A Lightweight Human Action Classification Method for Green IoT Sport Applications

<table class="table-group" id="tab5"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left" rowspan="2">Dataset name</td><td class="align_center" colspan="2">Total accuracy (%)</td></tr><tr class="thead"><td class="align_center">No distillation</td><td class="align_center">With distillation</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left"><i>Data1</i></td><td class="align_center">52.8</td><td class="align_center">90.5</td></tr><tr><td class="align_left"><i>Data2</i></td><td class="align_center">52.2</td><td class="align_center">84.5</td></tr><tr><td class="align_left"><i>Data3</i></td><td class="align_center">64.7</td><td class="align_center">80.5</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The total accuracy of the sHCRF model of both the old and the new data with and without distillation.</div>

Journal of Sensors

tab5

Table 5

Table 5: A Lightweight Human Action Classification Method for Green IoT Sport Applications 