Estimation of Site-specific radio propagation loss with minimal information

  • * Register (or log in) to the Neural Network to add this session to your agenda or watch the replay

  • Date
    21 August 2025
    Timeframe
    10:00 - 11:00 CET, Geneva
    Duration
    1 hours

    Stable mobile communication requires understanding radio propagation at specific areas, especially when using high-frequency bands like millimeter waves, which are highly affected by environmental factors such as buildings. Direct measurement of propagation characteristics across areas and frequencies is impractical due to cost and effort. To address this, AI/ML-based methods can estimate area-wide propagation using limited measurement data and environmental information like building layouts. Effective application of this approach involves not only building AI models but also selecting the most relevant data to improve estimation accuracy. This challenge invites participants to explore modeling and data selection methods using provided propagation loss data and 3D maps. Approaches may include propagation-based modeling or data-driven analysis, with or without 3D maps. Top-performing participants will be awarded a total prize of 3,000 CHF by KDDI Research, Inc.

    Learning Objectives:

    • Compare the modelling techniques for radio propagation
    • Design and construct models using datasets
    • Construct and demonstrate the models using applications and code.
    • Explain the results, inferences and findings from the various design iterations and models.

    Recommended Mastery Level / Prerequisites:

    • Basic understanding of wireless networks, the radio propagation estimation problems in general
    • Basic understanding of the characteristics of the next generation wireless networks, such as 5G and 6G
    • Basic data analysis and ML modelling techniques

    Are you sure you want to remove this speaker?