Umjetna inteligencija u nosivim uređajima za praćenje zdravlja ispitanika

undergraduate thesis

• Title (english): Artificial inteligence in portable health monitoring
• Author: Lovro Akmačić
• Mentor: Ratko Magjarević (mentor)
• Committee member: Ratko Magjarević (predsjednik povjerenstva)
• Committee member: Davorin Ambruš (član povjerenstva)
• Committee member: Krunoslav Jurčić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-07-08, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Najčešći korišteni senzori u nosivim uređajima su akcelerometri (za praćenje koraka i prijeđene udaljenosti), fotopletizmografski senzori (za praćenje broja otkucaja srca), altimetri (za praćenje altitude) i žiroskopi (za praćenje koraka i prijeđene udaljenosti).
Biološki markeri koji se mogu mjeriti ovise o tipu i modelu nosivog uređaja. Najčešće se procjenjuje broj otkucaja srca, krvni tlak, varijacija temperature kože, estimacija varijacije kisika i disanje.
Podatci se snimaju i pohranjuju na nosivom uređaju, no moguće je na aplikaciji ili na webu vidjeti pregled snimljenih podataka, unijeti podatke koje uređaj ne mjeri (tjelesna težina i sl.) i poslati snimljene podatke putem e-pošte ili korištenjem drugih ponuđenih servisa.
Statističkom analizom podataka zaključeno ja da model Charge 4 mjeri altitudu uz manju grešku, da promjena broja otkucaja srca ima negativnu korelaciju s promjenom altitude i da je moguće vidjeti mijenjanje broja otkucaja srca tijekom sna s obzirom na različite faze sna.

Abstract (english)

The most commonly used sensors in wearable devices are accelerometers (for monitoring steps and distance traveled), photoplethysmographic sensors (for monitoring heart rate), altimeters (for monitoring altitude) and gyroscopes (for monitoring steps and distance traveled).
The biological markers that can be measured depend on the type and model of the wearable device. Heart rate, blood pressure, skin temperature variation, oxygen variation estimation and respiration are most often estimated.
The data is recorded and stored on the wearable device, but it is possible to see an overview of the recorded data on the application or on the web, enter data that the device does not measure (body weight, etc.) and send the recorded data via e-mail or using other offered services.
The statistical analysis of the data concluded that the Charge 4 model measures altitude with a smaller error, that the change in heart rate has a negative correlation with the change in altitude, and that it is possible to see the change in heart rate during sleep with regard to different stages of sleep.

• Keywords: umjetna inteligencija; biometrika; Fitbit; Charge 4; zdravlje; praćenje zdravlja; nosivi uređaji za praćenje zdravlja; biomarkeri; statistička analiza podataka
• Keywords (english): artificial intelligence; biometrics; Fitbit; Charge 4; health; health monitoring; portable health monitoring; biomarkers; statistical data analysis
• Language: croatian
• URN:NBN: urn:nbn:hr:168:947674
• 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: 2024-10-12 19:57:31