ITU Journal: New special issues on Internet of Everything and machine learning for 5G
New special issues of the ITU Journal share research on the new concepts to enable the evolution of the Internet of Things into an Internet of Everything encompassing all possible information sources and destinations, as well as innovations in artificial intelligence (AI) and machine learning (ML) to optimize 5G and future networks.
The ITU Journal on Future and Evolving Technologies provides complete coverage of all communications and networking paradigms, free of charge for both readers and authors. The journal publishes online all year round, welcoming papers at any time, on all topics within its scope.
The journal is also inviting contributions to special issues to be published in 2022 on innovation towards 6G in vehicular networks, autonomous network management and control, and future services from Augmented and Virtual Reality to holographic telepresence, as well as the second special issue on AI/ML in 5G and future networks.
Internet of Everything
Innovation towards substantially evolved and more sophisticated form of the Internet of Things – the Internet of Everything conceptualized by Cisco – raises questions calling for radical rethinking of core communications and networking concepts to realize the Internet of Everything’s envisioned scale, heterogeneity of involved entities, sensitivity of the information managed, and user expectations.
Download the full special issue or navigate directly to papers of interest below for novel research contributions to the technological and theoretical advancement of the Internet of Everything concept.
Resource tokenization for crowdfunding of wireless networks
Lysis chatbot: A virtual assistant for IoT platforms
Raimondo Cossu, Roberto Girau, Luigi Atzori
SIoT for cognitive logistics: Leveraging the social graph of digital twins for effective operations on real-time events
Miha Cimperman, Angela Dimitriou, Kostas Kalaboukas, Aziz S. Mousas, Salvatore Quattropani
3-of-3 multisignature approach for enabling lightning network micro-payments on IoT devices
Ahmet Kurt, Suat Mercan, Enes Erdin, Kemal Akkaya
RF-based low-SNR classification of UAVs using convolutional neural networks
Ender Ozturk, Fatih Erden, Ismail Guvenc
From design to prototyping in the Internet of Things: A domotics case study
Sabrina Sicari, Alessandra Rizzardi, Alberto Coen-Porisini
IoE: Towards application-specific technology selection
Biswajit Paul, Gokul Chandra Biswas, Habib F. Rashvand
Federated learning for IoE environments: A service provider revenue maximization framework
Benedetta Picano, Romano Fantacci, Tommaso Pecorella, Adnan Rashid
Artificial intelligence and machine learning for 5G and future networks
The first edition of the ITU Challenge on AI/ML in 5G enabled over 1300 participants from 62 countries to connect with new partners in industry and academia — and new tools and data resources — to achieve goals set out by problem statements contributed by industry and academia in Brazil, China, India, Ireland, Japan, Russia, Spain, Turkey and the United States. Read more about the champions of 2020’s Challenge and learnings from 2020’s Challenge in a dedicated issue of ITU News Magazine.
The second edition of the Challenge in 2021 has provided opportunity for partners, hosts and participants to collaborate on new problem statements, datasets and solutions. The Challenge remains in constant focus in a series of AI for Good webinars en route to the Grand Challenge Finale & Prize Ceremony in December 2021.
Download the full special issue or navigate directly to papers of interest below to gain insight on key concepts advanced by the first edition of the Challenge.
Simulation of machine learning-based 6G systems in virtual worlds
Ailton Oliveira, Felipe Bastos, Isabela Trindade, Walter Frazao, Arthur Nascimento, Diego Gomes, Francisco Müller, Aldebaro Klautau
Analysis on route information failure in IP core networks by NFV-based test environment
Xia Fei, Aerman Tuerxun, Jiaxing Lu, Ping Du, Akihiro Nakao
Applying machine learning in network topology optimization
Zhouwei Gang, Qianyin Rao, Lin Guo, Lin Xi, Zezhong Feng, Qian Deng
AI-based network topology optimization system
Han Zengfu, Kong Jiankun, Wang Zhiguo, Zhang Yiwei, Liu Ke, Pan Liang, Li Sicong, Wu Desheng
Machine learning for performance prediction of channel bonding in next-generation IEEE 802.11 WLANS
Francesc Wilhelmi, David Góez, Paola Soto, Ramon Vallés, Mohammad Alfaifi, Abdulrahman Algunayah, Jorge Martín-Pérez, Luigi Girletti, Rajasekar Mohan, K Venkat Ramnan, Boris Bellalta
NetXplain: Real-time explainability of graph neural networks applied to networking
David Pujol-Perich, José Suárez-Varela, Shihan Xiao, Bo Wu, Albert Cabellos-Aparicio, Pere Barlet-Ros
A dynamic Q-learning beamforming method for inter-cell interference mitigation in 5G massive MIMO networks
Aidong Yang, Xinlang Yue, Mohan Wu, Ye Ouyang
Enhanced shared experiences in heterogeneous network with generative AI
Neeraj Kumar, Ankur Narang, Brejesh Lall, Nitish Kumar Singh
Site-specific millimeter-wave compressive channel estimation algorithms with hybrid MIMO architectures
Sai Subramanyam Thoota, Dolores Garcia Marti, Özlem Tugfe Demir, Rakesh Mundlamuri, Joan Palacios, Cenk M. Yetis, Christo Kurisummoottil Thomas, Sameera H. Bharadwaja, Emil Björnson, Pontus Giselsson, Marios Kountouris, Chandra R. Murthy, Nuria González-Prelcic, Joerg Widmer
Graph-neural-network-based delay estimation for communication networks with heterogeneous scheduling policies
Martin Happ, Matthias Herlich, Christian Maier, Jia Lei Du, Peter Dorfinger
ITU opportunities for research communities
ITU Academia members contribute to ITU expert groups responsible for radiocommunication, standardization and development, contributions that bring greater strength to the work of ITU and greater impact to research.
ITU Kaleidoscope conferences share research on topics of growing strategic relevance to ITU standardization. ITU Kaleidoscope 2021: Connecting physical and virtual worlds is scheduled for 6-10 December online. Submit an abstract by 29 October to be considered for the conference’s video demonstration track.