Wu, Jiayi and Dar, Usman and Anisi, Mohammad Hossein and Abolghasemi, Vahid and Wilkin, Chris Newenham and Wilkin, Andrey Ivanov (2023) Plant Disease Detection: Electronic System Design Empowered with Artificial Intelligence. In: 2023 IEEE Conference on AgriFood Electronics (CAFE), 2023-09-25 - 2023-09-27, Torino, Italy.
Wu, Jiayi and Dar, Usman and Anisi, Mohammad Hossein and Abolghasemi, Vahid and Wilkin, Chris Newenham and Wilkin, Andrey Ivanov (2023) Plant Disease Detection: Electronic System Design Empowered with Artificial Intelligence. In: 2023 IEEE Conference on AgriFood Electronics (CAFE), 2023-09-25 - 2023-09-27, Torino, Italy.
Wu, Jiayi and Dar, Usman and Anisi, Mohammad Hossein and Abolghasemi, Vahid and Wilkin, Chris Newenham and Wilkin, Andrey Ivanov (2023) Plant Disease Detection: Electronic System Design Empowered with Artificial Intelligence. In: 2023 IEEE Conference on AgriFood Electronics (CAFE), 2023-09-25 - 2023-09-27, Torino, Italy.
Abstract
Today, plant diseases have become a major threat to the development of agriculture and forestry, not only affecting the normal growth of plants but also causing food safety problems. Hence, it is necessary to identify and detect disease regions and types of plants as quickly as possible. We have developed a plant monitoring system consisting of sensors and cameras for early detection of plant diseases. First, we create a dataset based on the data collected from the strawberry plants and then use our dataset as well as some well-established public datasets to evaluate and compare the recent deep learning-based plant disease detection studies. Finally, we propose a solution to identify plant diseases using a ResNet model with a novel variable learning rate which changes during the testing phase. We have explored different learning rates and found out that the highest accuracy for classification of healthy and unhealthy strawberry plants is obtained with the learning rate of 0.01 at 99.77%. Experimental results confirm the effectiveness of the proposed system in achieving high disease detection accuracy.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Uncontrolled Keywords: | Plant disease detection; Deep learning; Crop monitoring; Computer vision |
Divisions: | Faculty of Science and Health Faculty of Science and Health > Computer Science and Electronic Engineering, School of |
SWORD Depositor: | Unnamed user with email elements@essex.ac.uk |
Depositing User: | Unnamed user with email elements@essex.ac.uk |
Date Deposited: | 07 Nov 2023 14:54 |
Last Modified: | 09 Sep 2024 21:24 |
URI: | http://repository.essex.ac.uk/id/eprint/36772 |
Available files
Filename: 2023180640-3.pdf