A Model for the Identification of Counterfeited and Adulterated Sika Deer Antler Cap Powder Based on Mid-Infrared Spectroscopy and Support Vector Machines

Cheng-en YANG; Hai-ei WU; Yu YANG; Ling SU; Yue-ming YUAN; Hao LIU; Ai-wu ZHANG; Zi-yang SONG

doi:10.3964/j.issn.1000-0593(2022)08-2359-07

Spectroscopy and Spectral Analysis, Volume. 42, Issue 8, 2359(2022)

A Model for the Identification of Counterfeited and Adulterated Sika Deer Antler Cap Powder Based on Mid-Infrared Spectroscopy and Support Vector Machines

Cheng-en YANG^1、*, Hai-ei WU^{1、1; *;}, Yu YANG^2、2;, Ling SU^2、2;, Yue-ming YUAN^1、1;, Hao LIU^1、1;, Ai-wu ZHANG^3、3;, and Zi-yang SONG^3、3;

Author Affiliations

¹1. College of Engineering and Technology, Jilin Agricultural University, Changchun 130118, China

²2. Engineering Research Center of Edible and Medicinal Fungi Ministry of Education, Jilin Agricultural University, Changchun 130118, China

³3. College of Animal Science and Technology, Jilin Agricultural University, Changchun 130118, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(11)

Fig. 1. Infrared spectra of samples
(a): Spectra of all samples;(b): Spectra after MSC processing

Download full size

View in Article

Fig. 2. Average spectra after normalization

Download full size

View in Article

Fig. 3. Scores of the first two principal components of the training set

Download full size

View in Article

Fig. 4. Training set parameter optimization curve of SVM

Download full size

View in Article

Fig. 5. Training set modeling and recognition results of RF

Download full size

View in Article

Fig. 6. Training set modeling and recognition results of ELM

Download full size

View in Article

Table 1. Informations of sika deer samples

View table

View in Article

Table 1. Informations of sika deer samples

梅花鹿角帽产区	样品数/个	马鹿角帽产区	样品数/个	梅花鹿骨产区	样品数/个
黑龙江兴凯湖	24	黑龙江大兴安岭	24	黑龙江兴凯湖	24
吉林长春双阳区	24	吉林长春双阳区	24	吉林长春双阳区	24
吉林东丰县	24	吉林东丰县	24	吉林东丰县	24
吉林长白山	24	吉林长白山	24	吉林长白山	24
辽宁省西丰县农贸交易大市场	24	辽宁省西丰县农贸交易大市场	24	辽宁省西丰县农贸交易大市场	24

Table 2. Principal component total variance interpretation of the training set

View table

View in Article

Table 2. Principal component total variance interpretation of the training set

主成分	特征值	方差百分比/%	累计贡献/%
PCA1	3 865.28	51.75	51.75
PCA2	1 414.26	18.94	70.69
PCA3	881.79	11.81	82.49
PCA4	650.06	8.70	91.20
PCA5	218.19	2.92	94.12
PCA6	162.20	2.17	96.29
PCA7	113.38	1.52	97.81
PCA8	54.63	0.73	98.54
PCA9	30.21	0.40	98.94
PCA10	18.09	0.24	99.18

Table 3. Test set identification results of SVM
View table
View in Article
Table 3. Test set identification results of SVM
品种测试集个数识别的正确个数
FS PCA
梅花鹿鹿角帽粉 30 30 30
马鹿角帽粉 30 30 30
梅花鹿骨粉 30 30 30
牛骨粉掺假梅花鹿角帽粉 30 30 30
全部 120 120 120

Table 4. Test set identification results of RF
View table
View in Article
Table 4. Test set identification results of RF
品种测试集个数识别的正确个数
FS PCA
梅花鹿鹿角帽粉 30 30 30
马鹿角帽粉 30 30 30
梅花鹿骨粉 30 30 26
牛骨粉掺假梅花鹿角帽粉 30 30 30
全部 120 120 116

Table 5. Test set identification results of ELM
View table
View in Article
Table 5. Test set identification results of ELM
品种测试集个数识别的正确个数
FS PCA
梅花鹿鹿角帽粉 30 29 29
马鹿角帽粉 30 30 29
梅花鹿骨粉 30 30 30
牛骨粉掺假梅花鹿角帽粉 30 26 29
全部 120 115 117

Tools

Get Citation

Copy Citation Text

Cheng-en YANG, Hai-ei WU, Yu YANG, Ling SU, Yue-ming YUAN, Hao LIU, Ai-wu ZHANG, Zi-yang SONG. A Model for the Identification of Counterfeited and Adulterated Sika Deer Antler Cap Powder Based on Mid-Infrared Spectroscopy and Support Vector Machines[J]. Spectroscopy and Spectral Analysis, 2022, 42(8): 2359

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites