Loading...
Publication
Validation of a similarity measurement method for clustering cardiac signals
| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 286.25 KB | Adobe PDF |
Advisor(s)
Abstract(s)
Development of personalized cardiovascular management systems involves automatic identification of the current data as normal or pathological; considering cardiac data as time-series, the illness identification may be performed by seeking similarity between the current patient's time-series data and a reference signal and then proceeding to illness stratification (clustering). Seven of the most common methods of time-series similarity measurement were assessed by imposing 6 types of distortions to the reference signal, considering for each distortion 20 possible variations. This study employed 10 seconds length records of arterial blood pressure signals of healthy subjects, collected from a public database. Then clustering using Partitioning Around Medoids was performed among pathological and non-pathological data considering 3 different clusters. Clustering results confirm usage of the reduced basis Discrete Wavelet Transform resulting from the combination of Haar wavelet decomposition with the Karhunen-Loeve transforms, presenting an accuracy ranging from 76% to 85% when partitioning around Medoids clustering is used.