1. College of Mechanical and Electronic Engineering, Northwest A&F University, Yangling 712100, China
2. Key Laboratory of Agricultural Internet of Things, Ministry of Agriculture and Rural Affairs, Yangling 712100, China
3. Shaanxi Key Laboratory of Agricultural Information Perception and Intelligent Service, Yangling 712100, China
4. College of Agronomy, Northwest A&F University, Yangling 712100, China
Abstract：In order to explore the feasibility of detecting wheat kernel black tip (BT) disease and investigating an optimized classification model based on mainstream machine learning algorithms, a large amount of 2 760 wheat kernels spectral data of Vis/NIR bands (579~1 099 nm) were collected by self-made spectral acquisition platform. After pretreated with standard normal variate correction (SNV) of 600~1 045 nm bands, 7 kinds of data sets were established. Successive Projections Algorithm (SPA) and Principal Component Analysis (PCA) of spectral data dimensionality reduction methods, and four machine learning algorithms, Support Vector Machine (SVM), Extreme Learning Machine (ELM), Random Forest (RF) and AdaBoost, were adopted to develop eight classification models. Results showed that Vis/NIR spectrums combined with all the machine learning methods could be used to detect BT disease with accuracies ranging from 93.3% to 98.6%, which indicated that Vis/NIR would be the more effectively compared to NIR. As SPA-SVM possessed a high average classification accuracy and PCA-AdaBoost showed better generalization performance than other algorithms, considering practical purposes, these two algorithms were adopted as optimized models in 2-category classification, 3-category classification and 4-category classification for various degrees of BT detection. Results indicated that the classification accuracies declined gradually with the classification number increasing, but the detection accuracy of non-diseased wheat kernel tended to be stable with an accuracy of more than 87.2%. Taken together, SPA-SVM performed better than PAC-AdaBoost in wheat BT disease detection. The models and conclusions of this research are intended to lead to the streamlining of VIS/NIR spectroscopy in automated wheat black tip inspection as well as to provide criteria for high speed sorting.
Key words：Wheat black tip disease; Vis/NIR; Machine learning; Optimized Models; Multiple classification
[1] Fox G, Watson L, Kelly A, et al. Developing an NIRS Method for Assessing Black Point in Single Kernels of Malting Barley. Proceedings of the 2012 World Brewing Congress, Portland, OR, 2012.
[2] Delwiche S R, Yang I C, Graybosch R A. Computers & Electronics in Agriculture, 2013, 98(7): 62.
[3] Armstrong Paul R, Maghirang Elizabeth B, Pearson Tom C. Cereal Chemistry, 2015, 92(4): 358.
[4] USDA-GIPSA-FGIS. Qrain Inspection Handbook Ⅱ. USA: Federal Grain Inspection Service, 2014. 1325.
[5] CHENG Shu-xi, XIE Chuan-qi, WANG Qiao-nan, et al(程术希, 谢传奇, 王巧男, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2014, 34(5): 1362.
[6] Galvao R K, Araujo M C, Jose G E, et al. Talanta, 2005, 67(4): 736.
[7] ElMasry G, Sun D-W, Allen P. Food Research International, 2011, 44(9): 2624.
[8] ZHOU Zhi-hua(周志华). Machine Learning(机器学习). Beijing: Tsinghua University Press (北京：清华大学出版社), 2016. 10.
[9] Liu D, Sun D W, Zeng X A. Food & Bioprocess Technology, 2014, 7(2): 307.
