Efficient Mining of Active Components in a Network of Time Series

Let a network of time series be a set of nodes assuming an underlying network structure, where each node is associated with a discrete time series. The road network, the human brain, online social media are a few examples of domain-specific applications that can be modelled as networks of time series. Now assume that the sequence of time series data points observed on a node determines whether the node is on (active) or off (inactive). Then, at each time step, a set of induced subgraphs can be formed from the subset of active nodes; we call these induced subgraphs active components. In this research, our goal is to efficiently detect and maintain/report the active components over time.