Zalila-Wenkstern, Rym

Permanent URI for this collectionhttps://hdl.handle.net/10735.1/6561

Rym Zalila-Wenkstern is an Associate Professor of Computer Science. She is the director of the Executive Master's of Software Engineering program and also serves as head of the Multi-Agent and Visualization Systems Lab. Her research interests include:

  • Software engineering
  • Multi-agent systems
  • Information visualization

ORCID page

Browse

Browsing Zalila-Wenkstern, Rym by Title

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    A Resilient Agent-Based Re-Organizing Traffic Network for Urban Evacuations
    (Springer Verlag) Al-Zinati, M.; Zalila-Wenkstern, Rym; 0000-0002-2062-6794 (Zalila-Wenkstern, R); 2863148574264724430006 (Zalila-Wenkstern, R); Zalila-Wenkstern, Rym
    Implementing effective traffic road reversals is a complex problem: it requires clearing roads from traffic before implementing safe road reversal operations and often results in anomalies in the network topology. Road reversals are further complicated when, due to unexpected events (e.g., torrential rains), roads are suddenly closed. Current traffic road reversal approaches are based on the execution of mathematical models which identify upfront, optimal reversal configurations for the entire traffic network. These approaches assume that the traffic network structure is static, and as such do not allow for dynamic road closures. In this paper, we present a resilient agent-based re-organizing traffic model for urban evacuations. Resilience refers to the traffic network’s ability to regain its evacuation function quickly and efficiently after severe perturbations. The proposed model integrates road reversal and zoning strategies. Experimental results show that: (a) the model improves the evacuation effort, and (b) the evacuation function is able to cope quickly and effectively with dynamic road closures.
  • Thumbnail Image
    Item
    A Self-Adaptive Collaborative Multi-Agent Based Traffic Signal Timing System
    (Institute of Electrical and Electronics Engineers Inc.) Torabi, Behnam; Zalila-Wenkstern, Rym; Saylor, R.; 0000-0002-2062-6794 (Zalila-Wenkstern, R); 2863148574264724430006 (Zalila-Wenkstern, R); Torabi, Behnam; Zalila-Wenkstern, Rym
    In this paper, we present DALI, a self-Adaptive, collaborative multi-Agent Traffic Signal Timing system (TST). Intersection controller agents collaborate with one another and adapt their timing plans based on the traffic conditions. Reinforcement learning is used to optimize values for the various thresholds necessary to dynamically determine the scope of collaboration between the agents. DALI was implement in MATISSE 3.0, a large-scale agent-based micro-simulator. Experimental results show an improvement over traditional and reinforcement learning TSTs. © 2018 IEEE.
  • Thumbnail Image
    Item
    Matisse 3.0: A Large-Scale Multi-Agent Simulation System for Intelligent Transportation Systems
    (Springer Verlag) Torabi, Behnam; Al-Zinati, M.; Zalila-Wenkstern, Rym; 0000-0002-2062-6794 (Zalila-Wenkstern, R); 2863148574264724430006 (Zalila-Wenkstern, R); Torabi, Behnam; Zalila-Wenkstern, Rym
    In this demo we present MATISSE 3.0, a microscopic simulator for agent-based Intelligent Transportation Systems (ITS). MATISSE provides abstract classes for the definition of vehicle and intersection-controller agents as well as components for the concurrent 2D and 3D visualizations of the simulation. The control GUI allows the user to change various agent properties at run time. The OSM converter imports entire traffic networks from Open Street Map. We illustrate the use of MATISSE through the development of a simulation for the City of Richardson, Texas.

Works in Treasures @ UT Dallas are made available exclusively for educational purposes such as research or instruction. Literary rights, including copyright for published works held by the creator(s) or their heirs, or other third parties may apply. All rights are reserved unless otherwise indicated by the copyright owner(s).