Fed-SCNN: A Federated Shallow-CNN Recognition Framework for Distracted Driving

<table class="table-group" id="tab2"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left" rowspan="4">Cloud-server (one device)</td><td class="align_center">Software platform</td><td class="align_center">TensorFlow federated</td></tr><tr><td class="align_center">CPU</td><td class="align_center">i7-8250U 3.2 GHz</td></tr><tr><td class="align_center">RAM</td><td class="align_center">16 GB DDR4 1600 MHz</td></tr><tr><td class="align_center">GPU</td><td class="align_center">NVIDIA 1080</td></tr><tr><td class="align_left" colspan="3"><hr/></td></tr><tr><td class="align_left" rowspan="4">User-side (three device)</td><td class="align_center">Software platform</td><td class="align_center">TensorFlow v 0.12</td></tr><tr><td class="align_center">CPU</td><td class="align_center">i5-7500 1.8 GHz</td></tr><tr><td class="align_center">RAM</td><td class="align_center">8 GB DDR4 1600 MHz</td></tr><tr><td class="align_center">GPU</td><td class="align_center">NVIDIA 1080</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Experimental environment of software and hardware.</div>

Security and Communication Networks

tab2

Table 2

Table 2: Fed-SCNN: A Federated Shallow-CNN Recognition Framework for Distracted Driving 