1. BaSaMa & HiWi
    2.  

Pattern Recognition in Dynamic Graphs for Shared Mobility Systems

Institut
Lehrstuhl für Fahrzeugtechnik
Typ
Bachelorarbeit / Semesterarbeit / Masterarbeit /
Inhalt
 
Beschreibung

Background

Shared mobility systems can be represented as dynamic graphs, where nodes correspond to locations (districts, stations, hexagons) and edges reflect trip flows. Anomalies in these systems are not only visible in individual time series, but also in the structure and evolution of the mobility network. For example, sudden demand spikes in one district, disrupted flows between areas, or structural breaks caused by large events may manifest as unusual graph patterns. Identifying, classifying, and linking these anomalous graph patterns to real-world causes is a promising approach to improve operational planning, anticipate disruptions, and support decision-making in urban mobility.

Your Role

  • Literature research: Review pattern recognition and anomaly detection methods for dynamic graphs (graph signal processing, temporal motifs, graph neural networks).
  • Graph modeling: Represent shared mobility trips as a dynamic graph with nodes, edges, and temporal features.
  • Pattern discovery: Detect recurring “normal” mobility patterns and identify anomalous deviations in graph structure or signals.
  • Anomaly reasoning: Relate detected graph anomalies to possible external causes (e.g., weather, events, strikes, policy changes).
  • Evaluation & visualization: Benchmark selected methods and present results using intuitive visualizations (dynamic network plots, heatmaps, map overlays).
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.

Svetlana Zubareva, s.zubarevatum.de

Tags
FTM Studienarbeit, FTM SM, FTM Zubareva
Möglicher Beginn
sofort
Kontakt
Svetlana Zubareva, M.Sc.
Raum: MW3505
Tel.: 017660388031
s.zubarevatum.de
Ausschreibung