Sequential change-point detection via the Cross-Entropy method

Georgy Sofronov*, Tatiana Polushina, Madawa Priyadarshana

*Corresponding author for this work

    Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

    9 Citations (Scopus)


    Change-point problems (or break point problems, disorder problems) can be considered one of the central issues of statistics, connecting asymptotic statistical theory and Monte Carlo methods, frequentist and Bayesian approaches, fixed and sequential procedures. In many real applications, observations are taken sequentially over time, or can be ordered with respect to some other criterion. The basic question, therefore, is whether the data obtained are generated by one or by many different probabilistic mechanisms. Change-point problems arise in a wide variety of fields, including biomedical signal processing, speech and image processing, climatology, industry (e.g. fault detection) and financial mathematics. In this paper, we apply the Cross-Entropy method to a sequential change-point problem. We obtain estimates for thresholds in the Shiryaev-Roberts procedure and the CUSUM procedure. We provide examples with generated sequences to illustrate the effectiveness of our approach to the problem.

    Original languageEnglish
    Title of host publication11th Symposium on Neural Network Applications in Electrical Engineering,NEUREL 2012 - Proceedings
    Place of PublicationPiscataway, N.J.
    PublisherInstitute of Electrical and Electronics Engineers (IEEE)
    Number of pages4
    ISBN (Electronic)9781467315722
    ISBN (Print)9781467315692
    Publication statusPublished - 2012
    Event2012 9th International Conference on High Capacity Optical Networks and Enabling Technologies, HONET 2012 - Istanbul, Turkey
    Duration: 14 Dec 201214 Dec 2012


    Other2012 9th International Conference on High Capacity Optical Networks and Enabling Technologies, HONET 2012


    Dive into the research topics of 'Sequential change-point detection via the Cross-Entropy method'. Together they form a unique fingerprint.

    Cite this