Bp 487 en

Z DCEwiki
Skočit na navigaci Skočit na vyhledávání
Verze k tisku již není podporovaná a může obsahovat chyby s vykreslováním. Aktualizujte si prosím záložky ve svém prohlížeči a použijte prosím zabudovanou funkci prohlížeče pro tisknutí.

Bicycle Transport Network Parameters Extraction Based on Mobile Phone Sensors

Author: Bednář Jan

Bakalářské práce 2017

Stáhnout práci v PDF

The aim of this work is to develop a neural network model which could be used used for determination of a road surface using mobile sensors data. Mobile was attached to a bike to be able to measure vibration while cycling. I used measured data for a neural network training. I used mainly the Python language for the implementation of data processing and the neural network. I have developed a neural network that can predict the surface with success rate of 81,7%. This model has following setting: 60 LSTMs, 200 sample sequence length, 50 ms resample. The results of the work show up that the road surface can be predicted with usage of the mobile sensors. It can help to map surfaces in cities and the application can offer better roads options.