LPIS Home Page
Google Search

Title: On the Discovery of Weak Periodicities in Large Time Series
Author(s): C. Berberidis, I. Vlahavas, W. Aref, M. Atallah, A. Elmagarmid.
Availability: Click here to download the PDF (Acrobat Reader) file (10 pages).
Appeared in: Proc. 6th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD '02), Springer-Verlag, LNAI 2431, pp. 51-61, 2002.
Abstract: The search for weak periodic signals in time series data is an active topic of research. Given the fact that rarely a real world dataset is perfectly periodic, this paper approaches this problem in terms of data mining, trying to discover weak periodic signals in time series databases, when no period length is known in advance. In existing time series mining algorithms, the period length is user-specified. We propose an algorithm for finding approximate periodicities in large time series data, utilizing autocorrelation function and FFT. This algorithm is an extension to the partial periodicity detection algorithm pre-sented in a previous paper of ours. We provide some mathematical background as well as experimental results.
See also :

        This paper has been cited by the following:

1 Yuan-Chang Wu, Cheng-Hsi Liu, Chen-Chau Yang, Similarity Mining from Time-series Data Proc. of the 14th workshop on Object Oriented Technolo-gies and Applications, Tainan, 2003 (in Chinese).
2 Tanaka, Y. and Uehara, K. Discover Motifs in Multi Dimensional Time-Series Using the Principal Component Analysis and the MDL Principle. In proceedings of the 3rd Int'l Conference on Machine Learning and Data Mining in Pattern Recognition. Leipzig, Germany, Jul 5-7. pp. 252--265, 2003
3 Rombo, S. and Terracina, G. Discovering Representative Models in Large Time Series Databases. In proceedings of the 6th International Conference On Flexible Query Answering Systems, pp. 84-97, 2004
4 Huiping Cao, David W. Cheung, Nikos Mamoulis, Discovering Partial Periodic Patterns in Discrete Data Sequences, Lecture Notes in Computer Science, Volume 3056, Jan 2004, Pages 653 - 658, 2004
5 Tanaka, Y. and Uehara, K. Motif Discovery Algorithm from Motion Data. In proceedings of the 18th Annual Conference of the Japanese Society for Artificial Intelligence (JSAI). Kanazawa, Japan, June 2-4, 2004
6 J.T. Lizier and T.J. Dawson, "On the Periodicity of Time-series Network and Ser-vice Metrics", in Proc. IEEE International Region 10 Conference (Tencon '05), Melbourne, November 2005.
7 Yoshiki Tanaka, Kazuhisa Iwamoto, Kuniaki Uehara, Discovery of Time-Series Motif from Multi-Dimensional Data Based on MDL Principle, Machine Learning, Volume 58, Issue 2 - 3, Feb 2005, Pages 269 300
8 Huang, K.Y. SMCA: A General Model for Mining Asynchronous Periodic Patterns in Temporal Databases. IEEE Transactions on Knowledge and Data Engineering, Vol. 17(6), pp. 774-785, 2005.
9 K.Y. Huang and C.H. Chang, SMCA: A General Model for mining Asynchronous Periodic Pattern in temporal database. IEEE Transaction on Knowledge and Date Engineering, Volume 17, No. 6, pp. 774--785, June 2005.
10 Srivatsan Laxman and P S Sastry, A survey of temporal data mining, SADHANA - Academy Proceedings in Engineering Sciences, Vol. 31(2), Indian Academy of Sciences, April 2006.
11 Fabian Moerchen, Time Series Knowledge Mining, PhD Thesis, Fachbereich Mathematik und Informatik der Philipps-Universitaet Marburg, 2006
12 Edi Winarko, The Discovery and Retrieval of Temporal Rules in Interval Se-quence Data, PhD Thesis, School of Informatics and Engineering, Faculty of Science and Engineering, Flinders University, Adelaide, South Australia, 2007.
13 Fabian Moerchen, Unsupervised pattern mining from symbolic temporal data, SIGKDD Explorations, vol. 9(1), pp. 41-45, 2007.