Deep Learning for analyzing chaotic dynamics in biological time series: Insights from frog heart signals

The study of experimental data is a relevant task in several physical, chemical and biological applications. In particular, the analysis of chaotic dynamics in cardiac systems is crucial as it can be related to certain pathological arrhythmias. When working with short and noisy experimental time series, some standard techniques for chaos detection cannot provide reliable results because of such data characteristics. Moreover, when small datasets are available, some Deep Learning techniques cannot be applied directly (that is, using part of the data to train the network, and using the trained network to analyze the remaining dataset). To overcome all these limitations, we propose an automatic algorithm that combines Deep Learning and some selection strategies based on a mathematical model of the same nature of the experimental data. To demonstrate its performance, we test it with experimental data obtained from ex-vivo frog heart experiments, achieving highly accurate results.