Audio-visual underdetermined blind source separation algorithm based on Gaussian potential function

2014 ◽  
Vol 11 (6) ◽  
pp. 71-80 ◽  
Author(s):  
Zhang Ye ◽  
Cao Kang ◽  
Wu Kangrui ◽  
Yu Tenglong ◽  
Zhou Nanrun
Keyword(s):  
Potential Function ◽  
Blind Source Separation ◽  
Source Separation ◽  
Separation Algorithm ◽  
Underdetermined Blind Source Separation ◽  
Gaussian Potential

A New Method for Adaptive Blind Source Separation Based on the Estimated Number of Dynamic Fault Sources

2012 ◽  
Vol 233 ◽  
pp. 211-217 ◽  
Author(s):  
Xiao Yan Yang ◽  
Xiong Zhou ◽  
Yi Ke Tang
Keyword(s):  
Fault Diagnosis ◽  
Blind Source Separation ◽  
Source Separation ◽  
Estimation Algorithm ◽  
Accurate Estimation ◽  
Separation Algorithm ◽  
Underdetermined Blind Source Separation ◽  
Source Signal ◽  
Fault Source ◽  
Source Number

In fault diagnosis of large rotating machinery, the number of fault sources may be subject to dynamic changes, which often lead to the failure in accurate estimation of the number of sources and the effective isolation of the fault source. This paper introduced the expansion of the fourth-order cumulant matrices in estimating the dynamic fault source number, plus the relationship between the source signal number and the number of sensors being utilized in the selection of the blind source separation algorithm to achieve adaptive blind source separation. Experiments showed that the source number estimation algorithm could be quite effective in estimating the dynamic number of fault sources, even in the underdetermined condition. This adaptive blind source separation algorithm could then effectively achieve fault diagnosis in respect to the positive-determined, overdetermined and underdetermined blind source separation.

Augmented Hardware Design of BSS in Real Time by Real Time Feasible Source Signal Separator

2020 ◽  
Vol 14 ◽  
Keyword(s):  
Real Time ◽  
Blind Source Separation ◽  
Source Separation ◽  
Separation Algorithm ◽  
Underdetermined Blind Source Separation ◽  
Memory Space ◽  
The Real ◽  
Wide Range ◽  
Source Signal ◽  
Band Limited

Blind source separation is a blooming sector in the digital signal processing for severing exact signal from the dense recorded. Exclusively, among the “Blind Source Separation” the “Under Determined Blind Source Separation” is considered than an over determined Blind Source Separation due to its wide range of usage. Nevertheless, it is seen that the real implementation is very rarely done in existing researches, because the real time implementation of UBSS (Underdetermined Blind Source Separation)is existed to be a challenging one due to its lacking hardware characteristics of increased latency, reduced speed and consumption of more memory space. Consequently, there is an increase need to implement an Underdetermined source signal separation real time with improved hardware utility that in this Unswerving framework a Real time feasible Source Signal separator is formulated in which initially the source signals are decomposed by Boosted band-limited VMD (Variational Mode Decomposition)into the “Multi component Signal” and then to an amount of "Band-Limited” IMF subjected to the Encompassed Hammer sley–Clifford source separation algorithm that uses expectation-maximization and Gibbs sampling an alternative to deterministic algorithms to determine the exact estimated parameter from E-M method. Subsequently, the source separation algorithm infers the best separation of sources signals by exact estimation and determination from the decomposed signals, whereas the iterations in E-M estimation are reduced by Gauss-Seidel method. Thus our novel source signal separator internally with a signal decomposer and a source separation algorithm with lesser number of iterations which reduces memory consumption and yields better hardware realization with reduced latency and increased speed. The proposed Implementation is done in Xilinx Platform.

Sign in / Sign up

Export Citation Format

Share Document