Abstract | ||
---|---|---|
In last years, the Internet of Things (IoT) has gained attention in relevant fields of application as Industry 4.0. IoT is usually structured around three layers according to computing capacity and energy cost: cloud, fog, and edge. This paper focuses on the edge layer which is close to the end-user. Specifically, the authors fully address a binary image classification problem in the edge without going toward upper layers, i.e., the intelligence and the computation is brought to the edge layer, instead of being simple sensing devices. To this end, the authors propose a cascade Support Vector Machine (SVM) embedded implementation specially designed to be executed within a low-cost FPGA, which could be embedded in an IoT edge device. The experimental results performed show the feasibility and correct functionality of the proposal when comparing to a regular computer. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/IECON.2018.8591634 | IECON 2018 - 44TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY |
Keywords | Field | DocType |
Internet of Things, Edge computing, Support Vector Machine, FPGA, FPSoC | Kernel (linear algebra),Support vector machine,Binary image,Field-programmable gate array,Control engineering,Edge device,Engineering,Face detection,Computer engineering,Cloud computing,Computation | Conference |
ISSN | Citations | PageRank |
1553-572X | 0 | 0.34 |
References | Authors | |
0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Aleksa Damljanovic | 1 | 1 | 1.12 |
José Manuel Lanza-Gutiérrez | 2 | 71 | 9.31 |