Ελληνικό Μεσογειακό Πανεπιστήμιο
Χρήση μεθόδων τεχνητής νοημοσύνης για την επίλυση προβλημάτων με εφαρμογές στον ηλεκτρομαγνητισμό, την βιοϊατρική και τις τηλεπικοινωνίες
Abstract
dc:descriptionThis PhD thesis focuses on solving problems related to Electromagnetics and Biomedical Engineering through the use of artificial neural networks. At the same time, it examines the monitoring of the electromagnetic environment in a popular tourist region of Greece, with the aim of informing the public. Initially, is proposed a methodology based on a neural network architecture that utilizes measurements, in order to accurately determine the position and electric dipole moment of equivalent electric dipoles for unit characterization. These dipoles, are used to match the electric field generated by various sources within a spacecraft during space exploration missions. The identification and characterization of these sources aim to ensure electromagnetic cleanliness. In the second part of the dissertation, which pertains to the biomedical domain, a neural network model is developed to estimate heart rate during physical exercise. The prediction is based on artificially generated data from 40 different constant and 40 exponentially increasing speeds. In both cases, the model achieves high accuracy, with a Mean Absolute Error of 0.0201 beats per minute. Finally, the evolution of electromagnetic radiation levels is studied, using continuous monitoring data from a sensor belonging to the National Observatory of Electromagnetic Fields in Greece and is installed in Platanias, Chania, a region with significant tourist activity. The recorded data are presented for both the past decade and a 12-month period. The maximum recorded electric field intensity was 1.274 V/m, remaining within the legally defined safety limits.
Degree
thesis:*- Grantor dc:publisher
- Ελληνικό Μεσογειακό Πανεπιστήμιο
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Lampou, Anna
- Λάμπου, Άννα
Subjects
dc:subject × 16- Nευρωνικά δίκτυα
- Μοντελοποίηση ηλεκτρικού διπόλου
- Ηλεκτρομαγνητισμός
- Μετρήσεις ηλεκτρικού πεδίου
- Εκτίμηση του καρδιακού ρυθμού
- Νeural networks
- Electric dipole modeling
- Εlectromagnetics
- Εlectric field measurements
- Ηeart rate estimation
- Επιστήμη Ηλεκτρολόγου Μηχανικού, Ηλεκτρονικού Μηχανικού, Μηχανικού Η/Υ
- Επιστήμες Μηχανικού και Τεχνολογία
- Μηχανική και συστήματα επικοινωνιών, Τηλεπικοινωνίες
- Electrical Engineering, Electronic Engineering, Information Engineering
- Engineering and Technology
- Communication engineering and systems, Telecommunications
Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/59293