论文部分内容阅读
本文旨在建立一种生长/非生长界面模型来预测蜡样芽胞杆菌在环境因子交互作用下的生长概率。选取五株蜡样芽孢杆菌菌株的混合菌株作为研究对象,研究温度、pH、Aw对混合菌株生长概率的交互影响。获得的生长/非生长实验数据用logistic回归方程拟合,建立了环境因子交互作用下蜡样芽孢杆菌生长/非生长界面模型。实验采取部分析因设计方案,选定80%的实验数据用做模型的拟合,20%的数据用做模型的验证。并从已发表的文献中选取30个数据作为测试集,通过比较预测值和观察值来检测已建模型的适用度。实验结果表明,训练集的一致性指数为0.991,验证集的一致率为0.988,说明模型对同类数据预测准确度高;同时模型的R2-Nagelkerke值也较高,为0.949;Hosmer-Lemeshow检验中的χ2=0.012,P=1,logistic回归模型拟合度较高。模型对测试集的预测准确率达83.3%,该模型对所选数据具有较高的预测能力,说明模型具有较广的适用范围。
This article aims to establish a growth / non-growth interface model to predict the growth probability of Bacillus cereus under the interaction of environmental factors. Five strains of Bacillus cereus were selected as research objects to study the interactive effects of temperature, pH and Aw on the growth probability of mixed strains. The obtained growth / non-growth experiment data were fitted by logistic regression equation to establish a model of Bacillus cereus growth / non-growth interface under the interaction of environmental factors. Partial factorial design was adopted in the experiment, 80% of the selected experimental data were used as the model fitting, and 20% of the data were used as the model verification. And from the published literature selected 30 data as the test set, by comparing the predictive value and the observed value to detect the applicability of the established model. The experimental results show that the consistency index of the training set is 0.991 and the consistency rate of the validation set is 0.988, which shows that the model has high prediction accuracy for the same type of data. Meanwhile, the R2-Nagelkerke value of the model is also higher, which is 0.949. In the Hosmer-Lemeshow test Χ2 = 0.012, P = 1, logistic regression model fitted higher. The accuracy of the model in predicting the test set is 83.3%. This model has a high predictive ability for the selected data, indicating that the model has a wide range of applicability.