用传感器阵列和遗传基因块区分两种食醋

近年来,对将传感器阵列技术和模式识别技术用于识别食品挥发气味的研究方兴未艾。模式识别技术的实施主要依赖于对传感器阵列输出信号的参数表达,迄今为止,不论是单个传感器还是传感器阵列均没有通用的参数选择的方法。该文从8个氧化锡气敏传感器与食醋气味反应中提出初始特征值,采用一种基于公式表达树的遗传基因块代码的编码算法的组织特征参数法(OFP)对所提取的特征参数进行融合,从而得到最优的组织特征参数很容易区分不同的气味。它不但解决了怎样得到最优特征参数的问题,而且用这种算法进行遗传运算更直观、更方便。并详细讨论了怎样进行基因编码来融合不同特征参数,同时对这种遗传算法怎样进行选择、交叉、变异进行了研究。将其用于气敏传感器阵列对不同食醋识别的应用实例证明,该方法是一种非常有效的模式识别方法

Identification of Two Types of Vinegar Using a Gas Sensor Array and Genetic Program

Considerable interest has recently arisen in the use of arrays of gas sensors together with an associated pattern recognition technique to identify the odours given out from food. The performance of the pattern recognition technique depends upon the choice of parametric expression used to define the array output. At present, there is no generally agreed choice of this parameter for either individual sensors or array of sensors. In this paper, feature parameter (FP) on experimental data gathered from the response of eight tin oxide gas sensors was used to identify two types of vinegar. And the technique of organizing feature parameter (OFP) based on formulae expression tree by using genetic algorithms was applied to parametric data. Then the optimum FP to distinguish different odours can be used sensitively. It could solve the problem on how to get optimum feature parameters, and make the genetic algorithm more convenient and straight. The formulae expression tree for the fusion of feature parameters was discussed and then the selection, cross over and mutation for the genetic algorithm were studied. The result showed that the new method is useful and effective for odour recognition.