Optimization techniques on fuzzy inference systems to detect Xanthomonas campestris disease

Velandia, Julio Barón; Calderón, Camilo Enrique Rocha; Lara, Daniel David Leal

doi:10.11591/ijece.v11i4.pp3510-3518

Cited by 2 publications

(2 citation statements)

References 26 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chen et al, [10] the fully automated identification and categorization of plant leaf infections are handled in a novel way in this paper. The feature engineering assessment was carried out predicated on the image processing technologies, and the index system for the estimation methodologies was built.…”

Section: Literature Reviewmentioning

confidence: 99%

Reliable and Automatic Recognition of Leaf Disease Detection using Optimal Monarch Ant Lion Recurrent Learning

O S,

Sasikala,

Balakrishnan

2023

IJRITCC

View full text Add to dashboard Cite

Around 7.5 billion people worldwide depend on agriculture production for their livelihood, making it an essential component in keeping life alive on the planet. Negative impacts are being caused on the agroecosystem due to the rapid increase in the use of chemicals to combat plant diseases. These chemicals include fungicides, bactericides, and insecticides. Both the quantity and quality of the output are impacted when there is a high-scale prevalence of diseases in crops. Plant diseases provide a significant obstacle for the agricultural industry, which has a negative impact on the growth of plants and the output of crops. The problem of early detection and diagnosis of diseases can be solved for the benefit of the farming community by employing a method that is both quick and reliable regularly. This article proposes a model for the detection and diagnosis of leaf infection called the Automatic Optimal Monarch AntLion Recurrent Learning (MALRL) model, which attains a greater authenticity. The design of a hybrid version of the Monarch Butter Fly optimization algorithm and the AntLion Optimization Algorithm is incorporated into the MALRL technique that has been proposed. In the leaf image, it is used to determine acceptable aspects of impacted regions. After that, the optimal characteristics are used to aid the Long Short Term Neural Network (LSTM) classifier to speed up the process of lung disease categorization. The experiment's findings are analyzed and compared to those of ANN, CNN, and DNN. The proposed method was successful in achieving a high level of accuracy when detecting leaf disease for images of healthy leaves in comparison to other conventional methods.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Reliable and Automatic Recognition of Leaf Disease Detection using Optimal Monarch Ant Lion Recurrent Learning

O S,

Sasikala,

Balakrishnan

2023

IJRITCC

View full text Add to dashboard Cite

show abstract

“…Optimization techniques are also implemented to increase the performance of classification methods such as modified simulated annealing and extreme learning machine which gets 69.7% accuracy [11], particle swarm optimization and extreme learning machine which gets 79.92% accuracy [12], particle swarm optimization and back-propagation neural network that achieves 96.2% accuracy [13], dempster-shafer optimization using genetic algorithm which gets 87.096% accuracy [14], and fuzzy inference systems optimization using Quasi-Newton and genetic algorithms which gets 94% accuracy [15]. One of drawback using hybrid methods is it tend to require higher computational time.…”

Section: Introductionmentioning

confidence: 99%

Kenaf plant pest and disease detection using faster regional based convolutional neural network

Rakhmandasari

Mahmudy

Yulianti³

2021

IJEECS

View full text Add to dashboard Cite

<span>Kenaf plant is a fibre plant whose stem bark is taken to be used as raw material for making geo-textile, particleboard, pulp, fiber drain, fiber board, and paper. The presence of plant pests and diseases that attack causes crop production to decrease. The detection of pests and diseases by farmers may be a challenging task. The detection can be done using artificial intelligence-based method. Convolutional neural networks (CNNs) are one of the most popular neural network architectures and have been successfully implemented for image classification. However, the CNN method is still considered a long time in the process, so this method was developed into namely faster regional based convolution neural network (RCNN). As the selection of the input features largely determines the accuracy of the results, a pre-processing procedure is developed to transform the kenaf plant image into input features of faster RCNN. A computational experiment proves that the faster RCNN has a very short computation time by completing 10000 iterations in 3 hours compared to convolutional neural network (CNN) completing 100 iterations at the same time. Furthermore, Faster RCNN gets 77.50% detection accuracy and bounding box accuracy 96.74% while CNN gets 72.96% detection accuracy at 400 epochs. The results also prove that the selection of input features and its pre-processing procedure could produce a high accuracy of detection. </span>

show abstract

Optimization techniques on fuzzy inference systems to detect Xanthomonas campestris disease

Cited by 2 publications

References 26 publications

Reliable and Automatic Recognition of Leaf Disease Detection using Optimal Monarch Ant Lion Recurrent Learning

Reliable and Automatic Recognition of Leaf Disease Detection using Optimal Monarch Ant Lion Recurrent Learning

Kenaf plant pest and disease detection using faster regional based convolutional neural network

Contact Info

Product

Resources

About