摘要
采用了一种基于神经网络的杂交算法，用于识别来自氧化锡传感器阵列的三种化学品：丙酮、甲醇和乙醇的信号．算法利用梯度收敛方法并结合仿真退火和遗传算法进行权值初值化来加速运算速度和提高分类准确度。这种方法能较好地避免局部最小点，大量运算实例用来构造最优网络结构并说明这种方法是较好的模式分类方法并可以作为“人工电子鼻”的数据处理方法。
A hybridized algorithm of artificial neural network(ANN) was used to carry out the task of pattern classification on data from Taguchi tin-oxided sensors for the three substances acetone, ethanol and methanol. It made use of the Gradient Descent (GD) method with Simulated Annealing (SA) and Genetic algorithm (GA) to speed up the calculation and improve the classification accuracy. It performed good to elude foe41 minima, and consequently' improved the accuracy of classification. Extensive tests showed that this is a better approach as a pattern recognition method to construct artificial nose.
出处
《传感器技术》
CSCD
1996年第6期5-8,共4页
Journal of Transducer Technology
基金
国家自然基金
博士后科学基金
关键词
模式分类
神经网络
遗传算法
传感器阵列
Pattern classification Neural network Simulated annealing Genetic algorithms Sensor array
