Normal view MARC view ISBD view

Razvoj nove biometrijske metode za identifikaciju zasnovane na biološkim signalima : diplomski rad / Jelena Cvitanović ; [mentor Ratko Magjarević].

By: Cvitanović, Jelena.
Contributor(s): Magjarević, Ratko [ths].
Publisher: Zagreb, J. Cvitanović, 2014Description: 48 str. ; 30 cm + CD-ROM.Other title: Development of a new biometric method based on biological signals [Naslov na engleskom: ].Subject(s): biometrija klasifikacija ljudska identifikacija elektrokardiogram (EKG) hod | biometry classification human identification electrocardiograph (ECG) gaitDissertation note: diplomski studij Fakultet elektrotehnike i računarstva u Zagrebu Abstract: Sažetak na hrvatskom: U radu je istražena mogućnost ljudske identifikacije pomoću signala EKG-a i signala hoda. Korišteni su biološki signali snimljeni pomoću senzora mreže OZIMS. Prikupljeni su biološki signali za 18 zdravih osoba. EKG je snimljen pomoću pametne majice GOW za vrijeme mirovanja osoba. Stil hoda analiziran je na signalima ubrzanja s akcelerometra tijekom hoda. Izdvojene su vremenske i frekvencijske značajke bioloških signala. Korištenjem klasifikatora temeljenog na umjetnoj neuronskoj mreži dobivena je točnost identifikacije od 96.4 % za segmente EKG-a te od 64.9 % za signale ubrzanja.Abstract: Sažetak na engleskom: Thesis investigates the possibility of human identification using ECG signal and gait recognition. Biological signals were recorded using OZIMS sensor network. Collected data of 18 healthy subjects was analyzed. ECG was recorded with GOW smart T-shirt. Gait recognition was applied to signals recorded with accelerometer during walking. Features from both time and frequency domain of biological signals were extracted. Using a classifier based on artificial neural network (ANN) classification accuracy of 96% was obtained for ECG segment identification and accuracy of 64.9 % was obtained for the acceleration signal segment identification.
List(s) this item appears in: Magjarevic, Ratko - mentorstva
Tags from this library: No tags from this library for this title. Log in to add tags.
Item type Current location Call number Status Date due Barcode Item holds
Diplomski rad Diplomski rad Središnja knjižnica
Spremište
DI-62 Arhivski primjerak 0000000964081
Total holds: 0

diplomski studij Fakultet elektrotehnike i računarstva u Zagrebu

Sažetak na hrvatskom: U radu je istražena mogućnost ljudske identifikacije pomoću signala EKG-a i signala hoda. Korišteni su biološki signali snimljeni pomoću senzora mreže OZIMS. Prikupljeni su biološki signali za 18 zdravih osoba. EKG je snimljen pomoću pametne majice GOW za vrijeme mirovanja osoba. Stil hoda analiziran je na signalima ubrzanja s akcelerometra tijekom hoda. Izdvojene su vremenske i frekvencijske značajke bioloških signala. Korištenjem klasifikatora temeljenog na umjetnoj neuronskoj mreži dobivena je točnost identifikacije od 96.4 % za segmente EKG-a te od 64.9 % za signale ubrzanja.

Sažetak na engleskom: Thesis investigates the possibility of human identification using ECG signal and gait recognition. Biological signals were recorded using OZIMS sensor network. Collected data of 18 healthy subjects was analyzed. ECG was recorded with GOW smart T-shirt. Gait recognition was applied to signals recorded with accelerometer during walking. Features from both time and frequency domain of biological signals were extracted. Using a classifier based on artificial neural network (ANN) classification accuracy of 96% was obtained for ECG segment identification and accuracy of 64.9 % was obtained for the acceleration signal segment identification.

There are no comments for this item.

Log in to your account to post a comment.

Središnja knjižnica Fakulteta elektrotehnike i računarstva, Unska 3, 10000 Zagreb
tel +385 1 6129 886 | fax +385 1 6129 888 | ferlib@fer.hr