getFMMPeaks function

Peak and trough times and signal values

getFMMPeaks() is used to estimate peak and trough times and signal values at those times for each component of the model. These parameters result to be useful in multiple applications.

getFMMPeaks(objFMM, timePointsIn2pi = TRUE)

Arguments

• objFMM: Object of class 'FMM'
• timePointsIn2pi: TRUE to return peak and trough times in the $[0, 2\pi]$ interval. When timePointsIn2pi = FALSE the positions of peak and trough times are returned. Its default value is TRUE.

Returns

A list with the following components is returned: - tpeakU: a numeric vector with the time points at which the peak of each wave is estimated.

• tpeakL: a numeric vector with the time points at which the trough of each wave is estimated.

• ZU: a numeric vector with the estimated signal peak values of each wave.

• ZL: a numeric vector with the estimated signal trough values of each wave.

Examples

## Generate example data:
fmm2.data <- generateFMM(0, rep(2, 2), c(1.5, 3.4), c(0.2, 2.3), c(0.1, 0.2),
                         plot = FALSE, outvalues = TRUE,
                         sigmaNoise = 0.5) # add a gaussian noise with sigma = 0.5

## Fit the FMM model with nback = 2 components
## fit is an object of S4 class 'FMM'
fit <- fitFMM(fmm2.data$y,timePoints = fmm2.data$t,nback = 2,
              lengthAlphaGrid = 24,lengthOmegaGrid = 10)
getFMMPeaks(fit, timePointsIn2pi = TRUE) # times in the [0,2*pi] interval

References

Rueda C, Larriba Y, Peddada SD (2019). Frequency Modulated Moebius Model Accurately Predicts Rhythmic Signals in Biological and Physical Sciences. Scientific reports, 9 (1), 18701. https://www.nature.com/articles/s41598-019-54569-1