Blind Source Separation for Noisy Time Series by Combining Non-Gaussianity and Time-Correlation

2008 ◽  
Author(s):  
Hongjuan Zhang ◽  
Chonghui Guo ◽  
Zhenwei Shi
Keyword(s):  
Time Series ◽  
Blind Source Separation ◽  
Source Separation ◽  
Time Correlation ◽  
Noisy Time Series

scholarly journals Blind source separation problem in GPS time series

2015 ◽  
Vol 90 (4) ◽  
pp. 323-341 ◽  
Author(s):  
A. Gualandi ◽  
E. Serpelloni ◽  
M. E. Belardinelli
Keyword(s):  
Time Series ◽  
Blind Source Separation ◽  
Source Separation ◽  
Separation Problem ◽  
Gps Time Series

scholarly journals A Novel Damage Detection Algorithm using Time-Series Analysis-Based Blind Source Separation

2013 ◽  
Vol 20 (3) ◽  
pp. 423-438 ◽  
Author(s):  
A. Sadhu ◽  
B. Hazra
Keyword(s):  
Time Series ◽  
Time Series Analysis ◽  
Damage Detection ◽  
Blind Source Separation ◽  
Source Separation ◽  
Damage Index ◽  
Detection Algorithm ◽  
Mode Shapes ◽  
Series Analysis ◽  
Modal Response

In this paper, a novel damage detection algorithm is developed based on blind source separation in conjunction with time-series analysis. Blind source separation (BSS), is a powerful signal processing tool that is used to identify the modal responses and mode shapes of a vibrating structure using only the knowledge of responses. In the proposed method, BSS is first employed to estimate the modal response using the vibration measurements. Time-series analysis is then performed to characterize the mono-component modal responses and successively the resulting time-series models are utilized for one-step ahead prediction of the modal response. With the occurrence of newer measurements containing the signature of damaged system, a variance-based damage index is used to identify the damage instant. Once the damage instant is identified, the damaged and undamaged modal parameters of the system are estimated in an adaptive fashion. The proposed method solves classical damage detection issues including the identification of damage instant, location as well as the severity of damage. The proposed damage detection algorithm is verified using extensive numerical simulations followed by the full scale study of UCLA Factor building using the measured responses under Parkfield earthquake.

Blind source separation with time series variational Bayes expectation maximization algorithm

2012 ◽  
Vol 22 (1) ◽  
pp. 17-33 ◽  
Author(s):  
Shijun Sun ◽  
Chenglin Peng ◽  
Wensheng Hou ◽  
Jun Zheng ◽  
Yingtao Jiang ◽  
...  
Keyword(s):  
Time Series ◽  
Blind Source Separation ◽  
Expectation Maximization ◽  
Source Separation ◽  
Expectation Maximization Algorithm ◽  
Variational Bayes

scholarly journals Blind Source Separation for Compositional Time Series

2020 ◽  
Author(s):  
Klaus Nordhausen ◽  
Gregor Fischer ◽  
Peter Filzmoser
Keyword(s):  
Time Series ◽  
Blind Source Separation ◽  
Source Separation

scholarly journals Dimension Reduction for Time Series in a Blind Source Separation Context Using R

2021 ◽  
Vol 98 (15) ◽  
Author(s):  
Klaus Nordhausen ◽  
Markus Matilainen ◽  
Jari Miettinen ◽  
Joni Virta ◽  
Sara Taskinen
Keyword(s):  
Time Series ◽  
Dimension Reduction ◽  
Blind Source Separation ◽  
Source Separation

Functional Semi-Blind Source Separation Identifies Primary Motor Area Without Active Motor Execution

2018 ◽  
Vol 28 (03) ◽  
pp. 1750047 ◽  
Author(s):  
Camillo Porcaro ◽  
Carlo Cottone ◽  
Andrea Cancelli ◽  
Carlo Salustri ◽  
Franca Tecchio
Keyword(s):  
Blind Source Separation ◽  
Upper Limb ◽  
Source Separation ◽  
Motor Task ◽  
Time Correlation ◽  
Motor Area ◽  
High Time Resolution ◽  
Isometric Handgrip ◽  
Active Motor ◽  
Motor Condition

High time resolution techniques are crucial for investigating the brain in action. Here, we propose a method to identify a section of the upper-limb motor area representation (FS_M1) by means of electroencephalographic (EEG) signals recorded during a completely passive condition (FS_M1bySS). We delivered a galvanic stimulation to the median nerve and we applied to EEG the semi-Blind Source Separation (s-BSS) algorithm named Functional Source Separation (FSS). In order to prove that FS_M1bySS is part of FS_M1, we also collected EEG in a motor condition, i.e. during a voluntary movement task (isometric handgrip) and in a rest condition, i.e. at rest with eyes open and closed. In motor condition, we show that the cortico-muscular coherence (CMC) of FS_M1bySS does not differ from FS_ M1 CMC (0.04 for both sources). Moreover, we show that the FS_M1bySS’s ongoing whole band activity during Motor and both rest conditions displays high mutual information and time correlation with FS_M1 (above 0.900 and 0.800, respectively) whereas much smaller ones with the primary somatosensory cortex [Formula: see text] (about 0.300 and 0.500, [Formula: see text]). FS_M1bySS as a marker of the upper-limb FS_M1 representation obtainable without the execution of an active motor task is a great achievement of the FSS algorithm, relevant in most experimental, neurological and psychiatric protocols.

Sign in / Sign up

Export Citation Format

Share Document