Sinha Rakesh Kumar, Aggarwal Yogender, Das Barda Nand
Department of Biomedical Instrumentation, Birla Institute of Technology, Mesra, Ranchi, Jharkhand 835215, India.
J Med Syst. 2007 Feb;31(1):63-8. doi: 10.1007/s10916-006-9043-y.
This paper presents an effective application of backpropagation artificial neural network (ANN) in differentiating electroencephalogram (EEG) power spectra of syncopic and normal subjects. Digitized 8-channel EEG data were recorded with standard electrodes placement and amplifier settings from five confirmed syncopic and five normal subjects. The preprocessed EEG signals were fragmented in two-second artifact free epochs for calculation and analysis of changes due to syncope. The results revealed significant increase in percentage delta and alpha (p < 0.5 or better) with significant reduction in percentage theta activity (p < 0.05). The backpropagation ANN used for classification contains 60 nodes in input layer, weighted from power spectrum data from 0 to 30 Hz, 18 nodes in hidden layer and an output node. The ANN was found effective in differentiating the EEG power spectra from syncopic EEG power spectra and the normal EEG power spectra with an accuracy of 88.87% (85.75% for syncopic and 92% for normal).
本文介绍了反向传播人工神经网络（ANN）在区分晕厥患者和正常受试者脑电图（EEG）功率谱方面的有效应用。采用标准电极放置和放大器设置，从5名确诊的晕厥患者和5名正常受试者记录了数字化的8通道EEG数据。将预处理后的EEG信号分割为两秒无伪迹时段，以计算和分析晕厥引起的变化。结果显示，δ波和α波百分比显著增加（p < 0.5或更佳），θ波活动百分比显著降低（p < 0.05）。用于分类的反向传播ANN在输入层包含60个节点，由0至30Hz的功率谱数据加权，隐藏层有18个节点和一个输出节点。发现该ANN能够有效区分晕厥患者的EEG功率谱和正常EEG功率谱，准确率为88.87%（晕厥患者为85.75%，正常受试者为92%）。
Zotero 插件