AI/ML Challenge Finale: Beam-Level Traffic Forecasting and Site specific radio propagation loss

Channel:
Subscribers:
20,600
Published on ● Video Link: https://www.youtube.com/watch?v=015SVnOV6dE



Duration: 0:00
226 views
11


The ITU AI/ML in 5G Challenge in 2024 (Fifth edition) offers a platform for collaboratively addressing the problems in applying AI/ML in communication networks including 5G & 6G. The Challenge connects participants (students and professionals) from more than 100 countries, with industry and academia solving real-world problems using AI/ML in communication networks. The challenge is offering several problem statement in 2024. Some of these problem statements includes;

Spatio-Temporal Beam-Level Traffic Forecasting Challenge
Estimation of Site specific radio propagation loss
Participants are tasked with the development of solutions leveraging state-of-the-art (SOTA) forecasting machine learning models capable of analyzing complex, multivariate time series data on forecasting traffic throughput volumes within communication networks. In the second challenge, participants were tasked to use ML to estimate propagation loss within a certain area from a transmission point (Tx) using 3D map data and propagation loss data from multiple Txs.

In this webinar, top teams from these competitions presents their ML solutions. Stay tuned till the end, where we’ll be announcing and celebrating the winners for their excellent contributions. 

Cash Prizes: The ITU AI/ML in 5G Challenge has set up prize pools of different sizes to reward outstanding teams totaling to 13,000 CHF.

Judges:
Tareq Si Salem
Senior Researcher
Huawei

Nicola Piovesan
Senior Researcher
Huawei

Moderators:
Miya Nishio
Student
University of Tokyo

🔴 Watch the latest #AIforGood videos!


📩 Stay updated and join our weekly AI for Good newsletter:
http://eepurl.com/gI2kJ5

🗞 Check out the latest AI for Good news:
https://aiforgood.itu.int/newsroom/

📱 Explore the AI for Good blog:
https://aiforgood.itu.int/ai-for-good-blog/

🌎 Connect on our social media:
Website: https://aiforgood.itu.int/
Twitter: https://twitter.com/AIforGood
LinkedIn Page: https://www.linkedin.com/company/26511907
LinkedIn Group: https://www.linkedin.com/groups/8567748
Instagram: https://www.instagram.com/aiforgood
Facebook: https://www.facebook.com/AIforGood

Disclaimer:
The views and opinions expressed are those of the panelists and do not reflect the official policy of the ITU.




Other Videos By AI for Good


2025-01-13AI for Good Innovation Factory
2024-12-20Post-quantum cryptography and what the telco industry is doing for quantum secure future
2024-12-20Full stack AI hardware, software & Granite models for language, code, time series & geospatial
2024-12-20ITU standards for Supporting Accessible Movable communication in complex settings
2024-12-20Indonesia’s Circular Economy Roadmap in the Electronics Waste Sector: from Industry Perspective
2024-12-20Engaging with ITU-T SG15 for building the world’s digital backbone
2024-12-20AI for Good Global Summit 2025 Trailer
2024-12-182024 ITU GeoAI Challenge Finale
2024-12-17Expertise, Artificial Intelligence, and the Work of the Future
2024-12-13Advancing AI, Neurotech, and Cybersecurity: Mexico’s Neurorights Bill
2024-12-13AI/ML Challenge Finale: Beam-Level Traffic Forecasting and Site specific radio propagation loss
2024-12-13AI for Good Innovation Factory Baltics
2024-12-12AI for Good Impact India
2024-12-10AI-Generated Draft Replies Integrated Into E-Health Records & Physician-Patient Communication
2024-12-03Wavecontrol EMF human exposure test instruments: How they relate to ITU-T Standards
2024-12-03Pangu AI Meteorological Model for climate change
2024-12-03Shaping AI Standards for Climate Response and Disaster Management
2024-12-03ITU-T norms and deliverables: Towards a SMARTer connectivity in Portugal
2024-12-03Use Cases of the Implementation and Adoption of ITU-T Recommendations by the TTA
2024-12-03QoS from Space – Potential QoS assessment of Direct-To-Cell (D2C) Networks
2024-12-03Toward robust surrogate components of land surface states for hybrid earth system models