Shrimp Freshness Detection Method Based on Broad Learning System
YE Rong-ke1, KONG Qing-chen1, LI Dao-liang1, 2, CHEN Ying-yi1, 2, ZHANG Yu-quan1, LIU Chun-hong1, 2*
1. College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China
2. National Innovation Center for Digital Fishery, China Agricultural University, Beijing 100083, China
Abstract：To improve the accuracy of shrimp freshness discrimination, we proposed a shrimp freshness detection method based on a broad learning system in this paper. In this study, firstly, multivariate scatter correction (MSC), standard normal variate (SNV), and direct orthogonal signal correction (DOSC) were used to preprocess the raw hyperspectral data of shrimp with different days of refrigeration. And secondly, t-distributed stochastic neighbor embedding (t-SNE) was used to visualize the data after preprocessing, and the visualization results showed that the DOSC-processed data had the best clustering effect. Then, the spectral data after DOSC preprocessing were used for feature extraction using random forest (RF), principal component analysis (PCA), and two-dimensional correction spectroscopy (2D-COS). Finally, the shrimp freshness was modeled based on the characteristic wavelength, and the broad learning system (BLS) was used in shrimp freshness modeling for the first time in this paper and compared with the classical discriminant models such as partial least squares discrimination analysis (PLS-DA) and extreme learning machine (ELM). The results indicated that the RF method minimized the redundant information in the spectra, while the BLS had high accuracy and shorter discrimination time than the linear modeling method PLS-DA and the nonlinear modeling method ELM, and thus the combined RF-BLS model obtained the best freshness discrimination performance. The experimental results indicated that the hyperspectral imaging technology combined with broad learning system to identify shrimp freshness is feasible. The method proposed in this paper can provide a theoretical basis for developing an online shrimp freshness detection system.
Key words：Freshness of shrimp; Direct orthogonal signal correction; Random forest; Broad learning system; Hyperspectral imaging technology
叶荣珂，孔庆辰，李道亮，陈英义，张玉泉，刘春红. 宽度学习的虾新鲜度检测方法[J]. 光谱学与光谱分析, 2022, 42(01): 164-169.
YE Rong-ke, KONG Qing-chen, LI Dao-liang, CHEN Ying-yi, ZHANG Yu-quan, LIU Chun-hong. Shrimp Freshness Detection Method Based on Broad Learning System. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(01): 164-169.
[1] WANG Wei(王 伟). Food Research and Development(食品研究与开发), 2017, 38(22): 176.
[2] WANG Su-hua, CHEN Ji-ming, ZHU Hai, et al(王素华, 陈积明, 朱 海, 等). Science and Technology of Food Industry(食品工业科技), 2011, 32(7): 386.
[3] LING Ping-hua, XIE Jing, ZHAO Hai-peng, et al(凌萍华, 谢 晶, 赵海鹏, 等). Jiangsu Journal of Agricultural Sciences(江苏农业学报), 2010, 26(4): 828.
[4] WANG Wei, CHAI Chun-xiang, LU Xiao-xiang(王 伟, 柴春祥, 鲁晓翔). Food & Machinery(食品与机械), 2013, 29(4): 233.
[5] Baek I, Kusumaningrum D, Kandpal L, et al. Sensors, 2019, 19(2): 271.
[6] Yu X J, Tang L, Wu X F, et al. Food Analytical Methods, 2018, 11(3): 768.
[7] Zhang C, Wu W Y, Zhou L, et al. Food Chemistry, 2020, 319: 126536.
[8] Zhou X, Sun J, Tian Y, et al. Food Chemistry, 2020, 321: 126503.
[9] Cheng J H, Dai Q, Sun D W, et al. Journal of Food Engineering, 2015, 161: 33.
[10] HUANG Chong, XU Zhao-xin, ZHANG Chen-chen, et al(黄 翀, 许照鑫, 张晨晨, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2020, 36(9): 177.
[11] Zhang L, Sun H, Rao Z H, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2020, 229: 117973.
[12] Jiang H Z, Cheng F N, Shi M H. Foods, 2020, 9(2): 154.
[13] Bai Z Z, Hu X J, Tian J P, et al. Food Chemistry, 2020, 331: 127290.
[14] Ye R K, Chen Y Y, Guo Y C, et al. Applied Sciences, 2020, 10(16): 5498.
[15] Chen C L, Liu Z L, et al. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(1): 10.
[16] Zhang L, Rao Z H, Ji H Y. Spectroscopy Letters, 2020, 53(3): 207.
