Graduate Thesis Or Dissertation
 

Environment-adaptive RF Sensing with Transferable ANN Features

Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/7d279215t

Descriptions

Attribute NameValues
Creator
Abstract
  • Radio frequency (RF) sensing arises as a promising option for enabling the internet of things (IoT) applications that transform our life into a world of smart homes, smart cities, and smart industries. The innovation of IoT reveals the benefits of RF sensing across cost, pervasiveness, unobtrusiveness, and privacy. However, challenges like interference and multipath are underway in realizing those promises. Furthermore, crucial studies demonstrate the trade-offs in accuracy, accessibility, power consumption, and many other factors for undertaking RF sensing. This dissertation presents a set of studies, including RF channel model characterization, the design of a novel RF sensing system for indoor localization, and the environmental impact of RF exposure in such systems. The first part covers a use case of measurement-based RF channel modeling in a challenging environment. The second part introduces an environment-adaptive RF sensing system for indoor localization that consists of 1) a dynamic phase calibration de-noising method, and 2) The implementation of a localization system that utilizes an artificial neural network (ANN) with transferable features. Lastly, a collaboration work that explores the potential impact of RF radiation and how RF exposure could affect human health.
License
Resource Type
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Rights Statement
Publisher
Peer Reviewed
Language

Relationships

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details WangGuangxin2023.pdf 2023-01-17 Public Download