Detection method of mutton adulteration based on PSO-LSSVM and characteristic wavelengths extraction

Authors

Tian-tian CHENG, Hebei Agricultural University, Baoding, Hebei 071000 , China ；National MuttonProcessing Technology Research and Development Center〔Hengshui Zhihao AnimalHusbandry Technology Co., Ltd.〕, Hengshui, Hebei 053000 , China
Ke-jian WANG, Hebei Agricultural University, Baoding, Hebei 071000 , China
Xian-zhong HAN, Hebei Agricultural University, Baoding, Hebei 071000 , China
Shi LI, Hebei Agricultural University, Baoding, Hebei 071000 , China
Yuan WANG, National MuttonProcessing Technology Research and Development Center〔Hengshui Zhihao AnimalHusbandry Technology Co., Ltd.〕, Hengshui, Hebei 053000 , China

Abstract

In order to solve the problem of fast detection of adulteration of mutton and pork, the spectral collection of adulterated mutton was carried out by using a multi-spectral instrument, and the reflectivity of samples at the band of 350~1 100 nm was obtained. For data preprocessing, Particle Swarm Optimization (PSO) was used to optimize the Least Squares Support Vector Machine (LSSVM), and a Least Squares Support Vector Machine (PSO-LSSVM) model based on Particle Swarm Optimization was established, compared with Partial Least Squares(PLS), Back Propagation Neural Network (BPNN) and LSSVM models. The result showed that PSO algorithm could effectively optimize LSSVM model,and the decision coefficient and root mean square error of prediction was 0.920 4 and 0.089 2. Furthermore, Random frog (RF), Uninformative Variable Elimination (UVE) and Competitive Adaptive Reweighed Sampling (CARS) were used to extract the characteristic wavelengths and establishing the model of PLS. The results showed that the UVE-PLS model’s decision coefficient and the root mean square error of prediction set were 0.996 7 and 0.016 2, and UVE was better than other feature wavelengths extraction methods.

Publication Date

2-18-2023

First Page

46

Last Page

50

DOI

10.13652/j.issn.1003-5788.2020.11.008

Recommended Citation

CHENG, Tian-tian; WANG, Ke-jian; HAN, Xian-zhong; LI, Shi; and WANG, Yuan (2023) "Detection method of mutton adulteration based on PSO-LSSVM and characteristic wavelengths extraction," Food and Machinery: Vol. 36: Iss. 11, Article 8.
DOI: 10.13652/j.issn.1003-5788.2020.11.008
Available at: https://www.ifoodmm.cn/journal/vol36/iss11/8

References

[1] 赵从民,宋桂芳.吃羊肉与保健[J].肉品卫生,2001(5):20.
[2] 施姿鹤,VOGLMEIR Josef,刘丽.肉及其加工制品的掺假鉴别技术研究进展[J].食品科学,2019,40(23):319-326.
[3] 王飞翔.调理肉多光谱图像在线检测设备的设计与试验[D].洛阳:河南科技大学,2019:33-43.
[4] 范卉.基于多光谱技术与光学层析方法的地沟油特征研究[D].西安:西安工业大学,2017:37-62.
[5] 郝广.基于多光谱成像技术的番茄酱品质与安全快速检测研究[D].合肥:合肥工业大学,2018:29-34.
[6] LIU Chang-hong,HAO Guang,SU Min.Potential of multispectral imaging combined with chemometric methods for rapid detection of sucrose adulteration in tomato paste[J].Journal of Food Engineering,2017,215:78-83.
[7] ROPODI A I,PAVLIDIS D E,MOHAREB F.Multispectral image analysis approach to detect adulteration of beef and pork in raw meats[J].Food Research International,2015,67:12-18.
[8] 刘友华,白亚斌,邱祝福,等.基于高光谱图像技术和波长选择方法的羊肉掺假检测方法研究[J].海南师范大学学报(自然科学版),2015,28(3):265-269.
[9] 白京,李家鹏,邹昊,等.近红外特征光谱定量检测羊肉卷中猪肉掺假比例[J].食品科学,2019,40(2):287-292.
[10] LIU Jin-xia,CAO Yue,WANG Qiu.Rapid and non-destructive identification of water-injected beef samples using multispectral imaging analysis[J].Food Chemistry,2016,190:938-943.
[11] 刘锦霞.基于多光谱成像技术快速检测注水肉及冷冻肉的品质安全[D].合肥:合肥工业大学,2016:21-28.
[12] 王迪,张敬埔,张珏,等.基于高光谱技术的羊肉含水率无损检测[J].食品工业科技,2018,39(4):215-218.
[13] 邢素霞,王九清,陈思,等.基于K-means-RBF的鸡肉品质分类方法研究[J].食品科学技术学报,2018,36(4):93-99.
[14] 郑剑,周竹,仲山民,等.基于近红外光谱与随机青蛙算法的褐变板栗识别[J].浙江农林大学学报,2016,33(2):322-329.
[15] 于慧春,付晓雅,殷勇,等.拉曼光谱结合UVE-SVR算法预测加热食用油反式脂肪酸的含量[J].核农学报,2020,34(3):582-591.
[16] 王怡淼,朱金林,张慧,等.基于MC-UVE、GA算法及因子分析对葡萄酒酒精度近红外定量模型的优化研究[J].发光学报,2018,39(9):1 310-1 316.
[17] 王海龙,杨国国,张瑜,等.竞争性自适应重加权算法和相关系数法提取特征波长检测番茄叶片真菌病害[J].光谱学与光谱分析,2017,37(7):2 115-2 119.