First Advisor

Suresh Singh

Term of Graduation

Spring 2025

Date of Publication

5-30-2025

Document Type

Thesis

Degree Name

Master of Science (M.S.) in Electrical and Computer Engineering

Department

Electrical and Computer Engineering

Language

English

Subjects

Angle of arrival, Deep learning

Physical Description

1 online resource (vi, 65 pages)

Abstract

Deep learning (DL)-based angle-of-arrival (AoA) estimation offers significant advantages over traditional signal processing methods, especially in complex and high-noise environments. However, situational complexity and differences in hardware can significantly impact the estimator's performance. It is therefore of interest to investigate the relationship between the performance of deep learning models and the variation of physical parameters such as the number of signal sources, the number of receiving antennas, and the signal-to-noise ratio (SNR). In this study, we investigate the impact of these variations on deep learning-based AoA estimation by systematically analyzing how the variations in the characteristics of the received signal affect the accuracy, robustness, and computational efficiency of the model. This thesis explores the sensitivity of deep neural networks (DNNs) to different physical conditions and evaluate their adaptability to dynamic channel environments. This thesis also compare the performance variations of traditional estimation methods under the same conditions. These results provide insights into neural network architectures for optimizing AoA estimation under different physical conditions and contribute to developing more robust and versatile deep learning models for wireless positioning and communication systems.

Rights

In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).

Persistent Identifier

https://archives.pdx.edu/ds/psu/43866

Download

Share

COinS