A Novel Optimized Convolutional Neural Network Based on Marine Predators Algorithm for Citrus Fruit Quality Classification

Gehad Ismail Sayed, Aboul Ella Hassanien () and Mincong Tang ()
Additional contact information
Gehad Ismail Sayed: Faculty of Computers and AI and Scientific Research Group in Egypt (SRGE)
Aboul Ella Hassanien: Faculty of Computers and AI and Scientific Research Group in Egypt (SRGE)
Mincong Tang: Beijing Jiaotong University

A chapter in LISS 2021, 2022, pp 682-692 from Springer

Abstract: Abstract Plant diseases have a huge impact on the reduction in production in agriculture. This may lead to economic losses. Citrus is one of the major sources of nutrients on the planet such as vitamin C. Last decade, machine learning algorithms have been widely used for the classification of diseases in plants. In this paper, a new hybrid approach based on the marine predators algorithm (MPA) and convolutional neural network for the classification of citrus disease is proposed. MPA is used to find the optimal values of batch size, drop-out rate, drop-out period, and maximum epochs. The experimental results showed that the proposed optimized ResNet50 based on MPA is superior. It achieved overall accuracy 100% for citrus disease classification.

Keywords: Marine predators algorithm; Convolutional neural network; Citrus diseases; Fruit quality (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:lnopch:978-981-16-8656-6_60

Ordering information: This item can be ordered from
http://www.springer.com/9789811686566

DOI: 10.1007/978-981-16-8656-6_60

Access Statistics for this chapter

More chapters in Lecture Notes in Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().