Visitors: 1383

  MAZEDAN DIGITAL LIBRARY    

  JOURNAL MANAGEMENT SYSTEM

MDL
JMS  
MAZEDAN DIGITAL LIBRARY

Testing of a mathematical model for the classification of diseases in agricultural plants using convolutional neural networks

JOURNAL:MAZEDAN INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS

Download pdf
# Authors First Online DOI Downloads Citations
1. Vivek Srivastava, Sonal Saxena 27 Jun 2022 NA 10 0
Abstract

Plants are the most important contributor to the production of food for societies through agriculture. Plant diseases can have a negative impact not only on production costs but also on human health. In order to keep these disorders under control, constant monitoring of their progression is required. The traditional techniques of monitoring these disorders require a significant amount of time and effort. It is an extremely lengthy document that has several typos in it. We are currently living through a transition into a new era characterised by emerging tendencies and technologies such as machine learning, deep learning, and artificial intelligence. These developments have the potential to assist in mitigating the negative effects of disease and overcoming the limitations imposed by human monitoring. In the course of this body of work involving study, we investigated various CNN classification models using 22,912 tomato leaf pictures. These models included Resnet, Resnet18, DenseNet201, VGG16, VGG19, InceptionV3, Imagenet, and MobileNet. Within the scope of our investigation, we made use of Google Collaborative, trained the model, and then reported on the degree to which each model accurately classified 10 distinct categories of photographs (healthy and different types of unhealthy). It has been demonstrated that DenseNet201 has an accuracy of 98.11 percent. The findings have been compared with the findings of studies on machine learning carried out by other researchers, and it has been discovered that the deep learning model is more accurate than other machine learning models in identifying tomato leaf illnesses.

Keywords

Deep Learning, Convolutional Neural Network, Transfer Learning, Agriculture, Classification

References

  1. [1]         Sannakki S.S et al., Diagnosis and Classification of Grape Leaf Diseases using Neural Networks, in: Com411 puting, Communications and Networking Technologies (ICCCNT), 2013 Fourth International Conference on, IEEE, pp. 3-7.

    [2]         A. Breitenreiter A et al, Deep Learning, Nature 521 (2015) 2015.https://plantvillage.psu.edu/topics/tomato/infos

    [3]         http://www.kaggle.com/noulam/tomato

    [4]         Tian H et al., 2020 Computer vision technology in agricultural automation-A Review Information Processing in Agriculture 7 1–19.

    [5]         Kamilaris A et al., 2018 Deep learning in agriculture: A survey Computers and