Please use this identifier to cite or link to this item:
https://elibrary.tucl.edu.np/handle/123456789/18005
Title: | INTERNET OF VEHICLE (IOV) BASED DRIVER EMOTION DETECTION USING FEDERATED LEARNING |
Authors: | Regmi, Pankaj Nidhi |
Keywords: | System architecture;Federated learning |
Issue Date: | Apr-2023 |
Publisher: | IOE Pulchowk Campus |
Institute Name: | Institute of Engineering |
Level: | Masters |
Series/Report no.: | 076MSICE011; |
Abstract: | With the advancement of edge smart computing devices and Internet of Vehicle (IoV) technologies emotion detection has become one of the most used methods in smart vehicle while driving. Many models have been employed however, privacy disclosure and communication cost are still a question. To address this question a federated learning driver emotion detection system model is proposed. It intelligently utilizes collaboration between edge, client and cloud for realizing dynamic model also protecting edge data privacy. Federated Learning has an advantage on privacy. In this thesis two different algorithm FedAvg and FedSGD are compared. It is found that accuracy of FedAvg is better than FedSGD. Also, FedSGD takes more steps to converge than FedAvg. |
Description: | Internet of Things (IoT) has revolutionized the world and the way we live. With the advancement of edge smart computing devices and IoT technologies we are able to control our smart device from any part of the world. Internet of Vehicle (IoV) is a subset of IoT which rather focus on vehicle to on vehicle-to-vehicle (V2V) or vehicle-toinfrastructure (V2I) communication transferring the way we interact with cars, and enabling the new features that were previously impossible |
URI: | https://elibrary.tucl.edu.np/handle/123456789/18005 |
Appears in Collections: | Electronics and Computer Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
pankaj nidhi regmi076msice011_ electronics &compu.pdf | 1.42 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.