Feasibility of terahertz spectroscopy for hybrid purity verification of rice seeds

Yaling Yang, Shengling zhou, Jie Song, Jie Huang, Guanglin Li, Shiping Zhu

Abstract


The purity of hybrid rice seeds reflects the typical consistency of seed varieties in characteristics. The accuracy and reliability of seed purity detecting are of great significance to ensure the quality of seeds. In this study, the feasibility of identifying the purity of hybrid rice seeds, Xinong 1A/89, by terahertz (THz) time-domain spectroscopy system combined with chemometrics was explored. Three quantitative identification models for testing the purity of Xinong 1A/89 hybrid rice seed were developed and compared by THz absorption spectroscopy with extreme learning algorithm (ELM), Principal cComponent Regression (PCR) and Partial Least Squares Regression (PLSR). Experimental results showed that comparing with classical PLSR and PCR models, ELM presents a better feasibility and stability. For the testing set, the quantitative prediction result of ELM (ELoo=2.005×10-5, R2=96.75%) is significantly better than those of PCR (ELoo=7.346×10-5, R2=88.10%) and PLSR (ELoo=8.007×10-5, R2=87.03%). The results highlight the feasibility of THz spectroscopy combined with ELM as an efficient and reliable method for verification of hybrid rice seeds.
Keywords: purity detection, hybrid rice seeds, terahertz spectroscopy, extreme learning algorithm
DOI: 10.25165/j.ijabe.20181105.3898

Citation: Yang Y L, Zhou S L, Song J, Huang J, Li G L, Zhu S P. Feasibility of terahertz spectroscopy for hybrid purity verification of rice seeds. Int J Agric & Biol Eng, 2018; 11(5): 65–69.

Keywords


purity detection, hybrid rice seeds, terahertz spectroscopy, extreme learning algorithm

Full Text:

PDF

References


Lai Y H. Identification of the authenticity and purity of hybrid rice seed. China Seed Industry, 2015; 6: 19–21. (in Chinese)

Jia S Q, Liu Z, Li S M, Li L, Ma Q, Zhang X D, et al. Study on method of maize hybrid purity identification based on hyperspectral image technology. Spectroscopy and Spectral Analysis, 2013; 33(10): 2847–2852. (in Chinese)

Liang L, Yang M H, Liu Z X, Xu H W, Liu F H, He Q Z, et al. Purity measurement of hybrid rice seed Yixiang 725 with visible-near infrared reflectance spectra. Spectroscopy and Spectral Analysis, 2009; 29(11): 2962–2965. (in Chinese)

Farhadi M, Tigabu M, Stener L G, Odén P C. Feasibility of visible + near infrared spectroscopy for non-destructive verification of European × Japanese larch hybrid seeds. New Forests, 2016; 47(2): 271–285.

Attaviroj N, Kasemsumran S, Noomhorm A. Rapid variety identification of pure rough rice by fourier-transform near-infrared spectroscopy. Cereal Chemistry, 2011; 88(5): 490–496.

Li T X, Jia S Q, Liu X, Zhao S Y, Ran H, Yan Y L, et al. Maize hybrid seed purity identification based on near infrared reflectance (NIR) and transmittance (NIT) spectra. Spectroscopy and Spectral Analysis, 2015; 35(12): 3388–3392. (in Chinese)

Zhou S L, Zhu S P, Li G L, Huang J, Yang Y L. Study on the measurement and optimization of soybean oil optical spectrum in THz range. Spectroscopy and Spectral Analysis, 2016; 36(4): 924–928. (in Chinese)

Zhou S L, Valchev D G, Dinovitser A, Chappell J M, Iqbal A, Ng B W-H, et al. Terahertz signal classification based on geometric algebra. IEEE Transactions on Terahertz Science & Technology, 2016; 6(6): 793–802.

Deshmukh Y, Khare P, Nadaf A B, Patra D. Discrimination between 2AP producing and non‐producing rice rhizobacterial isolates using volatile profiling: a chemometric approach. Journal of Chemometrics, 2016; 29(12): 648–658.

Xu W D, Xie L J, Ye Z Z, Gao W L, Yao Y, Chen M, et al. Discrimination of transgenic rice containing the Cry1Ab protein using terahertz spectroscopy and chemometrics. Sci Rep., 2015; 5: 11115.

Xu W D, Liu X, Xie L J, Ying Y. Comparison of Fourier transform near-infrared, visible near-infrared, mid-infrared, and Raman spectroscopy as non-invasive tools for transgenic rice discrimination. Transactions of the ASABE, 2014; 57(1): 141–150.

Xie L J, Yao Y, Ying Y B. The application of terahertz spectroscopy to protein detection: A review. Applied Spectroscopy Reviews, 2014; 49(6): 448–461.

Li T J, Liu J J, Shao G F, Fan L L. A novel THz spectroscopy recognition method for transgenic organisms based on APSO combined with SVM. Optics & Spectroscopy, 2016; 120(4): 660–665.

Shen X C, Li B, Li X, Long Y. Identification of transgenic and non-transgenic cotton seed based on terahertz range spectroscopy. Transactions of the CSAE, 2017; 33(S1): 288–292. (in Chinese)

Ge H Y, Jiang Y Y, Lian F Y, Zhang Y, Xia S H. Characterization of wheat varieties using terahertz time-domain spectroscopy. Sensors, 2015; 15(6): 12560–12572.

Gao H, Huang G B, Song S J, You K. Trends in extreme learning machines: A review. Neural Networks, 2015; 61(C): 32–48.

Baum E B, Haussler D. What size net gives valid generalization? Neural Computation, 2014; 1(1): 151–160.

Heeswijk M V, Miche Y. Binary/ternary extreme learning machines. Neurocomputing, 2015; 149: 187–197.




Copyright (c) 2018



2023-2026 Copyright IJABE Editing and Publishing Office