Revolutionizing agriculture with deep learning current trends and future directions

Ahmad Radzi, Syafeeza and NORAZLINA BINTI ABD RAZAK, NORAZLINA BINTI ABD RAZAK and Mohd Zaimi, Muhammad Zaim and Amsan, Azureen Naja and Mohd Saad, Wira Hidayat and Abdul Hamid, Norihan (2024) Revolutionizing agriculture with deep learning current trends and future directions. International Journal of Integrated Engineering, 16 (3). pp. 192-211. ISSN 2229-838X

Text 01145031220241439281315.pdf Download (682kB)

Abstract

Deep learning (DL) presents new opportunities for agricultural technologies, offering superior accuracy over traditional methods. This study reviews 61 publications employing DL to address various agricultural issues, including disease identification, plant and crop detection, and classification. Notable performances include the VGG model for plant disease detection with 99.53% accuracy, AlexNet and GoogleNet with 99.76% accuracy, and ResNet-152 with 99.75% accuracy. In plant and crop classification, AlexNet achieved 99.80% accuracy, while MobileNet achieved 99% accuracy in fruit detection for mango and pitaya. A fine-tuned VGG-16 model reached 99.75% and 96.75% accuracy in fruit classification using two datasets. Additionally, CNN achieved 98% accuracy in improving efficiency, and a modified Inception-ResNet model achieved 91% and 93% accuracy in fruit counting on real and synthetic images, respectively. By analyzing frameworks, data sources, pre-processing methods, and results, the survey reveals that deep learning significantly enhances learning capabilities and precision in agricultural applications through hierarchical data representation and convolutional layers. This review underscores DL’s potential in promoting smarter, safer food production and sustainable farming practices, encouraging further exploration and adoption of DL in various unexplored agricultural domains.

Item Type:	Article
Uncontrolled Keywords:	Agriculture, Convolutional neural networks, Smart farming, Deep learning, Predictive agriculture
Divisions:	Faculty Of Electronics And Computer Technology And Engineering
Depositing User:	Norfaradilla Idayu Ab. Ghafar
Date Deposited:	08 Oct 2025 00:30
Last Modified:	08 Oct 2025 00:30
URI:	http://eprints.utem.edu.my/id/eprint/28952
Statistic Details:	View Download Statistic

Actions (login required)

View Item