Razpoznavanje specifičnih premikov mobilne naprave iz signalov zajetih s pomočjo vgrajenih inercijskih senzorjev

diplomsko delo

Jože Kraner (Author), Boris Cigale (Mentor), Sebastijan Šprager (Co-mentor)

Abstract

Diplomsko delo zajema aktualno tematiko naprednejšega načina interakcije človek-mobilni telefon. V diplomskem delu je predstavljen postopek, ki s pomočjo signalov, zajetih iz pospeškometra, vgrajenega v mobilno napravo, razpozna specifične premike mobilne naprave. Opisani so postopki zajemanja, segmentacije, prevzorčenja in časovnega poravnavanja signalov. Predlagan postopek razpoznavanja med različnimi premiki mobilne naprave temelji na analizi glavnih komponent. Predstavili smo rezultate testiranj zgrajenega postopka in prišli do ugotovitev, da postopek z 99% natančnostjo razpozna med tremi različnimi premiki. Pri razpoznavanju med 10 različnimi premiki je natančnost 75%. Postopek se je dobro izkazal tudi na področju biometrije, saj v 73% pravilno razpozna osebo, ki je izvedla določen premik naprave.

Keywords

razpoznavanje premikov;peškometer;mobilne naprave;analiza glavnih komponent;interakcija človek-mobilni telefon;

Data

Language:	Slovenian
Year of publishing:	2012
Source:	Maribor
Typology:	2.11 - Undergraduate Thesis
Organization:	UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher:	[J. Kraner]
UDC:	004.94:621.395.721.5(043.2)
COBISS:	16495382
Views:	1442
Downloads:	90
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Recognition of specific movements of mobile device from signals acquired by integrated inertial sensors
Secondary abstract:	This diploma covers a topical issue of advanced method of human-device interaction using mobile phones. It describes a method, which recognizes the specific movements or gestures of the mobile device by using built-in accelerometer data. The procedures of data acquisition and segmentation, as well as resampling and time warping of the signals are described in detail. The proposed gesture-based recognition procedure of the mobile device is based on the Principal Component Analysis (PCA). Our test results show that by using the described method, the mobile device recognizes and differs among three different mobile device gestures with 99% accuracy. Moreover, the proper recognition of 10 different gestures occurs in 75% of all cases. Finally, the method yields fair results in the field of biometrics as it identifies the person who performs the movement with 73% accuracy.
Secondary keywords:	recognition of gestures;mobile device;principal component analysis;mobile interaction;
URN:	URN:SI:UM:
Type (COBISS):	Bachelor thesis/paper
Thesis comment:	Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko
Pages:	VIII, 34 f.
Keywords (UDC):	science and knowledge;organization;computer science;information;documentation;librarianship;institutions;publications;znanost in znanje;organizacije;informacije;dokumentacija;bibliotekarstvo;institucije;publikacije;prolegomena;fundamentals of knowledge and culture;propaedeutics;prolegomena;splošne osnove znanosti in kulture;computer science and technology;computing;data processing;računalniška znanost in tehnologija;računalništvo;obdelava podatkov;application-oriented computer-based techniques;računalniške tehnike za namensko rabo;aplikativno usmerjene računalniško podprte tehnike;simulation;simulacija;applied sciences;medicine;technology;uporabne znanosti;medicina;tehnika;engineering;technology in general;inženirstvo;tehnologija na splošno;mechanical engineering in general;nuclear technology;electrical engineering;machinery;strojništvo;electrical engineering;elektrotehnika;
ID:	1026674