On using the modularity of recurrence network communities to detect change-point behaviour

The behaviour of a dynamical system can be examined from time series using the technique of recurrence plots through visualization and quantification methods. One such method is the quadrant scan in which a recurrence plot of a time series is converted into a second time series whose local maxima can be identified and interpreted as possible transitions in dynamic behaviour. A recurrence plot can also be represented as a complex network. A quadrant scan can similarly be thought of as a partition of the network vertices into two communities. Here, we argue that different dynamic behavioural regimes can be realized as network communities and the quality of such partitions can be assessed using modularity. Thereby, community modularity can be used as an alternative to the quadrant scan. We investigate this correspondence with respect to two promising arenas for quadrant scan uptake, namely, concept drift detection from machine learning and tipping point or failure and damage monitoring in system maintenance. We also examine two additional data sets to highlight the potential of the methods. These are a geophysical time series of earth tremor data and a physiological time series of an electrocardiogram.