,
This function returns an extended eeg_lst, eeg_ica_lst, with the mixing and unmixing
matrix of every recording. It is possible to visualize the topography
of the components with plot_components(). In order to extract the amplitude of
the components with respect to time use eeg_ica_show(), see examples section. To remove the
unwanted components, use eeg_ica_keep().
eeg_ica(
.data,
...,
.ignore = .type == "artifact",
.method = fast_ICA,
.config = list()
)An eeg_lst object
Channels to include in ICA transformation. All the channels by default, but eye channels and reference channels should be removed.
Events that should be ignored in the ICA, set to NULL for not using the events table.
Methods from different packages: fast_ICA, a wrapper of fastICA::fastICA, (default), and some more experimental .methods: fast_ICA2 and adapt_fast_ICA adapted from fICA package. It can also accept a custom function, see details.
Other parameters passed in a list to the ICA method. See the documentation of the relevant .method.
An eeg_ica_lst object
It is possible to also use a custom function in the method argument. The function should return
a list that with A (mixing matrix), consistent with the formulation X = S %*% A, where X is matrix
of N_samples by N_channels and/or W (unmixing matrix), consistent with the formulation X %*% W = S.
Some packages with other ICA methods or implementations: steadyICA and ica.
Other ICA functions:
eeg_ica_cor_tbl(),
eeg_ica_keep(),
eeg_ica_show(),
eeg_ica_summary_tbl(),
eeg_ica_var_tbl(),
plot_components()
Other preprocessing functions:
eeg_baseline(),
eeg_downsample(),
eeg_ica_keep(),
eeg_rereference(),
eeg_segment(),
filt
# For demonstration only, since ICA won't converge
# Suppressing an important warning:
suppressWarnings(data_faces_10_trials %>%
eeg_ica(-EOGH, -EOGV, -M1, -M2, .method = fast_ICA, .config = list(maxit = 10)))
#> # ICA is being done using fast_ICA...
#> # ICA finished in 9 iterations. With a tolerance of 0.991338. (Maximum expected tolerance: 1e-06.)
#> # ICA took 1.06 secs
#> # EEG data:
#>
#> # Signal table:
#> Key: <.id, .sample>
#> .id .sample Fp1 Fpz Fp2
#> <int> <sample_int> <channel_dbl> <channel_dbl> <channel_dbl>
#> 1: 1 15000 -75.03562 -28.57522 -28.165712
#> 2: 1 15001 -65.61619 -33.53533 -24.389921
#> 3: 1 15002 -53.28476 -33.01109 -16.815264
#> 4: 1 15003 -49.85156 -31.56947 -12.792553
#> 5: 1 15004 -51.95777 -30.04367 -11.117691
#> ---
#> 43325: 1 58324 -20.42674 -14.87641 -10.669024
#> 43326: 1 58325 -19.79967 -13.65431 -9.698612
#> 43327: 1 58326 -18.61094 -13.91012 -10.128812
#> 43328: 1 58327 -16.96312 -14.78610 -11.301287
#> 43329: 1 58328 -15.31518 -15.08285 -11.722956
#> F7 F3 Fz F4 F8
#> <channel_dbl> <channel_dbl> <channel_dbl> <channel_dbl> <channel_dbl>
#> 1: -35.1809807 -29.561008 -11.504043 -4.137532 9.616964
#> 2: -24.2422733 -26.622681 -13.667097 -6.835285 11.225069
#> 3: -11.4339190 -19.439884 -13.724218 -7.711213 10.861008
#> 4: -6.6371970 -16.500380 -13.453588 -7.477996 9.886633
#> 5: -7.1528592 -15.707507 -12.726236 -6.223224 10.369526
#> ---
#> 43325: -0.5581126 -10.197008 -8.468801 -5.040645 -9.132243
#> 43326: -0.6716754 -8.732699 -7.252934 -3.377731 -8.813243
#> 43327: -0.7749598 -8.517799 -6.654031 -2.315117 -7.843120
#> 43328: -0.7414806 -9.084275 -6.622538 -1.845731 -6.556810
#> 43329: -0.3960888 -9.219618 -6.436240 -1.520404 -5.406781
#> FC5 FC1 FC2 FC6 M1
#> <channel_dbl> <channel_dbl> <channel_dbl> <channel_dbl> <channel_dbl>
#> 1: -13.626797 -16.7902756 -4.733483 20.05954933 -1.8668146
#> 2: -9.239326 -15.9672518 -8.509321 4.00367641 -3.2960243
#> 3: -10.491687 -11.6829367 -10.936778 -5.81625843 -3.7450671
#> 4: -13.772001 -9.7923832 -11.740524 -5.40025806 -3.7946916
#> 5: -11.491154 -9.8350058 -10.939524 -0.02480793 -3.2719884
#> ---
#> 43325: -7.535339 -2.3418787 -3.478385 -9.38459492 0.8050708
#> 43326: -9.061241 -1.0433049 -1.930508 -7.47599792 0.9832335
#> 43327: -7.603340 -0.6127751 -1.379790 -5.71040392 1.2051768
#> 43328: -2.782797 -1.4022492 -1.640656 -4.64086485 1.4103985
#> 43329: 2.897767 -2.5480108 -1.864611 -4.35131598 1.1627738
#> T7 C3 Cz C4 T8
#> <channel_dbl> <channel_dbl> <channel_dbl> <channel_dbl> <channel_dbl>
#> 1: -24.323915482 -16.1792583 -17.846788 7.3229218 -16.999569
#> 2: -15.526218414 -14.2676773 -16.833292 2.9823387 1.561563
#> 3: -9.126789093 -6.4200578 -14.397903 0.2715862 16.691229
#> 4: -12.452255249 -1.2270993 -14.878461 0.3950298 16.609812
#> 5: -17.832372665 -1.3789420 -16.662720 1.3136983 9.947195
#> ---
#> 43325: 0.003161311 -0.1895013 -4.354355 -8.3621836 -5.082950
#> 43326: 0.534484148 1.4632750 -2.513818 -6.4180498 -5.036983
#> 43327: 0.933975220 1.7615180 -1.322806 -5.1856117 -1.183164
#> 43328: 1.373799086 -0.1813622 -1.508159 -5.1739321 3.655909
#> 43329: 1.512201071 -3.2800312 -2.576048 -5.2422166 5.829760
#> M2 CP5 CP1 CP2 CP6
#> <channel_dbl> <channel_dbl> <channel_dbl> <channel_dbl> <channel_dbl>
#> 1: 1.8668146 -5.6213522 -19.5446644 -10.161226 9.255368
#> 2: 3.2960243 -5.7683177 -18.2775211 -9.952282 12.423758
#> 3: 3.7450671 -1.5748284 -14.0693884 -7.703567 16.022276
#> 4: 3.7946916 3.9857802 -12.2347841 -7.086234 18.729359
#> 5: 3.2719884 6.8450770 -13.1421146 -8.301058 16.974117
#> ---
#> 43325: -0.8050708 3.3321576 0.7318851 -8.517914 -14.386089
#> 43326: -0.9832335 3.6177154 2.1529536 -6.548975 -11.468288
#> 43327: -1.2051768 3.1916180 2.6771717 -5.318815 -8.818744
#> 43328: -1.4103985 1.9870222 1.8302985 -5.515146 -7.753020
#> 43329: -1.1627738 0.5995106 0.1455368 -6.459312 -7.319424
#> P7 P3 Pz P4 P8
#> <channel_dbl> <channel_dbl> <channel_dbl> <channel_dbl> <channel_dbl>
#> 1: -2.1418185 -7.6355362 -12.714437 -5.254761 -10.3836517
#> 2: -1.8970445 -8.8778076 -12.883518 -4.029041 -4.5240870
#> 3: 0.5571944 -6.6042719 -11.049878 -1.706636 0.7570043
#> 4: 3.3928101 -3.9107032 -10.942114 -1.011510 1.3604219
#> 5: 4.5437369 -3.4414954 -12.527228 -2.947548 -2.2667072
#> ---
#> 43325: 7.0251837 0.5382314 -4.589949 -10.580815 -11.0312319
#> 43326: 6.4313159 0.9306827 -3.111303 -8.619126 -9.3256149
#> 43327: 4.4492149 0.3993354 -2.119561 -6.606555 -6.3650703
#> 43328: 2.3532932 -1.1857104 -2.376006 -5.663703 -4.0656471
#> 43329: 1.0884135 -3.2549555 -3.662545 -5.691663 -3.3207316
#> POz O1 Oz O2 EOGV
#> <channel_dbl> <channel_dbl> <channel_dbl> <channel_dbl> <channel_dbl>
#> 1: -14.801150 -13.6920586 -16.631485 -15.5945311 -205.85693
#> 2: -13.380352 -10.6821909 -12.549113 -11.1155939 -214.15259
#> 3: -10.860615 -7.1099706 -8.650514 -7.0801344 -220.57965
#> 4: -10.532288 -5.4831371 -8.433714 -7.1516109 -218.24934
#> 5: -12.728923 -7.6384282 -12.844979 -11.7087927 -217.16670
#> ---
#> 43325: -5.136292 1.4443915 -5.164615 -8.2288170 18.41424
#> 43326: -3.689569 1.4091530 -3.915735 -6.4314718 19.22052
#> 43327: -2.319134 0.5369543 -2.351812 -3.4845843 19.74028
#> 43328: -1.927569 -0.5624531 -1.339175 -1.1418194 19.20309
#> 43329: -2.687999 -1.2014523 -1.284558 -0.7185705 18.72752
#> EOGH
#> <channel_dbl>
#> 1: 164.320831
#> 2: 158.389755
#> 3: 157.559784
#> 4: 162.165161
#> 5: 168.559723
#> ---
#> 43325: 6.434383
#> 43326: 7.837689
#> 43327: 8.659687
#> 43328: 8.609533
#> 43329: 8.829977
#>
#> ## Events table:
#> Index: <.type>
#> .id .type .description .initial .final .channel
#> <int> <char> <char> <sample_int> <sample_int> <char>
#> 1: 1 Bad Interval Bad Min-Max 15000 15128 FC6
#> 2: 1 Bad Interval Bad Min-Max 15000 15146 F8
#> 3: 1 Bad Interval Bad Min-Max 15000 15142 Fp1
#> 4: 1 Bad Interval Bad Min-Max 15000 15132 Fp2
#> 5: 1 Bad Interval Bad Min-Max 15000 15140 Fpz
#> ---
#> 540: 1 Bad Interval Bad Min-Max 55058 55400 Fpz
#> 541: 1 Bad Interval Bad Min-Max 55077 55314 F8
#> 542: 1 Stimulus s130 56380 56380 <NA>
#> 543: 1 Stimulus s70 56750 56750 <NA>
#> 544: 1 Stimulus s130 58328 58328 <NA>
#>
#> # ICA:
#> # Component_names:ICA1, ICA2, ICA3, ICA4, ICA5, ICA6, ICA7, ICA8, ICA9, ICA10, ICA11, ICA12, ICA13, ICA14, ICA15, ICA16, ICA17, ICA18, ICA19, ICA20, ICA21, ICA22, ICA23, ICA24, ICA25, ICA26, ICA27, ICA28, ICA29, ICA30
#> # Channels_used: Fp1, Fpz, Fp2, F7, F3, Fz, F4, F8, FC5, FC1, FC2, FC6, T7, C3, Cz, C4, T8, CP5, CP1, CP2, CP6, P7, P3, Pz, P4, P8, POz, O1, Oz, O2
#>
#> # Segments table:
#> Key: <.id>
#> .id .recording segment
#> <int> <char> <int>
#> 1: 1 faces.vhdr 1
## The example can only bu run, if python is properly configured (see reticulate package help)
## Here a python ICA function is used:
if (FALSE) {
library(reticulate)
use_condaenv("anaconda3") # use the appropriate environment
sk <- import("sklearn.decomposition")
py_fica <- function(x) {
x <- as.matrix(x)
ica <- sk$FastICA(whiten = TRUE, random_state = 23L)
X <- scale(x, scale = FALSE) %>%
as.matrix(x)
S <- ica$fit_transform(X)
W <- t(ica$components_)
list(W = W)
}
data_ica_py <- eeg_ica(data_faces_10_trials, -EOGH, -EOGV, -M1, -M2, .method = py_fica)
}