Dr Jenifer Steffi J

@jeppiaararts.in

Assistant professor, Department of Mathematics
Jeppiaar College of Arts and Science, Padur, Chennai, Tamil

Dr Jenifer Steffi J


            Download Compact PDF  
https://researchid.co/drjenifer

RESEARCH INTERESTS

Graph Pebbling
Graph theory
Number theory
Computational mathematics
4

Scopus Publications

Scopus Publications

  • IoT and AI Integration in Traffic Management
    J. Steffi, K. Merriliance, Mary Immaculate Sheela Lourdusamy
    Artificial Intelligence AI for Smart and Sustainable Urban Transportation, 2026
    Traffic congestion in cities is a growing challenge; it leads to more travel time, consumption of fuel, and environmental pollution. Traditional traffic management is often unable to cope with the real-time traffic fluctuations well. Implementing IoT and AI will give an edge because it offers data-driven solutions by using real-time traffic data to enhance efficiency, optimize traffic flow, and enhance road safety. It refers to the processing of continuous data collected by IoT-enabled sensors, such as GPS, RFID, LiDAR, and computer vision systems, about the movement of vehicles, pedestrians, and road conditions using AI techniques such as machine learning, deep learning, reinforcement learning, and predictive analytics for real-time decisions in traffic control. For instance, adaptive traffic signals based on reinforcement learning base the adjustment of light timings to real-time congestion levels to reduce traffic delay. Similarly, computer vision models such as YOLO and Faster R-CNN are implemented for the purposes of vehicle and pedestrian detection; this will facilitate better automated incident detection and more effective emergency responses. Another critical application of AI in traffic management is forecasting traffic. These LSTM networks and GNNs analyze historical as well as real-time traffic data to predict the congestion patterns, thus suggesting the alternative routes for travel. Optimizing public transport using AI enables scheduling and planning routes with better techniques such as genetic algorithms and reinforcement learning in order to demand-based fleet management. AI-driven traffic rerouting systems use analytics in real-time to guide the drivers toward efficient routes, hence reducing congestion hotspots. Recent advances in edge computing and federated learning enable real-time processing of local traffic data without latency and loss of data privacy. The integration of AI along with the Internet of Things (IoT) lowers greenhouse gas emissions, reduces fuel consumption, and idle time, all at the same time boosting sustainable urban mobility and green. Despite these benefits, several challenges face the wide-scale adoption of such systems. The data related to real-time traffic is prone to risks associated with data privacy and cybersecurity. It demands robust encryption and secure communication protocols. Other barriers include high infrastructure costs and system interoperability in developing regions. Therefore, overcoming these challenges is critical for ensuring the scalability and reliability of AI-IoT-based traffic management systems. This chapter discusses the role of AI and IoT in intelligent traffic management, including key technologies, real-world applications, and future trends. With the help of AI and IoT, cities can make a transition toward smart, efficient, and sustainable transportation networks that will enhance urban mobility and reduce congestion-related problems.
  • Lourdusamy's conjecture on ZZ n (C 2 k ) × G
    J. Jenifer Steffi, A. Lourdusamy
    Aip Conference Proceedings, 2020
    Given a distribution of pebbles on the vertices of a connected graph G, a pebbling move consists of taking two pebbles off one vertex and placing one on an adjacent vertex. The pebbling number f (G) of a connected graph G is the smallest positive integer such that every distribution of f (G) pebbles on the vertices of G, we can move a pebble to any target vertex. The t-pebbling number ft (G) of a connected graph G is the smallest positive integer such that every distribution of ft (G) pebbles on the vertices of G, we can move t pebbles to any target vertex by a sequence of pebbling moves. Graham conjectured that for any connected graph G and H, f (G × H) ≤ f (G) f (H). Lourdusamy further conjectured that ft (G × H) ≤ f (G) ft (H) for any positive integer t. In this paper, we show that Lourdusamy’s Conjecture is true when G is a zig-zag chain graph of n copies of even cycles and H is a graph having 2t- pebbling property.
  • Pebbling on zig-zag chain graph of n odd cycles
    A. Lourdusamy, J. Jenifer Steffi
    Proyecciones, 2019
    Given a distribution of pebbles on the vertices of a connected graph G, a pebbling move on G consists of removing two pebbles from one vertex and placing one pebble on an adjacent vertex. The pebbling number of G, f (G), is the least n such that any distribution of n pebbles on G allows one pebble to be reached to any specified, but an arbitrary vertex. Similarly, the t−pebbling number of G, ft(G), is the least m such that from any distribution of m pebbles, we can move t pebbles to any specified, but an arbitrary vertex. In this paper, we determine the pebbling number, and the t−pebbling number of the zigzag chain graph of n copies of odd cycles.
  • PEBBLING ON THE MIDDLE GRAPH OF A COMPLETE BINARY TREE
    A. Lourdusamy, S. Saratha Nellainayaki, J. Jenifer Steffi
    Journal of Applied Mathematics and Informatics, 2019