jaccard.index: Jaccard Index similarity coefficient

In ialmodovar/RFASTfMRI: FAST Adaptive Smoothing and Thresholding for Improved Activation Detection in Low-Signal fMRI

Jaccard Index similarity coefficient

Description

Compute Jaccard index to determine similarity between activation maps.

Usage

jaccard.index(x, y, value.if.both.nulls = 1)

Arguments

x	vector of 0's (inactives) and 1's (actives).
y	vector of 0's (inactives) and 1's (actives).
value.if.both.nulls	value to be returned if both x and y are all 0. By default, this is set to 1 but can be set by the user to a desired value, for instance, when it is known that x and y are incorrectly all 0.

Details

x and y need to be of the same size. NAs will be automatically removed. A value close to 1 means excellent similarity between the actives in x and those in y while values close to zero indicate very little similarity.

Author(s)

Israel Almodovar-Rivera and Ranjan Maitra.

References

Almodovar-Rivera, I., & Maitra, R. (2019). FAST adaptive smoothing and thresholding for improved activation detection in low-signal fMRI. IEEE Transactions on Medical Imaging, 38(12), 2821-2828.

Maitra, R. (2010). A re-defined and generalized percent-overlap-of-activation measure for studies of fMRI reproducibility and its use in identifying outlier activation maps. Neuroimage, 50(1), 124-135.

Jaccard, P. (1901). Etude comparative de la distribution florale dans une portion des Alpes et des Jura. Bull Soc Vaudoise Sci Nat, 37, 547-579.

Examples

## Not run: 
set.seed(787)
x <- sample(x = 0:1,size = 50,replace=TRUE)
y <- sample(x = 0:1,size = 50,replace=TRUE)
jaccard.index(x = x,y = y)

## End(Not run)

ialmodovar/RFASTfMRI documentation built on Aug. 30, 2022, 1:33 a.m.