Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.0
2.3
Journals
Mathematics
Special Issues
Computational Intelligence in Communication Networks
share announcement

Computational Intelligence in Communication Networks

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "E1: Mathematics and Computer Science".

Deadline for manuscript submissions: 20 January 2026 | Viewed by 2700

Special Issue Editor

Prof. Dr. Georgi Iliev

E-Mail Website
Guest Editor
Faculty of Telecommunications, Technical University of Sofia, 1000 Sofia, Bulgaria
Interests: deep learning; network security; computational intelligence

Special Issue Information

Dear Colleagues,

In the near future, all types of objects and structures in the natural physical environment will be computerized and have the ability to communicate with each other. Applications of significant economic and social importance will be created by exploiting these new capabilities of physical objects in time and space. The proper functioning of the various objects and applications will depend on the provision of reliable and secure communications. One of the main characteristics of the networks that provide these communications will be their heterogeneity. Different parts of the networks will have different resource capabilities. For example, resource-constrained areas of IoT, or Tactile Internet featuring extremely low latency, high availability, reliability, and security. The proper functioning of such types of infrastructures requires the application of intelligent computational methods for data processing and protection as well as efficient transmission of information. 

This Special Issue calls for papers on the following topics:

  • Intelligent approaches providing data security using not only the classical cryptographic techniques but also physical layer security methods;
  • Intelligent algorithms for secure communications using information theory;
  • Efficient information transmission, deploying smart technologies for data collection and processing;
  • Computational intelligence for network architecture simulation;
  • Intelligent network protocols;
  • Intelligent algorithms for network resource allocation;
  • Intelligent algorithms for power and interference control.

The above list of topics is not exhaustive.

Prof. Dr. Georgi Iliev
Guest Editor

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. Mathematics 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

  • intelligent algorithms for data collection and processing
  • intelligent methods for data analytics and security
  • intelligent algorithms for physical layer security
  • intelligent information transmission techniques
  • ML and AI for network monitoring and control
  • intelligent network protocols

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (2 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

29 pages, 2617 KiB  
Article
Hypercomplex Numbers—A Tool for Enhanced Efficiency and Intelligence in Digital Signal Processing
by Zlatka Valkova-Jarvis, Maria Nenova and Dimitriya Mihaylova
Mathematics 2025, 13(3), 504; https://doi.org/10.3390/math13030504 - 3 Feb 2025
Viewed by 1127
Abstract
Mathematics is the wide-ranging solid foundation of the engineering sciences which ensures their progress by providing them with its unique toolkit of rules, methods, algorithms and numerical systems. In this paper, an overview of the numerical systems that have currently found an application [...] Read more.
Mathematics is the wide-ranging solid foundation of the engineering sciences which ensures their progress by providing them with its unique toolkit of rules, methods, algorithms and numerical systems. In this paper, an overview of the numerical systems that have currently found an application in engineering science and practice is offered, while also mentioning those systems that still await full and comprehensive applicability, recognition, and acknowledgment. Two possible approaches for representing hypercomplex numbers are proposed—based on real numbers and based on complex numbers. This makes it possible to justify the creation and introduction of numerical systems specifically suited to digital signal processing (DSP), which is the basis of all modern technical sciences ensuring the technological progress of mankind. Understanding the specifics, peculiarities, and properties of the large and diverse family of hypercomplex numbers is the first step towards their more comprehensive and thorough study, and hence their use in a number of high-tech intelligent applications in various engineering and scientific fields, such as information and communication technologies (ICT), communication and neural networks, cybersecurity and national security, artificial intelligence (АI), space and military technologies, industrial engineering and machine learning, astronomy, applied mathematics, quantum physics, etc. The issues discussed in this paper are, however, far from exhausting the scientific topics related to both hypercomplex numbers in general and those relevant to DSP. This is a promising scientific area, the potential of which has not yet been fully explored, but research already shows the enhanced computational efficiency and intelligent performance of hypercomplex DSP. Full article
(This article belongs to the Special Issue Computational Intelligence in Communication Networks)
►▼ Show Figures

Figure 1

29 pages, 11294 KiB  
Article
Pilot Contamination Attack Detection Methods—An Exhaustive Performance Evaluation Through Probability Metrics and Statistical Classification Parameters
by Dimitriya Mihaylova, Georgi Iliev, Zlatka Valkova-Jarvis and Viktor Stoynov
Mathematics 2024, 12(22), 3524; https://doi.org/10.3390/math12223524 - 12 Nov 2024
Viewed by 1027
Abstract
Among the numerous strategies that an attacker can initiate to enhance its eavesdropping capabilities is the Pilot Contamination Attack (PCA). Two promising methods, based on Phase-Shift Keying (PSK) modulation of Nth order—2-N-PSK and Shifted 2-N-PSK, can detect an existing PCA by [...] Read more.
Among the numerous strategies that an attacker can initiate to enhance its eavesdropping capabilities is the Pilot Contamination Attack (PCA). Two promising methods, based on Phase-Shift Keying (PSK) modulation of Nth order—2-N-PSK and Shifted 2-N-PSK, can detect an existing PCA by means of analysis of the constellation that the correlation product of received pilot signals belongs to. The overall efficiency of the methods can be studied by the most commonly used probability metrics—detection probability and false alarm probability. However, this information may be insufficient for comparison purposes; therefore, to acquire a more holistic perspective on the methods’ performances, statistical evaluation metrics can be obtained. Depending on the particular application of the system in which the PCA detection methods are incorporated and the distribution of attack initiation among all samples, different classification parameters are of varying significance in the efficiency assessment. In this paper, 2-N-PSK and Shifted 2-N-PSK are comprehensively studied through their probability parameters. In addition, the methods are also compared by their most informative statistical parameters, such as accuracy, precision and recall, F1-score, specificity, and fall-out. A large number of simulations are carried out, the analyses of which indisputably prove the superior behavior of the Shifted 2-N-PSK compared to the 2-N-PSK detection method. Since a method’s performance is strongly related to the number of antenna elements at the base station, all simulations are conducted for scenarios with different antennae numbers. The most promising realization of Shifted 2-N-PSK improves the receiver operating characteristics results of the original 2-N-PSK by 7.38%, 4.33%, and 5.61%, and outperforms the precision recall analyses of 2-N-PSK by 10.02%, 4.82% and 3.86%, for the respective number of 10, 100 and 300 antenna elements at the base station. Full article
(This article belongs to the Special Issue Computational Intelligence in Communication Networks)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-2
Back to TopTop