摘要
采用小波变换方法对麻醉监测脑电信号进行分析, 通过基于小波变换系数的奇异值分解构造特征向量的特征提取方法提取麻醉状态下中潜伏期听觉诱发脑电的特征, 并用BP网络分类器对提取的特征进行聚类, 从而实现麻醉深度的估计, 实验仿真结果表明了该方法的有效性.
A feature extraction method to evoke the potential signal during anesthesia monitoring based onwavelet transformation coefficients singular value decomposition is presented. The features extracted fromMLAEP during anesthesia are classified with a BP neural network to estimate the anesthesia depth. The simu-lated experiment results show that the method is effective.
出处
《昆明理工大学学报（理工版）》
2003年第3期97-100,共4页
Journal of Kunming University of Science and Technology(Natural Science Edition)
基金
国家自然科学基金资助项目(项目编号: 69871010)
桂林工学院青年扶持基金资助项目.
