Non-arbitrary judgment algorithm for periodicity of time series

Daisuke Tominaga, Brice Horton Ii Paul

Research output: Contribution to conferencePaper

Abstract

For biological time series data, such as expression of genes, population of individuals, etc., it is often desirable to detect if the measured phenomenon has a significant periodicity for a particular time length (day, year, etc). However, in most cases the criteria used are defined by arbitrary parameters based on characteristics of data and analysts' experiences. An effective and objective procedure is strongly needed. We developed an algorithm for objective detection of periodicity. We applied the algorithm to randomly generated time series data and gene expression profiles of mice to find circadian genes, and compared it with a widely used conventional detection method. Our algorithm shows both high sensitivity and specificity.

Original languageEnglish
Pages17-22
Number of pages6
Publication statusPublished - 2006 Dec 1
Event10th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2006, Jointly with the 12th International Conference on Information Systems Analysis and Synthesis, ISAS 2006 - Orlando, FL, United States
Duration: 2006 Jul 162006 Jul 19

Other

Other10th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2006, Jointly with the 12th International Conference on Information Systems Analysis and Synthesis, ISAS 2006
CountryUnited States
CityOrlando, FL
Period06-07-1606-07-19

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Information Systems

Cite this

Tominaga, D., & Paul, B. H. I. (2006). Non-arbitrary judgment algorithm for periodicity of time series. 17-22. Paper presented at 10th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2006, Jointly with the 12th International Conference on Information Systems Analysis and Synthesis, ISAS 2006, Orlando, FL, United States.