Skip to main content
. Author manuscript; available in PMC: 2018 Nov 30.
Published in final edited form as: Physiol Meas. 2017 Nov 30;38(12):2235–2248. doi: 10.1088/1361-6579/aa9772

Figure 1.

Figure 1

Schematic diagram of the proposed algorithm. The DV partitions obtained from the space of time-lagged HR and MAP time series are transformed to a network g - which consists of a set of nodes and an Adjacency matrix. Every time scale will have a corresponding network. Various topological attributes and features derived from the constructed networks are used as inputs to the SVM classifier. In addition to the network attributes, EMR features are also fed into the SVM classifier