Beam prediction using convolutional neural network and artificial neural network

Name: Charith Dissanayake

keyword: Sixth-Generation Mobile Network

MeSH: Computer engineering

Classification :.DDC: e-Theses

; Beam Training

MeSH: Neural networks (Computer science)

LCSH: Computer engineering

LCSH: Neural networks (Computer science)

Abstract: In the Sixth-Generation mobile network, beam training methods will be used due to energy loss that requires more computation. Therefore, this study introduces a beam prediction approach using machine learning techniques with data preprocessing methods. The model contains a convolutional neural network and a multilayer perceptron network that accepts images and global positioning system (GPS) data as inputs. This study used 15281 images and 15281 GPS data samples from an online dataset to evaluate the model. The proposed approach was tested with 64 and 32 beam indexes output classes and resulted in 88.98% and 85.72% accuracies respectively. Furthermore, the model showed precision and recall values of 89.09% and 89.15% for 64 classes and 85.87% and 85.66% for 32 classes respectively.

Mae Fah Luang University. Learning Resources and Educational Media Center

Address: CHIANG RAI

Email: library@mfu.ac.th

Name: Punnarumol Temdee

Role: Advisor

Created: 2023

Modified: 2024-07-26

Issued: 2024-07-26

วิทยานิพนธ์/Thesis

application/pdf

CallNumber: e-Theses

eng

DegreeName: Master of Engineering

Level: Master's Degree

Descipline: Computer Engineering

Grantor: Mae Fah Luang University

©copyrights Mae Fah Luang University

ลำดับที่.	ชื่อแฟ้มข้อมูล	ขนาดแฟ้มข้อมูล	จำนวนเข้าถึง	วัน-เวลาเข้าถึงล่าสุด
1	138083.pdf	3.32 MB	2	2025-10-01 15:43:10

ใช้เวลา

0.034387 วินาที