Rapid Detection of Somatic Cell Count Based on Hybrid Variable Selection Method  

作　　者：Shen Weizheng Cui Xiang Wang Yan Nie Debao Zhang Qinggang Zheng Wei Sun Jian Yang Xin Dai Baisheng 

机构地区：[1]College of Electrical and Information,Northeast Agricultural University,Harbin 150030,China [2]Heilongjiang Animal Husbandry Service,Harbin 150060,China [3]School of Information Engineering,Shandong Huayu University of Technology,Dezhou 253000,Shandong,China

出　　处：《Journal of Northeast Agricultural University(English Edition)》2024年第3期59-73,共15页东北农业大学学报（英文版）

基　　金：Supported by the Natural Science Foundation of Heilongjiang Province of China(LH2023C016);the Key Research and Development Program of Heilongjiang Province of China(2022ZX01A24);the National Modern Agricultural Industry Technology System(CARS36)。

摘　　要：Somatic cell count detection is the daily work of dairy farms to monitor the health of cows.The feasibility of applying near-infrared spectroscopy to somatic cell count detection was researched in this paper.Milk samples with different somatic cell counts were collected and preprocessing methods were studied.Variable selection algorithm based on hybrid strategy and modelling method based on ensemble learning were explored for somatic cell count detection.Detection model was used to diagnose subclinical mastitis and the results showed that near-infrared spectroscopy could be a tool to realize rapid detection of somatic cell count in milk.

关 键 词：near-infrared spectroscopy somatic cell count MASTITIS rapid detection 

分 类 号：S156.2[农业科学—土壤学]