Projects

macHine leARning MethOds aNd algorIthms fOr 6G terahertz cellUlar acceSs (HARMONIOUS)

PI: Lempiäinen Jukka

The terahertz band offering tens or even hundreds of gigahertz of consecutive bandwidth is nowadays considered as a major candidate for new radio access technology in 6G systems. By wisely utilizing this bandwidth one may not only provide extreme data rates at the access interface but enable principally new applications over-the-air such as Tactile Internet, holographic telepresence, and virtual reality. The aim of the project is to develop the set of fundamentally new models and algorithms to enable truly mobile ultra-broadband THz cellular radio access technology. These models will contribute to better understanding of THz specifics as well as requirements and constraints imposed at practical communications mechanisms and algorithms in THz systems. Thus, the successful completion of the project will make a decisive step closer to enabling principally new applications over the commercial systems.

Switch-Mode Analog Integrated Circuits for beyond-5G Radio Transceivers (SMASH)

PI: Unnikrishnan Vishnu

SMASH is an ambitious project with an aim to perform groundbreaking scientific research, bringing a paradigm-shift to the analog circuit design methodology by representing analog information with time-based parameters of pulse waveform and processing it with switch components. The project will demonstrate the results through applied research that significantly advances the performance of radio receivers, thereby enabling low-cost fixed wireless broadband coverage in rural areas with speeds up to 100 Gbps, 10X the state-of-the-art cable technology.

NSF-AoF: CNS Core: Small: Machine Learning Based Physical Layer and Mobility Management Solutions Towards 6G

PI: Valkama Mikko

5G evolution and future 6G cellular networks are targeting operation at higher millimeter wave and sub-THz bands due to large available channel bandwidths. However, the use of these bands for mobile radio access imposes substantial technical challenges, including the quality, cost- and energy-efficiency of the electronics, the extreme path loss and propagation characteristics, and the overall deployment costs to provide indoor and outdoor network coverage with mobility support. Considering these challenges, this project will harness machine learning algorithms for designing physical layer technologies and network management procedures that aim to improve robustness and reliability of connectivity under mobility. The project’s expected contributions are at the forefront of emerging 6G standard and applications of modern machine learning tools in wireless communications at high frequency bands. The project is a joint effort between Tampere University, Finland, and UCLA, US.

The objective of the jointly funded projects is to support research collaboration between Finland and the United States in the fields of artificial intelligence (AI) and/or wireless communication technologies.

Fundamental Limits and Performance Trade-Offs in Integrated Sensing and Communications (6G Fun-ISAC)

PI: Valkama Mikko

Extracting information and performing learning, inference, and choosing optimal actions through sensing the physical world and its phenomena with large numbers of networked multimodal sensors are of high and rapidly increasing importance in various applications. An important special case of networked sensing is the use of communications networks, devices, and spectrum to also perform the sensing tasks so that the resources are shared within the two functionalities. The concept is known as integrated sensing and communications (ISAC) or joint communications and sensing (JCAS). FunISAC project will explore the underlying theories, optimality, and performance boundaries of ISAC to create fundamental research understanding of the field. The focus is on ISAC functionalities and their fundamental performance bounds, optimization of operational parameters and trade-offs between sensing and communications performances and resource consumption.

Distributed AI for enhanced security in satellite-aided wireless navigation (RESILIENT)

PI: Kuusniemi Heidi

RESILIENT will address the challenges of ensuring cyber-security and privacy for civilian location-based applications, offering increased robustness and resilience of satellite-based positioning signals to various types of intentional and non-intentional interference. This project is composed of a team of researchers from US and Finland, in a joint effort to advance worldwide security of GNSS against existing threats while providing an excellent opportunity for students to participate in an international project on cutting-edge technologies and methodology development.
The goal of this project is to develop tools for interference management in geolocation applications. The specific goals of the project are divided into three research goals. The first goal investigates the use of deep learning for detection/classification of interference and fusion of multiple correlated classifiers providing local threat detection probabilities. The second goal aims to localize and track the interference sources through the creation of global threat probability maps. This goal is achieved by advancing the field federated learning in a threefold way: (i) to efficiently digesting non-independent and identically distributed data; (ii) combining with active learning methods, whereby moving agents sample specific locations to improve estimation performance; and (iii) investigating federated meta-learning strategies that use task-level knowledge to improve global learning. The third goal of the project investigates the use of those global threat maps to mitigate their effects on collaborative receivers using robust factor graph optimization.

Advancing Sustainable Economic Growth through Space Economy (SpacEconomy)

PI: Kuusniemi Heidi

The SpacEconomy project strengthens Finland’s position in the rapidly growing global space economy. A key challenge is the fragmentation of Finland’s space-related activities and the underutilization of growth potential. By promoting innovation, education opportunities, and cross-sector collaboration, we bring together experts from science, industry, business, and the public sector to enhance the foundations of economic growth, productivity, and societal well-being through the space economy.
Within SpacEconomy, we develop space-data-driven AI innovations, multidisciplinary education pathways, and new business models. We promote fair and sustainable growth using metrics beyond GDP and engage stakeholders from all sectors of society through citizen and expert panels. The project is multidisciplinary, combining expertise in space technology, economics, governance, social sciences, and AI to drive systemic change. In collaboration with diverse actors, we strengthen national resilience and safeguard critical infrastructures.

The project is funded by the Strategic Research Council, established within the Research Council of Finland.

Read more: www.spaceconomy.fi

Sustainable 6G Radio Access Networks: Methods, Models, and Algorithms (S6GRAN)

PI: Valkama Mikko

When entering towards the sixth generation (6G) mobile communications era, the huge numbers of connected devices with increased data traffic and new services imply significant challenges for the involved radio access network (RAN) design to be able to provide the system capacity and Quality-of-Service (QoS) with sustainable power and energy consumption. The S6GRAN project focuses on fundamental research for design and optimization of 6G RAN, wireless transceivers, and the related algorithms. The overall objective is to develop new scientific knowledge and novel wireless transceiver and system optimization solutions enabling sustainable 6G radio access networks. The core academic collaborators include Chalmers University of Technology, University of Luxembourg, and Queen’s University of Belfast. Industrial collaboration is also conducted largely with several companies creating the 6G technology.

Unleashing Integrated Sensing and Communication Pontentials by Exploiting Shared Scatterers in Millimeter-Wave Systems: ISAC-SS

PI: Riihonen Taneli

Unleashing Integrated Sensing and Communication Pontentials by Exploiting Shared Scatterers in Millimeter-Wave Systems: ISAC-SS

In the next-generation millimeter-Wave (mm-Wave) networks, sensing is assumed a vital role in various applications, including transport systems, smart cities, and public safety. Integrated sensing and communication (ISAC) is identified as a key technology to achieve ubiquitous sensing with communication systems, where the convergence of sensing and communication functionalities on shared hardware holds the promise of reduced costs, enhanced spectral and energy efficiency, and reduced latency. Before incorporating ISAC into next-generation communication standards, however, the sensing and communication capacities of ISAC should be further improved.
The 2-year MSAC Postdoctoral Fellowship, ISAC-SS, seeks to unlock the full potential of ISAC systems by exploiting the shared scatterers in communication and sensing channels. The state-of-the-art (SoA) in ISAC signal processing has largely overlooked this critical element, leaving room for performance improvement.

Jamming and Spoofing Resilient Deep Learning based Software-Defined multi-antenna GNSS Receiver (JASMINE)

PI: Nurmi Jari

The goal of this project is to develop ‘Jamming and Spoofing Resilient Deep Learning based Software-Defined multi-antenna GNSS Receiver (JASMINE)’, that inherits the superiority of signal and navigation processing through Deep learning technology. To achieve reconfigurability and optimized performance, Graphics processing unit (GPU) based Software Defined Radio (SDR) approach is preferred for JASMINE.

Read more: Jamming and Spoofing Resilient Deep Learning based Software-Defined multi-antenna GNSS Receiver (JASMINE) | Tampere universities