人工神经网络在中医脉象信号检测中的应用

Application of neural networks to the detection of pulse signals

人工神经网络是在结构上模仿生物神经连接的连接型网络,经训练的网络可用来进行模式分类,信号处理与检测等。针对海洛因吸食者的脉象信号与正常人脉象信号的特征差异,成功地应用BP网络对15例海洛因吸食者和15例正常人的脉象信号进行了识别。为此,建立了一个40～20～1的二层BP网络模型,选取每一例脉象信号的一段特征信号作为网络的输入信号,采用了训练样本和加噪声的训练样本分别训练网络的方法。论文还比较了共轭梯度法与基本BP算法训练网络的快慢问题。实验结果除1例正常人被误判外,吸毒病人全被检测出来,网络达到了96.7%的识别率,其结果说明训练的网络对检测脉象信号是十分有效的。

Artificial neural networks are a class of interconnected network, which imitate the biological interconnections in structures. A trained neural network may be used to realize pattern recognitions, signal processing and detection, etc.. Considering the characteristic differences between the pulse signals of heroin addicts and healthy persons, we successfully use BP network to identify heroin addicts from the pulse signals of 15 heroin addicts and 15 healthy persons. A two-layer BP network with 40～20～1 is constructed. The input signals of the network are obtained by clipping the characteristic section of every pulse signal. The network is trained by the training samples obtained by the clipping and the training samples with additive noise, respectively. The training speed of the basic BP algorithm is compared with that of the Conjugate Gradient algorithm. The experimental result shows that all of the heroin addicts are identified except that one healthy person is misjudged. The identification rate of the trained networks reaches 96.7%, which shows that the trained networks in this paper are effective for detecting pulse signals.