Abstract
This paper presents a method for analyzing changes in information contents of time series based on a combined adaptive approximate similarity detection and temporal modeling using Bregman information. This work extends previous results on using information geometry for musical signals by suggesting a method for optimal model selection using Information Rate (IR) as a measure of an overall model predictability.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Cont, A., Dubnov, S., Assayag, G.: On the Information Geometry of Audio Streams with Applications to Similarity Computing. IEEE Transactions on Audio, Speech and Language Processing 19(4), 837–846 (2011)
Allauzen, C., Crochemore, M., Raffinot, M.: Factor oracle: A new structure for pattern matching. In: Conference on Current Trends in Theory and Practice of Informatics, pp. 295–310 (1999)
Abdallah, S.A., Plumbley, M.D.: Information dynamics: patterns of expectation and surprise in the perception of music. Connection Science 21(2), 89–117 (2009)
Banerjee, A., Merugu, S., Dhillon, I.S., Ghosh, J.: Clustering with bregman divergences. Journal of Machine Learning Research 6, 1705–1749 (2005)
Nielsen, F., Boissonnat, J.-D., Nock, R.: On bregman voronoi diagrams. In: Proc. 18th ACM-SIAM Sympos. Discrete Algorithms (2007)
Lefebvre, A., Lecroq, T.: Compror: Compression with a Factor Oracle. In: Proceedings of the Data Compression Conference (2001)
Dubnov, S., Assayag, G., Cont, A.: Audio Oracle: A New Algorithm for Fast Learning of Audio Structures. In: Proceedings of International Computer Music Conference, ICMC (September 2007)
Dubnov, S., Assayag, G., Cont, A.: Audio Oracle analysis of Musical Information Rate. In: Proceedings of IEEE Semantic Computing Conference, ICSC 2011, Stanford (September 2011)
Van Bellegem, S.: Locally stationary volatility modeling, CORE Discussion Papers, Universit catholique de Louvain, Center for Operations Research and Econometrics, CORE (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dubnov, S. (2013). Characterizing Time Series Variability and Predictability from Information Geometry Dynamics. In: Nielsen, F., Barbaresco, F. (eds) Geometric Science of Information. GSI 2013. Lecture Notes in Computer Science, vol 8085. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40020-9_73
Download citation
DOI: https://doi.org/10.1007/978-3-642-40020-9_73
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40019-3
Online ISBN: 978-3-642-40020-9
eBook Packages: Computer ScienceComputer Science (R0)