| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 1.22 MB | Adobe PDF |
Advisor(s)
Abstract(s)
This work proposes to analyze the capacity of several ECG features ofLead I to discriminate 28 pairs of study groups, combining 7 patholog-ical groups and 1 control group, presented in the PTB Diagnostic ECGDatabase. For each pair, it was achieved an accuracy between 66.7% and96.9% using feature selection algorithm and SVM classifiers.