New approach for sugarcane disease recognition through visible and near-infrared spectroscopy and a modified wavelength selection method using machine learning models

• Main Authors: Pauline Ong, Pauline Ong, Jinbao Jian, Jinbao Jian, Xiuhua Li, Xiuhua Li, Chengwu Zou, Chengwu Zou, Jianghua Yin, Jianghua Yin, Guodong Ma, odong Ma
• Format: Article
• Language: English
• Published: Elsevier 2023
• Subjects: TA170-171 Environmental engineering
• Online Access: http://eprints.uthm.edu.my/10107/1/J16248_dfba6cf89b35312a27fbc7fff1ce39b0.pdf; http://eprints.uthm.edu.my/10107/; https://doi.org/10.1016/j.saa.2023.123037

The proliferation of pathogenic fungi in sugarcane crops poses a significant threat to agricultural productivity and economic sustainability. Early identification and management of sugarcane diseases are therefore crucial to mitigate the adverse impacts of these pathogens. In this study, visible and near-infrared spectroscopy (380–1400 nm) combined with a novel wavelength selection method, referred to as modified flower pollination algorithm (MFPA), was utilized for sugarcane disease recognition. The selected wavelengths were incorporated into machine learning models, including Naïve Bayes, random forest, and support vector machine (SVM). The developed simplified SVM model, which utilized the MFPA wavelength selection method yielded the best performances, achieving a precision value of 0.9753, a sensitivity value of 0.9259, a specificity value of 0.9524, and an accuracy of 0.9487. These results outperformed those obtained by other wavelength selection approaches, including the selectivity ratio, variable importance in projection, and the baseline method of the flower pollination algorithm.