diplomsko delo
Tanis Kodrun (Author), Matej Črepinšek (Mentor)

Abstract

V današnjem svetu igrajo pomembno vlogo mobilne naprave. Le-te vsebujejo vse več senzorjev, s pomočjo katerih zaznavajo okolico. V tej nalogi smo se lotili obdelave podatkov, ki smo jih pridobili iz senzorjev gibanja, s pomočjo genetskega programiranja. Naša želja je bila, da s pomočjo giroskopa mobilne naprave izboljšamo zaznavo hitrostnih ovir. Ideja je bila, da se pri tem uporabi simbolična regresija. Preučili smo lastnosti posameznih senzorjev in spoznali njihove prednosti in slabosti. Implementirali smo algoritem simbolične regresije, s pomočjo katerega smo podatke obdelali. Pridobljene rezultate smo analizirali in jih skušali še izboljšati.

Keywords

giroskop;simbolična regresija;pospeškometer;genetsko programiranje;evolucijsko računanje;diplomske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.11 - Undergraduate Thesis
Organization: UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher: [T. Kodrun]
UDC: [004.42:004.8]:528.526.6(043.2)
COBISS: 17515542 Link will open in a new window
Views: 1414
Downloads: 114
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: TUNING MOTION SENSOR ON MOBILE DEVICE
Secondary abstract: Mobile devices play an important role in the modern world. They include more and more sensors to perceive their surroundings. In this assignment we take a closer look at the processing of data, which were obtained with the help of motion detectors, with the assistance of genetic programming. Our desire was to improve the detection of speed bumps using a mobile gyroscope. The idea was to use symbolic regression. We have examined the characteristics of each sensor and have become aware of their advantages and disadvantages. We have also implemented a symbolic regression algorithm, which has helped us process the data. The results we obtained have been analysed and partially improved.
Secondary keywords: gyroscope;symbolic regression;genetic programming;evolutionary computation;
URN: URN:SI:UM:
Type (COBISS): Bachelor thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Računalništvo in informacijske tehnologije
Pages: VII, 35 str.
ID: 8727096