Teorijski izračun i analiza korelacija WiFi signala i broja ljudi pomoću strojnog učenja

master's thesis

• Title (english): Theoretical calculation and analysis of WiFi signals with machine learning
• Author: Vinko Kliček
• Mentor: Hrvoje Buljan (mentor)
• Committee member: Hrvoje Buljan (predsjednik povjerenstva)
• Committee member: Andrej Novak (član povjerenstva)
• Committee member: Željko Skoko (član povjerenstva)
• Committee member: Vedran Đerek (član povjerenstva)
• Committee member: Ivica Smolić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Science; (Department of Physics); Zagreb
• Defense date and country: 2022-09-28, Croatia
• Scientific / art field, discipline and subdiscipline: NATURAL SCIENCES; Physics

Abstract

Cilj istraživanja je korištenjem analize WiFi signala otkriti prisustvo ljudi u WiFi polju. Podatci koje analiziramo su intenziteti elektromagnetskog (WiFi) polja u danim točkama prostora, za danu konfiguraciju objekata koji se nalaze u prostoriji. Koristimo tri različite metode strojnog učenja na istim setovima podataka. Gledamo rješenja koja nam daje strojno učenje za pojedinu metodu te ih uspoređujemo s ostalim metodama. Zanima nas koja metoda daje bolje rezultate te što možemo u budućnosti poboljšati da dobijemo bolja rješenja. Jedan set podataka je dobiven teorijski koristeći program COMSOL, dok je drugi set podataka dobiven eksperimentalno.

Abstract (english)

The goal of the research is to detect the presence of people in the WiFi field using WiFi signal analysis. The data that we analyze are the intensities of the electromagnetic (WiFi) field in given points of space, for a given configuration of objects located in the room. We are using three machine learning methods on same datasets. Machine learning give us results for individual method and then we compare those results with other machine learning results. We do that because we want to see what method works the beast and how we can upgrade to get better results. One dataset was obtained theoretically using the COMSOL program, while the other dataset was obtained experimentally.

• Keywords: DTC; Decision Tree Classification; GNB; Gaussian Naive Bayes; EM; elektromagnetski
• Keywords (english): DTC; Decision Tree Classification; GNB; Gaussian Naive Bayes; EM; electromagnetic
• Language: croatian
• URN:NBN: urn:nbn:hr:217:463744
• Study programme: Title: Physics and Computer Science; specializations in: Education; Course: Education; Study programme type: university; Study level: integrated undergraduate and graduate; Academic / professional title: magistar/magistra fizike i informatike (magistar/magistra fizike i informatike)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access; Embargo expiration date: 2024-03-28
• Created on: 2022-10-19 07:17:29