基于电子鼻与统计学方法的海鲈鱼新鲜度品质预测

Freshness Quality Prediction of Latelabrax japonicas based on Electronic Nose and Statistic Analysis

通过电子鼻系统采集贮藏在0℃下海鲈鱼的气体指纹信息,并测定挥发性盐基氮(TVB-N)、菌落总数和假单胞菌。分析不同贮藏期海鲈鱼电子鼻传感器响应值的变化,采用主成分分析(PCA)、线性判别分析(LDA)进行数据分析,采用偏最小二乘法(PLS)建立TVB-N、菌落总数和假单胞菌的预测模型。结果表明:随着海鲈鱼贮藏时间的延长,电子鼻的响应值数值在海鲈鱼贮藏过程中增加。采用PCA、LDA方法可较好区分不同贮藏时间海鲈鱼的腐败程度。通过偏最小二乘法(PLS)建立TVB-N、菌落总数和假单胞菌的快速预测模型,其决定系数(R2)分别为0.9737、0.8778、0.5943,而假单胞菌预测模型的R2较低,模型拟合度不高,故不适合用PLS建立假单胞菌预测模型。利用电子鼻结合化学计量学方法对海鲈鱼新鲜度品质进行快速检测是可行的。

The odor fingerprint information of Latelabrax japonicus storage at 0℃ were collected by electronic nose system, and total volatile base nitrogen （TVB-N）value, total number of colonies, and Pseudomonas colony count were measured. Changes of the response value of the electronic nose sensor of Latelabrax japonicus in different storage periods were analyzed in the article, principal component analysis（ PCA ）, linear discriminant analysis （LDA）were used in the data analysis, prediction model of TVB-N,TMA,total number of colonies, and Pseudomonas colony count were buih with the partial least squares（PLS） .The results showed that the intensity of the response value of electronic nose sensors increased with increasing of the storage time of Latelabrax japonicus.The method of PCA and LDA could be well used to distinguish the Latelabrax japonicus in different storage time.The rapid count prediction model of TVB- N, total number of colonies, the correlation coefficients of PLS calibration models for TVB - N, total number of colonies, and Pseudomonas colony count were 0.9737,0.8778,0.5943.However, the correlation coefficients of Pseudomonas prediction model was low, and the model fitting was inadequate, so it was not suitable for the use of PLS to establish Pseudomonas prediction model.The results showed that it was feasible to test the freshness quality of Latelabrax japonicus by electronic nose combined with chemometrics method.