Abstract

Near infrared (NIR) spectroscopy, coupled with multivariate data analysis, is proposed as a rapid and effective analytical method for evaluating the quality of pernambuco (Caesalpina echinata Lam.) wood for making bows for stringed instruments. For this purpose, a set of 30 pernambuco sticks were ranked based on their suitability for making high-quality bows and they were assigned to one of the following categories: 0=very poor to poor, 1 = good to very good and 2 = excellent. Considering the low number of samples in the poor category, the classification study focused on the discrimination between samples of the two higher quality groups. Linear discriminant analysis (LDA) was applied to the NIR data as a classification technique and in order to ensure a more appropriate ratio between the number of objects (samples) and number of variables (absorbance at different wavenumbers), LDA was preceded by feature selection. Based on LDA, 100% of the samples were correctly classified and 92.6% of the samples were correctly predicted by the cross-validation procedure.

© 2010 IM Publications LLP

Wood quality of Chinese zither panel based on convolutional neural network and near-infrared spectroscopy

Yinglai Huang, Shiyu Meng, Peng Zhao, and Chao Li
Appl. Opt. 58(18) 5122-5127 (2019)

Pattern recognition of visible and near-infrared spectroscopy from bayberry juice by use of partial least squares and a backpropagation neural network

Haiyan Cen, Yidan Bao, and Yong He
Appl. Opt. 45(29) 7679-7683 (2006)

Discrimination of lymphoma using laser-induced breakdown spectroscopy conducted on whole blood samples

Xue Chen, Xiaohui Li, Sibo Yang, Xin Yu, and Aichun Liu
Biomed. Opt. Express 9(3) 1057-1068 (2018)

Optical properties of drying wood studied by time-resolved near-infrared spectroscopy

Keiji Konagaya, Tetsuya Inagaki, Ryunosuke Kitamura, and Satoru Tsuchikawa
Opt. Express 24(9) 9561-9573 (2016)

Spectral characterization and discrimination of synthetic fibers with near-infrared hyperspectral imaging system

Xiaoke Jin, Hafeezullah Memon, Wei Tian, Qinli Yin, Xiaofang Zhan, and Chengyan Zhu
Appl. Opt. 56(12) 3570-3576 (2017)