Page 7 - ITU Journal Future and evolving technologies Volume 2 (2021), Issue 4 – AI and machine learning solutions in 5G and future networks

ITU Journal on Future and Evolving Technologies, Volume 2 (2021), Issue 4

complexity and better convergence efficiency. Performance analysis shows the quality-of-service
improvement in terms of signal-to-interference-plus-noise-ratio (SINR) and the robustness towards
different environments.

The paper “Enhanced shared experiences in heterogeneous network with generative AI” considers an
environment where the participants can interact with each other through video conferencing by only
sending the audio in the network. The authors propose a multi-modal adaptive normalization-based
architecture (MAN) to synthesize a talking person video of arbitrary length using as input an audio
signal and a single image of a person. The architecture uses the multi-modal adaptive normalization,
keypoint heatmap predictor, optical flow predictor and class activation map-based layers to learn
movements of expressive facial components and hence generates a highly expressive talking-head video
of the given person.
Digital representations of the real world are being used in many applications such as augmented reality.
6G systems will not only support use cases that rely on virtual worlds but also benefit from the rich
contextual information to improve performance and reduce communication overhead. The paper
“Simulation of machine learning-based 6G systems in virtual worlds” focuses on the simulation of 6G
systems that rely on a 3-D representation of the environment, as captured by cameras and other sensors.
New strategies for obtaining paired MIMO channels and multimodal data are presented and tradeoffs
between speed and accuracy when generating channels via ray-tracing are discussed.

This special issue was made possible due to the tireless and selfless efforts by the Guest Editors. The
leading Guest Editor – Chih-Lin I, China Mobile Research Institute, China – as well as the Guest Editors
– Akihiro Nakao, University of Tokyo, Japan; Aldebaro Klautau, The Federal University of Pará
(UFPA), Brazil; Nuria González Prelcic, North Carolina State University, USA; and Albert Cabellos-
Aparicio, Technical University of Catalonia, Spain – worked together as a team to guide the authors.
The insights, expert comments and recommendations of the well experienced Guest editors were
invaluable for bringing out the innovations behind the Challenge in the form of this journal. We also
thank the numerous reviewers who worked hard to make sure that we have quality manuscripts for this
special issue. Furthermore, we would like to thank the authors who not only submitted solutions to the
Challenge but also took the trouble to document them and share them to our readers. Last but not least
we are grateful to the Editor-in-Chief of the ITU Journal, Ian Akyildiz, for his enthusiasm and guidance.
The second edition of the ITU AI/ML in 5G Challenge is already underway in 2021. This provides an
opportunity for partners, hosts and participants to collaborate on new problem statements, datasets and
solutions. The call for papers resulting from the second edition of the Challenge provides a further
opportunity for collaboration and learning for our hosts and participants.

We invite you to enjoy reading the current special issue and to join us on our journey of the next one.

Vishnu Ram Thomas Basikolo Reinhard Scholl
Independent Researcher ITU ITU

– v –