Date of Award

12-2019

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Engineering and Sciences

First Advisor

Josko Zec

Second Advisor

Ivica Kostanic

Third Advisor

Kunal Mitra

Fourth Advisor

Philip J. Bernhard

Abstract

Minimizing Drive Test is a statistical protocol used to evaluate the network performance. It provides several benefits with respect to traditional drive test analysis; however, multiple inconveniences exist that prevent cell companies from precisely retrieving most of the locations of these reports. . MATLAB and Jupyter Notebook were used to prepare the data and create the models. Multiple supervised regression algorithms were tested and evaluated. The best predictions were obtained from the K-Nearest Neighbor algorithm with one ‘k’ and distance-weighted predictions. The UE geolocation was predicted with a median accuracy of 5.42 meters, a mean error of 61.62 meters, and a mode distance error of zero meters. Based on these results, there is evidence of the promising potential of machine learning algorithms applied to MDT geolocation problems.

Download

Share

COinS