...
首页> 外文期刊>Sensing and imaging >Human Age Recognition by Electrocardiogram Signal Based on Artificial Neural Network
【24h】

Human Age Recognition by Electrocardiogram Signal Based on Artificial Neural Network

机译:基于人工神经网络的心电信号对人类年龄的识别

获取原文
获取原文并翻译 | 示例
           

摘要

The objective of this work is to make a neural network function approximationrnmodel to detect human age from the electrocardiogram (ECG) signal. Therninput vectors of the neural network are the Katz fractal dimension of the ECG signal,rnfrequencies in the QRS complex, male or female (represented by numeric constant)rnand the average of successive R–R peak distance of a particular ECG signal. The QRSrncomplex has been detected by short time Fourier transform algorithm. The successivernR peak has been detected by, first cutting the signal into periods by auto-correlationrnmethod and then finding the absolute of the highest point in each period. The neuralrnnetwork used in this problem consists of two layers, with Sigmoid neuron in the inputrnand linear neuron in the output layer. The result shows the mean of errors as u00020:49,rn1.03, 0.79 years and the standard deviation of errors as 1.81, 1.77, 2.70 years duringrntraining, cross validation and testing with unknown data sets, respectively.
机译:这项工作的目的是建立一个神经网络功能近似模型,以从心电图(ECG)信号中检测人类的年龄。神经网络的输入向量是ECG信号的Katz分形维数,QRS复数中的频率(男性或女性)(由数字常数表示)rn和特定ECG信号的连续R–R峰值距离的平均值。已通过短时傅立叶变换算法检测到QRSrncomplex。通过以下方法检测到连续的R峰值:首先通过自相关方法将信号切分成多个周期,然后求出每个周期中最高点的绝对值。此问题中使用的神经网络由两层组成,其中Sigmoid神经​​元位于输入层,线性神经元位于输出层。结果显示,在训练,交叉验证和使用未知数据集进行测试期间,误差的平均值分别为u00020:49,rn1.03、0.79年和误差的标准偏差分别为1.81、1.77、2.70年。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号