Non-Destructive Detection of Multi-Indicator Chilled Mutton Freshness Based on Improved Artificial Neural Network
XU Zi-yang1, 2, JIANG Xin-hua1, 2*, ZHAI Cheng-jun3, MA Xue-lei1, 2, LI Jing1, 2
1. College of Computer and Information Engineering, Inner Mongolia Agricultural University, Huhhot 010018, China
2. Inner Mongolia Key Laboratory of Big Data Research and Application in Agriculture and Animal Husbandry, Huhhot 010018, China
3. Inner Mongolia Education Examination Institute, Huhhot 010018, China
Abstract：The freshness of chilled mutton is influenced by various factors and can be comprehensively evaluated through multiple physical, chemical, and microbiological indicators. Traditional testing methods are complex and inefficient. Hyperspectral imaging technology, as a rapid and non-destructive detection technique, can effectively detect the changes in different components during the freshness variation of chilled mutton. To study the feasibility of using hyperspectral imaging technology for the multi-indicator evaluation of chilled mutton freshness, this paper proposes an improved artificial neural network (ANN) algorithm that enhances the correlation between labels by redefining the loss function and fully utilizes multiple freshness indicators to classify the freshness of chilled mutton. Experimental high-spectral images were collected for chilled mutton samples from 0 to 14 days in the 400 to 1 000 nm range. Laboratory methods were used to determine the values of total volatile basic nitrogen (TVB-N), pH value, total aerobic count (TAC), and an approximate number of coliforms (ANC) indicators. The original spectral data of chilled mutton samples were preprocessed using the S-G smoothing filter and multivariate scatter correction. The continuous projection algorithm (SPA) was used to select 18 feature bands of the spectral data as input data, and the proposed improved ANN algorithm was employed to establish a multi-indicator chilled mutton freshness grading model. The results showed that the improved ANN achieved a classification accuracy of 96% on the test set. The recognition rates for the three freshness levels of the samples were 100%, 89.28%, and 98.68%, respectively. The model was evaluated using four multi-label model evaluation metrics: Hamming loss, one-error, ranking loss, and coverage. The corresponding evaluation scores were 0.008, 0.002, 0.002 5, and 4.048, respectively. The accuracy and various model evaluation metrics of the improved ANN classification model were superior to those of traditional ANN, demonstrating the feasibility of using the improved ANN for non-destructive detection of multi-indicator chilled mutton freshness.
Key words：Nondestructive testing; Hyperspectral; Neural network; Multi label; Classification
[1] ZHANG Fan, SHU Ying, ZHANG Zhi-sheng, et al(张 凡，淑 英，张志胜，等). Journal of Chinese Institute of Food Science and Technology(中国食品学报), 2021, 21(11): 191.
[2] JIANG Sha, YAN Cai-xia, FAN Xin, et al(姜 莎，闫彩霞，范 鑫，等). Meat Industry(肉类工业), 2021, 2021(2): 38.
[3] SUN Wu-liang, LI Wen-bo, JIN Zhi-min, et al(孙武亮，李文博，靳志敏，等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2021, 37(4): 24.
[4] ZHAO Jing-yuan, ZHANG Jun-qin, SUN Mei, et al(赵静远，张俊芹，孙 梅，等). Food and Machinery(食品与机械), 2022, 38(10): 61.
[5] Liu Cunchuan, Chu Zhaojie, Weng Shizhuang, et al. Food Chemistry, 2022, 385(15): 132651.
[6] ZHAO Ting-ting, WANG Ke-jian, SI Yong-sheng, et al(赵停停, 王克俭, 司永胜, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2023, 43(3): 830.
[7] Fan Binbin, Zhu Rongguang, He Dongyu, et al. Foods, 2022, 11(15): 2278.
[8] Jang S, Han J, Cho J, et al. Horticulturae, 2023, 10(1): 35.
[9] Jussi J, Aarne H, Miina R. European Journal of Remote Sensing, 2023, 56(1): 2161420.
[10] ZHANG Jue, TIAN Hai-qing, WANG Ke(张 珏, 田海清, 王 轲, 等). Journal of China Agricultural University(中国农业大学学报), 2020, 25(5): 100.
[11] Wan G L, Fan S X, Liu G S, et al. Food Control, 2023, 144: 109332.
[12] Liu C C, Chu Z J, Weng S Z, et al. Food Chemistry, 2022, 15(385): 132651.
[13] Zhang M, Zhou Z. IEEE Transactions on Knowledge & Data Engineering，2014, 26(8): 1819.
[14] Zhu J, Ma C, Zhang Y, et al. Electronics, 2023, 12(24): 4976.
[15] Vibha B, Prashant P B. Applied Sciences, 2024, 14(10): 4208.
[16] Agatonovic K S, Beresford R. Journal of Pharmaceutical & Biomedical Analysis, 2000, 22(5): 717.
[17] Abiy A Z, Wiederholt R P, Lagerwoll G L, et al. Water, 2022, 14(21): 3495.
[18] Er M J, Wu S, Lu J, et al. IEEE Transactions on Neural Networks and Learning Systems, 2002, 13(3): 697.
[19] Zhou Xin, Meng Xin, Li Zhenyu. Energies, 2024, 17(5): 1102.
[20] Zhang M L, Zhou Z H. IEEE Transactions on Knowledge & Data Engineering, 2006, 18(10): 1338.
[21] National Health and Family Planning Commission(国家卫生和计划生育委员会). GB/5009.228—2016 National Food Safety Standard, Determination of Total Volatile Base Nitrogen in Food(GB/5009.228—2016 食品国家安全标准食品中挥发性盐基氮的测定), 2016.
[22] National Health and Family Planning Commission(国家卫生和计划生育委员会). GB/5009.237—2016 National Food Safety Standard, Determination of pH of Food(GB/5009.237—2016 食品国家安全标准食品pH值的测定), 2016.
[23] Ministry of Health, the People's Republic of China(中华人民共和国卫生部). GB/4789.2—2022 National Food Safety Standard, Food Microbiological Examination: Aerobic Plate Count(GB/4789.2—2022食品国家安全标准食品微生物学检验菌落总数测定), 2022.
[24] Ministry of Health, the People's Republic of China(中华人民共和国卫生部). GB/4789.3—2016 National Food Safety Standard, Food Microbiological Examination: Approximate Number of Coliforms(GB/4789.3—2016 食品国家安全标准食品微生物学检验大肠杆菌计数), 2016.
[25] General Administration of Quality Supervision, Inspection and Quarantine of China(国家质量监督检验检疫总局). GB/T 9961—2008 Fresh and Frozen Lamb Carcass(GB/T 9961—2008 鲜、冻胴体羊肉), 2008.
[26] JIANG Yi-he, WANG Tao, CHANG Hong-wei(姜一河, 王 涛, 常红伟). Electronics Optics and Control(电光与控制), 2020, 27(10): 5.
[27] BAI Jing, LI Jia-peng, ZOU Hao, et al(白 京, 李家鹏, 邹 昊，等). Food Science(食品科学), 2019, 40(2): 287.
