Rice Germination Rate Detection Based on Fluorescent Spectrometry and Deep Belief Network
LU Wei, GUO Yang-ming, DAI De-jian, ZHANG Cheng-yu, WANG Xin-yu
College of Engineering, Jiangsu Province Engineering Laboratory of Modern Facility Agriculture Technology and Equipment, Nanjing Agricultural University, Nanjing 210031, China
Abstract：Traditional rice seed germination rate detection methods have low efficiency, poor accuracy and high specialization. The paper proposed a novel method by using fluorescent spectrometry combined with Deep Belief Network (DBN) to establish forecasting model for rice seed germination rate. Firstly, two varieties of seeds, Lianjing 7 and Wuyunjing, with 0～7 artificial aged days separately were soaked into purified water for 5～30 minutes with every 5 minutes’ interval. Then the fluorescence spectrums of the soak solutions were detected using fluorescence spectrometer. In addition, the spectrum data were centralized and then denoised with Ensemble Empirical Mode Decomposition (EEMD). The characteristic fluorescence wavelength of 441.5nm was extracted using Principal Component Anamysis (PCA). Finally, the rice seed germination predicting models were establishee with Partial Least Squares Regression (PLSR), Back Propagation Neural Network (BPNN), Radial Basis Function Neural Network (RBFNN) and Deep Belief Network (DBN), respectively. The results showed that the accuracy of DBN model was the highest in the case of less data and weak signal, and Rp=0.979 2, RMSEP=0.101. At the same time,we got the best soaking time is 22.1 min by analyzing the changing trend of mixed rice seed fluorescent data Rp, actually, it took about 5 min to get the accuracy more than 0.95 (Rp). The research results demonstrated the feasibility and high accuracy for predicting rice seed germination rate non-invasively by combining the fluorescent spectrometry and EEMD-DBN model, moreover, it adapts to the detection of rice seeds with different colors and contaminated levels.
基金资助: The National Natural Science Foundation of China Youth Foundation of China (11604154), the Three New Project of Agricultural Machinery in Jiangsu Province (SZ120170036), the Fundamental Research Funds for the Central Universities (KJQN2017011)
作者简介: LU Wei，(1978—), Ph.D., associate professor, master tutor, College of Engineering, Nanjing Agricultural University e-mail:
njaurobot@njau.edu.cn
引用本文:
卢 伟，郭阳鸣，代德建，张澄宇，王新宇. 基于荧光光谱法与深度信念网络的稻种发芽率检测方法研究[J]. 光谱学与光谱分析, 2018, 38(04): 1303-1312.
LU Wei, GUO Yang-ming, DAI De-jian, ZHANG Cheng-yu, WANG Xin-yu. Rice Germination Rate Detection Based on Fluorescent Spectrometry and Deep Belief Network. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(04): 1303-1312.
[1] Sharif M K, Butt M S, Anjum F M, et al. Critical Reviews in Food Science and Nutrition, 2014, 54(6): 807.
[2] Paiva E P, Torres S B, Almeida J P N D, et al. Revista Ciência Agronmica, 2017, 48(1)：118.
[3] Na Y W, Shim S I, Chung J S, et al. Korean Journal of Crop Science, 2014, 59(2)：188.
[4] Lohumi S, Mo C, Cho B K, et al. Journal of Biosystems Engineering, 2013, 38(4): 312.
[5] Song L, Wang Q, Wang C, et al. Journal of Stored Products Research, 2015, 62: 46.
[6] Yu S M, Lu W, Ding D, et al. Laser & Optoelectronics Progress, 2016, 53(1): 113.
[7] Fang W H, Lu W, Xu H L, et al. Spectroscopy and Spectral Analysis, 2016, 36(8): 2692.
[8] Li H, Lu W, Du C, et al. Chinese Journal of Lasers, 2015, 42(11): 1115003.
[9] Fang W, Lu W, Hong D, et al. Optics Journal, 2015, 35(10): 111.
[10] Lu L, Tian S, Zhang J, et al. PLoS One, 2013, 8(2): e57360.
[11] Ambrose A, Lohumi S, Lee W H, et al. Sensors & Actuators B Chemical, 2016, 224: 500.
[12] Yang J, Gong W, Shi S, et al. Scientific Reports, 2016, 6: 28787.
[13] Chen Q, Qi S, Li H, et al. Spectrochimica Acta Part A Molecular & Biomolecular Spectroscopy, 2014, 131(19)：177.
[14] Agati G, Foschi L, Grossi N, et al. European Journal of Agronomy, 2013, 45: 39.
[15] Sergiel I, Pohi P, Biesaga M, et al. Food Chemistry, 2014, 145: 319.
[16] Ko K Y, Lee C A, Choi J C, et al. Food Additives & Contaminants Part A Chemistry Analysis Control Exposure & Risk Assessment, 2014, 31(9): 1451.
[17] Singhal V, Gogna A, Majumdar A. Deep Dictionary Learning vs Deep Belief Network vs Stacked Autoencoder: An Empirical Analysis. International Conference on Neural Information Processing. Springer International Publishing, 2016. 337.
[18] Shaban M. International Journal of Agriculture and Crop Sciences, 2013, 6(11): 627.
[19] Kaewkham T, Russell K H, Boonmee S. Biocontrol Science and Technology, 2016, 26(8): 1048.
[20] Yang H, Fu Y B. Frontiers in Plant Science, 2016, 7: 1474.
[21] Mala D M, Yoshimura M, Kawasaki S, et al. LWT-Food Science and Technology, 2016, 68: 14.
[22] Zhang Y, Liu B, Ji X, et al. Neural Processing Letters, 2017, 45(2): 365.
[23] vokelj M, Samo Z, Ivan P. Journal of Sound and Vibration, 2016, 370: 394.
[24] Jolliffe I T, Jorge C. Phil. Trans. R. Soc. A, 2016, 374: 20150202.
[25] Bro R, Age K S. Analytical Methods, 2014, 6(9): 2812.
[26] Wang L, Zeng Y, Chen T. Expert Systems with Applications, 2015, 42(2): 855.
[27] Lian R J. IEEE Transactions on Industrial Electronics, 2014, 61(3): 1493.
[28] O’Connor P, Neil D, Liu S C, et al. Frontiers in Neuroscience, 2013, 7(178): 1.
[29] Kuremoto Takashi, Shinsuke K, Kunikazu K, et al. Neurocomputing, 2014, 137: 47.
[30] Elena A G, Alexander N T, Folkert A H. Plant Physiology, 1997, 114: 383.
[31] Olivier L, Frans J M H, Julia B, et al. Plant Physiology, 2000, 122(2): 597.
[32] Brits G J, Brown N A C, Calitz F J, et al. South African Journal of Botany, 2015, 97: 1.
[33] Zhao Q, Lv Q, Wang H. Biosensors and Bioelectronics, 2015, 70: 188.
