Submit to Future Internet Review for Future Internet Propose a Special Issue

Journal Menu

Journal Browser

► Journal Browser

AI, Machine Learning and Data Analytics for Wireless Communications

Special Issue Editors
Special Issue Information
Keywords
Related Special Issue
Published Papers

A special issue of Future Internet (ISSN 1999-5903). This special issue belongs to the section "Internet of Things".

Deadline for manuscript submissions: closed (10 February 2023) | Viewed by 13454

Share This Special Issue

Special Issue Editors

Prof. Dr. Xavier Fernando

E-Mail Website
Guest Editor

Department of Electrical and Computer Engineering, Ryerson University, 350 Victoria Street, Toronto, ON M5B 2K3, Canada
Interests: wireless communications; signal processing; optical communications; optical–wireless communications; machine learning; IoT; tracking and localization; underground communication systems
Special Issues, Collections and Topics in MDPI journals

Dr. Kandasamy Illanko

E-Mail Website
Guest Editor

Department of Electrical Computer and Biomedical Engineering, Ryerson University, 350 Victoria Street, Toronto, ON M5B 2K3, Canada
Interests: neural networks; deep learning; non-convex optimization

Special Issue Information

Dear Colleagues,

One of the pressing necessities of future internet is ubiquitous and reliable wireless connectivity regardless of location, time, or user case. This is not just needed for people but also for billions of IoT nodes that need to communicate several exabytes of data. Hence, future wireless networks are not only expected to provide connectivity and bandwidth, but they also should be intelligent and able to multitask to accomplish the numerous missions that cannot be preprogrammed. For instance, rapidly emerging video conferencing and augmented reality applications consume a huge bandwidth per user, while innumerable IoT nodes often require only low bitrate sporadic connectivity. Safe operation of fast-moving autonomous vehicles requires low-latent ultrareliable message delivery, while remote communities need basic voice and internet services at a reasonable cost. Very complex scenarios such as those of future wireless networks are unlikely to adhere to traditional analytical models. In order to face this emerging complexity crunch challenge, disruptive approaches such as machine learning (ML) and artificial intelligence (AI) shall be wisely incorporated in addition to established techniques. That is the focus of this Special Issue.

Prof. Dr. Xavier Fernando
Dr. Kandasamy Illanko
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. Future Internet is an international peer-reviewed open access monthly 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 1600 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

machine learning (ML)
artificial intelligence
deep learning
reinforcement learning
big data
6G wireless networks
IoT
cloud computing
heterogeneous networks
vehicular networks
location-based services

Related Special Issue

AI, Machine Learning and Data Analytics for Wireless Communications II in Future Internet (2 articles)

Published Papers (5 papers)

Download All Papers

Research

18 pages, 793 KiB

Open AccessArticle

Intelligent Reflecting Surface-Aided Device-to-Device Communication: A Deep Reinforcement Learning Approach

by Ajmery Sultana and Xavier Fernando

Future Internet 2022, 14(9), 256; https://doi.org/10.3390/fi14090256 - 29 Aug 2022

Cited by 16 | Viewed by 2369

Abstract

Recently, the growing demand of various emerging applications in the realms of sixth-generation (6G) wireless networks has made the term internet of Things (IoT) very popular. Device-to-device (D2D) communication has emerged as one of the significant enablers for the 6G-based IoT network. Recently, the intelligent reflecting surface (IRS) has been considered as a hardware-efficient innovative scheme for future wireless networks due to its ability to mitigate propagation-induced impairments and to realize a smart radio environment. Such an IRS-assisted D2D underlay cellular network is investigated in this paper. Our aim is to maximize the network’s spectrum efficiency (SE) by jointly optimizing the transmit power of both the cellular users (CUs) and the D2D pairs, the resource reuse indicators, and the IRS reflection coefficients. Instead of using traditional optimization solution schemes to solve this mixed integer nonlinear optimization problem, a reinforcement learning (RL) approach is used in this paper. The IRS-assisted D2D communication network is structured by the Markov Decision Process (MDP) in the RL framework. First, a Q-learning-based solution is studied. Then, to make a scalable solution with large dimension state and action spaces, a deep Q-learning-based solution scheme using experience replay is proposed. Lastly, an actor-critic framework based on the deep deterministic policy gradient (DDPG) scheme is proposed to learn the optimal policy of the constructed optimization problem considering continuous-valued state and action spaces. Simulation outcomes reveal that the proposed RL-based solution schemes can provide significant SE enhancements compared to the existing optimization schemes. Full article

(This article belongs to the Special Issue AI, Machine Learning and Data Analytics for Wireless Communications)

► Show Figures

Figure 1

12 pages, 2031 KiB

Open AccessCommunication

A Public Infrastructure for a Trusted Wireless World

by Renee Carnley and Sikha Bagui

Future Internet 2022, 14(7), 200; https://doi.org/10.3390/fi14070200 - 30 Jun 2022

Cited by 1 | Viewed by 1910

Abstract

The novelty of this work lies in examining how 5G, blockchain-based public key infrastructure (PKI), near field communication (NFC), and zero trust architecture securely provide not only a trusted digital identity for telework but also a trusted digital identity for secure online voting. The paper goes on to discuss how blockchain-based PKI, NFC, and the cloud provide a roadmap for how industry and governments can update existing frameworks to obtain a trusted digital identity in cyberspace that would provide secure telework and online voting capabilities. Full article

(This article belongs to the Special Issue AI, Machine Learning and Data Analytics for Wireless Communications)

► Show Figures

Figure 1

28 pages, 2237 KiB

Open AccessArticle

A Multi-Service Adaptive Semi-Persistent LTE Uplink Scheduler for Low Power M2M Devices

by Nusrat Afrin, Jason Brown and Jamil Y. Khan

Future Internet 2022, 14(4), 107; https://doi.org/10.3390/fi14040107 - 27 Mar 2022

Cited by 2 | Viewed by 2219

Abstract

The prominence of Machine-to-Machine (M2M) communications in the future wide area communication networks place various challenges to the cellular technologies such as the Long Term Evolution (LTE) standard, owing to the large number of M2M devices generating small bursts of infrequent data packets with a wide range of delay requirements. The channel structure and Quality of Service (QoS) framework of LTE networks fail to support M2M traffic with multiple burst sizes and QoS requirements while a bottleneck often arises from the limited control resources to communicate future uplink resource allocations to the M2M devices. Moreover, many of the M2M devices are battery-powered and require a low-power consuming wide area technology for wide-spread deployments. To alleviate these issues, in this article we propose an adaptive semi-persistent scheduling (SPS) scheme for the LTE uplink which caters for multi-service M2M traffic classes with variable burst sizes and delay tolerances. Instead of adhering to the rigid LTE QoS framework, the proposed algorithm supports variation of uplink allocation sizes based on queued data length yet does not require control signaling to inform those allocations to the respective devices. Both the eNodeB and the M2M devices can determine the precise uplink resource allocation related parameters based on their mutual knowledge, thus omitting the burden of regular control signaling exchanges. Based on a control parameter, the algorithm can offer different capacities and levels of QoS satisfaction to different traffic classes. We also introduce a pre-emptive feature by which the algorithm can prioritize new traffic with low delay tolerance over ongoing delay-tolerant traffic. We also build a model for incorporating the Discontinuous Reception (DRX) mechanism in synchronization with the adaptive SPS transmissions so that the UE power consumption can be significantly lowered, thereby extending their battery lives. The simulation and performance analysis of the proposed scheme shows significant improvement over the traditional LTE scheduler in terms of QoS satisfaction, channel utilization and low power requirements of multi-service M2M traffic. Full article

(This article belongs to the Special Issue AI, Machine Learning and Data Analytics for Wireless Communications)

► Show Figures

Figure 1

20 pages, 1483 KiB

Open AccessArticle

A Density-Based Random Forest for Imbalanced Data Classification

by Jia Dong and Quan Qian

Future Internet 2022, 14(3), 90; https://doi.org/10.3390/fi14030090 - 14 Mar 2022

Cited by 12 | Viewed by 2855

Abstract

Many machine learning problem domains, such as the detection of fraud, spam, outliers, and anomalies, tend to involve inherently imbalanced class distributions of samples. However, most classification algorithms assume equivalent sample sizes for each class. Therefore, imbalanced classification datasets pose a significant challenge in prediction modeling. Herein, we propose a density-based random forest algorithm (DBRF) to improve the prediction performance, especially for minority classes. DBRF is designed to recognize boundary samples as the most difficult to classify and then use a density-based method to augment them. Subsequently, two different random forest classifiers were constructed to model the augmented boundary samples and the original dataset dependently, and the final output was determined using a bagging technique. A real-world material classification dataset and 33 open public imbalanced datasets were used to evaluate the performance of DBRF. On the 34 datasets, DBRF could achieve improvements of 2–15% over random forest in terms of the F1-measure and G-mean. The experimental results proved the ability of DBRF to solve the problem of classifying objects located on the class boundary, including objects of minority classes, by taking into account the density of objects in space. Full article

(This article belongs to the Special Issue AI, Machine Learning and Data Analytics for Wireless Communications)

► Show Figures

Graphical abstract

14 pages, 2669 KiB

Open AccessArticle

Time Optimization of Unmanned Aerial Vehicles Using an Augmented Path

by Abdul Quadir Md, Divyank Agrawal, Monark Mehta, Arun Kumar Sivaraman and Kong Fah Tee

Future Internet 2021, 13(12), 308; https://doi.org/10.3390/fi13120308 - 29 Nov 2021

Cited by 18 | Viewed by 2777

Abstract

With the pandemic gripping the entire humanity and with uncertainty hovering like a black cloud over all our future sustainability and growth, it became almost apparent that though the development and advancement are at their peak, we are still not ready for the worst. New and better solutions need to be applied so that we will be capable of fighting these conditions. One such prospect is delivery, where everything has to be changed, and each parcel, which was passed people to people, department to department, has to be made contactless throughout with as little error as possible. Thus, the prospect of drone delivery and its importance came around with optimization of the existing system for making it useful in the prospects of delivery of important items like medicines, vaccines, etc. These modular AI-guided drones are faster, efficient, less expensive, and less power-consuming than the actual delivery. Full article

(This article belongs to the Special Issue AI, Machine Learning and Data Analytics for Wireless Communications)

► Show Figures