Skip to main content
UOIT Home
Please use this identifier to cite or link to this item: http://hdl.handle.net/10155/1123

Issue Date: 1-Dec-2019
Title: Time-efficient offloading and execution of machine learning tasks between embedded systems and fog nodes
Authors: Saguil, Darren
Publisher : University of Ontario Institute of Technology
Degree : Master of Applied Science (MASc)
Department : Electrical and Computer Engineering
Supervisor : Azim, Akramul
Keywords: Machine learning
Embedded systems
Offloading
Fog networks
Abstract: As embedded systems become more prominent in society, it is important that the technologies that run on them must be used efficiently. One such technology is the Neural Network (NN). NN's, combined with the Internet of Things (IoT), can utilize the massive amounts of data produced to optimize, control, and automate embedded systems, giving them more functionality than ever before. However, the status quo of offloading all NN functionality onto external devices has many flaws. It forces the embedded system to completely rely on networks which may have high latency or connection issues. Networks may also expose them to security risks. To reduce the reliance of IoT devices on networks, we examined several solutions such as delegating some NN's to run solely on the IoT device or splitting the NN and distributing the subnetworks into different devices. It was found that, for shallow NN's, the IoT device itself could run the NN at a rate faster than offloading it to an external device, but the IoT device needed to offload its inputs once the NN's started to increase in layers and complexity. When splitting the NN, it was found that the number of messages sent between devices could be reduced by up to 97% while only reducing the accuracy of the NN by 3%.
Appears in Collections:Electronic Theses and Dissertations (Public)
Faculty of Engineering and Applied Science - Master Theses

Files in This Item:

File Description SizeFormat
Saguil_Darren.pdf2.3 MBAdobe PDFView/Open

Items in e-scholar@UOIT are protected by copyright, with all rights reserved, unless otherwise indicated.