Food and Fermentation Industries >

2023 , Vol. 49 >Issue 8: 281 - 288

DOI: https://doi.org/10.13995/j.cnki.11-1802/ts.032551

Comparison and recognition of spectral signal pretreatment methods for animal and vegetable oils based on filters

  • QIU Weilun ,
  • DING Sheng
Expand
  • 1(School of Forensic Science, Hunan Police Academy, Changsha 410138, China)
    2(Network Security Brigade, Tianxin Branch of Changsha Public Security Bureau, Changsha 410004, China)

Received date: 2022-06-03

  Revised date: 2022-07-05

  Online published: 2023-05-16

Fold

Abstract

To achieve the rapid and non-destructive determination of animal and vegetable oils and explore the feasibility of the filter in improving the discrimination ability of the spectral analysis model, the study collected the spectral information data of 347 samples of animal oil (159 samples) and vegetable oil (188 samples) with the help of attenuated total reflection-surface-enhanced infrared absorption spectroscopy. Three discrimination models, including Fisher discriminant analysis, support vector machine, and decision tree were constructed. Among them, five filters (Hilbert transform, finite length unit impulse response filter, infinite length impulse response filter, fast Fourier transform, and wavelet transform) were considered to discuss the improvement of the model accuracy. Besides, the discrimination differences of filter window functions (rectangular window, Hanning window, Hamming window, and Blackman window), wavelet basis functions (Morlet, Dgauss, Mexhat, Haar, Daubechies, and Biorthogonal) and filtering methods (low-pass, high-pass, band-pass, and band-stop) were investigated and explored. Results showed that filters could significantly improve the models' accuracy. Low-pass/band-stop filtering modes, rectangular window, and Blackman window functions were superior and satisfactory. The support vector machine was optimal in distinguishing all samples. The SVM model (RBF kernel function) based on FIR low-pass/band-stop filter could be considered as the favorable model. It achieved 100% accurate differentiation. Filters and ATR-SEIRAS could effectively distinguish animal and vegetable oils. It could provide the application of enhancing the model performance.

Key words： animal and vegetable oils; attenuated total reflection-surface-enhanced infrared absorption spectroscopy; filter; Fisher discriminant analysis; support vector machine; decision tree

Cite this article

QIU Weilun , DING Sheng . Comparison and recognition of spectral signal pretreatment methods for animal and vegetable oils based on filters[J]. Food and Fermentation Industries, 2023 , 49(8) : 281 -288 . DOI: 10.13995/j.cnki.11-1802/ts.032551

References

[1] 张方圆, 吴凌涛, 林晨, 等.气相色谱结合化学计量学用于6种食用植物油的分类[J].分析试验室, 2016, 35(11):1 254-1 258.
ZHANG F Y, WU L T, LIN C, et al.Classification of 6 edible vegetable oils by gas chromatography combined with chemometrics[J].Chinese Journal of Analysis Laboratory, 2016, 35(11):1 254-1 258.
[2] HEIDARI M, TALEBPOUR Z, ABDOLLAHPOUR Z, et al.Discrimination between vegetable oil and animal fat by a metabolomics approach using gas chromatography-mass spectrometry combined with chemometrics[J].Journal of Food Science and Technology, 2020, 57(9):3 415-3 425.
[3] 郭莲仙, 梁福睿, 赵祖国, 等.基于稳定碳同位素技术的痕量动物油和植物油的区分检验研究[J].化学研究与应用, 2014, 26(8):1 232-1 236.
GUO L X, LIANG F R, ZHAO Z G, et al.Discrimination between the oils from animals and vegetables by stable carbon isotope analysis[J].Chemical Research and Application, 2014, 26(8):1 232-1 236.
[4] 涂斌, 陈志, 彭博, 等.基于多源光谱特征融合技术的花生油掺伪检测[J].食品与发酵工业, 2016, 42(4):169-173.
TU B, CHEN Z, PENG B, et al.Research on detection method of peanut oil adulteration based on data fusion technology of multi-source spectral characteristics[J].Food and Fermentation Industries, 2016, 42(4):169-173.
[5] 武烈, 孙建龙, 姜秀娥.表面增强红外吸收光谱——表面敏感的原位免标记光谱电化学技术[J].电化学, 2019, 25(2):202-222.
WU L, SUN J L, JIANG X E.Surface-enhanced infrared absorption spectroscopy-surface sensitive in situ label-free spectroelectrochemistry[J]. Journal of Electrochemistry, 2019, 25(2):202-222.
[6] CHANG R L J, YANG J.Para-Mercaptobenzoic acid-modified silver nanoparticles as sensing media for the detection of ammonia in air based on infrared surface enhancement effect[J].The Analyst, 2011, 136(14):2 988-2 995.
[7] SATO Y, NODA H, MIZUTANI F, et al.In situ surface-enhanced infrared study of hydrogen bond pairing of complementary nucleic acid bases at the electrochemical interface[J].Analytical Chemistry, 2004, 76(18):5 564-5 569.
[8] QI W L, TIAN Y L, LU D L, et al.Research progress of applying infrared spectroscopy technology for detection of toxic and harmful substances in food[J].Foods(Basel,Switzerland), 2022, 11(7):930-942.
[9] GEORGOULI K, MARTINEZ DEL RINCON J, KOIDIS A.Continuous statistical modelling for rapid detection of adulteration of extra virgin olive oil using mid infrared and Raman spectroscopic data[J].Food Chemistry, 2017, 217:735-742.
[10] 张胜利, 李伟.基于窗函数与FFT算法的信号谐波分析[J].工业控制计算机, 2019, 32(5):35-36;38.
ZHANG S L, LI W.Signal harmonic analysis based on window functions and FFT algorithms[J].Industrial Control Computer, 2019, 32(5):35-36;38.
[11] 陈丛, 卢启鹏, 彭忠琦.基于NLMS自适应滤波的近红外光谱去噪处理方法研究[J].光学学报, 2012, 32(5):294-299.
CHEN C, LU Q P, PENG Z Q.Preprocessing methods of near-infrared spectrum based on NLMS adaptive filtering[J].Acta Optica Sinica, 2012, 32(5):294-299.
[12] MACK W, HABETS E A P.Deep filtering:Signal extraction and reconstruction using complex time-frequency filters[J].IEEE Signal Processing Letters, 2020, 27:61-65.
[13] 古锟山, 王继芬, 曾啸虎.基于滤波器-光谱数据降维的指甲地区识别[J].分析测试学报, 2022, 41(5):746-753;760.
GU K S, WANG J F, ZENG X H.Recognition of fingernail region based on filter-spectral feature extraction[J]. Journal of Instrumental Analysis, 2022,41(5):746-753;760.
[14] 何欣龙, 王继芬, 李青山, 等.基于多层感知器-Fisher判别分析的车用保险杠红外光谱鉴别[J].中国测试, 2019, 45(5):74-78;92.
HE X L, WANG J F, LI Q S, et al.Identification of vehicle bumper debris based on multi-layer perception-Fisher discriminant and infrared spectroscopy[J]. China Measurement & Test, 2019, 45(5):74-78;92.
[15] 杜靖媛, 葛宏立, 路伟, 等.基于Fisher判别的层次分类法的森林遥感影像分类[J].西南林业大学学报(自然科学), 2017, 37(4):175-182.
DU J Y, GE H L, LU W, et al.Classification of unbalanced data based on SVM mixed sampling[J]. Mathematics in Practice and Theory, 2017, 37(4):175-182.
[16] 杨红云, 黄琼, 孙爱珍, 等.基于卷积神经网络和支持向量机的水稻种子图像分类识别[J].中国粮油学报, 2021, 36(12):144-150.
YANG H Y, HUANG Q, SUN A Z, et al.Rice seed image classification and recognition based on convolutional neural network and support vector machine[J].Journal of the Chinese Cereals and Oils Society, 2021, 36(12):144-150.
[17] 黄勇, 郭剑辉.结合深度信念网络与支持向量机的地表分类算法[J].计算机与数字工程, 2022, 50(1):129-134.
HUANG Y, GUO J H.Surface classification algorithm based on depth belief network and support vector machine[J].Computer and Digital Engineering, 2022, 50(1):129-134.
[18] 姜飞, 杨明, 刘雨欣.基于支持向量机混合采样的不平衡数据分类方法[J].数学的实践与认识, 2021, 51(1):88-96.
JIANG F, YANG M, LIU Y X.ECG signals pre-processing based on FIR filtering and mathematical morphology[J]. China Medical Devices, 2021, 51(1):88-96.
[19] 孙亚楠, 李仙岳, 史海滨, 等.基于特征优选决策树模型的河套灌区土地利用分类[J].农业工程学报, 2021, 37(13):242-251.
SUN Y N, LI X Y, SHI H B, et al.Classification of land use in Hetao Irrigation District of Inner Mongolia using feature optimal decision trees[J].Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(13):242-251.
[20] 郑秀玉, 卢瑞祥.基于FIR滤波和数学形态学的心电信号预处理算法[J].中国医疗设备, 2015, 30(9):20-23.
ZHENG X Y, LU R X.Research of high precision photoacoustic second harmonic detection technology based on FFT filter[J]. China Medical Equipment, 2015, 30(9):20-23.
[21] 万留杰, 甄超, 邱宗甲, 等.基于FFT滤波高精度光声二次谐波检测技术的研究[J].光谱学与光谱分析, 2020, 40(10):2 996-3 001.
WAN L J, ZHEN C, QIU Z J, et al.Confocal Raman image denoising method based on wavelet transform[J].Spectroscopy and Spectral Analysis, 2020, 40(10):2 996-3 001.
[22] 张胜利, 李伟.基于窗函数与FFT算法的信号谐波分析[J].工业控制计算机, 2019, 32(5):35-36;38.
ZHANG S L, LI W.Signal harmonic analysis based on window functions and FFT algorithms[J].Industrial Control Computer, 2019, 32(5):35-36;38.
[23] 方松琼, 邵荣君, 邱丽荣, 等.基于小波变换的共焦拉曼图像去噪方法[J].光学技术, 2019, 45(3):330-335.
FANG S Q, SHAO R J, QIU L R, et al.Denoising method of confocal raman image based on wavelet transform[J].Optical Technique, 2019, 45(3):330-335.
[24] 肖绪桐, 虞天遥.简述信号特征提取使用小波变换的优点[J].今日科苑, 2009(12):163-164.
XIAO X T, YU T Y.The advantages of wavelet transform in signal feature extraction are briefly described[J]. Modern Science, 2009(12):163-164.
[25] 田秀伟, 郑喜凤, 丁铁夫.基于小波-Contourlet变换的图像压缩算法[J].数据采集与处理, 2010, 25(4):437-441.
TIAN X W, ZHENG X F, DING T F, et al.Image compression algorithm using wavelet-based contourlet transform[J]. Journal of Data Acquisition and Processing, 2010, 25(4):437-441.
Options
Outlines

/

〈 〉

Powered by Beijing Magtech Co. Ltd,.