A carregar...
Projeto de investigação
Sem título
Financiador
Autores
Publicações
A Low Complexity Linear Precoding Method for Extremely Large-Scale MIMO Systems
Publication . Berra, Salah; Benchabane, Abderrazak; Chakraborty, Sourav; Maruta, Kazuki; Dinis, Rui; Beko, Marko; Faculdade de Ciências e Tecnologia (FCT); Institute of Electrical and Electronics Engineers (IEEE)
Massive multiple-input multiple-output (MIMO) systems are critical technologies for the next generation of networks. In this field of research, new forms of deployment are emerging, such as extremely large-scale MIMO (XL-MIMO), in which the antenna array at the base station (BS) is of extreme dimensions. As a result, spatial non-stationary features emerge as users view just a section of the antenna array, known as the visibility regions (VRs). The XL-MIMO systems can achieve higher spectral efficiency, improve cell coverage, and provide significantly higher data rates than standard MIMO systems. It is a promising technology for future sixth-generation (6G) networks. However, due to the large number of antennas, linear precoding algorithms such as Zero-Forcing (ZF) and regularized Zero-Forcing (RZF) methods suffer from unacceptable computational complexity, primarily due to the required matrix inversion. This work aims to develop low-complexity precoding techniques for the downlink XL-MIMO system. These low-complexity linear precoding methods are based on Gauss-Seidel (GS) and Successive Over-Relaxation (SOR) techniques, which avoid calculating the complex matrix inversion and lead to stable linear precoding performance. To further enhance linear precoding performance, we incorporate the Chebyshev acceleration method with the SOR and GS methods, referred to as the Cheby-SOR and Cheby-GS methods. As these proposed methods require optimizing parameters, we create a deep unfolded network (DUN) to optimize the algorithm parameters. Our performance results demonstrate that the proposed method significantly reduces computational complexity from to O K2, where K represents the number of users. Moreover, our approach outperforms the original algorithms, requiring only a few iterations to achieve the RZF bit error rate (BER) performance.
Automatic Event Detection For Motorsports Integrating Computer Vision Techniques with Racing Events
Publication . Fernandes, Duarte Pereira; Silvestre, Daniel; Frazão, Xavier
The current surge in popularity of specific motorsports, particularly Formula 1, has led
to an increasing number of individuals seeing races via streaming platforms. For anyone
unable to attend the event physically, these services offer comprehensive coverage of
the races. Streaming providers should provide a shortened version of the race that
encompasses all significant moments for viewers with limited time. This method enables
spectators to remain apprised of the critical advancements in the race.
The primary focus of this thesis will be the development of an application that effec-
tively delivers a condensed version of a race. This document examines previously created
and validated solutions for various sports and applies these concepts to an application
designed to automatically recognize events in motorsports. The developed solution will
employ techniques including optical character recognition and image similarity algorithms.
LSTM-Based Trajectory and Phase-Shift Prediction for RSMA Networks Assisted by AIRS
Publication . Sousa Lima, Brena Kelly; Matos-Carvalho, João Pedro; Dinis, Rui; da Costa, Daniel Benevides; Beko, Marko; Oliveira, Rodolfo; CTS - Centro de Tecnologia e Sistemas; DEE - Departamento de Engenharia Electrotécnica e de Computadores; Institute of Electrical and Electronics Engineers (IEEE)
This paper investigates rate-splitting multiple access (RSMA) networks with multiusers assisted by aerial intelligent reflecting surfaces (AIRS). To improve the sum-rate of the system, the UAV’s trajectory and phase-shift vectors are optimized, in which the mobility scenarios with static and dynamic users are explored. In particular, long short-term memory (LSTM)-based frameworks for predicting the UAV’s trajectory and the phase-shift of the reflecting elements of AIRS are proposed. For more insight, a third model is created by combining information from the static and dynamic scenarios. Furthermore, to improve the transmit beamforming at the BS, an algorithm based on alternating optimization (AO) under the assumptions of imperfect successive interference cancelation (SIC) is presented. Training progress and testing results are provided to demonstrate the efficiency of the proposed models. In addition, numerical simulations are presented to verify the performance gains in terms of sum-rate. The simulation results show that the UAV performs better in trajectory prediction and phase-shift when different investigated scenarios are not combined.
Prevention of forest fires using computer vision
Publication . Tavares, Afonso Brito Caldeira Viegas; Silvestre, Daniel
The increase in both the number and size of fires demonstrates an urgent need for
new and innovative interventions, not only in firefighting, but also in prevention, since
firefighting is far more efficient when combined with improved prevention strategies.
One of the most effective methods of preventing the spread of fires is to ensure that
fields, especially tree plantations, are regularly trimmed and cleaned, preventing fire from
spreading from the ground to the tree canopy, making it tremendously difficult to control
and extinguish a fire.
The use of videos of tree plantations taken by an Unmanned Aerial Vehicle (UAV) and
the subsequent creation of an algorithm that processes them, with the use of computer
vision and OpenCV algorithms, has the effect of significantly reducing the laborious
task of checking whether parts of a field are cleaned. This process eliminates the need
for human intervention and reliance on a database of images of trees to create a neural
network model.
The script implemented is designed to process and compare two videos, one repre-
senting a clean field of a tree plantation and the other representing the same plantation
after some time (with potential overgrowth). The objective is to identify tree trunks that
are occluded by vegetative growth and require cleaning.
Although further testing of the algorithm is required in order to guarantee its efficacy
in a broader range of scenarios and with a greater quantity of data, the results of this work
are promising.
Conceptual Design of an Unmanned Electrical Amphibious Vehicle for Ocean and Land Surveillance
Publication . Policarpo, Hugo; Lourenço, João P.B.; Anastácio, António M.; Parente, Rui; Rego, Francisco; Silvestre, Daniel; Afonso, Frederico; Maia, Nuno M.M.; CTS - Centro de Tecnologia e Sistemas; Faculdade de Ciências e Tecnologia (FCT); MDPI AG
Unmanned vehicles (UVs) have become increasingly important in various scenarios of civil and military operations. The present work aims at the conceptual design of a modular Amphibious Unmanned Ground Vehicle (A-UGV) that can be easily adapted for different types of land and/or water missions with low monetary cost (EUR < 5 k, without sensors). Basing the design on the needs highlighted in the 2021 review of the Strategic Directive of the Portuguese Navy, the necessary specifications and requirements are established for two mission scenarios. Then, a market research analysis focused on vehicles currently available and their technological advances is conducted to identify existing UV solutions and respective characteristics/capabilities of interest to the current work. To study and define the geometry of the hull and the configuration of the A-UGV itself, preliminary computational structural and fluid analyses are carried out to ensure it complies with the specifications initially established. As a result, one obtains a fully electric vehicle with approximate dimensions of 1050 × 670 × 450 mm (length–width–height), enabled with 6 × 6 traction capable of reaching 20 km/h on land, which possesses amphibious capabilities of independent propulsion in water up to 8 kts and an estimated autonomy of over 60 min.
Unidades organizacionais
Descrição
Palavras-chave
Contribuidores
Financiadores
Entidade financiadora
Fundação para a Ciência e a Tecnologia
Programa de financiamento
Concurso de avaliação no âmbito do Programa Plurianual de Financiamento de Unidades de I&D (2017/2018) - Financiamento Base
Número da atribuição
UIDB/04111/2020