Using a novel convolutional neural network for plant pests detection and disease classification
Journal of the Science of Food and Agriculture · 2023-09 · 103 (12) · 5849-5861
DOI: 10.1002/jsfa.12700 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the Science of Food and Agriculture, online erschienen am 24.05.2023. Verfasst von Wasswa Shafik und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Digital Science, Universiti Brunei Darussalam, Gadong, Brunei Darussalam. Hauptthemen laut MEDLINE: Agriculture, Malus. Die Arbeit wurde bisher 60-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: Universiti Brunei Darussalam.
Abstract (Originalsprache)
Background
Early plant diseases and pests identification reduces social, economic, and environmental deficiencies entailing toxic chemical utilization on agricultural farms, thus posing a threat to global food security. Methodology An enhanced convolutional neural network (CNN) along with long short‐term memory (LSTM) using a majority voting ensemble classifier has been proposed to tackle plant pest and disease identification and classification. Within pre‐trained models, deep feature extractions have been obtained from connected layers. Deep features have been extracted and are sent to the LSTM layer to build a robust, enhanced LSTM‐CNN model for detecting plant pests and diseases. Experiments were carried out using a Turkey dataset, with 4447 apple pests and diseases categorized into 15 different classes.
Results
The study was evaluated in different CNNs using logistic regression (LR), LSTM, and extreme learning machine (ELM), focusing on plant disease detection problems. The ensemble majority voting classifier was used at the LSTM layer to detect and classify plant disease labels. Furthermore, an autonomous selection of the optimal LSTM layer network parameters was applied. Finally, the performance was validated based on sensitivity, F 1 score, accuracy, and specificity using LSTM, ELM, and LR classifiers.
Conclusion
The presented model attained 99.2% accuracy compared to the cutting‐edge models on different classifiers such as LSTM, LR, and ELM, and performed better compared to transfer learning. Pre‐trained models, such as VGG19, VGG18, and AlexNet, demonstrated better accuracy when the fc6 layer was compared with other layers. © 2023 Society of Chemical Industry.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Digital Science, Universiti Brunei Darussalam, Gadong, Brunei Darussalam.
ORCID-Profile: Wasswa Shafik, Ali Tufail, Chandratilak De Silva Liyanage
Förderung
- Universiti Brunei Darussalam
Zitieren
APA
Shafik, W., Tufail, A., Liyanage, C. S., & Apong, R. A. A. H. M. (2023). Using a novel convolutional neural network for plant pests detection and disease classification. Journal of the Science of Food and Agriculture, 103(12), 5849-5861. https://doi.org/10.1002/jsfa.12700
Vancouver
Shafik W, Tufail A, Liyanage CS, Apong RAAHM. Using a novel convolutional neural network for plant pests detection and disease classification. Journal of the Science of Food and Agriculture. 2023;103(12):5849-5861. doi:10.1002/jsfa.12700
BibTeX
@article{Shafik2023,
author = {Shafik, Wasswa and Tufail, Ali and Liyanage, Chandratilak De Silva and Apong, Rosyzie Anna Awg Haji Mohd},
title = {Using a novel convolutional neural network for plant pests detection and disease classification},
journal = {Journal of the Science of Food and Agriculture},
year = {2023},
volume = {103},
number = {12},
pages = {5849--5861},
doi = {10.1002/jsfa.12700}
}
EUVIMED