Raspoznavanje kognitivnog opterećenja na temelju fizioloških značajki i strojnog učenja

master's thesis

• Title (english): Cognitive load recognition based on physiological features and machine learning
• Author: Ante Pušić
• Mentor: Siniša Popović (mentor)
• Committee member: Siniša Popović (predsjednik povjerenstva)
• Committee member: Alan Jović (član povjerenstva)
• Committee member: Nikolina Frid (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-07-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Kognitivno opterećenje odnosi se na opterećenje koje čovjekov kognitivni sustav snosi vršeći zadatak. Ovaj rad opisuje metodologiju za prepoznavanje kognitivnog opterećenja temeljenu na strojnom učenju, koja koristi fiziološke signale prikupljene neinvazivnim metodama prikladnim za uporabu u praksi. Postupak prikupljanja i odabira podataka te sama metodologija detaljno su opisani, a efikasnost metodologije je iscrpno vrednovana i uspoređena sa srodnim radovima u znanstvenom polju. Rezultati potvrđuju njihova otkrića u prepoznavanju kognitivnog opterećenja i razlikovanju njegovih različitih razina te donose nove spoznaje o predikciji subjektivnih procjena kognitivnog opterećenja.

Abstract (english)

Cognitive load refers to the load put on a person’s cognitive system when performing a task. This thesis describes a machine-learning based methodology for cognitive load recognition that utilizes physiological signals gathered with non-invasive methods suitable for real-life use. The data acquisition and selection procedure and the methodology itself are described in detail, and the efficacy of the methodology is exhaustively evaluated and compared against related work in the field of study. The results corroborate their findings in recognizing cognitive load and distinguishing between different levels thereof, and provide new insights on predicting subjective cognitive load assessments.

• Keywords: prepoznavanje kognitivnog opterećenja; strojno učenje; psihofiziološki signali; multimodalni podatci
• Keywords (english): cognitive load detection; machine learning; psychophysiological signals; multimodal data
• Language: english
• URN:NBN: urn:nbn:hr:168:670675
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-10-11 10:15:45