prikaz prve stranice dokumenta Multichannel electroencephalogram frequency domain feature extraction method for brain activity state transition detection
  Download
PDF 18.06 MB
doctoral thesis
Multichannel electroencephalogram frequency domain feature extraction method for brain activity state transition detection
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. urn:nbn:hr:168:341252
Stančin, Igor
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Stančin, I. (2023). Multichannel electroencephalogram frequency domain feature extraction method for brain activity state transition detection (Doctoral thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:341252

Stančin, Igor. "Multichannel electroencephalogram frequency domain feature extraction method for brain activity state transition detection." Doctoral thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:341252

Stančin, Igor. "Multichannel electroencephalogram frequency domain feature extraction method for brain activity state transition detection." Doctoral thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:341252

Stančin, I. (2023). 'Multichannel electroencephalogram frequency domain feature extraction method for brain activity state transition detection', Doctoral thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 08 May 2024, https://urn.nsk.hr/urn:nbn:hr:168:341252

Stančin I. Multichannel electroencephalogram frequency domain feature extraction method for brain activity state transition detection [Doctoral thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2024 May 08] Available at: https://urn.nsk.hr/urn:nbn:hr:168:341252

I. Stančin, "Multichannel electroencephalogram frequency domain feature extraction method for brain activity state transition detection", Doctoral thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:341252

Metadata
TitleMultichannel electroencephalogram frequency domain feature extraction method for brain activity state transition detection
Title (croatian)Metoda izlučivanja značajki višekanalnoga elektroencefalograma u frekvencijskoj domeni za detekciju promjene stanja moždane aktivnost
AuthorIgor Stančin
MentorAlan Jović (mentor)
Committee memberDomagoj Jakobović (predsjednik povjerenstva)
Committee memberMario Cifrek (član povjerenstva)
Committee memberMarijan Palmović (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2023-06-20, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Universal decimal classification
(UDC)		621.3 - Electrical engineering
Abstract
Focusing on the improvements in detecting brain state transitions, this thesis specifically investigates the transition from a waking state to a drowsy state during driving. Driver drowsiness is a significant road safety concern that contributes to numerous accidents and fatalities worldwide. The conducted research focuses on the detection and prediction of driver drowsiness using multichannel electroencephalography (EEG) signals. The published review paper [Pub1] systematically examines EEG signal features, drowsiness detection systems, and discusses potential improvements. A key insight found during the review is that current methods focus on a single brain region, while frequency-domain features from different brain regions behave differently during transition to drowsiness state. Based on this insight, a novel brain state transition detection method that extracts multichannel frequency-domain features for improved drowsiness identification was developed [Pub2]. Further research also revealed that male and female subjects have different brain states and brain state transitions when experiencing drowsiness during driving [Pub4]. Incorporating information on the driver's sex improved drowsiness detection accuracy, and a reliable sex classifier was constructed using EEG data [Pub3].
Abstract (croatian)
Fokusirajući se na poboljšanja u detekciji prijelaza stanja moždane aktivnosti, ovaj doktorski rad posebno istražuje prijelaz iz budnog stanja u stanje pospanosti tijekom vožnje. Pospanost vozača značajan je problem sigurnosti na cestama koji pridonosi brojnim nesrećama i smrtnim slučajevima diljem svijeta. Provedeno istraživanje usmjereno je na detekciju i predviđanje pospanosti vozača pomoću signala višekanalne elektroencefalografije (EEG). Objavljeni pregledni rad [Pub1] sustavno ispituje značajke EEG signala, sustave za otkrivanje pospanosti i raspravlja o mogućim poboljšanjima. Ključni uvid do kojeg je došlo tijekom pregleda je da se trenutne metode fokusiraju na jednu regiju mozga, dok se značajke frekvencijske domene iz različitih regija mozga ponašaju različito tijekom prijelaza u stanje pospanosti. Na temelju ovog uvida razvijena je nova metoda detekcije prijelaza stanja moždane aktivnosti koja izdvaja višekanalne značajke frekvencijske domene za poboljšanu identifikaciju pospanosti [Pub2]. Daljnja istraživanja također su otkrila da ispitanici muškog i ženskog spola imaju različita stanja mozga i prijelaze među stanjima moždane aktivnosti kada postaju pospani tijekom vožnje [Pub4]. Uključivanje informacija o spolu vozača poboljšalo je točnost otkrivanja pospanosti, a razvijen je i pouzdani klasifikator spola temeljem EEG signalu [Pub3].
Keywords
Keywords (croatian)
Languageenglish
URN:NBNurn:nbn:hr:168:341252
Promotion2024
Study programmeTitle: Doctoral study programme "Electrical Engineering and Computing"
Study programme type: university
Study level: postgraduate
Academic / professional title: doktor/doktorica znanosti, po-dručje tehničkih znanosti (doktor/doktorica znanosti, po-dručje tehničkih znanosti)
Type of resourceText
Extentix, 133 str. : graf. prikazi ; 31 cm.
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2024-02-15 14:46:03