Non-Destructive Detection of Pre-Incubation Breeding Duck Egg Fertilization Information Based on Visible/Near Infrared Spectroscopy and Joint Optimization Strategy
CHEN Zhuo-ting1, WANG Qiao-hua1, 2*, WANG Dong-qiao1, CHEN Yan-bin1, LI Shi-jun1, 2
1. College of Engineering, Huazhong Agricultural University, Wuhan 430070, China
2. Key Laboratory of Agricultural Equipmentin Mid-Lower Yangtze River, Wuhan 430070, China
Abstract：The hatching of duck eggs is an important guarantee for producing duck eggs and duck meat. Eggs without sperm cannot hatch ducklings, and they are prone to spoilage in the incubator, which affects the hatching of fertilized eggs. To solve the problems of high labor intensity and resource waste caused by manually removing -sperm-free eggs through egg photography, this paper takes pre-hatching duck eggs as the research object. It proposes a non-destructive detection method for pre-hatching fertilization information of duck eggs based on visible near-infrared spectroscopy and deep learning. This article uses a visible near-infrared fiber optic spectrometer to collect spectral data from 321 Cherry Valley duck eggs (144 fertilized eggs and 177 azoospermia eggs). The spectral data is divided into training and testing sets in a 3∶1 ratio, and the training set is expanded by adding noise and random offset to the original spectral data, randomly selecting and calculating the average spectrum. This article designs an end-to-end deep learning model: the Autoencoder 1DCNN, which uses convolutional and pooling layers instead of the fully connected layers in the autoencoder to obtain an improved convolutional autoencoder CAE. The CAE-1DCNN model is trained using a joint optimization strategy to enable the autoencoder to extract useful features during the data compression reconstruction process and selectively extract features suitable for classification tasks. This article uses three commonly used feature wavelength selection algorithms, namely Competitive Adaptive Reweighted Sampling (CARS), Continuous Projection (SPA), and Uninformative Variable Elimination (UVE), as well as three machine learning classification models, K-Nearest Neighbor (KNN), Naive Bayes (NB), and Random Forest (RF), to combine and compare with the proposed model. The t-distribution Random Neighborhood Embedding (t-SNE) algorithm is used to visualize the feature extraction effect. Finally, this article used a weighted Class Activation Graph (Grad CAM) to visualize the focus areas of spectral data designed in this paper. It explored the biological interpretability of spectral information. The research results indicate that the CAE-1DCNN model proposed in this paper can effectively extract information from spectral data with a discrimination accuracy of 95.06%. The combination of visible near-infrared spectroscopy technology and deep learning can achieve non-destructive detection of pre-incubation fertilization information in duck eggs. The convolutional autoencoder trained using a joint optimization strategy has good feature extraction ability. The end-to-end CAE-1DCNN model facilitates integration and provides technical support for the development of non-destructive testing equipment.
陈灼廷，王巧华，王东桥，陈燕斌，李世军. 可见-近红外光谱与联合优化策略的孵前种鸭蛋受精信息无损检测[J]. 光谱学与光谱分析, 2025, 45(05): 1469-1475.
CHEN Zhuo-ting, WANG Qiao-hua, WANG Dong-qiao, CHEN Yan-bin, LI Shi-jun. Non-Destructive Detection of Pre-Incubation Breeding Duck Egg Fertilization Information Based on Visible/Near Infrared Spectroscopy and Joint Optimization Strategy. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(05): 1469-1475.
[1] Mbuthia P G, Njagi L W, Nyaga P N, et al. Kenya Veterinarian, 2007, 31(1): 6.
[2] LI Qing-xu, WANG Qiao-hua, GU Wei, et al(李庆旭, 王巧华, 顾 伟，等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2020, 51(1): 188.
[3] Liu Y, Xiao D, Liu Y, et al. Journal of Thermal Biology, 2022, 110: 103384.
[4] Bain M M, Fagan A J, Mullin J M, et al. Journal of Magnetic Resonance Imaging, 2007, 26(1): 198.
[5] Park E, Lohumi S, Cho B K. Sensors and Actuators B: Chemical, 2019, 281: 204.
[6] ZHAO Juan, SHEN Mao-sheng, PU Yu-ge, et al(赵 娟, 沈懋生, 浦育歌，等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2023, 54(2): 386.
[7] Dong J, Dong X, Li Y, et al. Computers and Electronics in Agriculture, 2019, 157: 471.
[8] LI Qing-xu, WANG Qiao-hua, GU Wei, et al(李庆旭, 王巧华, 顾 伟, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2020, 40(12): 3847.
[9] Zhao J, Hu L, Dong Y, et al. International Journal of Applied Earth Observation and Geoinformation, 2021, 102: 102459.
[10] ZHENG Jiang-peng, YU Ping, ZHAO Meng, et al(郑江鹏, 余 平, 赵 萌，等). Chinese Optics(中国光学), 2022, 15(3): 443.
[11] Tsakiridis N L, Samarinas N, Kokkas S, et al. Computers and Electronics in Agriculture, 2023, 212: 108098.
[12] Liu Y, Zhou S, Wu H, et al. Computers and Electronics in Agriculture, 2022, 198: 107007.
[13] Syduzzaman M, Rahman A, Alin K, et al. Engineering in Agriculture, Environment and Food, 2019, 12(3): 289.
[14] Syduzzaman M, Khaliduzzaman A, Rahman A, et al. British Poultry Science, 2023, 64(2): 195.
