Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 13
Encontrada(s) 1 página(s)

Repisalud
Publication Artículo científico (JournalArticle)

Modelling and Evaluation of the Absorption of the 866 MHz Electromagnetic Field in Humans Exposed near to Fixed I-RFID Readers Used in Medical RTLS or to Monitor PPE

  • Zradziński, Patryk
  • Karpowicz, Jolanta
  • Gryz, Krzysztof
  • Owczarek, Grzegorz
  • Ramos-Gonzalez, Maria Victoria
The aim of this study was to model and evaluate the Specific Energy Absorption Rate (SAR) values in humans in proximity to fixed multi-antenna I-RFID readers of passive tags under various scenarios mimicking exposure when they are incorporated in Real-Time Location Systems (RTLS), or used to monitor Personal Protective Equipment (PPE). The sources of the electromagnetic field (EMF) in the modelled readers were rectangular microstrip antennas at a resonance frequency in free space of 866 MHz from the ultra-high frequency (UHF) RFID frequency range of 865-868 MHz. The obtained results of numerical modelling showed that the SAR values in the body 5 cm away from the UHF RFID readers need consideration with respect to exposure limits set by international guidelines to prevent adverse thermal effects of exposure to EMF: when the effective radiated power exceeds 5.5 W with respect to the general public/unrestricted environments exposure limits, and with respect to occupational/restricted environments exposure limits, when the effective radiated power exceeds 27.5 W.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

ASSIST-IoT: A Modular Implementation of a Reference Architecture for the Next Generation Internet of Things

  • Szmeja, Pawel
  • Ganzha, Maria
  • Pawlowski, Wieslaw
  • Paprzycki, Marcin
  • Schabbink, Johan
  • Fornés Leal, Alejandro|||0000-0001-5914-6045
  • Lacalle-Úbeda, Ignacio|||0000-0002-6002-4050
  • Palau Salvador, Carlos Enrique|||0000-0002-3795-5404
[EN] Next Generation Internet of Things (NGIoT) addresses the deployment of complex, novel IoT ecosystems. These ecosystems are related to different technologies and initiatives, such as 5G/6G, AI, cybersecurity, and data science. The interaction with these disciplines requires addressing complex challenges related with the implementation of flexible solutions that mix heterogeneous software and hardware, while providing high levels of customisability and manageability, creating the need for a blueprint reference architecture (RA) independent of particular existing vertical markets (e.g., energy, automotive, or smart cities). Different initiatives have partially dealt with the requirements of the architecture. However, the first complete, consolidated NGIoT RA, covering the hardware and software building blocks, and needed for the advent of NGIoT, has been designed in the ASSIST-IoT project. The ASSIST-IoT RA delivers a layered and modular design that divides the edge-cloud continuum into independent functions and cross-cutting capabilities. This contribution discusses practical aspects of implementation of the proposed architecture within the context of real-world applications. In particular, it is shown how use of cloud-native concepts (microservices and applications, containerisation, and orchestration) applied to the edge-cloud continuum IoT systems results in bringing the ASSIST-IoT concepts to reality. The description of how the design elements can be implemented in practice is presented in the context of an ecosystem, where independent software packages are deployed and run at the selected points in the hardware environment. Both implementation aspects and functionality of selected groups of virtual artefacts (micro-applications called enablers) are described, along with the hardware and software contexts in which they run., This work was funded by the European Commission, under the Horizon Europe project ASSIST-IoT, grant number 957258.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

In-cabin and outdoor environmental monitoring in vehicular scenarios with distributed computing

  • Ramos-Sorroche, Emilio
  • Rubio-Aparicio, Jesus
  • Santa, Jose
  • Egea-Lopez, Esteban
  • Guardiola, Carlos|||0000-0002-3150-8566
[EN] Accurate environmental monitoring is becoming the basis for assuring sustainable development in administrations at different levels, including cities and industry as key actors. However, current techniques rely on static stations that may not be representative of larger areas, for the case of outdoor scenarios, or even not considering indoor spaces where people can remain for long periods. This is the case of vehicles. The COVID-19 pandemic has remarked the importance of measuring air quality indoors, for instance. With the aim of solving this twofold issue, this work proposes an in-cabin and outdoor air pollution monitoring system to assure healthy conditions when travelling, driving and operating vehicles, and to analyse the evolution of environmental parameters in cities. This effort is carried out exploiting distributed computing with micro-services, betting for an on-board hardware solution provided with sensors for measuring particulate matter, CO, CO2, NO2, O3, temperature and humidity. While basic data pre-processing is carried out in this acquisition unit, edge processing is performed on a single board computer aboard and intermediary communication nodes in the network path from the vehicle to the cloud. Vehicle connectivity is provided by 4G cellular and Low-Power Wide Area (LPWAN) networks. Global environmental perception is acquired by cloud-based software powered by machine learning and time series analysis. The whole solution has been validated and tested in the city of Cartagena (Spain), with good performance in terms of data collection, communication links and service offered., This work was supported by the grants PID2020-112675RBC41 (ONOFRE-3) , funded by MCIN/AEI/10.13039/501100011033; RYC-2017-23823, funded by MCIN/AEI/10.13039/501100011033 and by "ESF Investing in your future"; CNS2022-136150 (WILLIOT) , funded by MCIN/AEI/10.13039/501100011033 and by "European Union NextGenerationEU/PRTR"; and H2020 957258 (ASSIST-IoT) , funded by the European Commission.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A Novel Orchestrator Architecture for Deploying Virtualized Services in Next-Generation IoT Computing Ecosystems

  • Mahedero-Biot, Francisco
  • Fornés Leal, Alejandro|||0000-0001-5914-6045
  • Vañó-García, Rafael|||0000-0003-2372-6253
  • Reinosa-Simón, Raúl|||0000-0001-6593-5163
  • Lacalle-Úbeda, Ignacio|||0000-0002-6002-4050
  • Guardiola, Carlos|||0000-0002-3150-8566
  • Palau Salvador, Carlos Enrique|||0000-0002-3795-5404
[EN] The Next-Generation IoT integrates diverse technological enablers, allowing the creation of advanced systems with increasingly complex requirements and maximizing the use of available IoT¿edge¿cloud resources. This paper introduces an orchestrator architecture for dynamic IoT scenarios, inspired by ETSI NFV MANO and Cloud Native principles, where distributed computing nodes often have unfixed and changing networking configurations. Unlike traditional approaches, this architecture also focuses on managing services across massively distributed mobile nodes, as demonstrated in the automotive use case presented. Apart from working as MANO framework, the proposed solution efficiently handles service lifecycle management in large fleets of vehicles without relying on public or static IP addresses for connectivity. Its modular, microservices-based approach ensures adaptability to emerging trends like Edge Native, WebAssembly and RISC-V, positioning it as a forward-looking innovation for IoT ecosystems, This research was funded by European Union s Horizon 2020 and Horizon Europe research and innovation programs, grant agreements 957258 and 101069732, respectively.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Flexible Deployment of Machine Learning Inference Pipelines in the Cloud-Edge-IoT Continuum

  • Bogacka, Karolina
  • Sowinski, Piotr
  • Danilenka, Anastasiya
  • Biot, Francisco Mahedero
  • Wasielewska-Michniewska, Katarzyna
  • Ganzha, Maria
  • Paprzycki, Marcin
  • Palau Salvador, Carlos Enrique|||0000-0002-3795-5404
[EN] Currently, deploying machine learning workloads in the Cloud-Edge-IoT continuum is challenging due to the wide variety of available hardware platforms, stringent performance requirements, and the heterogeneity of the workloads themselves. To alleviate this, a novel, flexible approach for machine learning inference is introduced, which is suitable for deployment in diverse environments-including edge devices. The proposed solution has a modular design and is compatible with a wide range of user-defined machine learning pipelines. To improve energy efficiency and scalability, a high-performance communication protocol for inference is propounded, along with a scale-out mechanism based on a load balancer. The inference service plugs into the ASSIST-IoT reference architecture, thus taking advantage of its other components. The solution was evaluated in two scenarios closely emulating real-life use cases, with demanding workloads and requirements constituting several different deployment scenarios. The results from the evaluation show that the proposed software meets the high throughput and low latency of inference requirements of the use cases while effectively adapting to the available hardware. The code and documentation, in addition to the data used in the evaluation, were open-sourced to foster adoption of the solution., This work was funded by the European Commission, in part under the Horizon 2020 project ASSIST-IoT, grant number 957258. The work of Marcin Paprzycki and Katarzyna WasielewskaMichniewska was funded under the Horizon Europe project aerOS, grant number 101069732.
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Towards a library of deep neural networks for experimenting with on-device training on microcontrollers

  • Aatab, Soufiane
  • Freitag, Fèlix|||0000-0001-5438-479X
Despite the limited computing capacity of microcontrollers, there is a growing interest in training neural networks on these devices for tiny machine learning applications. The traditional approach is to train models off-device on powerful machines, but this limits the model's ability on the microcontroller to adapt to changing data. A limitation for further research on on-device training is the lack of open source deep neural network implementations for the training on microcontroller boards. In this paper, we present the design and implementation of a library in C++ to enable neural network training and inference on microcontroller boards. We conduct a functional validation of the implementation by comparing a Convolutional Neural Network (CNN) and autoencoder model defined with our library with a reference implementation. We then integrate the library into a machine learning application and flash it on an Arduino Portenta board to demonstrate its usability for on-device training. The developed library is open source and is flexible for defining different neural network architectures. Researchers and developers can use the given implementation as a tool for building new trainable machine learning applications, but can also extend it with recent model optimization techniques for tiny nodes from the research in this field., This work has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 957258 — ASSIST-IoT, and was partially supported by the Spanish Government under contract PID2019-106774RB-C21, and the Generalitat de Catalunya as Consolidated Research Group 2021-SGR-01059., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

The effects of weight quantization on online federated learning for the IoT: a case study

  • Llisterri Giménez, Nil
  • Lee, Junkyu
  • Freitag, Fèlix|||0000-0001-5438-479X
  • Vandierendonck, Hans
Many weight quantization approaches were explored to save the communication bandwidth between the clients and the server in federated learning using high-end computing machines. However, there is a lack of weight quantization research for online federated learning using TinyML devices which are restricted by the mini-batch size, the neural network size, and the communication method due to their severe hardware resource constraints and power budgets. We name Tiny Online Federated Learning (TinyOFL) for online federated learning using TinyML devices in the Internet of Things (IoT). This paper performs a comprehensive analysis of the effects of weight quantization in TinyOFL in terms of accuracy, stability, overfitting, communication efficiency, energy consumption, and delivery time, and extracts practical guidelines on how to apply the weight quantization to TinyOFL. Our analysis is supported by a TinyOFL case study with three Arduino Portenta H7 boards running federated learning clients for a keyword spotting task. Our findings include that in TinyOFL, a more aggressive weight quantization can be allowed than in online learning without FL, without affecting the accuracy thanks to TinyOFL’s quasi-batch training property. For example, using 7-bit weights achieved the equivalent accuracy to 32-bit floating point weights, while saving communication bandwidth by 4.6× . Overfitting by increasing network width rarely occurs in TinyOFL, but may occur if strong weight quantization is applied. The experiments also showed that there is a design space for TinyOFL applications by compensating for the accuracy loss due to weight quantization with an increase of the neural network size., This work was supported in part by the European Union’s Horizon 2020 Research and Innovation Program (ASSIST-IoT) under Grant 957258, in part by the Spanish Government (DiPET CHIST-ERA) under Contract PID2019-106774RB-C21 and Contract PCI2019-111850-2, and in part by the Generalitat de Catalunya as Consolidated Research Group under Grant 2021-SGR-01059., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Integrating a neural network library in embedded federated learning

  • Aatab, Soufiane
  • Freitag, Fèlix|||0000-0001-5438-479X
Federated learning has become a popular collaborative machine learning approach in which clients use their local data for training. This results in bandwidth savings since the training data does not have to be transferred to a central node, and also protects the privacy of these data. However, doing federated learning in tiny Internet of Things (IoT) devices is challenging due to the resource constraints of the devices and lack of experimental tools. In this paper, we develop a federated learning implementation that allows training of different machine learning models on embedded IoT devices. Our starting point is a library of neural network models which we have developed. We analyze the metadata to describe these models, design the interaction process between clients and server of a federated learning network, and implement the software. We validate the system by conducting experiments with our implementation deployed on real embedded boards. We observe in a non-IID experiment the capacity of federated learning to provide a trained model whose capacities go beyond those that the node could train by itself. Being heterogeneous data distribution a realistic scenario in distributed IoT devices, we believe that our implementation can be useful for the community as a tool to explore the training of neural networks on microcontrollers with the support of federated learning., This work has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 957258 — ASSIST-IoT, and was partially supported by the Spanish Government under contract PID2019-106774RB-C21, and the Generalitat de Catalunya as Consolidated Research Group 2021-SGR-01059., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Capítulo o parte de un libro (BookPart)

Position paper: LoRa mesh networks for enabling distributed intelligence on tiny IoT nodes

  • Freitag, Fèlix|||0000-0001-5438-479X
  • Miquel Solé, Joan|||0000-0003-3737-376X
  • Meseguer Pallarès, Roc|||0000-0002-9414-646X
LoRaWAN is a widely used solution in today’s Internet of Things (IoT) applications to connect remote sensor nodes to the Internet. At the same time, microcontroller-based sensor nodes with increased processing capacities are in- creasingly becoming smart nodes applied for performing machine learning tasks. We argue that LoRaWAN has important connectivity limitations to truly unleash the potential of these smart tiny nodes. We position to apply LoRa mesh networks as a communication substrate to enable novel networking capacities for the new scenario of distributed smart IoT nodes., This work has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 957258 — ASSIST-IoT, and was partially supported by the Spanish Government under contract PID2019-106774RB-C21, and the Generalitat de Catalunya as Consolidated Research Group 2021-SGR-01059., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

The effects of weight quantization on online federated learning for the IoT: a case study

  • Llisterri Giménez, Nil
  • Lee, Junkyu
  • Freitag, Fèlix
  • Vandierendonck, Hans
Many weight quantization approaches were explored to save the communication bandwidth between the clients and the server in federated learning using high-end computing machines. However, there is a lack of weight quantization research for online federated learning using TinyML devices which are restricted by the mini-batch size, the neural network size, and the communication method due to their severe hardware resource constraints and power budgets. We name Tiny Online Federated Learning (TinyOFL) for online federated learning using TinyML devices in the Internet of Things (IoT). This paper performs a comprehensive analysis of the effects of weight quantization in TinyOFL in terms of accuracy, stability, overfitting, communication efficiency, energy consumption, and delivery time, and extracts practical guidelines on how to apply the weight quantization to TinyOFL. Our analysis is supported by a TinyOFL case study with three Arduino Portenta H7 boards running federated learning clients for a keyword spotting task. Our findings include that in TinyOFL, a more aggressive weight quantization can be allowed than in online learning without FL, without affecting the accuracy thanks to TinyOFL’s quasi-batch training property. For example, using 7-bit weights achieved the equivalent accuracy to 32-bit floating point weights, while saving communication bandwidth by 4.6× . Overfitting by increasing network width rarely occurs in TinyOFL, but may occur if strong weight quantization is applied. The experiments also showed that there is a design space for TinyOFL applications by compensating for the accuracy loss due to weight quantization with an increase of the neural network size., This work was supported in part by the European Union’s Horizon 2020 Research and Innovation Program (ASSIST-IoT) under Grant 957258, in part by the Spanish Government (DiPET CHIST-ERA) under Contract PID2019-106774RB-C21 and Contract PCI2019-111850-2, and in part by the Generalitat de Catalunya as Consolidated Research Group under Grant 2021-SGR-01059., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Towards a library of deep neural networks for experimenting with on-device training on microcontrollers

  • Aatab, Soufiane
  • Freitag, Fèlix
Despite the limited computing capacity of microcontrollers, there is a growing interest in training neural networks on these devices for tiny machine learning applications. The traditional approach is to train models off-device on powerful machines, but this limits the model's ability on the microcontroller to adapt to changing data. A limitation for further research on on-device training is the lack of open source deep neural network implementations for the training on microcontroller boards. In this paper, we present the design and implementation of a library in C++ to enable neural network training and inference on microcontroller boards. We conduct a functional validation of the implementation by comparing a Convolutional Neural Network (CNN) and autoencoder model defined with our library with a reference implementation. We then integrate the library into a machine learning application and flash it on an Arduino Portenta board to demonstrate its usability for on-device training. The developed library is open source and is flexible for defining different neural network architectures. Researchers and developers can use the given implementation as a tool for building new trainable machine learning applications, but can also extend it with recent model optimization techniques for tiny nodes from the research in this field., This work has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 957258 — ASSIST-IoT, and was partially supported by the Spanish Government under contract PID2019-106774RB-C21, and the Generalitat de Catalunya as Consolidated Research Group 2021-SGR-01059., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Integrating a neural network library in embedded federated learning

  • Aatab, Soufiane
  • Freitag, Fèlix
Federated learning has become a popular collaborative machine learning approach in which clients use their local data for training. This results in bandwidth savings since the training data does not have to be transferred to a central node, and also protects the privacy of these data. However, doing federated learning in tiny Internet of Things (IoT) devices is challenging due to the resource constraints of the devices and lack of experimental tools. In this paper, we develop a federated learning implementation that allows training of different machine learning models on embedded IoT devices. Our starting point is a library of neural network models which we have developed. We analyze the metadata to describe these models, design the interaction process between clients and server of a federated learning network, and implement the software. We validate the system by conducting experiments with our implementation deployed on real embedded boards. We observe in a non-IID experiment the capacity of federated learning to provide a trained model whose capacities go beyond those that the node could train by itself. Being heterogeneous data distribution a realistic scenario in distributed IoT devices, we believe that our implementation can be useful for the community as a tool to explore the training of neural networks on microcontrollers with the support of federated learning., This work has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 957258 — ASSIST-IoT, and was partially supported by the Spanish Government under contract PID2019-106774RB-C21, and the Generalitat de Catalunya as Consolidated Research Group 2021-SGR-01059., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication

Position paper: LoRa mesh networks for enabling distributed intelligence on tiny IoT nodes

  • Freitag, Fèlix
  • Miquel Solé, Joan
  • Meseguer Pallarès, Roc
LoRaWAN is a widely used solution in today’s Internet of Things (IoT) applications to connect remote sensor nodes to the Internet. At the same time, microcontroller-based sensor nodes with increased processing capacities are in- creasingly becoming smart nodes applied for performing machine learning tasks. We argue that LoRaWAN has important connectivity limitations to truly unleash the potential of these smart tiny nodes. We position to apply LoRa mesh networks as a communication substrate to enable novel networking capacities for the new scenario of distributed smart IoT nodes., This work has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 957258 — ASSIST-IoT, and was partially supported by the Spanish Government under contract PID2019-106774RB-C21, and the Generalitat de Catalunya as Consolidated Research Group 2021-SGR-01059., Peer Reviewed, Postprint (published version)