|
|
|
|
|
|
| Reflectance Spectroscopy for Accurate and Fast Analysis of Saturated
Fatty Acid of Edible Oil Using Spectroscopy-Based 2D Convolution
Regression Network |
| WENG Shi-zhuang*, CHU Zhao-jie, WANG Man-qin, WANG Nian |
National Engineering Research Center for Agro-Ecological Big Data Analysis & Application, Anhui University, Hefei 230601, China
|
|
|
|
|
Abstract The edible oil in the humandaily diet is rich in saturated fatty acids, which can provide energy and other healthy nutrients for the human body, but excessive intake of saturated fatty acids can lead to a variety of cardiovascular diseases. In this study, a method for analyzing the content of saturated fatty acidsin edible oils was developed by combining reflectance spectroscopy and machine learning. Firstly, the reflectance spectra of 7 edible vegetable oils, such as rapeseed oil, soybean oil, sunflower seed oil, corn oil, olive oil, sesame oil and peanut oil, were measured in the range of 350～2 500 nm, as well as the contents of palmitic acid, arachidonic acid and behenic acid were obtained by GC-MS. Spectral preprocessing algorithms were employed to eliminate the noise in spectra, including centralization, multiple scattering correction, standard normal variable transformation and standardization. Then, a novel two-dimensional spectral convolution regression network (S2DCRN) was constructed for fatty acids analysis, and a full convolutional network (FCN), partial least squares regression (PLSR), support vector regression (SVR) and random forest (RF) were compared with S2DCRN. Finally, sequential forward selection (SFS), random frog (RFrog) and genetic algorithm were used to select important wavelength spectra to re-build more simple and robust analysis models. The results showed that the S2DCRN obtained optimal performance after pretreatment of edible oil spectra with the determination coefficient of prediction set (R2P) of 0.987 9 and the root mean square error of prediction set (RMSEP) of 0.510 0. Based on important wavelengths selected by combination RFrog and SFS, the S2DCRN exhibited excellent performance with R2P=0.967 9 and RMSEP=0.462 7. Although the results based on important wavelengths obtained is slightly worse, the number of wavelengths is less than 1% of the full spectra. It is convenient for the measurement of spectra and remarkably reduces the complexity of the model, which is helpful for the further development of portable and simplified detection devices. In addition, to further explore the generalization and applicability of S2DCRN, S2DCRN was used to analyze the content of arachidonic acid and behenic acid and gain a prediction result for arachidonic acid R2P=0.950 1, RMSEP=0.152 9. Therefore, the proposed method accurately and rapidly analysed various fatty acids in edible vegetable oils by reflectance spectroscopy.
|
|
Received: 2021-01-06
Accepted: 2021-06-29
|
|
|
|
Corresponding Authors:
WENG Shi-zhuang
|
|
[1] Cao G D, Ding C, Ruan D L, et al. Food Control, 2019, 96: 494.
[2] Nosratpour M, Farhoosh R, Sharif A. European Journal of Lipid Science and Technology, 2017, 119(12)：1700203.
[3] Li X, Zhang L X, Zhang Y, et al. Trends in Food Science & Technology, 2020, 101：172.
[4] Rohman A. International Journal of Food Properties, 2017, 20(7): 1447.
[5] Xu L Z, Xu X H, Xiong H, et al. Sensors and Actuators B: Chemical, 2014, 203: 697.
[6] Jovic O. Food Chemistry, 2016, 213: 791.
[7] Kwofie F, Lavine B K, Ottaway J, et al. Journal of Chemometrics, 2020, 34(7): 3173.
[8] Sundaram J, Kandala C V, Holser R A, et al. Journal of the American Oil Chemists Society, 2010, 87(10): 1103.
[9] Zhang Y Z, Zhang L B, Wang J, et al. Molecules, 2018, 23(9): 2332.
[10] Xing C R, Yuan X Y, Wu X Y, et al. LWT-Food Science and Technology, 2019, 108: 437.
[11] Zhang X L, Xu J F, Yang J, et al. Analytica Chimica Acta, 2020, 1119: 41.
[12] Acquarelli J, van Laarhoven T, Gerretzen J, et al. Analytica Chimica Acta, 2017, 954: 22.
|
| [1] |
ZHANG Yang1, 2, YUE Jun1*, JIA Shi-xiang1, LI Zhen-bo2, SHENG Guo-rui1. Recognition of Shellfish Based on Visible Spectrum and Convolutional Neural Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3298-3306. |
| [2] |
DAI Qiu-fang1, 2, 3, LIAO Chen-long1, 2, LI Zhen1, 2, 3*，SONG Shu-ran1, 2, 3，XUE Xiu-yun1, 2, 3，XIONG Shi-lu1, 2. Hyperspectral Visualization of Citrus Leaf Moisture Content Based on CARS-CNN[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2848-2854. |
| [3] |
WU Meng-ruo, QIN Zhen-fang, HAN Liu-yang, HAN Xiang-na*. Preparation and Spectra Study of Artificially Degraded Waterlogged Wood[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2941-2946. |
| [4] |
WANG Jing1, 2*, CHEN Zhen3, GAO Quan-zhou1. Diffuse Reflectance Spectroscopy Study of Mottled Clay in the Coastal
Area of Fujian and Guangdong Provinces and the Interpretation of Its
Origin and Sedimentary Environment[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(08): 2494-2498. |
| [5] |
ZHU Meng-yuan1, 2, LÜ Bin1, 2*, GUO Ying2. Comparison of Haematite and Goethite Contents in Aeolian Deposits in Different Climate Zones Based on Diffuse Reflectance Spectroscopy and Chromaticity Methods[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(06): 1684-1690. |
| [6] |
JI Jiang-tao1, 2, LI Peng-ge1, JIN Xin1, 2*, MA Hao1, 2, LI Ming-yong1. Study on Quantitative Detection of Tomato Seedling Robustness
in Spring Seedling Transplanting Period Based on VIS-NIR
Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(06): 1741-1748. |
| [7] |
PENG Ren-miao1, 2, XU Peng-peng2, ZHAO Yi-mo2, BAO Li-jun1, LI Cheng2*. Identification of Two-Dimensional Material Nanosheets Based on Deep Neural Network and Hyperspectral Microscopy Images[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(06): 1965-1973. |
| [8] |
JI Rong-hua1, 2, ZHAO Ying-ying2, LI Min-zan2, ZHENG Li-hua2*. Research on Prediction Model of Soil Nitrogen Content Based on
Encoder-CNN[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(05): 1372-1377. |
| [9] |
JIANG Rong-chang1, 2, GU Ming-sheng2, ZHAO Qing-he1, LI Xin-ran1, SHEN Jing-xin1, 3, SU Zhong-bin1*. Identification of Pesticide Residue Types in Chinese Cabbage Based on Hyperspectral and Convolutional Neural Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(05): 1385-1392. |
| [10] |
ZHAO Yong1, HE Men-yuan1, WANG Bo-lin2, ZHAO Rong2, MENG Zong1*. Classification of Mycoplasma Pneumoniae Strains Based on
One-Dimensional Convolutional Neural Network and
Raman Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(05): 1439-1444. |
| [11] |
TAN Ai-ling1, CHU Zhen-yuan1, WANG Xiao-si1, ZHAO Yong2*. Detection of Pearl Powder Adulteration Based on Raman Spectroscopy and DCGAN Data Enhancement[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(03): 769-775. |
| [12] |
WANG Chun-juan1, 2, ZHOU Bin1, 2*, ZHENG Yao-yao3, YU Zhi-feng1, 2. Navigation Observation of Reflectance Spectrum of Water Surface in Inland Rivers[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(03): 878-883. |
| [13] |
JIANG Jie1, YU Quan-zhou1, 2, 3*, LIANG Tian-quan1, 2, TANG Qing-xin1, 2, 3, ZHANG Ying-hao1, 3, ZHANG Huai-zhen1, 2, 3. Analysis of Spectral Characteristics of Different Wetland Landscapes Based on EO-1 Hyperion[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(02): 517-523. |
| [14] |
DENG Shi-yu1, 2, LIU Cheng-zhi1, 4*, TAN Yong3*, LIU De-long1, ZHANG Nan1, KANG Zhe1, LI Zhen-wei1, FAN Cun-bo1, 4, JIANG Chun-xu3, LÜ Zhong3. A Combination of Multiple Deep Learning Methods Applied to Small-Sample Space Objects Classification[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(02): 609-615. |
| [15] |
JIAO Qing-liang1, LIU Ming1*, YU Kun2, LIU Zi-long2, 3, KONG Ling-qin1, HUI Mei1, DONG Li-quan1, ZHAO Yue-jin1. Spectral Pre-Processing Based on Convolutional Neural Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(01): 292-297. |
|
|
|
|
