摘要
在获得传感器与食醋挥发气体反应的整个过程的数据的基础上,提取了传感器与食醋散发的气体反应的特征值。利用分辨率指数来确定所提取的特征参数是否最优,从而决定该特征值在以后模式识别中是否有用。再对那些分辨率指数大的特征参数进行主成分分析和神经网络分析。主成分分析结果表明不同醋之间区分得比较开,神经网络的识别正确率达到100%。该方法也可用于解决其它形式传感器阵列问题。
Based on the parameters of process that the sensor acts with vinegar gas during the whole acting process, the feature parameters are picked up. ″Distinguish index″ is used to confirm whether the feature parameter is optimum or not. Thus we can assure the symptom parameter is useful in the later pattern recognition process. Principal component analysis (PCA) and artificial neural network (ANN) are used to combine the optimum feature parameters. Good separation among the gases with different vinegar is obtained using principal component analysis. The recognition probability of the ANN is 100%. The new method can also be applied to other pattern recognition problems.
出处
《计算机测量与控制》
CSCD
2003年第10期815-817,共3页
Computer Measurement &Control
基金
国家科技部社会公益基金项目(2001DTA40038)
