Objective: Sleep spindles contain crucial brain dynamics information. We introduce the novel non-linear time-frequency analysis tool 'Concentration of Frequency and Time' (ConceFT) to create an interpretable automated algorithm for sleep spindle annotation in EEG data and to measure spindle instantaneous frequencies (IFs). Methods: ConceFT effectively reduces stochastic EEG influence, enhancing spindle visibility in the time-frequency representation. Our automated spindle detection algorithm, ConceFT-Spindle (ConceFT-S), is compared to A7 (non-deep learning) and SUMO (deep learning) using Dream and MASS benchmark databases. We also quantify spindle IF dynamics. Results: ConceFT-S achieves F1 scores of 0.749 in Dream and 0.786 in MASS, which is equivalent to or surpass A7 and SUMO with statistical significance. We reveal that spindle IF is generally nonlinear. Conclusion: ConceFT offers an accurate, interpretable EEG-based sleep spindle detection algorithm and enables spindle IF quantification.

This README is intended as an introduction to anyone with experience programming in Python who is interested in delving deeper into analysis of data from the Green Bank Telescope. It assumes little or no knowledge of radio astronomy or of techniques used in the search for extraterrestrial intelligence. Intended audiences include those who may be interested in running machine learning or other sophisticated analyses on Breakthrough Listen data. First, if you haven't already read the five-page introduction on our webpage, please visit seti.berkeley.edu/listen We're going to concentrate on radio searches here, specifically those that we're doing with the 100-meter diameter Green Bank Telescope (GBT) in West Virginia - the largest fully-steerable radio telescope on the planet.

Many studies of feature importance with tree based models assume the independance of the predictors.