Dynamical complexity of short and noisy time series: Compression-Complexity vs. Shannon entropy

Nagaraj, Nithin and Balasubramanian, Karthi (2017) Dynamical complexity of short and noisy time series: Compression-Complexity vs. Shannon entropy. The European Physical Journal Special Topics, 226 (2191). p. 2204.

2017-Nithin-Nagaraj-EPJST.pdf - Published Version

Download (98kB) | Preview
Abstract: Shannon entropy has been extensively used for characteriz- ing complexity of time series arising from chaotic dynamical systems and stochastic processes such as Markov chains. However, for short and noisy time series, Shannon entropy performs poorly. Complexity measures which are based on lossless compression algorithms are a good substitute in such scenarios. We evaluate the performance of two such Compression-Complexity Measures namely Lempel-Ziv complexity(LZ)andEffort-To-Compress( ETC)onshorttimeseriesfrom chaoticdynamicalsystemsinthepresenceofnoise.Both LZ and ETC outperform Shannon entropy (H) in accurately characterizing the dynamical complexity of such systems. For very short binary sequences (which arise in neuroscience applications), ETC has higher number of distinct complexity values than LZ and H, thus enabling a finer resolution. For two-state ergodic Markov chains, we empirically show that ETC converges to a steady state value faster than LZ. Compression-Complexity measures are promising for applications which involve short and noisy time series.
Item Type: Journal Paper
Additional Information: copyright belongs to the author
Subjects: School of Humanities > Cognitive Science
Programmes > Consciousness Studies Programme > Time-Series Analysis
Programmes > Consciousness Studies Programme
Divisions: Schools > Humanities
Date Deposited: 27 Jan 2017 06:35
Last Modified: 04 Oct 2017 06:56
Official URL: http://link.springer.com/article/10.1140%2Fepjst%2...
Related URLs:
    Funders: UNSPECIFIED
    Projects: UNSPECIFIED
    DOI: 10.1140/epjst/e2016-60397-x
    URI: http://eprints.nias.res.in/id/eprint/1229

    Actions (login required)

    View Item View Item