Title: Deep learning-based hybrid optimisation for multiclass plant disease detection using leaf images in a distributed environment

Authors: Bandi Ranjitha; Arpakkam Karuppan Sampath

Addresses: Department of CSE, Presidency University, Bangalore, Karnataka, 560064, India ' Department of CSE, Presidency University, Bangalore, Karnataka, 560064, India

Abstract: A novel module is designed for multi-class plant disease detection named fractional geese jellyfish search optimisation enabled deep convolutional neural network (FGJSO_DCNN). The input plant leaf image is partitioned utilising enhanced fuzzy c-means clustering (FCM). In the mapper phase, pre-processing is performed by an adaptive Kalman filter (AKF), and leaf disease segmentation is carried out by Link-net, which is trained to employ FGJSO. The augmentation progress is conducted to alter the provided image. The progression of feature extraction is carried out, and it is given to the reducer phase. On the other hand, in the reducer phase, plant disease classification is accomplished in terms of first level classification using DCNN tuned by FGJSO and second level classification that is detection progress is performed by FGJSO_DCNN. The suggested FGJSO_DCNN model achieved a maximum accuracy of 0.915, TPR of 0.908, FPR of 0.080, F1-score of 0.918, and precision of 0.928.

Keywords: plant disease detection; MapReduce framework; wild geese migration optimisation; GMO; jellyfish search optimisation; JSO; deep convolutional neural network; deep CNNs.

DOI: 10.1504/IJIIDS.2026.150437

International Journal of Intelligent Information and Database Systems, 2026 Vol.18 No.1, pp.48 - 82

Received: 16 Jan 2024
Accepted: 28 Aug 2024
Published online: 13 Dec 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article