Improving teoretic train driving time with AI and TensorFlow

The aim of that paper is to improve theoretic train driving time between stations with use of machine learning and framework TensorFlow. For fluent train traffic management, it is very important to know accurate train arriving time. Then operation can be adapt depending on train delay. We can alread...

Full description

Saved in:

Bibliographic Details
Published in:	2020 4th International Symposium on Informatics and its Applications (ISIA) pp. 1 - 4
Main Authors:	Krsak, Emil, Kello, Tomas
Format:	Conference Proceeding
Language:	English
Published:	IEEE 15-12-2020
Subjects:	artificial intelligence Delays driving time prediction Internet Machine learning Rail transportation Security Servers TensorFlow Tensors train driving time
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	The aim of that paper is to improve theoretic train driving time between stations with use of machine learning and framework TensorFlow. For fluent train traffic management, it is very important to know accurate train arriving time. Then operation can be adapt depending on train delay. We can already calculate theoretic driving time, it includes multiple parameters as distance, angel of curves, angel of ascent and descent, maximal speed limit, engine parameters and driving parameters to save electricity with slowly decelerating before station. But it doesn't include state of railway, train set, weather conditions, weight of passengers,... So, we will use historic data and artificial intelligence to improve prediction to make railway management simpler.
DOI:	10.1109/ISIA51297.2020.9416531