ODHEPDC: Optimal Trained Deep Hybrid Ensemble of Classifier for Plant Disease Classification With Improved Deep Fuzzy Clustering DOI
R. K. Mittal, Varun Malik, Geetanjali Singla

et al.

Journal of Phytopathology, Journal Year: 2024, Volume and Issue: 172(6)

Published: Nov. 1, 2024

ABSTRACT Plant diseases are the major factors that affects quality production as it or interrupts plant's vital functions. The early detection of crop disease could assist farmers in implementing right preventative measures at moment to eradicate it. main goal ODHEPDC (Optimal Trained Deep Hybrid Ensemble Classifier for Classification Disease) model is classification leaf images. primary step improve input image by using MF remove noise. This considered preprocessing step. Improved fuzzy clustering algorithm, leading identification regions, ROI well non‐ROI. Next this, appropriate features extracted define feature set includes MPPT feature, PHOG and MTP well. However, curse dimensionality greatest crisis problem, hence, improved level fusion progressed, which simple concatenation features. In calculation information gain ensures reduction set. fused inputs ensemble with classifiers like CNN, RNN, DBN classifiers, gives classified results. To boost up performance model, Maxout optimally trained a new Bald Eagle Search Updated Pelican Optimization (BESUPO) Algorithm via optimal weights tuning determines final outcome. validation results prove given architecture than extant schemes.

Language: Английский

Classification of maize leaf diseases with deep learning: Performance evaluation of the proposed model and use of explicable artificial intelligence DOI
Feyyaz Alpsalaz, Yıldırım ÖZÜPAK, Emrah Aslan

et al.

Chemometrics and Intelligent Laboratory Systems, Journal Year: 2025, Volume and Issue: 262, P. 105412 - 105412

Published: April 23, 2025

Language: Английский

Citations

0
An Approach Toward Classifying Plant-Leaf Diseases and Comparisons With the Conventional Classification DOI Creative Commons
Anita Shrotriya, Akhilesh Sharma, Srikanth Prabhu

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 117379 - 117398

Published: Jan. 1, 2024

Language: Английский

Citations

2
Refining tomato disease recognition: hyperparameter tuning on ResNet-101 architecture for precise leaf-based classification DOI Open Access
Tegar Arifin Prasetyo, Tiurma Lumban Gaol, Nico Felix Sipahutar

et al.

Indonesian Journal of Electrical Engineering and Computer Science, Journal Year: 2024, Volume and Issue: 34(2), P. 1204 - 1204

Published: March 23, 2024

Tomatoes plants are widely recognized as versatile vegetables globally. This study aims to develop a high-precision web interface for classifying various leaf diseases in tomatoes. Utilizing convolutional neural network (CNN) algorithm using the residual network-101 (ResNet-101) architecture, this tool aids farmers accurately identifying tomatoes, thereby reducing risk of crop failure. The dataset comprises 6,800 images, categorized into four classes: early blight, spider mites two spotted, tomato yellow curl virus, and healthy each containing 1,700 images. Hyperparameter tuning was conducted part an experiment aimed at enhancing performance model. Experiments involved varying epoch values (10, 25, 30, 50, 60, 75, 100, 110), fixed batch size 4, different learning rates (0.1, 0.01, 0.001, 0.0001), num workers (4, 8, 16). results demonstrated accuracy 99% with 100 epochs, rate 16 workers. Consequently, research contributes deeper understanding disease management plants, ensuring optimal quality quantity harvest.

Language: Английский

Citations

1
Breeding 4.0 vis-à-vis application of artificial intelligence (AI) in crop improvement: an overview DOI

R. Ansari,

Anindita Manna,

Soham Hazra

et al.

New Zealand Journal of Crop and Horticultural Science, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 43

Published: Oct. 6, 2024

The field of plant breeding has witnessed significant transformations over millennia evolving from rudimentary selection strategies (Breeding 1.0) in ancient times to sophisticated techniques the modern era 4.0) which can identify desirable alleles and engineer contain them all a short amount time, essence, creating 'designer plants'. This evolution aims enhance crop variety improve food security. However, challenges, such as climate change, population growth limited arable land, necessitate more precise efficient methods. Here, artificial intelligence (AI) emerges promising solution. By mimicking human intelligence, AI process vast datasets efficiently, addressing complexities breeding. In this context, facilitates high-throughput phenotyping, gene functional analysis processing extensive environmental data. It revolutionises decision-making by transforming fragmented market information into systematic strategies. review explores historical journey breeding, emphasising shift traditional methods AI-driven approaches. highlights AI's critical role developing climate-resilient pest-resistant crops, ensuring that key staples like maize, wheat, rice, tomato, potato cotton meet global security challenges effectively.

Language: Английский

Citations

1
Special Issue on “Plant Biology and Biotechnology: Focus on Genomics and Bioinformatics 2.0” DOI Open Access
Yuriy L. Orlov, Ming Chen

International Journal of Molecular Sciences, Journal Year: 2023, Volume and Issue: 24(24), P. 17588 - 17588

Published: Dec. 18, 2023

The analysis of molecular mechanisms underlying plant adaptation to environmental changes and stress response is crucial for biotechnology [...].

Language: Английский

Citations

1
Medicinal Plant Classification Using Transfer Learning Through Hybrid Machine Learning and Image Processing Techniques DOI
A. Lakshmanarao,

Pathuri Sudeep Kumar,

Dighvijay Singh Chauhan

et al.

Published: May 3, 2024

Language: Английский

Citations

0
Modeling the Effects of Temperature and Leaf Wetness on Sclerotinia Stem Rot in Soybeans to Predict Disease Incidence and Severity Using Decision Trees DOI

G. S. Davi,

Ederson Antônio Civardi, David Henriques da Matta

et al.

Published: Jan. 1, 2024

Language: Английский

Citations

0
ODHEPDC: Optimal Trained Deep Hybrid Ensemble of Classifier for Plant Disease Classification With Improved Deep Fuzzy Clustering DOI
R. K. Mittal, Varun Malik, Geetanjali Singla

et al.

Journal of Phytopathology, Journal Year: 2024, Volume and Issue: 172(6)

Published: Nov. 1, 2024

ABSTRACT Plant diseases are the major factors that affects quality production as it or interrupts plant's vital functions. The early detection of crop disease could assist farmers in implementing right preventative measures at moment to eradicate it. main goal ODHEPDC (Optimal Trained Deep Hybrid Ensemble Classifier for Classification Disease) model is classification leaf images. primary step improve input image by using MF remove noise. This considered preprocessing step. Improved fuzzy clustering algorithm, leading identification regions, ROI well non‐ROI. Next this, appropriate features extracted define feature set includes MPPT feature, PHOG and MTP well. However, curse dimensionality greatest crisis problem, hence, improved level fusion progressed, which simple concatenation features. In calculation information gain ensures reduction set. fused inputs ensemble with classifiers like CNN, RNN, DBN classifiers, gives classified results. To boost up performance model, Maxout optimally trained a new Bald Eagle Search Updated Pelican Optimization (BESUPO) Algorithm via optimal weights tuning determines final outcome. validation results prove given architecture than extant schemes.

Language: Английский

Citations

0