Abstract
Farmers in rural areas with limitation of internet connectivity can be made possible for early plant diseases detection by using optimization of mobile devices which implemented an application based on Convolutional Neural Network (CNN) because of the computational efficiency.The researchers used a dataset containing 79 different classes of plant which was merged from several public domain datasets, which was evaluated and compared using four CNN models, consisting of MobileNetV3, EfficientNetB0, Mason model, and ShuffleNetV2.The experiment results showed that Mason model has a highest accuracy of 90.54% and the smallest output file of 0.85MB, MobileNetV3 88.83% with 16.85MB, EfficientNetB0 88.75% with 16.08MB, and ShuffleNetV2 83.52% with 15.89MB, which the four models have a slight accuracy decrease on both workstation and mobile devices.However, on resource consumption overall, MobileNetV3 consumed less than the others model, even though the value hasn't a huge difference of several points.It can be concluded that Mason model is the most suitable model to be implemented on mobile devices because of accuracy and low resource consumption.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 8
Claim · model-written summary
Mason reached the highest accuracy, 90.54%, for plant disease classification.
Verbatim
e0“Mason model has a highest accuracy of 90.54%”
t0“Plant Diseases”
Claim · model-written summary
Mason had the smallest output file, 0.85MB.
Verbatim
e0“Mason model has a highest accuracy of 90.54% and the smallest output file of 0.85MB”
t0“Plant Diseases”
Claim · model-written summary
MobileNetV3 achieved 88.83% accuracy and a 16.85MB file.
Verbatim
e0“MobileNetV3 88.83% with 16.85MB”
e1“Mason model has a highest accuracy of 90.54% and the smallest output file of 0.85MB”
t0“Plant Diseases”
Claim · model-written summary
EfficientNetB0 achieved 88.75% accuracy and a 16.08MB file.
Verbatim
e0“EfficientNetB0 88.75% with 16.08MB”
e1“Mason model has a highest accuracy of 90.54% and the smallest output file of 0.85MB”
t0“Plant Diseases”
Claim · model-written summary
ShuffleNetV2 achieved 83.52% accuracy and a 15.89MB file.
Verbatim
e0“ShuffleNetV2 83.52% with 15.89MB”
e1“Mason model has a highest accuracy of 90.54% and the smallest output file of 0.85MB”
t0“Plant Diseases”
Claim · model-written summary
All four models had a slight accuracy decrease on workstations and mobile devices.
Verbatim
e0“the four models have a slight accuracy decrease on both workstation and mobile devices”
e1“Mason model has a highest accuracy of 90.54%”
t0“Plant Diseases”
Claim · model-written summary
MobileNetV3 consumed fewer resources overall than the other models.
Verbatim
e0“MobileNetV3 consumed less than the others model”
e1“on resource consumption overall”
t0“Plant Diseases”
Claim · model-written summary
The authors recommend Mason for mobile devices based on accuracy and low resource consumption.
Verbatim
e0“Mason model is the most suitable model to be implemented on mobile devices because of accuracy and low resource consumption”
t0“Plant Diseases”