About
253
Publications
58,715
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
3,481
Citations
Introduction
His work focuses on machine learning and signal processing for communications and embedded systems.
Skills and Expertise
Publications
Publications (253)
Digital twins are an important technology for advancing mobile communications, specially in use cases that require simultaneously simulating the wireless channel, 3D scenes and machine learning. Aiming at contributing towards a solution to this demand, this work describes a modular co-simulation methodology called CAVIAR, for implementing the virtu...
In distributed multiple-input multiple-output (D-MIMO), a large number of distributed antenna points (APs) are coordinated by a central processing unit (CPU) to serve a limited number of users at the same time/frequency resources, which brings improvements in spectral efficiency. The success of D-MIMO relies on precoding and power allocation, where...
RESUMOO monitoramento contínuo da qualidade da energia elétrica (QEE)é essencial para fornecedores e consumidores de energia elétrica.Dentre as métricas avaliadas, as distorções harmônicas são distúrbiosem frequência indesejados nos sistemas elétricos e, por isso,são importantes parâmetros de QEE. O cálculo da Transformada Rápidade Fourier (FFT) é...
Modern wireless communication systems rely heavily on multiple antennas and their corresponding signal processing to achieve optimal performance. As 5G and 6G networks emerge, beamforming and beam management become increasingly complex due to factors such as user mobility, a higher number of antennas, and the adoption of elevated frequencies. Artif...
The performance of modern wireless communication systems is highly dependent on the adoption of multiple antennas and the associated signal processing. In 5G and 6G networks, beamforming and beam management become challenging tasks due to aspects such as user mobility, increased number of antennas, and the adoption of higher frequencies. Artificial...
Network slicing at the radio access network (RAN) domain, called RAN slicing, requires elasticity, efficient resource sharing, and customization. In this scenario, radio resource scheduling (RRS) is responsible for dealing with scarce and limited frequency spectrum resources available at the RAN domain while fulfilling the slice intents. The wide v...
It is challenging to generate wireless channels for 5G/6G scenarios with sophisticated mobility patterns. Raytracing (RT) is one of the most adopted techniques, especially when 5G/6G millimeter frequency bands are considered. However, most ray tracers, such as Wireless InSite and Sionna’s, provide limited support to mobility: only the radio transce...
The virtualized radio access network (vRAN) placement problem consists of jointly choosing a functional split and the placement of virtualized network functions on vRAN nodes scattered in the network. The most prominent solutions present optimal approaches to solve the problem, but they are computationally expensive for large instances. Non-exact a...
Disaggregated and virtualized RANs (vRANs) offer the opportunity for flexible and efficient use of computing resources through the proper placement of the RAN Virtualized Network Functions (VNFs). However, many works neglect the necessary coordination between VNF placement and the processing of the RAN tasks inside these VNFs. This can negatively i...
Abstract—Machine learning has become a powerful tool for
improving vehicle-to-vehicle (V2V) communication systems, and
in general requires large datasets for model training and assessment.
However, creating large and realistic datasets using
field measurements is challenging due to the large bandwidths
involved and usage of multiple antennas. Simul...
The telecommunication system being a critical pillar of emergency management, intelligent deployment and management of slices in an affected area will help emergency responders. Techniques such as automated management of Machine Learning (ML) pipelines across the edge and emergency responder devices, usage of hierarchical closed-loops, and offloadi...
The fifth generation of mobile networks evolved to serve applications with distinct requirements, which results in a high management complexity due to simultaneous real-time tasks. In the physical layer, code words that allow proper data exchange between the Base Station (BS) and the served users must be chosen. While, in higher layers, the BS must...
Linear prediction and entropy coding are widely used in speech, audio, video, and other coding systems. Rate-distortion optimization (RDO) is another relevant coding technique, which is especially useful when the encoder performance depends on tunable parameters from distinct coding subsystems. This work presents a RDO strategy for variable-rate en...
Unmanned Aerial Vehicles (UAVs) and communication systems are fundamental elements in mission critical services, such as search and rescue. In this article, we introduce an architecture for managing and orchestrating 5G and beyond networks that operate over a heterogeneous infrastructure with UAVs' aid. UAVs are used for collecting and processing d...
Digital representations of the real world are being used in many applications, such as augmented reality. 6G systems will not only support use cases that rely on virtual worlds but also benefit from their rich contextual information to improve performance and reduce communication overhead. This paper focuses on the simulation of 6G systems that rel...
In recent years, technology-based studies have surfaced due to the growing interest in the global problem of antibiotic resistance, especially in the bioinformatics field applied to metagenomics, which is able to represent the microorganism and its associated genes in terms of antibiotic resistance. This paper aims to present a novel approach to ca...
This work evaluates the O-RAN compression methods specified for in-phase and quadrature (IQ) data compression, which are applied to transport the frequency domain representation of the radio signals. The methods were evaluated in terms of computational cost and quantization-noise ratio vs IQ bit-width. It was found that the O-RAN compression algori...
Fifth-generation (5G) cellular communication systems have embraced massive multiple-input-multiple-output (MIMO) in the low- and mid-band frequencies. In a multiband system, the base station can serve different users in each band, while the user equipment can operate only in a single band simultaneously. This paper considers a massive MIMO system w...
Digital representations of the real world are being used in many applications, such as augmented reality. 6G systems will not only support use cases that rely on virtual worlds but also benefit from their rich contextual information to improve performance and reduce communication overhead. This paper focuses on the simulation of 6G systems that rel...
In the context of Fifth Generation mobile networks (5G), Search and Rescue (SAR) missions using Unmanned Aerial Vehicles (UAVs) can benefit from a dynamic, intelligent, and autonomous placement of both Network Functions (NFs) and Artificial Intelligence (AI) systems to quickly adapt in minimal human intervention scenarios. This article examines cur...
Devido às medidas de distanciamento social implementadas durante a pandemia Covid-19, várias instituições de ensino superior estão usando aplicativos de Internet para fornecer conteúdo instrutivo aos seus alunos. No entanto, há uma desigualdade generalizada no acesso a esses recursos. Neste trabalho, modelamos a dispersão do sinal de Internet móvel...
With the advent of 5G, more stringent application requirements were imposed to the cellular networks. The adoption of Software Defined Network (SDN) technology in the transport network enables more dynamic network control, suitable for several real-time operations and use cases present in 5G deployments. Implementing testbed for various transport n...
Some 6G use cases include augmented reality and high fidelity holograms, with this information flowing through the network. Hence, it is expected that 6G systems can feed machine learning algorithms with such context information to optimize communication performance. This paper focuses on the simulation of 6G MIMO systems that rely on a 3-D represe...
The increasing complexity of configuring cellular networks suggests that machine learning (ML) can effectively improve 5G technologies. Deep learning has proven successful in ML tasks such as speech processing and computational vision, with a performance that scales with the amount of available data. The lack of large datasets inhibits the flourish...
Some 6G use cases include augmented reality and high-fidelity holograms, with this information flowing through the network. Hence, it is expected that 6G systems can feed machine learning algorithms with such context information to optimize communication performance. This paper focuses on the simulation of 6G MIMO systems that rely on a 3-D represe...
This work proposes a compression method developed to transport radio signals over a centralized radio access network using a functional split in which the fronthaul transports frequency-domain samples. The proposed method allows detecting which subcarriers from an LTE/NR OFDM symbol are inactive to avoid sending them over the fronthaul, hence decre...
We consider the problem of channel estimation in low-resolution multiple-input multiple-output (MIMO) systems operating at millimeter wave (mmWave) and present a deep transfer learning (DTL) approach that exploits previously trained models to speed up site adaptation. The proposed model is composed of a feature extractor and a regressor, with only...
Unmanned aerial vehicles (UAVs) and communication systems are fundamental elements in Mission Critical services, such as search and rescue. In this article, we introduce an architecture for managing and orchestrating 5G and beyond networks that operate over a heterogeneous infrastructure with UAVs' aid. UAVs are used for collecting and processing d...
This work explores clock synchronization algorithms used to process timestamps from the IEEE 1588 precision time protocol (PTP). It focuses on the PTP-unaware network scenario, where the network nodes do not actively contribute to PTP’s operation. This scenario typically imposes a harsh environment for accurate clock distribution, primarily due to...
Millimeter wave (mmWave) carrier frequencies, a key feature of 5G cellular systems, are ideally suited to provide high data rates thanks to higher‐bandwidth channels. This chapter explains the potential of mmWave for unmanned aerial vehicles (UAVs). Then it summarizes important considerations for propagation at millimeter wave frequencies and revie...
The fifth-generation (5G) cellular networks incorporate a large variety of technologies in order to address very distinct use cases. Assessing these technologies and investigating future alternatives is complicated when one relies only on simulators. 5G testbeds are an important alternative to simulators and many have been recently described, empha...
Nos últimos anos, o particionamento de redes neu-rais profundas vem ganhando atenção de pesquisadores, pois permite implementar tais redes com uma combinação de proces-samento local em dispositivos de baixo poder computacional e processamento em nuvem. Neste artigo,é proposto um método de compressão que utiliza normalização de bloco e quantização e...
Drones, also known as unmanned aerial vehicles (UAVs), plays a fundamental role in the applications envisioned for 5G and beyond 5G (B5G), with several studies in topics such as UAV-assisted wireless networks, product shipping, traffic monitoring, and surveillance, to name a few. In this context, channel modeling is an essential step in using drone...
Fifth generation (5G) mobile networks are adopting several techniques to provide higher data rates while meeting strict latency requirements. Advanced compression techniques and distributed data processing are among them supporting cost efficient network deployments. Also, the usage of machine learning techniques to optimize telecommunication syste...
This paper presents a feasibility study of performing equipment inspection on networked environments by exploring networks specially designed for semantic segmentation task. It is assumed that the neural network needs to be split and the resulting two pieces need to be allocated in two devices. The provided results suggest that the current state of...
This article presents an energy consumption analysis of two differentemulation scenarios of a GSM (Global System for Mobile)network; one with a traditional computer and another with RaspberryPi 3. The network is created by open-source software thatemulates the main modules of a GSM network, this emulation combinedwith a radio generator equipment en...
We propose an SNR estimation procedure for systems that transmit frequency-multiplexed analog signals in a channel. It is agnostic to the type of radio signal transmitted, can be performed without increasing the required bandwidth, and without interrupting the transmission of the signals. We simulate the transmission of frequency-multiplexed OFDM s...
This work investigates a mechanism for alignment of the timing on which spatially distributed and cooperative radio units transmit in radio-frequency (RF) when served over a packet-based fronthaul. It analyzes the problem by considering the imperfect clock synchronization of the radio units and the packet delay variation that fronthaul packets are...
Millimeter waves is one of 5G networks strategies to achieve high bit rates. Measurement campaigns with these signals are difficult and require expensive equipment. In order to generate realistic data this paper refines a methodology for virtual measurements of 5G channels, which combines a simulation of urban mobility with a ray-tracing simulator....
Unmanned Aerial Vehicles (UAVs) became very popular in a vast number of applications in recent years, especially drones with computer vision functions enabled by on-board cameras and embedded systems. Many of them apply object detection using data collected by the integrated camera. However, several applications of real-time object detection rely o...
Virtualization is a key feature in Cloud Radio Access Network (C-RAN). It can help to save costs since it allows the use of virtualized base stations instead of physically deployment in different areas. However, the creation and management of virtual base stations pools is not trivial and introduces new challenges to C-RAN deployment. This paper re...
This paper presents a compression scheme developed for the transport of downlink radio signals in packet fronthaul of centralized-radio access networks (C-RAN). The technique is tailored to frequency-domain functional splits, in which inactive LTE (or 5G NR) resource elements may not be transmitted in the packets. This allows decreasing the link da...
Considerando o volume de dados produzidos diariamente por centros medico-hospitalares, algoritmos de compressão para imagens médicas representam uma alternativa para reduzir custos de transmissão e armazenamento em sistemas PACS. Nesse caso, esquemas adaptativos podem maximizar a compressão evitando a perda de qualidade visual e, por conseguinte, o...
Currently, there are about 3.6 billion people in the world without any kind of Internet access. Parallel to this, we have the connectivity as a fundamental part for insertion of the individual in a globalized society. Thus, with the understanding of Internet access as a basic right of citizenship, the concept of community networks arises. This netw...
Redes comunitárias são opções para conectividade em regiões isoladas que não possuem nenhum tipo de serviços de telecomunicações. Estas localidades não são atrativas financeiramente para as grandes concessionárias de telecomunicações que acabam por não provir seus serviços nestas regiões. Tratando-se de inclusão digital, um dos vários esforços feit...
The increasing usage of unmanned aerial vehicles in object detection and inspection called for the development and optimization of several computer vision algorithms. Deep learning in particular is showing outstanding results in similar use cases, mainly due to its great capabilities of learning good feature representations from raw data. This work...
C-RAN virtualization is a research topic with great interest since it allows to share baseband processing resources.Therefore, in this work, we report the implementation of a virtualized LTE testbed environment of C-RAN by integrating the OpenAirInterface (OAI) with Docker. Using the test bed,we conducted a workload study to understand the computat...
Millimeter wave communication systems can leverage information from sensors to reduce the overhead associated with link configuration. LIDAR (light detection and ranging) is one sensor widely used in autonomous driving for high resolution mapping and positioning. This paper shows how LIDAR data can be used for line-of-sight detection and to reduce...
5G networks will provide the platform for deploying large number of tenant-associated management, control and end-user applications having different resource requirements at the infrastructure level.In this context, the 5G infrastructure provider must optimize the infrastructure resource utilization and increase its revenue by intelligently admitti...
The use of higher frequencies and MIMO is important in many 5G use cases. However, the available channel models for millimeter waves (mmWaves) currently demand investigation and the number of measurements is still limited. Using simulators is a current practice in mmWave MIMO research and ray tracing is considered one of the most accurate technique...
5G networks will provide the platform for deploying large number of tenant-associated management, control and end-user applications having different resource requirements at the infrastructure level. In this context, the 5G infrastructure provider must optimize the infrastructure resource utilization and increase its revenue by intelligently admitt...
This work describes the implementation of a satellite tracking technique in a real antenna control system. The technique uses least squares estimation to search for the best antenna pointing position to receive the satellite beacon signal tracked in the 2D region created by the motion axes. The work also presents the technique implementation result...
G.fast is one of the most recent DSL system standardized by ITU. It aims to achieve transmission rates of the order of Gbps over short loops, using bandwidth of 106 MHz or 212 MHz. Owing to its large bandwidth, the G.fast is susceptible to interference from a wide range of sources, one of the most damaging being alien crosstalk. This study provides...
Millimeter wave communication systems can leverage information from sensors to reduce the overhead associated with link configuration. LIDAR (light detection and ranging) is one sensor widely used in autonomous driving for high resolution mapping and positioning. This paper shows how LIDAR data can be used for line-of-sight detection and to reduce...
An essential aspect of the network paradigm called Named Data Networking (NDN) is that all nodes in the network have the ability to cache contents natively. The focus of this work relies on efficiently choosing which content should be removed from a full cache to allow storing another one. We propose a new caching replacement algorithm for NDN netw...
Several forwarding strategies (FS) were already proposed to leverage packet delivery in information-centric networking (ICN). However, less attention has been given to FS potential to improve quality of service (QoS) in ICN. This work addresses the impact of FS on the performance of voice application, video streaming and file transfer protocol (FTP...
Establishing and tracking beams in millimeter-wave (mmWave) vehicular communication is a challenging task. Large antenna arrays and narrow beams introduce significant system overhead configuring the beams using exhaustive beam search. In this paper, we propose to learn the optimal beam pair index by exploiting the locations and types of the receive...
Introduction Several speech processing algorithms assume the signal is stationary during short intervals (approximately 20 to 30 ms). This assumption is valid for several applications, but it is too restrictive in some contexts. This work investigates the application of adaptive signal processing to the problem of estimating the formant frequencies...
Information-centric networking (ICN) is one of the most promising research topics for the future Internet. ICN aims at circumventing several issues of current Internet protocol (IP) solutions such as efficient multimedia distribution. Given the huge growth rate of video transmission over mobile networks, it is sensible to consider how 4G/5G network...