diplomsko delo
Abstract
Današnje mobilne naprave z vgrajenimi senzorji in GPS sprejemniki nam omogočajo beleženje podatkov, s pomočjo katerih lahko izvemo veliko informacij o uporabniku. Cilj diplomske naloge je razviti mobilno aplikacijo oziroma storitev za detekcijo prevoznega sredstva uporabnika. Nabor izbranih prevoznih sredstev predstavljajo mestni avtobus, tramvaj in vlak. Za zajem podatkov smo uporabili merilnik pospeškov, giroskop in GPS sprejemnik mobilne naprave. S pomočjo zajetih podatkov, prosto dostopnih podatkov o geografski legi železniških objektov in različnih metod strojnega učenja smo razvili napovedni model. Metoda naključnih gozdov je s 97 % natančnostjo pokazala najboljši rezultat.
Keywords
Android;detekcija prevoznih sredstev;strojno učenje;računalništvo in informatika;univerzitetni študij;diplomske naloge;
Data
Language: |
Slovenian |
Year of publishing: |
2023 |
Typology: |
2.11 - Undergraduate Thesis |
Organization: |
UL FRI - Faculty of Computer and Information Science |
Publisher: |
[M. Robič] |
UDC: |
004.9(043.2) |
COBISS: |
147555843
|
Views: |
34 |
Downloads: |
15 |
Average score: |
0 (0 votes) |
Metadata: |
|
Other data
Secondary language: |
English |
Secondary title: |
The Development for Transportation Mode Detection |
Secondary abstract: |
Modern mobile devices with embedded sensors and GPS receivers allow us to collect all sorts of data, that we can use to gain information about users. The goal of this thesis is to develop a mobile app service for detecting user transportation mode. Our set of selected transportation modes consists of city bus, tram, and train. We used accelerometer, gyroscope, and GPS receiver for data collection. With the use of collected data, geographical railway data and different classification methods we developed a prediction model. Random forest performed best with 97 % accuracy. |
Secondary keywords: |
Android;application;detection;machine learning;transportation mode;computer science;computer and information science;diploma;Mobilne aplikacije;Vozila;Računalništvo;Univerzitetna in visokošolska dela; |
Type (COBISS): |
Bachelor thesis/paper |
Study programme: |
1000468 |
Embargo end date (OpenAIRE): |
1970-01-01 |
Thesis comment: |
Univ. v Ljubljani, Fak. za računalništvo in informatiko |
Pages: |
36 str. |
ID: |
18254256 |