Sequential learning of Multi-state autoregressive time series

Mohammad Noshad, Jie Ding, Vahid Tarokh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Modeling and forecasting streaming data has fundamental importance in many real world applications. In this paper, we present an online model selection technique that can be used to model non-stationary time series in a sequential manner. Multi-state autoregressive (AR) model is used to describe non-stationary time series, and a dynamic algorithm is applied to learn the states at each time step. The proposed technique estimates a candidate AR filter from the most recent data points at every time step, and checks whether starting a new state significantly decreases prediction error or not. To that end, a time-varying threshold is compared with the reduction in the prediction error caused by postulating a new AR filter. The threshold is calculated by sampling and clustering uniformly distributed stable AR filters. Numerical simulations show that the proposed algorithm accurately estimates the state transitions with a small delay.

Original languageEnglish (US)
Title of host publicationProceeding of the 2015 Research in Adaptive and Convergent Systems, RACS 2015
PublisherAssociation for Computing Machinery, Inc
Pages44-51
Number of pages8
ISBN (Electronic)9781450337380
DOIs
StatePublished - Oct 9 2015
Externally publishedYes
EventResearch in Adaptive and Convergent Systems, RACS 2015 - Prague, Czech Republic
Duration: Oct 9 2015Oct 12 2015

Publication series

NameProceeding of the 2015 Research in Adaptive and Convergent Systems, RACS 2015

Other

OtherResearch in Adaptive and Convergent Systems, RACS 2015
Country/TerritoryCzech Republic
CityPrague
Period10/9/1510/12/15

Keywords

  • Autoregressive process
  • Multi-state process
  • Online update
  • Sequential learning

Fingerprint

Dive into the research topics of 'Sequential learning of Multi-state autoregressive time series'. Together they form a unique fingerprint.

Cite this