ITU AI/ML in 5G Challenge — “Machine learning for wireless LANs + Japan challenge introduction”

Go back to programme

ITU AI/ML in 5G Challenge — “Machine learning for wireless LANs + Japan challenge introduction”

  • Zoom

    Watch on zoom

    watch on youtube

    * Register (or log in) to the AI4G Neural Network to add this session to your agenda or watch the replay

  • In this webinar, we will host expert talks and introduce ITU-ML5G-PS-031: Network State Estimation by Analyzing Raw Video Data and ITU-ML5G-PS-032: Analysis on route information failure in IP core networks by NFV-based test environment.

    This first part of the webinar will be on Machine Learning for Wireless LANs. This talk provides applications of deep supervised learning and reinforcement learning for microwave and mmWave wireless LANs (WLANs). Furthermore, the talk will address how to apply the machine learning techniques to challenges in WLANs based on mmWave, received power prediction and handover.

    Second part will be introducing problem statements from Japan Challenge. Firstly, “Analysis on route information failure in IP core networks by NFV-based test environment” will be discussed. The stable and high-quality Internet connectivity is mandatory to 5G mobile networks. Anomaly detection is desired to be automatically and rapidly performed by AI/ML. In this problem, the data sets at border gateway routers are provided along with network status information such as normal, failure, mis-operation, etc, as normal/abnormal labels. Participants are required to create the model to pinpoint the network status of failures and mis-operation using the data sets and evaluate the performance of the developed model.

    Secondly, Network State Estimation by Analyzing Raw Video Data will be discussed. Due to COVID-19 pandemic, the importance of interactive live video streaming services, e.g., telework system using web cameras, has been increasing. However, the increasing traffic generated from such bandwidth-consuming video streaming services results in heavy congestion. Service providers should control the video quality according to the network state. This situation is challenging for passive network state estimation by analyzing raw video data. This challenge is the first step to understand relationship between raw video images and network state. The goal of this challenge is to estimate network state, i.e., throughput and loss ratio, from given raw video data sets. The participants are expected to train and test an AI model using the video data with labels of network state.

    Share this session

    Are you sure you want to remove this speaker?