PROLIFIC - PROfile LIkelihood based on FIbonaCci search

Find the onset of an EMG signal by Fibonacci maximization of the Profile Likelihood

The main function is prolific that estimates the onset starting from an EMG signal. The core methodology is based on the Profile Likelihood that maximizes the Likelihood of the data assuming (possibly different) distributions at the left and the right of the possible onset. The algorithm is made fast by relying on the Fibonacci search algorithm for integer numbers.

The function choosedistr selects the best distributions among a defined set at the left and right of an approximate onset (estimated inside the function) according to the Kolmogorov-Smirnov, Lilliefors or Anderson-Darling tests. The following distributions are included:
Kolmogorov-Smirnov: Gaussian, Extreme Value, Laplace, Cauchy, Logistic, Lognormal, Weibull, Gamma. Birnbaum-Saunders, Exponential, Burr
Anderson-Darling and Lilliefors: Gaussian, Extreme Value, Lognormal, Weibull, Exponential

The function choosedistrKSOracle selects the best distribution when the 'true' onset is known and provided as an argument

All functions produce informative plots

Several input arguments control the functions, output and plots. Detailed description of the I/O arguments to each function and examples can be obtained by the usual help <functionname>

The original method has been published in S.E. Selvan, D. Allexandre, U. Amato, G.H. Yue (2018): Unsupervised Stochastic Strategies for Robust Detection of Muscle Activation Onsets in Surface Electromyogram. IEEE Trans. Neur. Syst. Rehabil. Engin. 26(6), 1279-1291. The fast algorithm and the selection of distribution have been published in S.E. Selvan, D. Allexandre, U. Amato, B. Della Vecchia, G.H. Yue: A Fast and Robust Profile-Likelihood-Based Muscle Onset Detection in EMG using Discrete Fibonacci Search. IEEE Access 8, 105362-105375 (2020), doi:10.1109/ACCESS.2020.3000693
This work was supported by the European Union’s Horizon 2020 Research and Innovation Program under Grant 826589