Eros Innocenti

Mr. Eros Innocenti

Marconi University, Rome, Lazio, Italy
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 July 2021 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
Romeo GiulianoRomeo Giuliano
Romeo Giuliano
Eros InnocentiEros Innocenti
Eros Innocenti
Franco MazzengaFranco Mazzenga
Franco Mazzenga
Anna Maria  VegniAnna Maria Vegni
Anna Maria Vegni
Alessandro VizzarriAlessandro Vizzarri
Alessandro Vizzarri
Recently, pushed by the COVID-19 pandemic, the need of respecting social distancing has motivated several researchers to define novel technological solutions to monitor and track user movements. Information and Communications Technologies (ICT) world has addressed this challenge by means of the use of different technologies, such as Bluetooth, in order to track user interdistance and encounter time. Technology solutions should be able to not only track contacts, but also alert users to restore social distancing. In this article, we present IMPERSONAL framework, with the twofold aim of both: 1) tracking and monitoring social distancing and 2) alerting users in case of gatherings. The framework is based on a subnetwork of computer vision-based devices that are adopted to monitor and track users’ movements to estimate their interdistance and compute the encounter time. Such information is then the input to an Internet of Things subnetwork, aiming to retrieve the anonymous IDs of people belonging to a gathering, as well as to send alert messages to them. We assess IMPERSONAL framework by means of extensive Monte Carlo simulations and experimental results, showing its effectiveness in terms of accuracy in correctly identifying users and gatherings in videos taken from live cameras, both in case of indoor and outdoor real scenarios. The benefits of the IMPERSONAL framework are expressed in terms of the ability to track people, solve gatherings, and send warning messages.

28 January 2023 in Electronics
Verified
Journal Article
Open access
PDF file
Romeo GiulianoRomeo Giuliano
Romeo Giuliano
Eros InnocentiEros Innocenti
Eros Innocenti
Traditionally, non-terrestrial networks (NTNs) are used for a limited set of applications, such as TV broadcasting and communication support during disaster relief. Nevertheless, due to their technological improvements and integration in the 5G 3GPP standards, NTNs have been gaining importance in the last years and will provide further applications and services. 3GPP standardization is integrating low-Earth orbit (LEO) satellites, high-altitude platform stations (HAPSs) and unmanned aerial systems (UASs) as non-terrestrial elements (NTEs) in the NTNs within the terrestrial 5G standard. Considering the NTE characteristics (e.g., traffic congestion, processing capacity, oscillation, altitude, pitch), it is difficult to dynamically set the optimal connection based also on the required service to properly steer the antenna beam or to schedule the UE. To this aim, machine learning (ML) can be helpful. In this paper, we present novel services supported by the NTNs and their architectures for the integration in the terrestrial 5G 3GPP standards. Then, ML techniques are proposed for managing NTN connectivity as well as to improve service performance.

9 February 2023 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
Valeria LoscriValeria Loscri
Valeria Loscri
CRCarola Rizza
Carola Rizza
ABAbderrahim Benslimane
Abderrahim Benslimane
Anna Maria  VegniAnna Maria Vegni
Anna Maria Vegni
Eros InnocentiEros Innocenti
Eros Innocenti
Romeo GiulianoRomeo Giuliano
Romeo Giuliano
In this work, we consider Reconfigurable Intelligent Meta-surfaces (RIMs) to provide effective beam steering functionality, while enhancing the coverage of the fifth generation (5G) users in a urban city mobility context. In particular, we enable communications in the millimeter wave (mmWave) frequencies, that can occur simultaneously with other 5G communications. The main objective of this paper is to demonstrate the feasibility and advantages of an integrated Computed Vision (CV) approach for tuning the meta-atom states of a RIM structure working at mmWave frequency band, without estimating the interferes' radio channel. In particular, the CV system will feed a logic unit running a Machine Learning (ML) algorithm to compute in real-time the coding schemes, namely the sequence of binary states associated to each unit-cell of the RIM, in order to obtain the target reconfigurable radiation pattern. Specifically, a Genetic Algorithm (GA) is introduced to derive the most suitable radiation pattern for Beam Steering application, based on the input of a CV infrastructure. Results show the feasibility of such a kind of system, with an higher coverage achieved in dense scenarios, by improving the robustness against the potential blockages introduced by the mmWave technology. Moreover, we demonstrate the system is robust against the inaccuracy introduced by the CV and GA.

1 September 2023
Verified
Conference Paper
Closed access
Romeo GiulianoRomeo Giuliano
Romeo Giuliano
Eros InnocentiEros Innocenti
Eros Innocenti
Franco MazzengaFranco Mazzenga
Franco Mazzenga
Alessandro VizzarriAlessandro Vizzarri
Alessandro Vizzarri
Luca Di NunzioLuca Di Nunzio
Luca Di Nunzio
IHIbrahim Habib
Ibrahim Habib
The integration of Non-Terrestrial Networks (NTNs) within the 6G framework provides full connectivity worldwide but some system procedures can be ineffective and should be modified for example in the timer thresholds, which may expire in NTN. Moreover, some procedures may also be affected by the different timeline of terrestrial networks and NTN. For example, the aging of the Channel State Information (CSI) collected by the User Equipment (UE) and sent to the gNode B (gNB) for the scheduler activities may affect its behavior reducing the user throughput, due to the high propagation latency in NTN and outdated data. In this paper we propose a strategy to overcome this problem by using a Transformer Neural Network (TNN) to predict the experienced Signal-to-Interference plus Noise Ratio (SINR) of a generic UE to the transmitting gNB. We assume a period in which the gNB receives frequently CSI/SINR reports by a given UE in order to train the TNN model. Next, the gNB uses data provided by the trained TNN to predict the UE channel behavior and then to properly select the best Modulation and Coding Scheme (MCS) for that UE, avoiding to transmit any CSI data. Results show that the throughput obtained with the TNN trained model is close to the highest CSI update rate (1 ms), while it is higher than the throughput obtained with a CSI update rate of 200 ms of about 5 Mbit/s in Sub-Urban environment for both always LOS and variable LOS/NLOS channel conditions, which corresponds to about a gain of 10 %.

18 October 2022 in Information
Verified
Journal Article
Open access
PDF file
Eros InnocentiEros Innocenti
Eros Innocenti
Giacomo AgostiniGiacomo Agostini
Giacomo Agostini
Romeo GiulianoRomeo Giuliano
Romeo Giuliano
Drone delivery has gained increasing importance in the past few years. Recent technology advancements have allowed us to think of systems capable of transporting and delivering goods precisely and efficiently. However, in order to switch from a test environment to a real environment, many open issues need to be addressed. In this paper, we focused on drop-off point localization based on fiducial markers, analyzing different systems and the configuration of different aspects. We tested our system in a real-world environment and drew conclusions which lead us to identify the most reliable fiducial system and family for this use case.

7 June 2021
Verified
Conference Paper
Open access
Valeria LoscriValeria Loscri
Valeria Loscri
Anna Maria  VegniAnna Maria Vegni
Anna Maria Vegni
Eros InnocentiEros Innocenti
Eros Innocenti
Romeo GiulianoRomeo Giuliano
Romeo Giuliano
Franco MazzengaFranco Mazzenga
Franco Mazzenga
Reconfigurable Intelligent Meta-surfaces (RIMs) are particular devices able to control and manipulate radio frequency wireless signals. This promising technology allows to improve the reliability of wireless networks, thanks to the capacity of reflecting the desired signals through appropriate phase shifts. The joint use of RIMs and Computer Vision (CV) technology is the main objective of this paper. This synergistic approach is used to correctly identify the specific configuration of a radiation pattern, to be used as input for computing optimal coding sequences of the RIM. Indeed, by the means of a CV algorithm it is possible to infer a connectivity graph related to a real scenario, where people is moving. The information about network nodes such as their distance, the relative position, etc. is used for feeding an intelligent logic, able to compute the optimal configuration for re-directing the signals towards a given receiver target node.Numerical results show the huge potentiality of this combined approach in terms of interference reduction. It has been observed that for high traffic load, it is possible to reduce the average interference in the network of 40%. Furthermore, an analysis including the positioning estimation error of the CV algorithm has been addressed, in order to consider how it affects the interference reduction. Results show that, even though there is an increasing effect of interference, when the error is accounted, the interference reduction impact is still important.