Professor Nicola Marchetti

Summary

Funding Agency

European Commission

Programme

Marie Sklodowska-Curie Action

Project Type

Staff Exchanges

Summary

This project aims to develop a smart environmental monitoring system that will bring about a revolution in biodiversity quantification in real time. It will address the connected challenge of addressing explicitly what is lost and gained through digital translation from animal to human understanding.

Funding Agency

Trinity College Dublin

Programme

Kinsella Challenge-Based E3 Multi-Disciplinary Project Award

Summary

The Internet of Things (IoT) is creating a new structure of awareness - a cybernetic one - upon physical processes. Industries of different kinds are expected to join soon this revolution, leading to the so-called Factories of the Future or Industry 4.0. Our considered IoT-based industrial cyber-physical system (CPS) works in three generic steps: 1) Large data acquisition / dissemination: A physical process is monitored by sensors that pre-process the (assumed large) collected data and send the processed information to an intelligent node (e.g. aggregator, central controller); 2) Big data fusion: The intelligent node uses machine learning techniques (e.g. data clustering, pattern recognition, neural networks) to convert the received ("big") data to useful information to guide short-term operational decisions related to the physical process; 3) Big data analytics: The physical process together with the acquisition and fusion steps can be virtualized, building then a cyber-physical process, whose dynamic performance can be analysed and optimized through visualization (if human intervention is available) or artificial intelligence (if the decisions are automatic) or a combination thereof.

Funding Agency

Irish Research Council

Programme

Future and Emerging Technologies (FET), EC ERA-NET

Summary

The fifth generation (5G) wireless communication network is expected to connect everything and everyone, including the traditional human-to-human communications but also those between autonomous smart entities, like buildings, vehicles and sensors. Applying previous practical experience at Nokia Bell Labs in the design and implementation of cutting edge 5G massive MIMO prototypes, the aim of this PhD is to further develop and enhance the performance of 5G networks. One of the main challenges of this project is to deal with the 5G traffic heterogeneity, i.e., delivering a larger capacity for broadband services (e.g. virtual reality), while providing reliable services to a multitude of Internet of Things (IoT) devices. To address this challenge, the focus will be on a new 5G heterogeneous network comprised of two disruptive technologies, massive multiple-input multiple-output and millimetre-wave, proposing novel theoretical analysis tools and machine learning algorithms to realize an efficient integration of both technologies into the new network and providing an efficient radio resource management able to deal with network dynamics. A novel theoretical framework is needed to understand the performance of thousands of new 5G base stations communicating with millions of users, and gain key insights to develop tailored algorithms. Machine learning will be the basis of such algorithms, allowing for the first time to leverage the vast amount of information that millions of nodes can produce at the physical and medium access control layers. The outcome of this project will be novel analysis tools and algorithms that allow an efficient 5G operation, enhancing the network capacity by a factor of 100x as compared to current deployments, as well as the publication of research articles, patents and standardization contributions that will help define the technology advantage of Nokia Bell Labs and enhance the scientific contribution of the Irish ecosystem to the new communication era.

Funding Agency

Irish Research Council

Programme

Irish Research Council Enterprise Partnership Scheme 2016

Summary

The continuous expansion of wireless networks both in size and functionalities has seen a larger number of nodes communicating over multiple heterogeneous technologies which share precious spectrum and similar applications. This ranges from cellular networks to IoT and everything in between. Traditional centralised approaches cannot manage a very vast and data intensive network efficiently as there is not enough bandwidth to support the control data necessary and the latency of a central decision maker would be too high. On the other hand, it is very hard to determine how local actions will impact global performance and as such, some form of bird's eye view is necessary. The work is at the interface between traditional wireless communication, complex Systems and machine learning. The main objectives of his project are to determine scalable, hierarchical multi agent solutions which include emergent properties of wireless networks in the feedback loop between a highly abstracted centralised monitor and local but data intensive controllers.

Funding Agency

EC Marie Sklodowska-Curie Action & US Air Force Office of Scientific Research

Programme

COFUND EDGE