Proceedings of the 1st International Conference on Neural Networks and Machine Learning 2022 (ICONNSMAL 2022)

<Previous Article In Volume
Next Article In Volume>

Comparing the Architecture of Convolutional Neural Network for Corn Leaves Diseases Image Classification

Authors
Aeri Rachmad1, *, Wahyudi Setiawan1, Eka Mala Sari Rochman1
1Faculty of Engineering, University of Trunojoyo Madura, Bangkalan, Indonesia
*Corresponding author. Email: aery_r@trunojoyo.ac.id
Corresponding Author
Aeri Rachmad
Available Online 22 May 2023.
DOI
10.2991/978-94-6463-174-6_9How to use a DOI?
Keywords
Corn Leaves Diseases; Image Classification; Convolutional Neural Network; Residual Network
Abstract

This article discusses the comparison of the Convolutional Neural Net- work (CNN) architecture for image classification of corn leaves diseases. This study uses public data on from Plantvillages. The data be contained in four classes: gray leaf spot, common rust, leaf blight, and healthy. Each class consists of 1000 images, except for the gray leaf spot only 500 images. The experiment uses five CNN architectures: SqueezeNet, AlexNet, ResNet18, ResNet50, and ResNet101. SqueezeNet and AlexNet are CNN sequential models with deeper layer models. While Residual Network (ResNet) is a CNN architecture that utilizes additional output from the previous two layers to be used as input to the next layer. The CNN parameters used during the training step are learning rate 0.0001, epoch 1, batch-size 8, and adaptive moment estimation (Adam). The experiment was running in a single Central processing Unit (CPU). The percentage of training and testing data is 70:30. ResNet50 shows the best accuracy up to 95.59% with a computation time of 79 min. and 10 s. The experiment shows that the use of CNN architecture with the residual network model is better than the sequential network model.

Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 1st International Conference on Neural Networks and Machine Learning 2022 (ICONNSMAL 2022)
Series
Advances in Intelligent Systems Research
Publication Date
22 May 2023
ISBN
978-94-6463-174-6
ISSN
1951-6851
DOI
10.2991/978-94-6463-174-6_9How to use a DOI?
Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Aeri Rachmad
AU  - Wahyudi Setiawan
AU  - Eka Mala Sari Rochman
PY  - 2023
DA  - 2023/05/22
TI  - Comparing the Architecture of Convolutional Neural Network for Corn Leaves Diseases Image Classification
BT  - Proceedings of the 1st International Conference on Neural Networks and Machine Learning 2022 (ICONNSMAL 2022)
PB  - Atlantis Press
SP  - 81
EP  - 88
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-174-6_9
DO  - 10.2991/978-94-6463-174-6_9
ID  - Rachmad2023
ER  -