Abstract
Smart agriculture has taken more attention during the last decade due to the bio-hazards of climate change impacts, extreme weather events, population explosion, food security demands and natural resources shortage. The Egyptian government has taken initiative in dealing with plants diseases especially tomato which is one of the most important vegetable crops worldwide that are affected by many diseases causing high yield loss. Deep learning techniques have become the main focus in the direction of identifying tomato leaf diseases. This study evaluated different deep learning models pre-trained on ImageNet dataset such as ResNet50, InceptionV3, AlexNet, MobileNetV1, MobileNetV2 and MobileNetV3.To the best of our knowledge MobileNetV3 has not been tested on tomato leaf diseases. Each of the former deep learning models has been evaluated and optimized with different techniques. The evaluation shows that MobileNetV3 Small has achieved an accuracy of 98.99% while MobileNetV3 Large has achieved an accuracy of 99.81%. All models have been deployed on a workstation to evaluate their performance by calculating the prediction time on tomato leaf images. The models were also deployed on a Raspberry Pi 4 in order to build an Internet of Things (IoT) device capable of tomato leaf disease detection. MobileNetV3 Small had a latency of 66 ms and 251 ms on the workstation and the Raspberry Pi 4, respectively. On the other hand, MobileNetV3 Large had a latency of 50 ms on the workstation and 348 ms on the Raspberry Pi 4.
Highlights
In the last few years, climate change impacts on food production and human life have become more serious regarding the huge changes in humans lifestyle, urbanization, natural resources shortages
In order to measure the accuracy of the model, we can use the confusion matrix to identify the number of true positive (TP), number of true negative (TN), number of false positive (FP) and number of false negative (FN)
Several convolutional neural network (CNN) models pre-trained on ImageNet dataset were evaluated against the PlantVillage dataset in order to classify tomato leaf diseases
Summary
In the last few years, climate change impacts on food production and human life have become more serious regarding the huge changes in humans lifestyle, urbanization, natural resources shortages. The need to increase food production and mitigate or adapt to the climate change impacts on the agricultural field were the driving force for integrating the smart system in agriculture production. The rapid development in the field of IoT [2] has supported the revolution of smart agriculture and its ability to be deployed in the open field and the greenhouse. It is implemented by collecting data from sensors the data are diagnosed and analyzed by the system to identify anomalies.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
