节点文献
基于小波—卡尔曼滤波混合预报的处理EMD边缘问题新方法
New Method of EMD Edge Problem Based on Wavelet-Kalman Filtering Hybrid Forecast
【摘要】 经验模式分解(EMD)方法的提出为信号处理提供了新的方法。在已有经验模式分解的过程中,由于常用三次样条插值来拟合信号的上下包络,因此时常会出现边缘效应,从而影响了信号处理的质量。针对上述情况,利用周期性信号序列经离散小波变换后,使小波系数构成的周期性新序列具有随机游走特性;利用小波与卡尔曼滤波混合预报器对信号进行边界延拓,从而有效地抑制了EMD分解中的边缘效应。仿真结果验证了该方法的有效性。
【Abstract】 Empirical Mode Decomposition(EMD) is a new method which can process signal effectively.Cubic spline interpolation is used to create the upper and lower envelopes in traditional EMD process,which has worse behavior at the edges,and influences the quality of signal process.Aiming at the above case,since the new series from the wavelet coefficients of periodic signals satisfy random walk,hybrid filter which consists of wavelet transform and Kalman filtering is applied to the edges extension of signal.The new method creates the upper and lower envelopes better and restrains effectively edges effect.Computer simulation proves the effectiveness of the method presented.
【Key words】 Empirical Mode Decomposition(EMD); Kalman Filtering; Wavelet Transform; Edge Effect;
- 【文献出处】 计算机应用研究 ,Application Research of Computers , 编辑部邮箱 ,2007年01期
- 【分类号】TN911.7
- 【被引频次】12
- 【下载频次】313