jameel Syed, Muslim UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Food Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Artificial Intelligence
Depositing User:	Ciara O'Brien
Date Deposited:	20 Jun 2025 09:03
Last Modified:	20 Jun 2025 09:03
URI:	https://norma.ncirl.ie/id/eprint/7957

Actions (login required)

View Item