Corrections to “Performance Analysis of the FastICA Algorithm and CramÉr–Rao Bounds for Linear Independent Component Analysis”

Tichavský, Petr; Koldovsky, Zbynek; Oja, Erkki

doi:10.1109/tsp.2007.910503

Cited by 55 publications

(121 citation statements)

References 2 publications

Supporting

Mentioning

120

Contrasting

Order By: Relevance

“…As we completely described in [25] and as it was shown in [38,39], the bounded magnitude signals such as BPSK and uniformly distributed signals have better performance according to the CRB. So, in this paper we consider them for radar signal design as described in the next subsection.…”

Section: Signal Designmentioning

confidence: 91%

Target Detection in Pulse-Train Mimo Radars Applying Ica Algorithms

Hatam¹,

Sheikhi²,

Masnadi-Shirazi³

2012

PIER

View full text Add to dashboard Cite

Abstract-In this paper, the problem of target detection in colocated "multi-input multi-output" (MIMO) radars is considered. A pulse-train signaling is assumed to be used in this system. As the doppler effect should be considered for the pulse-train signaling, we are confronted by a compound hypothesis testing problem, so in this paper a Generalized Likelihood Ratio (GLR) detector is derived. The high complexity of this detector makes us derive a new detector based on the theory of Independent Component Analysis (ICA). It is shown that the computational load of the ICA-based detector is much less than the GLR detector. It is also shown that the sensitivity of the ICA-based detector to the doppler effect is very low. According to this approach, an appropriate signal design method is presented, based on the separation performance of the ICA algorithms. It is shown that independent random sequences are proper signals in the sense of detection performance.

show abstract

Section: Signal Designmentioning

confidence: 91%

Target Detection in Pulse-Train Mimo Radars Applying Ica Algorithms

Hatam¹,

Sheikhi²,

Masnadi-Shirazi³

2012

PIER

View full text Add to dashboard Cite

show abstract

“…It attempts to find a set of independent components by estimating the maximum negative entropy [12]. The algorithm iteratively searches for the weight set i w of a neural network from a data set X via the procedure below [13]: , and find the winning node J whose value of D is the minimum.…”

Section: Fasticamentioning

confidence: 99%

A One-Stop BSS Analysis Method of Integrated System Signals Based on Wavelet Transform, FastICA and SOM

Li¹,

Ma²,

Chen³

et al. 2015

Advances in Intelligent Systems Research

View full text Add to dashboard Cite

Abstract.This paper proposes a new one-stop blind source separation analysis method by combining wavelet transform, FastICA and self-organization mapping network. Firstly, we suppress the Gauss noises by using wavelet transform. Secondly, we separate the mixed signals utilizing FastICA to get the independent components. Finally, we cluster the signals with SOM to reveal the latent relationship of independent signals. Experimental results have shown the validity and effectiveness of the proposed method.

show abstract

“…There are two classes of FastICA algorithms, the deflation algorithms (called also one-unit algorithms) and the symmetric algorithms [20]. In the deflation approach, the independent components (ICs) are extracted sequentially, one by one.…”

Section: Fastica -Deflation Approachmentioning

confidence: 99%

“…While in deflation approach vectors of weights are calculated one by one, in symmetric approach the estimation of all components (all weights vectors) proceeds in parallel [19][20]. Instead of Gram-Schmidt procedure, the following formula is used in the orthogonalization step:…”

Section: Fastica -Symmetric Approachmentioning

confidence: 99%

Independent Component Analysis for EEG Data Preprocessing - Algorithms Comparison

Rejer

Górski

2013

Computer Information Systems and Industrial Management

View full text Add to dashboard Cite

Abstract. Some scientific papers report that when Independent Component Analysis (ICA) is applied in the preprocessing step of designing a brain computer interface, the quality of this interface increases. At the same time, however, these papers do not provide information about the exact gain in classification precision obtained after applying different ICA algorithms. The aim of this paper is to compare three algorithms for Independent Component Analysis applied in the process of creating a brain computer interface in order to find out whether the choice of a specific ICA algorithm has an influence on the final classification precision of this interface. The comparison will be carried out with a set submitted to the second BCI Competition.

show abstract

Corrections to “Performance Analysis of the FastICA Algorithm and CramÉr–Rao Bounds for Linear Independent Component Analysis”

Cited by 55 publications

References 2 publications

Target Detection in Pulse-Train Mimo Radars Applying Ica Algorithms

Target Detection in Pulse-Train Mimo Radars Applying Ica Algorithms

A One-Stop BSS Analysis Method of Integrated System Signals Based on Wavelet Transform, FastICA and SOM

Independent Component Analysis for EEG Data Preprocessing - Algorithms Comparison

Contact Info

Product

Resources

About