AgroAId: A Mobile App System for Visual Classification of Plant Species and Diseases Using Deep Learning and TensorFlow Lite

This paper aims to assist novice gardeners in identifying plant diseases to circumvent misdiagnosing their plants and to increase general horticultural knowledge for better plant growth. In this paper, we develop a mobile plant care support system (“AgroAId”), which incorporates computer vision tech...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Reda, Mariam (author)
مؤلفون آخرون: Suwwan, Rawan (author), Alkafri, Seba (author), Rashed, Yara (author), Shanableh, Tamer (author)
التنسيق: article
منشور في: 2022
الموضوعات:
الوصول للمادة أونلاين:http://hdl.handle.net/11073/24065
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513443681271808
author Reda, Mariam
author2 Suwwan, Rawan
Alkafri, Seba
Rashed, Yara
Shanableh, Tamer
author2_role author
author
author
author
author_facet Reda, Mariam
Suwwan, Rawan
Alkafri, Seba
Rashed, Yara
Shanableh, Tamer
author_role author
dc.creator.none.fl_str_mv Reda, Mariam
Suwwan, Rawan
Alkafri, Seba
Rashed, Yara
Shanableh, Tamer
dc.date.none.fl_str_mv 2022-07-26T11:21:40Z
2022-07-26T11:21:40Z
2022
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv Reda, M.; Suwwan, R.; Alkafri, S.; Rashed, Y.; Shanableh, T. AgroAId: A Mobile App System for Visual Classification of Plant Species and Diseases Using Deep Learning and TensorFlow Lite. Informatics 2022, 9, 55. https://doi.org/10.3390/informatics9030055
2227-9709
http://hdl.handle.net/11073/24065
dc.language.none.fl_str_mv en_US
dc.publisher.none.fl_str_mv MDPI
dc.relation.none.fl_str_mv https://doi.org/10.3390/informatics9030055
dc.subject.none.fl_str_mv Plant disease
Deep learning
Computer vision
Transfer learning
Artificial intelligence
Agriculture
Mobile app system
Convolutional neural networks
Classification
Plant care support
dc.title.none.fl_str_mv AgroAId: A Mobile App System for Visual Classification of Plant Species and Diseases Using Deep Learning and TensorFlow Lite
dc.type.none.fl_str_mv Peer-Reviewed
Published version
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description This paper aims to assist novice gardeners in identifying plant diseases to circumvent misdiagnosing their plants and to increase general horticultural knowledge for better plant growth. In this paper, we develop a mobile plant care support system (“AgroAId”), which incorporates computer vision technology to classify a plant’s [species–disease] combination from an input plant leaf image, recognizing 39 [species-and-disease] classes. Our method comprises a comparative analysis to maximize our multi-label classification model’s performance and determine the effects of varying the convolutional neural network (CNN) architectures, transfer learning approach, and hyperparameter optimizations. We tested four lightweight, mobile-optimized CNNs – MobileNet, MobileNetV2, NasNetMobile, and EfficientNetB0 – and tested four transfer learning scenarios (percentage of frozen-vs.-retrained base layers): (1) freezing all convolutional layers; (2) freezing 80% of layers; (3) freezing 50% only; and (4) retraining all layers. A total of 32 model variations are built and assessed using standard metrics (accuracy, F1-score, confusion matrices). The most lightweight, highaccuracy model is concluded to be an EfficientNetB0 model using a fully retrained base network with optimized hyperparameters, achieving 99% accuracy and demonstrating the efficacy of the proposed approach; it is integrated into our plant care support system in a TensorFlow Lite format alongside the front-end mobile application and centralized cloud database. Finally, our system also uses the collective user classification data to generate spatiotemporal analytics about regional and seasonal disease trends, making these analytics accessible to all system users to increase awareness of global agricultural trends.
format article
id aus_8c9964f1f5c7c2dc9742273149e1127e
identifier_str_mv Reda, M.; Suwwan, R.; Alkafri, S.; Rashed, Y.; Shanableh, T. AgroAId: A Mobile App System for Visual Classification of Plant Species and Diseases Using Deep Learning and TensorFlow Lite. Informatics 2022, 9, 55. https://doi.org/10.3390/informatics9030055
2227-9709
language_invalid_str_mv en_US
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/24065
publishDate 2022
publisher.none.fl_str_mv MDPI
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling AgroAId: A Mobile App System for Visual Classification of Plant Species and Diseases Using Deep Learning and TensorFlow LiteReda, MariamSuwwan, RawanAlkafri, SebaRashed, YaraShanableh, TamerPlant diseaseDeep learningComputer visionTransfer learningArtificial intelligenceAgricultureMobile app systemConvolutional neural networksClassificationPlant care supportThis paper aims to assist novice gardeners in identifying plant diseases to circumvent misdiagnosing their plants and to increase general horticultural knowledge for better plant growth. In this paper, we develop a mobile plant care support system (“AgroAId”), which incorporates computer vision technology to classify a plant’s [species–disease] combination from an input plant leaf image, recognizing 39 [species-and-disease] classes. Our method comprises a comparative analysis to maximize our multi-label classification model’s performance and determine the effects of varying the convolutional neural network (CNN) architectures, transfer learning approach, and hyperparameter optimizations. We tested four lightweight, mobile-optimized CNNs – MobileNet, MobileNetV2, NasNetMobile, and EfficientNetB0 – and tested four transfer learning scenarios (percentage of frozen-vs.-retrained base layers): (1) freezing all convolutional layers; (2) freezing 80% of layers; (3) freezing 50% only; and (4) retraining all layers. A total of 32 model variations are built and assessed using standard metrics (accuracy, F1-score, confusion matrices). The most lightweight, highaccuracy model is concluded to be an EfficientNetB0 model using a fully retrained base network with optimized hyperparameters, achieving 99% accuracy and demonstrating the efficacy of the proposed approach; it is integrated into our plant care support system in a TensorFlow Lite format alongside the front-end mobile application and centralized cloud database. Finally, our system also uses the collective user classification data to generate spatiotemporal analytics about regional and seasonal disease trends, making these analytics accessible to all system users to increase awareness of global agricultural trends.American University of SharjahMDPI2022-07-26T11:21:40Z2022-07-26T11:21:40Z2022Peer-ReviewedPublished versioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfReda, M.; Suwwan, R.; Alkafri, S.; Rashed, Y.; Shanableh, T. AgroAId: A Mobile App System for Visual Classification of Plant Species and Diseases Using Deep Learning and TensorFlow Lite. Informatics 2022, 9, 55. https://doi.org/10.3390/informatics90300552227-9709http://hdl.handle.net/11073/24065en_UShttps://doi.org/10.3390/informatics9030055oai:repository.aus.edu:11073/240652024-08-22T12:07:45Z
spellingShingle AgroAId: A Mobile App System for Visual Classification of Plant Species and Diseases Using Deep Learning and TensorFlow Lite
Reda, Mariam
Plant disease
Deep learning
Computer vision
Transfer learning
Artificial intelligence
Agriculture
Mobile app system
Convolutional neural networks
Classification
Plant care support
status_str publishedVersion
title AgroAId: A Mobile App System for Visual Classification of Plant Species and Diseases Using Deep Learning and TensorFlow Lite
title_full AgroAId: A Mobile App System for Visual Classification of Plant Species and Diseases Using Deep Learning and TensorFlow Lite
title_fullStr AgroAId: A Mobile App System for Visual Classification of Plant Species and Diseases Using Deep Learning and TensorFlow Lite
title_full_unstemmed AgroAId: A Mobile App System for Visual Classification of Plant Species and Diseases Using Deep Learning and TensorFlow Lite
title_short AgroAId: A Mobile App System for Visual Classification of Plant Species and Diseases Using Deep Learning and TensorFlow Lite
title_sort AgroAId: A Mobile App System for Visual Classification of Plant Species and Diseases Using Deep Learning and TensorFlow Lite
topic Plant disease
Deep learning
Computer vision
Transfer learning
Artificial intelligence
Agriculture
Mobile app system
Convolutional neural networks
Classification
Plant care support
url http://hdl.handle.net/11073/24065