DOI

https://doi.org/10.25772/QA5Q-SX30

Author ORCID Identifier

https://orcid.org/0000-0002-4374-2763

Defense Date

2022

Document Type

Thesis

Degree Name

Master of Science

Department

Electrical & Computer Engineering

First Advisor

Dr. Sherif Abdelwahed

Abstract

In response to the growing urban population, "smart cities" are designed to improve people's quality of life by implementing cutting-edge technologies. The concept of a "smart city" refers to an effort to enhance a city's residents' economic and environmental well-being via implementing a centralized management system. With the use of sensors and actuators, smart cities can collect massive amounts of data, which can improve people's quality of life and design cities' services. Although smart cities contain vast amounts of data, only a percentage is used due to the noise and variety of the data sources. Information and communication technology (ICT) and the Internet of Things (IoT) play a far more prominent role in developing smart cities when it comes to making choices, designing policies, and executing different methods. Smart city applications have made great strides thanks to recent advances in artificial intelligence (AI), especially machine learning (ML) and deep learning (DL). The applications of ML and DL have significantly increased the accuracy aspect of decision-making in smart cities, especially in analyzing the captured data using IoT-based devices and sensors. Smart cities employ algorithms that use unlabeled and labeled data to manage resources and deliver individualized services effectively. It has instantaneous practical use in many crucial areas, including smart health, smart environment, smart transportation system, energy management, and smart water distribution system in a smart city. Hence, ML and DL have become hot research topics in AI techniques in recent years and are proving to be accurate optimization techniques in smart cities. In addition, artificial intelligence algorithms enable the processing massive datasets and identify patterns and characteristics that would otherwise go unnoticed. Despite these advantages, researchers' skepticism of AI's sometimes mysterious inner workings has prevented it from being widely used for smart cities. This thesis's primary intent is to explore the value of employing diverse AI and ML techniques in developing smart city-centric domains and investigate the efficacy of these proposed approaches in four different aspects of the smart city such as smart energy, smart transportation system, smart water distribution system and smart environment. In addition, we use these machine learning approaches to make a data analytics and visualization unit module for the smart city testbed. Internet-of-Things-based machine learning approaches in diverse aspects have repeatedly demonstrated greater accuracy, sensitivity, cost-effectiveness, and productivity, used in the built-in Virginia Commonwealth University's real-time testbed.

Rights

© The Author

Is Part Of

VCU University Archives

Is Part Of

VCU Theses and Dissertations

Date of Submission

12-10-2022

Share

COinS