sensors-logo

Journal Browser

Journal Browser

Knowledge Transfer in IoT and Edge Computing

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Internet of Things".

Deadline for manuscript submissions: closed (31 May 2022) | Viewed by 12703

Special Issue Editors


E-Mail Website
Guest Editor
1. AIR Institute, Deep Tech Lab, Paseo de Belén 9A, 47011 Valladolid, Spain
2. BISITE Research Group, University of Salamanca, 37008 Salamanca, Spain
3. Higher School of Engineering and Technology, International University of La Rioja (UNIR), Logroño, Spain
Interests: Internet of Things; edge computing; distributed ledger and blockchain technologies; embedded systems; indoor location systems; cloud computing; artificial intelligence
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
BISITE Research Group, University of Salamanca, 37007 Salamanca, Spain
Interests: artificial intelligence; blockchain; deep learning; satellite systems; robot vision; cognitive robotics; sensor fusion; data fusion; mobile robotics; wireless networks; robotics; security; Internet of Things
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
UNIR - Universidad Internacional de La Rioja, de García Martín, 21, 28224 Pozuelo de Alarcón, Madrid, Spain
Interests: big data; Artificial Intelligence; IoT; Industry 4.0; energy efficiency
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The Internet of Things is no longer a novel technology but is now widely used in many applications: smart cities, Industry 4.0, smart farming, healthcare or smart energy, among many others. In this sense, Edge Computing architectures allow freeing IoT devices from managing communication with the Cloud, reducing its energy consumption, and increasing its autonomy. Moreover, Edge nodes allow pre-processing data transmitted to the Cloud, reducing costs of transfer, processing, and storage in the Cloud. Furthermore, the possibility of running Machine Learning models at the Edge is very useful in those scenarios in which it is necessary to offer a low-latency response when detecting patterns or anomalies, even when communication with the cloud is interrupted. In this regard, the creation of models that run at the Edge brings with it different challenges. On one hand, training the models in the cloud involves sending all the data from the IoT layer to the Cloud, which implies a risk in terms of security and privacy. On the other hand, training the models on the Edge without considering the rest of the data obtained in other locations may waste some of the knowledge acquired. In this sense, it is necessary to develop new solutions that allow the creation and transfer of knowledge in Edge–IoT applications in an efficient and secure way.

For this purpose, this Special Issue will be conducted under, but not limited to, the following topics:

  • Innovative methods for transferring knowledge between Cloud and Edge;
  • Distributed and collaborative knowledge management;
  • Novel architectures, protocols, and algorithms in Edge–IoT scenarios;
  • Deep Learning and deep reinforcement learning at the Edge;
  • Multi-agent reinforcement learning;
  • Federated machine learning and federated reinforcement learning;
  • Osmotic computing in highly distributed and federated environments;
  • Machine learning in cloudlets and Fog computing architectures;
  • Knowledge transfer in Mobile Edge Computing architectures;
  • Intelligent algorithms to manage software-defined networks and network function virtualization in Edge–IoT scenarios;
  • Security and privacy frameworks for transferring data and models in Edge–IoT scenarios;
  • Innovative applications of Machine Learning in Edge–IoT scenarios: Industry 4.0, smart cities, healthcare, smart farming, smart energy, etc.

Dr. Ricardo S. Alonso
Dr. Javier Prieto
Dr. Óscar García
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Internet of Things
  • Edge Computing
  • Machine Learning
  • Multi-Agent Reinforcement Learning
  • Federated Machine Learning

Published Papers (4 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

25 pages, 1214 KiB  
Article
Modeling an Edge Computing Arithmetic Framework for IoT Environments
by Pedro Juan Roig, Salvador Alcaraz, Katja Gilly, Cristina Bernad and Carlos Juiz
Sensors 2022, 22(3), 1084; https://doi.org/10.3390/s22031084 - 30 Jan 2022
Cited by 5 | Viewed by 2816
Abstract
IoT environments are forecasted to grow exponentially in the coming years thanks to the recent advances in both edge computing and artificial intelligence. In this paper, a model of remote computing scheme is presented, where three layers of computing nodes are put in [...] Read more.
IoT environments are forecasted to grow exponentially in the coming years thanks to the recent advances in both edge computing and artificial intelligence. In this paper, a model of remote computing scheme is presented, where three layers of computing nodes are put in place in order to optimize the computing and forwarding tasks. In this sense, a generic layout has been designed so as to easily achieve communications among the diverse layers by means of simple arithmetic operations, which may result in saving resources in all nodes involved. Traffic forwarding is undertaken by means of forwarding tables within network devices, which need to be searched upon in order to find the proper destination, and that process may be resource-consuming as the number of entries in such tables grow. However, the arithmetic framework proposed may speed up the traffic forwarding decisions as relaying on integer divisions and modular arithmetic, which may result more straightforward. Furthermore, two diverse approaches have been proposed to formally describe such a design by means of coding with Spin/Promela, or otherwise, by using an algebraic approach with Algebra of Communicating Processes (ACP), resulting in a explosion state for the former and a specified and verified model in the latter. Full article
(This article belongs to the Special Issue Knowledge Transfer in IoT and Edge Computing)
Show Figures

Figure 1

27 pages, 1411 KiB  
Article
Bloom Filter Approach for Autonomous Data Acquisition in the Edge-Based MCS Scenario
by Martina Antonić, Aleksandar Antonić and Ivana Podnar Žarko
Sensors 2022, 22(3), 879; https://doi.org/10.3390/s22030879 - 24 Jan 2022
Cited by 1 | Viewed by 2331
Abstract
Mobile crowdsensing (MCS) is a sensing paradigm that allows ordinary citizens to use mobile and wearable technologies and become active observers of their surroundings. MCS services generate a massive amount of data due to the vast number of devices engaging in MCS tasks, [...] Read more.
Mobile crowdsensing (MCS) is a sensing paradigm that allows ordinary citizens to use mobile and wearable technologies and become active observers of their surroundings. MCS services generate a massive amount of data due to the vast number of devices engaging in MCS tasks, and the intrinsic mobility of users can quickly make information obsolete, requiring efficient data processing. Our previous work shows that the Bloom filter (BF) is a promising technique to reduce the quantity of redundant data in a hierarchical edge-based MCS ecosystem, allowing users engaging in MCS tasks to make autonomous informed decisions on whether or not to transmit data. This paper extends the proposed BF algorithm to accept multiple data readings of the same type at an exact location if the MCS task requires such functionality. In addition, we thoroughly evaluate the overall behavior of our approach by taking into account the overhead generated in communication between edge servers and end-user devices on a real-world dataset. Our results indicate that using the proposed algorithm makes it possible to significantly reduce the amount of transmitted data and achieve energy savings up to 62% compared to a baseline approach. Full article
(This article belongs to the Special Issue Knowledge Transfer in IoT and Edge Computing)
Show Figures

Figure 1

25 pages, 14003 KiB  
Article
Engineering Approaches for Programming Agent-Based IoT Objects Using the Resource Management Architecture
by Fabian Cesar Brandão, Maria Alice Trinta Lima, Carlos Eduardo Pantoja, Jean Zahn and José Viterbo
Sensors 2021, 21(23), 8110; https://doi.org/10.3390/s21238110 - 4 Dec 2021
Cited by 10 | Viewed by 2496
Abstract
The Internet of Things (IoT) allows the sharing of information among devices in a network. Hardware evolutions have enabled the employment of cognitive agents on top of such devices, which could help to adopt pro-active and autonomous IoT systems. Agents are autonomous entities [...] Read more.
The Internet of Things (IoT) allows the sharing of information among devices in a network. Hardware evolutions have enabled the employment of cognitive agents on top of such devices, which could help to adopt pro-active and autonomous IoT systems. Agents are autonomous entities from Artificial Intelligence capable of sensing (perceiving) the environment where they are situated. Then, with these captured perceptions, they can reason and act pro-actively. However, some agent approaches are created for a specific domain or application when dealing with embedded systems and hardware interfacing. In addition, the agent architecture can compromise the system’s performance because of the number of perceptions that agents can access. This paper presents three engineering approaches for creating IoT Objects using Embedded Multi-agent systems (MAS)—as cognitive systems at the edge of an IoT network—connecting, acting, and sharing information with a re-engineered IoT architecture based on the Sensor as a Service model. These engineering approaches use Belief-Desire-Intention (BDI) agents and the JaCaMo framework. In addition, it is expected to diversify the designers’ choice in applying embedded MAS in IoT systems. We also present a case study to validate the whole re-engineered architecture and the approaches. Moreover, some performance tests and comparisons are also presented. The study case shows that each approach is more or less suitable depending on the domain tackled. The performance tests show that the re-engineered IoT architecture is scalable and that there are some trade-offs in adopting one or another approach. The contributions of this paper are an architecture for sharing resources in an IoT network, the use of embedded MAS on top IoT Objects, and three engineering approaches considering agent and artifacts dimensions. Full article
(This article belongs to the Special Issue Knowledge Transfer in IoT and Edge Computing)
Show Figures

Figure 1

33 pages, 5153 KiB  
Article
BeSafe B2.0 Smart Multisensory Platform for Safety in Workplaces
by Sergio Márquez-Sánchez, Israel Campero-Jurado, Daniel Robles-Camarillo, Sara Rodríguez and Juan M. Corchado-Rodríguez
Sensors 2021, 21(10), 3372; https://doi.org/10.3390/s21103372 - 12 May 2021
Cited by 12 | Viewed by 3594
Abstract
Wearable technologies are becoming a profitable means of monitoring a person’s health state, such as heart rate and physical activity. The use of the smartwatch is becoming consolidated, not only as a novelty but also as a very useful tool for daily use. [...] Read more.
Wearable technologies are becoming a profitable means of monitoring a person’s health state, such as heart rate and physical activity. The use of the smartwatch is becoming consolidated, not only as a novelty but also as a very useful tool for daily use. In addition, other devices, such as helmets or belts, are beneficial for monitoring workers and the early detection of any anomaly. They can provide valuable information, especially in work environments, where they help reduce the rate of accidents and occupational diseases, which makes them powerful Personal Protective Equipment (PPE). The constant monitoring of the worker’s health can be done in real-time, through temperature, falls, noise, impacts, or heart rate meters, activating an audible and vibrating alarm when an anomaly is detected. The gathered information is transmitted to a server in charge of collecting and processing it. In the first place, this paper provides an exhaustive review of the state of the art on works related to electronics for human activity behavior. After that, a smart multisensory bracelet, combined with other devices, developed a control platform that can improve operators’ security in the working environment. Artificial Intelligence and the Internet of Things (AIoT) bring together the information to improve safety on construction sites, power stations, power lines, etc. Real-time and historic data is used to monitor operators’ health and a hybrid system between Gaussian Mixture Model and Human Activity Classification. That is, our contribution is also founded on the use of two machine learning models, one based on unsupervised learning and the other one supervised. Where the GMM gave us a performance of 80%, 85%, 70%, and 80% for the 4 classes classified in real time, the LSTM obtained a result under the confusion matrix of 0.769, 0.892, and 0.921 for the carrying-displacing, falls, and walking-standing activities, respectively. This information was sent in real time through the platform that has been used to analyze and process the data in an alarm system. Full article
(This article belongs to the Special Issue Knowledge Transfer in IoT and Edge Computing)
Show Figures

Figure 1

Back to TopTop