.png){kind=icon}
.png){kind=icon}
Return
ADTFD-RANSAC For multi-component IF estimation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.sigpro.2022.108494.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
A RANSAC-based instantaneous frequency (IF) estimation algorithm for multi-component signals having overlapping time-frequency signatures is developed. The proposed algorithm first analyzes a multi component signal using adaptive directional time-frequency distribution (ADTFD) to obtain a high resolution signal representation. The algorithm iteratively selects a set of peaks from the ADTFD, fits the IF curve, and evaluates the IF curve using a novel objective function that takes into account both amplitude and smoothness of the curve. Among all the candidate IF curves, the one minimizing the objective function is selected. The IF information is used to remove the corresponding component from the mixture signal and this process is iterated till the IFs of all the components are estimated. Experimental results indicate the superiority of the proposed method as compared to the state of the art.(c) 2022 Elsevier B.V. All rights reserved.
Keywords:
Instantaneous frequency
Adaptive directional time-frequency distribution
RANSAC
Multi-components