sensors-logo

Journal Browser

Journal Browser

Machine Learning for the Internet of Things: Challenges, Solutions and Future Directions

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

Deadline for manuscript submissions: closed (30 June 2023) | Viewed by 3488

Special Issue Editors


E-Mail Website
Guest Editor
Department of Informatics, Modeling, Electronics and Systems (DIMES), University of Calabria, 87036 Rende, Italy
Interests: cloud computing; social media and big data analysis; distributed knowledge discovery; data mining; Internet of Things
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

It is our pleasure to announce the opening of a new Special Issue in Sensors. The main topic of this Special Issue is machine learning on the edge-to-cloud continuum.

In the last few years, huge volumes of data have been generated by several sources, such as sensors, cameras, smart meters, mobile devices, and wearables, which are commonly referred to as Internet of Things (IoT) devices. Such huge volumes of data, coupled with the speed with which they are generated, pose new research challenges in regard to collecting, storing and analyzing them. To efficiently extract useful information and produce helpful knowledge for science, industry and public services, novel technologies, architectures and algorithms have been developed to capture and analyze these data.

In most cases, the applications used today for processing data from IoT devices are highly centralized and leverage cloud platforms to perform the main operations involving data collection, storing, processing and analysis. However, using only the cloud could generate significant inefficiencies in terms of network traffic, latency times and energy consumption. These issues become particularly critical for some kinds of applications, such as those in the medical and security fields, where it is essential to have low-latency response times to avoid serious problems such as fatal accidents.

Cooperation between cloud and edge devices becomes even more necessary when running applications that make use of machine learning algorithms, which usually require the availability of large computing resources, big data sets and long computation times for training models. In fact, IoT devices at the edge of the network usually are very limited in terms of computational resources, power supply, storage capacity and bandwidth, which makes them unsuitable to fully perform heavy learning tasks. For these reasons, several research efforts have been made for enabling machine learning algorithms to exploit cooperative training and inference on local data available on edge devices. However, this task presents many open issues, mainly related to the heterogeneity of hardware, software and protocols of edge devices, which makes integration and management difficult. In addition, data security, privacy and communication efficiency are other critical aspects to be considered during the execution of machine learning tasks, as data must be transferred and shared between different network nodes to be processed and analyzed in parallel.

From this perspective, this Special Issue aims to contribute to the field by presenting the most relevant advances in this research area.

Dr. Fabrizio Marozzo
Dr. Loris Belcastro
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

  • programming models and algorithms for edge-to-cloud environments
  • systems for data processing on cloud platforms
  • data analysis workflows for distributed environments
  • distributed data analytics
  • big data management in IoT environments
  • simulation and emulation tools for IoT applications
  • industrial Internet of Things applications
  • IoT systems for supporting decision making in smart cities
  • health monitoring systems based on IoT
  • programming models and scalable algorithms for big data
  • big data analytics and applications of IoT data
  • applications of machine learning in big data
  • cloud-based data mining applications
  • libraries, algorithms, and applications for big social data analysis
  • machine learning applications for IoT environments
  • techniques for distributing workloads on the edge-to-cloud continuum
  • real-time IoT data analysis using machine learning techniques
  • edge-to-cloud continuum system for IoT environments
  • distributed intelligence on the edge-to-cloud continuum
  • simulation scenarios for IoT systems
  • privacy preserving in edge-to-cloud environments

Published Papers (2 papers)

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

Research

24 pages, 4625 KiB  
Article
IoTTPS: Ensemble RKSVM Model-Based Internet of Things Threat Protection System
by Urooj Akram, Wareesa Sharif, Mobeen Shahroz, Muhammad Faheem Mushtaq, Daniel Gavilanes Aray, Ernesto Bautista Thompson, Isabel de la Torre Diez, Sirojiddin Djuraev and Imran Ashraf
Sensors 2023, 23(14), 6379; https://doi.org/10.3390/s23146379 - 13 Jul 2023
Cited by 1 | Viewed by 1353
Abstract
An Internet of Things (IoT) network is prone to many ways of threatening individuals. IoT sensors are lightweight, lack complicated security protocols, and face threats to privacy and confidentiality. Hackers can attack the IoT network and access personal information and confidential data for [...] Read more.
An Internet of Things (IoT) network is prone to many ways of threatening individuals. IoT sensors are lightweight, lack complicated security protocols, and face threats to privacy and confidentiality. Hackers can attack the IoT network and access personal information and confidential data for blackmailing, and negatively manipulate data. This study aims to propose an IoT threat protection system (IoTTPS) to protect the IoT network from threats using an ensemble model RKSVM, comprising a random forest (RF), K nearest neighbor (KNN), and support vector machine (SVM) model. The software-defined networks (SDN)-based IoT network datasets such as KDD cup 99, NSL-KDD, and CICIDS are used for threat detection based on machine learning. The experimental phase is conducted by using a decision tree (DT), logistic regression (LR), Naive Bayes (NB), RF, SVM, gradient boosting machine (GBM), KNN, and the proposed ensemble RKSVM model. Furthermore, performance is optimized by adding a grid search hyperparameter optimization technique with K-Fold cross-validation. As well as the NSL-KDD dataset, two other datasets, KDD and CIC-IDS 2017, are used to validate the performance. Classification accuracies of 99.7%, 99.3%, 99.7%, and 97.8% are obtained for DoS, Probe, U2R, and R2L attacks using the proposed ensemble RKSVM model using grid search and cross-fold validation. Experimental results demonstrate the superior performance of the proposed model for IoT threat detection. Full article
Show Figures

Figure 1

14 pages, 776 KiB  
Article
COSIBAS Platform—Cognitive Services for IoT-Based Scenarios: Application in P2P Networks for Energy Exchange
by Diego Gutiérrez Martín, Sebastian Lopez Florez, Alfonso González-Briones and Juan M. Corchado
Sensors 2023, 23(2), 982; https://doi.org/10.3390/s23020982 - 14 Jan 2023
Cited by 2 | Viewed by 1683
Abstract
The revolution generated by the Internet of Things (IoT) has radically changed the world; countless objects with remote sensing, actuation, analysis and sharing capabilities are interconnected over heterogeneous communication networks. Consequently, all of today’s devices can connect to the internet and can provide [...] Read more.
The revolution generated by the Internet of Things (IoT) has radically changed the world; countless objects with remote sensing, actuation, analysis and sharing capabilities are interconnected over heterogeneous communication networks. Consequently, all of today’s devices can connect to the internet and can provide valuable information for decision making. However, the data collected by different devices are in different formats, which makes it necessary to develop a solution that integrates comprehensive semantic tools to represent, integrate and acquire knowledge, which is a major challenge for IoT environments. The proposed solution addresses this challenge by using IoT semantic data to reason about actionable knowledge, combining next-generation semantic technologies and artificial intelligence through a set of cognitive components that enables easy interoperability and integration for both legacy systems and emerging technologies, such as IoT, to generate business value in terms of faster analytics and improved decision making. Thus, combining IoT environments with cognitive artificial intelligence services, COSIBAS builds an abstraction layer between existing platforms for IoT and AI technologies to enable cognitive solutions and increase interoperability across multiple domains. The resulting low-cost cross platform supports scalability and the evolution of large-scale heterogeneous systems and allows the modernization of legacy infrastructures with cognitive tools and communication mechanisms while reusing assets. Full article
Show Figures

Figure 1

Back to TopTop