摘要
目的研究生鲜猪肉水分含量与1000～1680nm范围内近红外吸收光谱之间的关系,对生鲜肉的水分含量进行快速无损检测。方法将原始光谱经中值平滑、多元散射校正和一阶导数复合预处理,结合多元线性回归和偏最小二乘回归两种建模方法建立生鲜肉水分含量的预测模型。结果应用所建立的模型对111个实际生鲜猪肉样品的水分含量进行预测,得到较为满意的预测结果,两种模型的预测相关系数分别为0.839和0.810。结论所建模型适合于生鲜猪肉水分的无损快速检测。
Objective To investigate the relationship between the water content in the fresh pork and the near infrared absorption spectrum in the range of 1000 nm～1680 nm.And to detect the water content in the fresh pork by using the rapid non-destructive technology.Methods Through spectral analysis,it indicated that the optimal pretreatment method was the combination of the median smooth,multiple scattering correction and first derivative.Two models were established with the multiple linear regression(MLR) and partial least square regression(PLSR) method.Results All 111 samples were predicted by the two models,both of which could give satisfactory results with the correlation coefficient of 0.839 and 0.810,respectively in the validation sets.Conclusion This research demonstrated that the model was suitable for the non-destructive rapid detection for the fresh pork water content.
出处
《食品安全质量检测学报》
CAS
2012年第1期23-26,共4页
Journal of Food Safety and Quality
基金
公益性行业(农业)科研专项经费资助(项目编号:201003008)
关键词
生鲜猪肉
近红外光谱技术
水分含量
多元线性回归
偏最小二乘回归
无损检测
fresh pork
near infrared spectroscopy
water content
multiple linear regression
partial least square regression
non-destructive detection
