Identification of pummelo cultivars by using Vis/NIR spectra and pattern recognition methods

• Published in: Precision agriculture Vol. 17; no. 3; pp. 365 - 374
• Main Authors: Li, Xun-lan, Shi-lai Yi, Shao-lan He, Qiang Lv, Rang-jin Xie, Yong-qiang Zheng, Lie Deng
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.06.2016; Springer Nature B.V
• Subjects: Agriculture; Analysis; Atmospheric Sciences; Back propagation; Biomedical and Life Sciences; Calibration; Chemistry and Earth Sciences; Citrus maxima; Computer Science; Cultivars; Discriminant analysis; Fruits; least squares; Leaves; Life Sciences; Methods; near-infrared spectroscopy; Neural networks; Pattern recognition; Physics; Precision farming; principal component analysis; Principal components analysis; pummelos; Remote Sensing/Photogrammetry; Software; Soil Science & Conservation; spectral analysis; Spectroscopy; Spectrum analysis; Statistics for Engineering; Studies; Support vector machines; BPNN; PLS-DA; LS-SVM; Vis/NIR spectroscopy; SIMCA; Pummelo
• ISSN: 1385-2256; 1573-1618
• DOI: 10.1007/s11119-015-9426-5

Vis/NIR spectroscopy was used in combination with pattern recognition methods to identify cultivars of pummelo (Citrus grandis (L.) Osbeck). A total of 240 leaf samples, 60 for each of the four cultivars were analyzed by Vis/NIR spectroscopy. Soft independent modeling of class analogy (SIMCA), partial least square discriminant analysis (PLS-DA), back propagation neural network (BPNN) and least squares support vector machine (LS-SVM) were applied to the spectral data. The first 8 principal components extracted by principal component analysis were used as inputs in building the BPNN and the LS-SVM models. The results showed that a 97.92 % of discrimination accuracy was achieved for both the BPNN and the LS-SVM models when used to identify samples of the validation set, indicating that the performance of the two models was acceptable. Comparatively, the results of the PLS-DA and the SIMCA models were unacceptable because they had lower discrimination accuracy. The overall results demonstrated that use of Vis/NIR spectroscopy coupled with the use of BPNN and LS-SVM could achieve an accurate identification of pummelo cultivars.