基于长球面波函数和最大相关熵准则的鲁棒信号重构
Robust Signal Reconstruction Using the Prolate Spherical Wave Functions and Maximum Correntropy Criterion
摘要:
信号重构是信号处理中的重要问题之一。提出了一种基于长球面波函数和最大相关熵准则的信号重构方法。PSWFs是一种特殊的函数,在信号重构中具有良好的性能。然而,现有的基于PSWFs的重建方法仅考虑均方误差(MSE)准则作为代价函数。由于均方误差准则是由高斯假设建立起来的,因此对非高斯噪声比较敏感。因此,对于脉冲噪声或野值,基于均方误差的重建方法将导致较大的重建误差。提出的基于MCC和PSWFS的鲁棒信号重建方法可以降低大噪声和非高斯噪声的影响。对合成信号的实验结果表明,该方法在大多数情况下都能显著提高均方误差。
英文摘要:
Signal Reconstruction is one of the most important problem in signal processing. This paper proposes a novel signal reconstruction method based on the prolate spherical wave functions (PSWFs) and maximum correntropy criterion (MCC). The PSWFs are a kind of special functions, which have been proved having good performance in signal reconstruction. However, the existing PSWFs based reconstruction methods only consider the mean square error (MSE) criterion as the cost functions. The MSE criterion is sensitive to the non-Gaussian noise, since it is builded up by the Gaussian assumption. Therefore, for the impulsive noise or outliers, the MSE based reconstruction methods will lead to the large reconstruction error. The proposed MCC and PSWFs based robust signal reconstruction method can reduce the impact of large and non-Gaussian noise. The experimental results on the synthetic signals show that the proposed method can improve the MSE with notable gains in most cases.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。