6533b7d0fe1ef96bd125b865
RESEARCH PRODUCT
Online Non-linear Topology Identification from Graph-connected Time Series
Joshin P. KrishnanRohan MoneyBaltasar Beferull-lozanosubject
Signal Processing (eess.SP)Kernel (linear algebra)Signal processingSeries (mathematics)Autoregressive modelComputer scienceFOS: Electrical engineering electronic engineering information engineeringGraph (abstract data type)InferenceTopology (electrical circuits)Electrical Engineering and Systems Science - Signal ProcessingWireless sensor networkAlgorithmdescription
Estimating the unknown causal dependencies among graph-connected time series plays an important role in many applications, such as sensor network analysis, signal processing over cyber-physical systems, and finance engineering. Inference of such causal dependencies, often know as topology identification, is not well studied for non-linear non-stationary systems, and most of the existing methods are batch-based which are not capable of handling streaming sensor signals. In this paper, we propose an online kernel-based algorithm for topology estimation of non-linear vector autoregressive time series by solving a sparse online optimization framework using the composite objective mirror descent method. Experiments conducted on real and synthetic data sets show that the proposed algorithm outperforms the state-of-the-art methods for topology estimation.
year | journal | country | edition | language |
---|---|---|---|---|
2021-03-31 |