A novel blind source separation method for single-channel signal

Authors:
Hong-Guang Ma;Qin-Bo Jiang;Zhi-Qiang Liu;Gang Liu;Zhi-Yuan Ma
Affiliations:
Xi'an Research Institute of High Technology, Xi'an 710025, P.R. China;Xi'an Research Institute of High Technology, Xi'an 710025, P.R. China;Xi'an Research Institute of High Technology, Xi'an 710025, P.R. China;Xi'an Research Institute of High Technology, Xi'an 710025, P.R. China;Xi'an Research Institute of High Technology, Xi'an 710025, P.R. China
Venue:
Signal Processing
Year:
2010

Citing 7
Cited 1

Singular-spectrum analysis: a toolkit for short, noisy chaotic signals

Conference proceedings on Interpretation of time series from nonlinear mechanical systems
Statistical Digital Signal Processing and Modeling

Statistical Digital Signal Processing and Modeling
Independent Component Analysis: Principles and Practice

Independent Component Analysis: Principles and Practice
A real-time blind source separation scheme and its application to reverberant and noisy acoustic environments

Signal Processing
Singular spectrum analysis of traffic workload in a large-scale wireless lan

Proceedings of the 10th ACM Symposium on Modeling, analysis, and simulation of wireless and mobile systems
Comparing time series using wavelet-based semblance analysis

Computers & Geosciences
Statistical models of reconstructed phase spaces for signal classification

IEEE Transactions on Signal Processing - Part I

Boundary extension for Hilbert-Huang transform inspired by gray prediction model

Signal Processing

Quantified Score

Hi-index	0.08

Visualization

Abstract

The blind separation of single-channel signal is one of the most important aspects in many fields. Our research is carried out to develop a blind separation method of single-channel signal, in which the singular spectrum analysis (SSA) and blind source separation (BSS) techniques are jointly used, i.e. the single-channel signal is firstly changed into pseudo-MIMO (multi-input and multi-output) mode, and then each source signal is separated via a fast BSS algorithm. A signal preprocessing procedure, which is mainly focused on testing the nonstationarity of single-channel signal, is conducted before the operations of mixed signal transform and separation. In this research, the approach of heuristic segmentation of a nonstationary time-series is proposed. Throughout the experiment, the effectiveness of the proposed method is validated with a data set taken from a digital wideband receiver in an outdoor test. Then, a comparison is made between the proposed method and the Hilbert-Huang transform (HHT)-based signal separation method. The advantage of the proposed method is exhibited.