人工神经网络在熏煮香肠质构预测中的应用  

Application of Artificial Neural Network on Predicting Sensory Texture of Smoked-and-cooked Sausage

作　　者：董庆利[1] 刘宝林[1] 李保国[1] 

机构地区：[1]上海理工大学食品与生物技术研究所,上海200093

出　　处：《农产品加工（下）》2008年第7期100-102,105,共4页Farm Products Processing

基　　金：上海高校选拔培养优秀青年教师科研专项基金(slg-07049)

摘　　要：应用BP神经网络对熏煮香肠质构的感官评定预测进行了改进。数学检验结果表明,建立的BP神经网络模型平方根误差(RMSE)和标准预测误差(%SEP)较低,显著低于多元回归模型,而偏差因子(B)f和准确性因子(A)f都在可接受范围。BP神经网络可以作为较好的预测模型,用于实际肉类工业中肉制品的质构感官评价,实现机械测定全部或部分代替感官评定的快速性、实时性、便捷性检测。Prediction of sensory texture evaluation from smoked-and-cooked sausage was obtained and improved by back propagation neural network （BPNN） , which had been analyzed on the basis of muhiple regressions by Dong and Luo （2004） previously. It indicated that the accuracy and goodness-of-fit from BPNN is higher significantly than those from multiple regressions with lower root-mean-squares error （RMSE） and standard error of prediction （SEP） , and accuracy factor （Af） aud bias factor （Bf） in acceptable range. Therefore, BPNN provides a useful and accurate method for predicting sensory texture evaluation in meat industry, and could be meaningful for the fast, on-time and convenient detection of instrumental texture measurement instead of sensory evaluation.

关 键 词：BP神经网络 熏煮香肠 质构于贞测 

分 类 号：TS251.65[轻工技术与工程—农产品加工及贮藏工程]