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.
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)。
