The next EarthByte seminar will be held at 11am–12pm on Wednesday 16th November in Madsen Seminar Room 331 at the University of Sydney. This week we will be hearing from Ben Fulcher from the Dynamics and Neural Systems Group within the School of Physics at the University of Sydney, discussing his work on “Quantifying patterns in time series.” As usual, the seminar will be streamed live over Zoom at the following link: https://uni-sydney.zoom.us/j/82037433636.
More details are below:
Quantifying patterns in time series
Over decades, an interdisciplinary scientific literature has contributed myriad methods for quantifying patterns in time series. These methods can be encoded as features that summarize different types of time-series structure as interpretable real numbers (e.g., the shape of peaks in the Fourier power spectrum). In this talk, I will show how large libraries of time-series features (>7k, implemented in the hctsa package) and time series (>30k, in the CompEngine database) enable new ways of analyzing time-series datasets, and of assessing the novelty and usefulness of time-series analysis methods. I will highlight new open tools that we’ve developed to enable these analyses, recent extensions to inferring dependence structures in multivariate time series and discuss applications to datasets from neuroscience and astronomy.