About
333
Publications
55,659
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
3,862
Citations
Introduction
Additional affiliations
February 2013 - present
Publications
Publications (333)
Federated Learning (FL) is a distributed approach to collaboratively training machine learning models. FL requires a high level of communication between the devices and a central server, thus imposing several challenges, including communication bottlenecks and network scalability. This article introduces ACSP-FL (https://github.com/AllanMSouza/ACSP...
Integrating big data and deep learning across various applications has significantly enhanced intelligence and efficiency in our daily lives. However, it also requires extensive data sharing, raising significant communication and privacy concerns. In this context, Federated Learning (FL) emerges as a promising solution to enable collaborative model...
There is a exponential growth of data usage, specially due to the proliferation of connected applications with personalized models for different applications. In this context, Federated Learning (FL) emerges as a promising solution to enable collaborative model training while preserving the privacy and autonomy of participating clients. In a typica...
Federated Learning (FL) emerges as a promising solution to enable collaborative model training for autonomous vehicles while preserving privacy and communication overhead issues. An efficient selection of clients to participate in the training process is still challenging, especially in scenarios with statistical heterogeneity of data distribution...
This article focuses on the challenge of providing services and applications by a swarm of mobile flying devices, which may belong to the same tenant or not. Starting by introducing the concepts of mobile edge computing and fog computing, this work shows how the latter can be leveraged to create a novel framework of airborne fog computing. This art...
91.501-970 | aassilva@inf.ufrgs.br ], and [ Hamm-Lippstadt University of Applied Sciences, 59063 Hamm, Germany | antonio.santosdasilva@hshl.de ] Paulo Mendes [ Airbus, Willy-Messerschmitt-Strasse 1, 82024 Taufkirchen, Ger-many | paulo.mendes@airbus.com ] Denis Rosário [ Federal University of Pará | denis@ufpa.br ] Eduardo Cerqueira [ Federal...
Os sistemas de condução autônoma utilizam frequentemente o Aprendizado por Imitação Condicional (Conditional Imitation Learning (CIL)) para aprender o comportamento da direção humana. No CIL, um conjunto de dados com demonstrações de um condutor é usado para treinar um modelo que replica o seu comportamento de condução. No entanto, a capacidade de...
As urban areas continue to expand, the infrastructural systems within these regions face multifaceted challenges that detrimentally affect inhabitants’ health and quality of life. The advent of smart urban mobility technologies has introduced a persistent surveillance mechanism over the movement patterns of individuals and the ambient environmental...
A crescente conexão de dispositivos na internet intensifica o uso de recursos de rede, destacando a Realidade Aumentada Multiusuário (RAMU), que combina elementos virtuais com o ambiente real, proporcionando uma experiência imersiva. Este serviço pode ser dividido em Cadeias de Funções de Serviço (SFCs) e distribuído entre servidores de borda, perm...
À medida que a demanda por mobilidade urbana cresce, surgem mais serviços que oferecem roteamento e sugestões de trajetos. No entanto, esses serviços geralmente se concentram apenas no tempo ou na distância da viagem, deixando de lado as preferências individuais dos usuários. Este estudo apresenta um sistema inovador de seleção de rotas que é multi...
O-RAN is an architecture that promotes interoperability and openness in 5G Radio Access Networks (RAN) using scheduling, disaggregation, and virtualization. RICs (RAN Intelligence Controllers) offer solutions such as Machine Learning (ML), traffic steering, anomaly detection, and QoS (Quality of Service) support. Novel intelligent handover strategi...
With population growth in urban areas, the more extensive city infrastructure faces several problems affecting the population’s health and quality of life. In this context, smart urban mobility solutions perform a ubiquitous way of sensing the population mobility and the local mobility context, such as criminality, accidents, and air quality near t...
O crescimento da disponibilidade de serviços de recomendação de rotas é uma consequência do aumento da necessidade de locomoção. Porém, tais serviços, em sua maioria, baseiam-se principalmente no tempo e distância das rotas, desconsiderando preferências individuais dos usuários. Este trabalho propõe um modelo de seleção de rotas multicritério e mul...
Os sistemas sem fio atuais, como as redes 5G, tem integrado recursos de Mobile Edge Computing (MEC). No entanto, ainda enfrentam desafios na entrega eficiente desses serviços a utilizadores móveis em cenários densos e dinâmicos. Este artigo apresenta o COOP, um algoritmo para otimizar redes terrestres assistidas por veículos aéreos não tripulados (...
A Realidade Aumentada Multiusuário (RAMU) usa computação em borda para colaboração em ambiente 3D em dispositivos móveis. Esse serviço pode ser decomposto em Service Function Chainings (SFCs) distribuídas em servidores de borda, permitindo execução paralela de usuários. Propomos a Orquestração de Encadeamento de Funções de Serviço Multicritério e S...
Novas aplicações que demandam conexões mais velozes e flexíveis impulsionam o crescimento de tráfego de internet e testam os limites da arquitetura atual de redes ópticas. Neste contexto, redes ópticas elásticas com multiplexação por divisão espacial (SDM-EONs) tornam-se candidatas importantes para substituir e aprimorar o padrão atual, uma vez que...
O artigo relata como as iniciativas de transformação digital podem ser conduzidas de maneira alinhada com o desenvolvimento sustentável, respeitando as necessidades e características regionais. Especial destaque é dado às iniciativas para criação de cidades sustentáveis e inclusivas, em consonância com os objetivos de desenvolvimento sustentável (O...
Federated Learning (FL) has rapidly become a crucial paradigm for training Machine Learning (ML) models when datasets are spread across several devices without compromising the privacy of the data owners. In vehicular networks, FL can be used to train driving models and object detection and classification over sensitive datasets to continuously imp...
Today, grid resilience as a feature has become non-negotiable, significantly when power interruptions can impact the economy. The widespread popularity of Intelligent Electronic Devices (IED) operating as smart meters enables an immense amount of fine-grained electricity consumption data to be collected. However, risk can still exist in the Smart G...
Unmanned Aerial Vehicles (UAVs) will be part of last-mile 5G/6G networks and will support Internet of Things (IoT) and low latency services in Flying Edge Computing (FEC). UAVs will densely populate aerial space in smart cities, providing networking and computing to interactive and monitoring services to ground users. FEC is composed of one or a se...
Time is a crucial and sensitive matter in most In-ternet of Things (IoT)-based systems and applications, includingin areas with intermittent connectivity. This paper focuses on thechallenge of deploying and executing services for IoT applicationsin intermittent networks based on the resources available by aswarm of drones. This paper shows how a se...
Considering that one of the goals of the future network generations is to provide ubiquitous communication in the most diverse scenarios to achieve high connection coverage, it is foreseen that the use of unmanned aerial vehicles as flying base stations (UAV-BSs) can potentially extend the network and communication range. UAVs as flying base statio...
This paper presents a study on the performance of Machine Learning techniques for the task of determining each of the electronics systems connected within the same electrical network, in the Internet of Smart Grid Things (IoSGT) architecture. This is regarded as an ecosystem which has cutting-edge technologies that work together to enable advanced...
Vehicular Edge Computing (VEC) is a promising paradigm that provides cloud computing services closer to vehicular users. In VEC, vehicles and communication infrastructures can form pools with computational resources to meet vehicular services with low-latency constraints. These resource pools are known as Vehicular Cloud (VC). The usage of VC resou...
People in smart cities tend to be constantly connected, and wireless connection technologies have become necessary in their routines. The Long Range Wide-Area Network protocol provides a resource allocation mechanism called Adaptive Data Rate that allocates the transmission parameters to increase scalability and reduce the devices’ power consumptio...
O aprendizado federado (Federated Learning – FL) é uma abordagem distribuída para o treinamento colaborativo de modelos de aprendizado de máquina. O FL requer um alto nível de comunicação entre os dispositivos e um servidor central, assim gerando diversos desafios, incluindo gargalos de comunicação e escalabilidade na rede. Neste trabalho, introduz...
Sub-GHz communication provides long-range coverage with low power consumption and reduced deployment cost. LoRa (Long-Range) has emerged, among existing LPWAN (Low Power Wide Area Networks) technologies, as a promising physical layer alternative to provide ubiquitous connectivity to outdoor IoT devices. LoRa modulation technology supports adapting...
A smartphone can collect behavioral data without requiring additional actions on the user's part and without the need for additional hardware. In an active or continuous user authentication process, information from integrated sensors, such as touch, and gyroscope, is used to monitor the user continuously. These sensors can capture behavioral (touc...
Smart urban mobility emerged from the urban citizen's need for a fast urbanization environment, using personal devices and city infrastructure integration, data generation, and mobility services provided on congested and possibly dangerous urban roads. However, traditional routing services need to consider users' experience, comfort and health beca...
Due to poor local range of the perception and object recognition mechanisms used by autonomous vehicles, incorrect decisions can be made, which can jeopardize a fully autonomous operation. A connected and autonomous vehicle should be able to combine its local perception with the perceptions of other vehicles to improve its capability to detect and...
Among the main problems faced in the context of electric mobility today, the management and monitoring of electric vehicle charging stations, the integration between the diverse types of technologies that make up its architecture, and its low scalability stand out. Therefore, we will present the implementation and complete integration of an electri...
In recent years, the introduction of new technologies and applications connected to the Internet has demonstrated the physical incapacity of current optical backbone networks in providing resources soon. One of the main proposals to deal with this problem today is space-division multiplexing elastic optical networks. However, to transport the massi...
Location-aware services provide valuable information for capturing human mobility patterns. In this context, analyzing the mobility dynamics, such as the means of transportation and their speeds, leads to better solutions by understanding the underlying data generating process and identifying different patterns. Strategies based on extracting Infor...
The prominence of the SG-toCloud continuum will pave the way towards advanced Smart Grid (SG) ecosystems and will enable cutting Edge applications and servers into the power energy vertical at unprecedented innovation levels. During the design of future Smart Grid ecosystems, legacy Intelligent Eletronic Device (IED) cannot be left behind, whereby...
This paper presents the Internet of Smart Grid Things (IoSGT) architecture, which is understood as an ecosystem of cutting-edge technologies that work together to enable advanced SG applications, which run at core/edge cloud datacenter premises connecting an underlying IoT networking infrastructure. The IoT-to-Edge-to-Cloud continuum paradigm that...
With the popularity of Unmanned Aerial Vehicles (UAVs), there is an increasing demand for autonomous navigation applications, which require the use of high-definition mapping techniques of the environments. However, in highly dynamic environments, maps need to be updated regularly, which has an impact on the path planning algorithms used by the aut...
The introduction of new technologies and applications connected to the Internet has demonstrated the inability of current optical networks to provide resources for next-generation Internet. Although the emergence of elastic optical networks with space-division multiplexing has shown to be a promising solution to deal with the capacity problem, some...
With the growth of the urban population, the urban mobility infrastructure suffers several types of problems, such as the more significant occurrence of traffic jams, which directly affects the quality of life of the population and the inhabitants who need to use different types of transport, also generating a more extraordinary occurrence of air p...
Electric vehicles are a promising option to contribute to energy diversification and the goal of reducing greenhouse gas emissions. However, as the market grows, the demand for charging stations increases, which requires a new structure to manage them. Internet of Things (IoT) technologies stand out as one of the most prominent strategies, as elect...
Wearables today play a key role in E-Health computing , with investments expected to exceed $70 billion by 2024. With the massive use of apps on wearable devices, it is crucial to improve safety when using wearables, considering that important information about user information is stored on these devices. We present SOMEONE ensemble learning, a set...
Levando em consideração a rápida modernização dos veículos, que os direciona para entidades cada vez mais inteligentes e conectadas, surge o paradigma de Computação de Borda Veicular. Esse paradigma fornece serviços de computação em nuvem mais próximos dos usuários veiculares através da agregação dos recursos de veículos, a qual é denominada formaç...
A Computação de Borda Veicular é um paradigma promissor que fornece serviços de computação em nuvem próximo dos usuários veiculares. Veículos e infraestruturas de comunicação podem cooperativamente atender serviços veiculares com restrições de baixa latência através da formação de nuvens veiculares e utilização dos recursos computacionais dessas nu...
O estado núcleo da rede alerta sobre a necessidade de mudanças para que seja entregue aos usuários o desempenho que se espera de redes de alta velocidade. Como solução para a expansão da rede é discutida a implantação das Redes Ópticas Elásticas com Multiplexação por Divisão Espacial, que introduz um novo problema para a gestão de recursos nessa re...
A crescente popularização de aplicações e dispositivos conectados à Internet evidenciou que as tecnologias atuais de backbone não suportarão a demanda prevista para as próximas décadas. Nesse contexto, as redes ópticas elásticas com multiplexação por divisão espacial (SDM-EON) tem tomado grande aceitação pela comunidade científica como possível sol...
Long Range Wide Area Network (LoRaWAN) emerges to connect devices that require long-range and low-cost (bandwidth and power) communication services. In this context, the adoption of this technology brings new challenges due to the densification of IoT devices, which causes signal interference and affects the QoS directly. On the other hand, the LoR...
This Special Section focused on gathering the most recent scientific research and insights on the evolution of communication architectures and protocols able to boost the creation of a truly global internet by means of the integration of the current internet with a new
Internet of Space
; how to support the operation of Tier-1, Tier-2, or even Ti...
In recent years, global communication has undergone intense transformations, especially in its use. The post-pandemic world shows new everyday situations where the connection needs specific characteristics, such as low latency, higher reliability, and higher bandwidth, among other things. The Space Division Multiplexing Elastic Optical Networks pro...
In modern networks, edge computing will be responsible for processing and learning from the critical network-and user-generated data, such as wireless link usage, mobility information, application requests, and many others. The presence of Artificial Intelligence-based (AI) applications at the edge of the network will enable the network to predict...
Future mobile communication networks need Unmanned Aerial Vehicles as Base Stations (UAVasBSs) with the fast-moving and long-term hovering capabilities to guarantee consistent network performance. UAVasBSs help 5G/B5G mobile communication systems to rapidly recover from emergency situations and handle the instant traffic of the flash crowd. In this...
Unmanned Aerial Vehicle as Base Stations (UAV-BS) is a promising technology for mitigating Terrestrial Base Stations (TBS) failures or becoming an ideal temporary solution to offloading. UAV-BS can be deployed to complement existing cellular systems by providing additional capacity to hotspot areas, as well as to provide network coverage in emergen...
A introdução de novas tecnologias e aplicações conectadas à Internet tem demonstrado a incapacidade física das redes ópticas atuais no aprovisionamento de recursos em um futuro próximo. Neste sentido, as redes ópticas elásticas com multiplexação por divisão espacial tem se mostrado uma solução promissora para lidar com este problema de capacidade....
Federated learning (FL) is a framework to train machine learning models using decentralized data, especially unbalanced and non-iid. Adaptive methods can be used to accelerate convergence, reducing the number of rounds of local computation and communication to a centralized server. This paper proposes an adaptive controller to adapt the number of e...
A localização robusta e precisa é fundamental para garantir o funcionamento de aplicações de Veículos Autônomos Conectados (CAVs). No entanto, os mecanismos de navegação veicular (GNSS) são afetados por diversos problemas nas áreas urbanas, principalmente devido à refração ou reflexão dos sinais de satélite em prédios. Assim, para usar a localização...
A interoperabilidade entre os sistemas e os dispositivos eletrônicos inteligentes (IEDs) legados, utilizados pela Smart Grid, tornou-se uma questão importante, visto que cada fabricante pode adotar um padrão diferente. Para integração de IEDs legados em um ambiente Smart Grid baseados na IoT, introduzimos o SG2IoT (do inglês Legacy Smart Grid to Io...
A técnica de virtualização baseadas em contêineres vem sendo amplamente utilizada através da adoção de tecnologias como Docker e Kubernetes que permitem a criação e o gerenciamento de contêineres. Assim, o presente artigo utilizou o Prometheus e o Grafana para analisar a performance de um cluster Kubernetes executando a plataforma Dojot e recebendo...
In modern 5G and Beyond (B5G) networks, thenumber of users and devices consuming highly-demanding ser-vices in terms of latency and throughput. Due to their highdynamicity and fine-grainess, such services must be supportedby a joint management and integration effort between tech-nologies such as Mobile Edge Computing (MEC), UnmannedAerial Vehicles...
LoRaWAN is the most adopted communication technology for the Internet of Things (IoT) applications for enabling flexible, cost-effective long-range communication with low power consumption. The deployment of a wide range of IoT devices brings many benefits to many applications, but new challenges arise from the network point of view with this deplo...
Intelligent Transportation Systems (ITSs) will be part of our daily lives, where new services are bringing novel challenges for smart cities. The ITS services rely on vehicular clouds (VC) to aggregate tasks from other vehicles to provide cloud services closest to the vehicular users. However, the resource and task allocation processes in dynamic a...