prikaz prve stranice dokumenta Višesenzorski sustav za analizu načina vožnje
Access restricted to authenticated users
master's thesis
Višesenzorski sustav za analizu načina vožnje
2021. urn:nbn:hr:179:334238
Vučina, Ana
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Cite this document

Vučina, A. (2021). Višesenzorski sustav za analizu načina vožnje (Master's thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:334238

Vučina, Ana. "Višesenzorski sustav za analizu načina vožnje." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:334238

Vučina, Ana. "Višesenzorski sustav za analizu načina vožnje." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:334238

Vučina, A. (2021). 'Višesenzorski sustav za analizu načina vožnje', Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 23 October 2024, https://urn.nsk.hr/urn:nbn:hr:179:334238

Vučina A. Višesenzorski sustav za analizu načina vožnje [Master's thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2021 [cited 2024 October 23] Available at: https://urn.nsk.hr/urn:nbn:hr:179:334238

A. Vučina, "Višesenzorski sustav za analizu načina vožnje", Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:179:334238

Please login to the repository to save this object to your list.
Metadata
TitleVišesenzorski sustav za analizu načina vožnje
Title (english)Multi-sensor system for estimating driving style
AuthorAna Vučina
MentorIvo Stančić (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2021-07-15, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Electronics
Abstract
Cilj ovog diplomskog rada je analizirati mogućnosti korištenja više inercijskih senzora u različitim konfiguracijama za analizu načina vožnje bicikle pri čemu je naglasak stavljen na umjetnu neuronsku mrežu. Cjelokupni uređaj sadrži jednu elekroničku pločicu s komponentama za uspješan rad uređaja. Na pločicu je postavljen Teensy 3.6 mikrokontroler, te dva akcelerometra, senzor orijentacije i magneti. Uređaj prikupljene podatke sprema na microSD karticu. Sklop je postavljen na bicikl i testirao se u 3 realna uvjeta: vožnja strogo pravo, normalna vožnja i vožnja s naglim ubrzanjem i kočenjem. Podaci su prilagođeni, uzeti su samo potrebni za treniranje neuronske mreže. Kasnije se ti podaci obrađuju u MATLAB programskom jeziku. Obrađeni podaci se koriste za kreiranje i treniranje umjetne neuronske mreže. Izabrana je Feedfoward neuronska mreža koja je pokazala 97% točnosti u klasifikaciji podataka.
Abstract (english)
The aim of this thesis is to analyze the possibility of using multiple inertial sensors in different configurations to analyze the mode of cycling, emphasizing the attitude towards the artificial neural network. The entire device contains one electronic board with components for successful operation of the device. The board has a Teensy 3.6 microcontroller, two accelerometers, an orientation sensor and magnets. The device saves the collected data on a microSD card. The assembly was mounted on a bicycle and tested in 3 real conditions: riding strictly straight, normal riding and riding with sudden acceleration and braking. The data were adjusted, only those needed to train neural networks were taken. This data is later processed in the MATLAB programming language. The processed data are used to create and train artificial neural networks. The Feedfoward neural network was selected which showed 97% accuracy in data classification.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:334238
Study programmeTitle: Electronics and Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka elektronike i računalnog inženjerstva (magistar/magistra inženjer/inženjerka elektronike i računalnog inženjerstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to authenticated users
Terms of useLicence In copyright icon
Created on2021-11-30 11:50:14