Detekcija vitalnih znakova pomoću radara sa sintetičkom aperturom

undergraduate thesis

• Title (english): Detection of vital signs using synthetic aperture radar
• Author: Grigor Škarić
• Mentor: Marko Bosiljevac (mentor)
• Committee member: Marko Bosiljevac (predsjednik povjerenstva)
• Committee member: Sonja Grgić (član povjerenstva)
• Committee member: Filip Turčinović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-05, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

FMCW radar korišten je za generiranje slika različitih objekata. Te slike korištene su za treniranje tri modela konvolucijskih neuronskih mreža različitih složenosti. Visoka preciznost na testnom skupu postignuta je svim modelima. Kompliciraniji modeli pokazuju bolje rezultate. Podaci dobiveni radarom korišteni su direktno kako bi se detektirali vitalni znakovi. Detekcija je provedena na dva načina, korištenjem Fourierove transformacije i direktnom usporedbom signala. Korištenjem obje metode moguće je uspješno detektirati vitalne znakove. Najbolji rezultati detekcije dobivaju se kada se metode koriste u kombinaciji.

Abstract (english)

FMCW radar was used to generate images of various objects. These images were used to train three models of convolutional neural networks of varying complexity. High precision on the test set was achieved by all models. More complicated models have shown better results. Radar data was used directly to detect vital signs. Detection was performed in two ways, using Fourier transform and with direct signal comparison. Using both methods, it is possible to successfully detect vital signs. The best detection results are obtained when the methods are used in combination.

• Keywords: Klasifikacija; Detekcija vitalnih znakova; Neuronske mreže; Radar
• Keywords (english): Classification; Detection of vital signs; Neural networks; Radar
• Language: croatian
• URN:NBN: urn:nbn:hr:168:632723
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-15 11:18:55