| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:AI for optimizing analog RF parameters on NFC frontends : magistrsko delo
Authors:ID Žnidarič, Matej (Author)
ID Rojc, Matej (Mentor) More about this mentor... New window
ID Kurvathodil, Manoj (Co-mentor)
Files:.pdf MAG_Znidaric_Matej_2022.pdf (5,31 MB, This file will be accessible after 03.06.2025)
MD5: C2D56489F9ECE5EBBAF85395035BF9EA
PID: 20.500.12556/dkum/9c7608f0-ae17-43da-bd2a-022577a33bd3
 
Language:English
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:In this Master’s thesis, we study in detail NFC technology, NFC standardization, Artificial intelligence and GUI topics.Our goal is to optimize the measurement process of the FeliCa listener phase window in order to define the best analog parameters for the NFC IC. Namely, by combining machine learning and test automation, we want to achieve a faster validation time of the NFC IC under test. Firstly, we introduce the main topics related to NFC and present the thesis alongside specific goals. Next, we present the NFC technology on a fewuse cases. We also cover international standards, emphasizing sections that directly affect our validation and, therefore, the understanding of our solution. The NFC coverage is described alongside data representation used to interpret data used in proprietary software. Artificial intelligence is integrated into this software for multidimensional data interpolation task. We also cover the basics of deep neural networks and the most common architectures used in the DL field. The neural network training process is also covered to understand how we can optimize neural network global minimum convergence. In the last part of the thesis, we also explain how proprietary software tool actually works and how it can outperform previous processes. In the end, specific solutions related to the tool are described in more detail to understand our software development decisions better. Finally, we present measurement results and evaluate our goals.
Keywords:NFC wireless communication, artificial intelligence, test coverage, FeliCa, graphical user interface, analog parameter extraction
Place of publishing:Maribor
Place of performance:Maribor
Publisher:[M. Žnidarič]
Year of publishing:2022
Number of pages:1 spletni vir (1 datoteka PDF (XVII, 58 f.))
PID:20.500.12556/DKUM-81667 New window
UDC:004.9(043.2)
COBISS.SI-ID:113461251 New window
Publication date in DKUM:08.06.2022
Views:936
Downloads:0
Metadata:XML RDF-CHPDL DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share


Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:17.05.2022

Secondary language

Language:Slovenian
Title:Optimizacija RF parametrov na NFC napravi z umetno inteligenco
Abstract:V tem magistrskem delu podrobno preučujemo tehnologijo NFC, standardizacijo NFC, umetno inteligenco in teme grafičnega vmesnika. Naš cilj je optimizirati postopek merjenja faznega okna poslušalca FeliCa, da bi opredelili najboljše analogne parametre za integrirani sistem NFC. Z združitvijo strojnega učenja in avtomatizacije testiranja želimo namreč doseči hitrejši čas validacije testiranega integriranega vezja NFC. Najprej predstavimo glavne teme, povezane z NFC, in predstavimo diplomsko nalogo ob specifičnih ciljih. Nato predstavimo tehnologijo NFC na nekaj primerih uporabe. Obravnavamo tudi mednarodne standarde, pri čemer poudarjamo dele, ki neposredno vplivajo na našo validacijo in s tem na razumevanje naše rešitve. Pokritost NFC je opisana skupaj s predstavitvijo podatkov, ki se uporablja za interpretacijo podatkov, uporabljenih v lastniški programski opremi. V to programsko opremo je vključena umetna inteligenca za nalogo interpolacije večdimenzionalnih podatkov. Opisujemo tudi osnove globokih nevronskih mrež in najpogostejše arhitekture, ki se uporabljajo na področju DL. Zajeti so tudi postopki usposabljanja nevronskih mrež, da bi razumeli, kako lahko optimiziramo globalno minimalno konvergenco nevronske mreže. V zadnjem delu diplomskega dela pojasnimo tudi, kako lastniško programsko orodje dejansko deluje in kako lahko preseže prejšnje postopke. Na koncu so podrobneje opisane posebne rešitve, povezane z orodjem, da bi bolje razumeli naše odločitve pri razvoju programske opreme. Na koncu predstavimo rezultate meritev in ovrednotimo naše cilje.
Keywords:Brezžična komunikacija NFC, umetna inteligenca, pokritost testov, FeliCa, grafični uporabniški vmesnik, ekstrakcija analognih parametrov


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica