A wavelet-based approach for time series pattern detection and events prediction applied to telemonitoring data

T Rocha; S Paredes; P Carvalho; J Henriques

doi:10.1109/IEMBS.2011.6091492

A wavelet-based approach for time series pattern detection and events prediction applied to telemonitoring data

Annu Int Conf IEEE Eng Med Biol Soc. 2011:2011:6037-40. doi: 10.1109/IEMBS.2011.6091492.

Authors

T Rocha¹, S Paredes, P Carvalho, J Henriques

Affiliation

¹ Departamento de Engenharia Informática e de Sistemas, Instituto Superior de Engenharia de Coimbra, Portugal. teresa@isec.pt

PMID: 22255716
DOI: 10.1109/IEMBS.2011.6091492

Abstract

This work aims the development of a predictive strategy able to estimate future events with relevant impact in the cardiovascular status. Based on wavelet transform, a new time series similarity metric is introduced, which is capable to detect a pre-defined pattern in time series data. In addition, a methodology combining a wavelet scheme with state space multi-models is proposed to achieve the prediction of future signal values. Blood pressure signals, collected by a telemonitoring platform (TEN-HMS), are used to detect the occurrence of future hypertension events.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Blood Pressure Determination / methods*
Diagnosis, Computer-Assisted / methods*
Humans
Hypertension / diagnosis*
Pattern Recognition, Automated / methods*
Reproducibility of Results
Sensitivity and Specificity
Telemedicine / methods*
Wavelet Analysis*