Atrial Fibrillation Detection with Low Signal-to-Noise Ratio Data Using Artificial Features and Abstract Features

<table class="table-group" id="tab8"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left" rowspan="2"> </td><td class="align_center" colspan="2">Feature scheme</td></tr><tr class="thead"><td class="align_center">All features</td><td class="align_center">All features except the PRE</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left">Acc</td><td class="align_center">0.857</td><td class="align_center">0.836</td></tr><tr><td class="align_left"><i>F</i><sub>1</sub></td><td class="align_center">0.837</td><td class="align_center">0.822</td></tr><tr><td class="align_left"><i>F</i><sub>1<i>p</i></sub></td><td class="align_center">0.735</td><td class="align_center">0.679</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Comparison results for the two feature schemes.</div>

Journal of Healthcare Engineering

tab8

Table 8

Table 8: Atrial Fibrillation Detection with Low Signal-to-Noise Ratio Data Using Artificial Features and Abstract Features 