Deep learning in wheat diseases classification: A systematic review

• Published in: Multimedia tools and applications Vol. 81; no. 7; pp. 10143 - 10187
• Main Authors: Kumar, Deepak, Kukreja, Vinay
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.03.2022; Springer Nature B.V
• Subjects: Agriculture; Bacterial diseases; Classification; Computer Communication Networks; Computer Science; Crop diseases; Crops; Data Structures and Information Theory; Datasets; Deep learning; Food security; Fungal diseases; Fungicides; Insects; Machine learning; Multimedia; Multimedia Information Systems; Plant diseases; Prediction models; Quality assessment; Research methodology; Special Purpose and Application-Based Systems; Systematic review; Visualization; Wheat; Deep learning; Support vector machine; Wheat diseases; Neural networks
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-022-12160-3

The main goal of this paper is to review systematically the recent studies that have been published and discussed WD prediction models. The literature analysis is performed based on studies published from January 1997 to February 2021 by following Kitchenham instructions. After inclusion/exclusion and quality assessment criteria screening, a total of 74 studies have been selected. The literature shows that WD is categorized into three (fungal diseases, bacterial diseases, and insect diseases) types. The research analysis shows that most of the work in the literature has been found on wheat stripe rust (60.81%) disease and the most used prediction technique is ANN (13.32%). The results show that accuracy (67%) is the most prominent performance metric and in the year 2020, a maximum number of papers are published on WD. Also, only five studies have used hybrid approaches which are the combination of SVM and NN techniques.