Journal: PLoS ONE

Article Title: Comparing the reliability of different ICA algorithms for fMRI analysis

doi: 10.1371/journal.pone.0270556

Figure Lengend Snippet: Repetition number k did not influence Iq values for non-deterministic ICA (sensory data).

Article Snippet: For both sensory data and motor data, only the results of FastICA exhibited good spatial consistency with the results of Infomax when considering median and minimum SCC values ( Tables and ).

Techniques:

Journal: PLoS ONE

Article Title: Comparing the reliability of different ICA algorithms for fMRI analysis

doi: 10.1371/journal.pone.0270556

Figure Lengend Snippet: ICASSO repetition number k with the highest median Iq of each algorithm (sensory data).

Article Snippet: For both sensory data and motor data, only the results of FastICA exhibited good spatial consistency with the results of Infomax when considering median and minimum SCC values ( Tables and ).

Techniques:

Journal: PLoS ONE

Article Title: Comparing the reliability of different ICA algorithms for fMRI analysis

doi: 10.1371/journal.pone.0270556

Figure Lengend Snippet: Repetition number k did not influence Iq values for non-deterministic ICA (motor data).

Article Snippet: For both sensory data and motor data, only the results of FastICA exhibited good spatial consistency with the results of Infomax when considering median and minimum SCC values ( Tables and ).

Techniques:

Journal: PLoS ONE

Article Title: Comparing the reliability of different ICA algorithms for fMRI analysis

doi: 10.1371/journal.pone.0270556

Figure Lengend Snippet: ICASSO repetition number k with the highest median Iq of each algorithm (motor data).

Article Snippet: For both sensory data and motor data, only the results of FastICA exhibited good spatial consistency with the results of Infomax when considering median and minimum SCC values ( Tables and ).

Techniques:

Journal: PLoS ONE

Article Title: Comparing the reliability of different ICA algorithms for fMRI analysis

doi: 10.1371/journal.pone.0270556

Figure Lengend Snippet: Differences in SCC values between the most reliable ICASSO results and the other nine results (sensory data).

Article Snippet: For both sensory data and motor data, only the results of FastICA exhibited good spatial consistency with the results of Infomax when considering median and minimum SCC values ( Tables and ).

Techniques:

Journal: PLoS ONE

Article Title: Comparing the reliability of different ICA algorithms for fMRI analysis

doi: 10.1371/journal.pone.0270556

Figure Lengend Snippet: Differences in SCC values between the most reliable ICASSO results and the other nine results (motor data).

Article Snippet: For both sensory data and motor data, only the results of FastICA exhibited good spatial consistency with the results of Infomax when considering median and minimum SCC values ( Tables and ).

Techniques:

Journal: PLoS ONE

Article Title: Comparing the reliability of different ICA algorithms for fMRI analysis

doi: 10.1371/journal.pone.0270556

Figure Lengend Snippet: Range of SCC values between the most reliable ICASSO results and the other nine results (sensory data).

Article Snippet: For both sensory data and motor data, only the results of FastICA exhibited good spatial consistency with the results of Infomax when considering median and minimum SCC values ( Tables and ).

Techniques:

Journal: PLoS ONE

Article Title: Comparing the reliability of different ICA algorithms for fMRI analysis

doi: 10.1371/journal.pone.0270556

Figure Lengend Snippet: Range of SCC values between the most reliable ICASSO results and the other nine results (motor data).

Article Snippet: For both sensory data and motor data, only the results of FastICA exhibited good spatial consistency with the results of Infomax when considering median and minimum SCC values ( Tables and ).

Techniques:

Journal: PLoS ONE

Article Title: Comparing the reliability of different ICA algorithms for fMRI analysis

doi: 10.1371/journal.pone.0270556

Figure Lengend Snippet: SCC values between the most reliable Infomax results and the other nine results (sensory data).

Article Snippet: For both sensory data and motor data, only the results of FastICA exhibited good spatial consistency with the results of Infomax when considering median and minimum SCC values ( Tables and ).

Techniques:

Journal: PLoS ONE

Article Title: Comparing the reliability of different ICA algorithms for fMRI analysis

doi: 10.1371/journal.pone.0270556

Figure Lengend Snippet: SCC values between the most reliable Infomax results and the other nine results (motor data).

Article Snippet: For both sensory data and motor data, only the results of FastICA exhibited good spatial consistency with the results of Infomax when considering median and minimum SCC values ( Tables and ).

Techniques:

Journal: BioMed Research International

Article Title: A Review of Feature Extraction Software for Microarray Gene Expression Data

doi: 10.1155/2014/213656

Figure Lengend Snippet: Summary of ICA software.

Article Snippet: 3 , HiPerSAT , Keith et al. [ ] , C++, MATLAB, and EEGLAB , (i) Integration of FastICA, Informax, and SOBI algorithms (ii) Data whitening is provided.

Techniques: Software, Extraction

Journal: Computational Intelligence and Neuroscience

Article Title: PWC-ICA: A Method for Stationary Ordered Blind Source Separation with Application to EEG

doi: 10.1155/2016/9754813

Figure Lengend Snippet: Comparison of Amari indices for different BSS approaches trained on randomly mixed VAR simulated data. The algorithms with average Amari indices significantly lower ( p < 0.05) than AMICA, Extended Infomax, and FastICA are bold, with the largest p value for the three comparisons shown in parentheses. The cells that are not bold had Amari index distributions that were not significantly lower ( p < 0.05) than at least one of the algorithms AMICA, Extended Infomax, and FastICA. The average baseline was computed by generating 50,000 random demixing matrices for each of the 20 mixing matrices, resulting in a distribution of one million Amari indices, the average of which is reported.

Article Snippet: More importantly, FastICA, Infomax ICA, AMICA, and the proposed Hilbert approach find many components with good dipole RV values but that do not correlate well with a source and/or are not physically close to a source they correlate well with.

Techniques: Comparison

Journal: Computational Intelligence and Neuroscience

Article Title: PWC-ICA: A Method for Stationary Ordered Blind Source Separation with Application to EEG

doi: 10.1155/2016/9754813

Figure Lengend Snippet: Average number of sources that are matched by a demixing solution component with absolute correlation ≥ 0.7 per experiment. Recall that Experiments 1 and 3 had 10 sources and Experiment 2 was generated by 5 sources. Bold values correspond to the significant PWC-ICA algorithms (by the Amari index) as described in Table 1 .

Article Snippet: More importantly, FastICA, Infomax ICA, AMICA, and the proposed Hilbert approach find many components with good dipole RV values but that do not correlate well with a source and/or are not physically close to a source they correlate well with.

Techniques: Generated

Journal: BMC Genomics

Article Title: Determining the optimal number of independent components for reproducible transcriptomic data analysis

doi: 10.1186/s12864-017-4112-9

Figure Lengend Snippet: Analysis of component reproducibility in independent datasets. a Graph of reciprocal correlations showing the reproducibility of the metagenes of independent components in 6 independent breast cancer datasets. Each node here is an independent component, represented by a metagene, from an ICA decomposition with M = 100 components. Edges show only reciprocal correlations between metagenes with Pearson correlation >0.3. Triangles (on the right) show the components driven by the expression of a small group of genes (frequently, one gene). Node size reflects the rank of the component based on the stability in multiple runs of fastICA (larger nodes are more stable ones). The edge width and the color reflect the value of the correlation coefficient between two metagenes, with thicker edges showing larger correlation values. Several pseudo-cliques of highly reproducible components are annotated either by the dominating small group of genes (pseudo-cliques of triangle nodes), or by comparing to the results of the previously published large-scale ICA-based analysis of gene expression or by performing the hypergeometric test using the set of top-contributing genes (with projection larger than 5.0 onto the component). The analogous correlation graph computed for MSTD number of components is provided in Additional file : Figure SF3. b average reproducibility score (sum of reciprocal correlation coefficients for an independent component) for the correlation graph shown in a), as a function of the relative (component rank minus MSTD value for a given dataset, for stability-based ranking) or absolute (for other ranking types) component rank. It is clear that only stability-based ranking matches the reproducibility score

Article Snippet: Computational time for ICA decomposition of different orders from 2 to 100 with step 5, using compiled MATLAB fastICA implementation and stability analysis by re-computing fastICA from 100 various initial conditions.

Techniques: Expressing