Detecting Anomalies in Bus Operations Using Realtime Data

Institut

Lehrstuhl für Fahrzeugtechnik

Typ

Bachelorarbeit / Semesterarbeit /

Inhalt

experimentell /  

Beschreibung

Background

Urban bus systems generate large amounts of Realtime data that can be used to analyze the operational performance. Identifying anomalies in delays and consumption patterns helps improve efficiency and reliability. Therefore, we are scraping data from different European cities to build a dataset for analysis.

 

Your Role

• Collect and preprocess Realtime data (vehicle positions, delays, stop sequences)

• Reconstruct trips and estimate energy consumption

• compare GFTS Realtime to static GTFS

• Apply anomaly detection methods to identify irregular patterns

• Interpret findings with respect to operational efficiency and reliability

• Propose a framework for continuous monitoring and improvement

Voraussetzungen

What should you bring along?

• Strong interest and motivation in mobility data science
• Initiative & independent way of working
• Basic programming skills (Python)

Language

English/German

If you are interseted write an email and attach a CV and a grade sheet to your application.

Louis Stille-Hönig, louis.stille-hoenig@tum.de

Verwendete Technologien

GTFS

Möglicher Beginn

sofort

Kontakt

Louis Stille-Hönig, M.Sc.
Raum: MW 3509
Tel.: +49 89 289 15341
louis.stille-hoenigtum.de