Special Issue "Advanced Technologies and Applications in Computer Science and Engineering"

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: 15 December 2023 | Viewed by 1468

Special Issue Editors

Faculty of Electronic Engineering and Technologies, Technical University of Sofia, 1000 Sofia, Bulgaria
Interests: artificial intelligence; electric vehicles; energy storage; mathematical modeling; control theory and applications; smart cities and smart grids; power electronic converters; power electronic systems
Special Issues, Collections and Topics in MDPI journals
Faculty of Computer Systems and Technologies, Technical University of Sofia, 1000 Sofia, Bulgaria
Interests: software engineering; software technologies and application systems; cloud technologies; internet of things; smart cities; cybersecurity; artificial intelligence
Faculty of Computer Systems and Technologies, Technical University of Sofia, 1000 Sofia, Bulgaria
Interests: artificial intelligence; machine learning and deep learning; neural networks; pattern recognition; image analyses; optimization algorithms; metaheuristics

Special Issue Information

Dear Colleagues,

Computer science is one of the fastest-growing branches of engineering. This is due both to the increased capabilities and accessibility of the hardware, and to the successful implementation of modern information and communication technologies. Achievements in the fields of artificial intelligence, big data, cloud technologies, modeling and computational mathematics are notable. In this respect, there is no other field of science that contributes so directly to improving the quality of life of modern society. Intelligent medicine, virtual and augmented reality, smart networks and cities, autonomous cars, digital factories and productions and many other achievements of modern civilization are the product of progress in the field of computer science.

The 2023 11th International Scientific Conference COMPUTER SCIENCE (COMPSCI 2023) organized by the Faculty of Computer Systems and Technologies continues the tradition of a series of ten conferences organized between 2004 and 2022 as a scientific forum to present a discussion of innovative ideas, concepts and technologies in the field of computer science, computer and software engineering, information technology and their application. Participation in the conference of researchers from different countries stimulates the building of a scientific community and encourages interaction and international cooperation.

This Special Issue primarily represents a collection of extended versions of selected papers presented at the 2023 11th International Scientific Conference COMPUTER SCIENCE (COMPSCI 2023). However, papers not presented at the COMPSCI 2023 are also welcome. We invite you to contribute original research articles or comprehensive review papers to this Special Issue. The topics of interest include, but are not limited to, the following:

  • Artificial intelligence, robotics and control;
  • Cyber security and cyber protection;
  • Data structures and storage;
  • Cloud and blockchain technologies;
  • Electric and autonomous vehicles;
  • High technology management;
  • Human-centered computing;
  • Renewable and green energy;
  • Smart cities and smart society;
  • Software engineering;
  • Software technologies and applications systems;
  • Telecommunications engineering.

Dr. Nikolay Hinov
Prof. Dr. Ognyan Nakov
Prof. Dr. Milena Lazarova
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. Electronics 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 2200 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

  • artificial intelligence, robotics and control
  • cyber security and cyber protection
  • data structures and storage
  • cloud and blockchain technologies
  • electric and autonomous vehicles
  • smart cities and smart society
  • software engineering
  • software technologies and applications systems
  • human-centered computing
  • renewable and green energy
  • telecommunications engineering

Published Papers (2 papers)

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

Research

22 pages, 96717 KiB  
Article
RepRCNN: A Structural Reparameterisation Convolutional Neural Network Object Detection Algorithm Based on Branch Matching
Electronics 2023, 12(19), 4180; https://doi.org/10.3390/electronics12194180 - 09 Oct 2023
Viewed by 457
Abstract
A CNN object detection method based on the structural reparameterisation technique using branch matching is proposed to address the problem of balancing accuracy and speed in object detection techniques. By the structural reparameterisation of the convolutional layer in the object detection network, the [...] Read more.
A CNN object detection method based on the structural reparameterisation technique using branch matching is proposed to address the problem of balancing accuracy and speed in object detection techniques. By the structural reparameterisation of the convolutional layer in the object detection network, the amount of computation and the number of parameters in the network inference are reduced, the memory overhead is lowered, and the use of the branch-matching method to improve the structural reparameterisation model improves the computational efficiency and speed of the network while maintaining the detection accuracy. Optimisation is also carried out in terms of target screening and loss function, and a new CPC NMS screening strategy was introduced to further improve the performance of the model. The experimental results show that the proposed method achieves competitive results on the PASCAL VOC2012 and MS COCO2017 datasets compared to the traditional object detection methods and the current mainstream models, achieving a better balance between the detection accuracy and detection speed. Full article
Show Figures

Figure 1

20 pages, 661 KiB  
Article
Beamsteering-Aware Power Allocation for Cache-Assisted NOMA mmWave Vehicular Networks
Electronics 2023, 12(12), 2653; https://doi.org/10.3390/electronics12122653 - 13 Jun 2023
Viewed by 527
Abstract
Cache-enabled networks with multiple access (NOMA) integration have been shown to decrease wireless network traffic congestion and content delivery latency. This work investigates optimal power control in cache-assisted NOMA millimeter-wave (mmWave) vehicular networks, where mmWave channels experience double-Nakagami fading and the mmWave beamforming [...] Read more.
Cache-enabled networks with multiple access (NOMA) integration have been shown to decrease wireless network traffic congestion and content delivery latency. This work investigates optimal power control in cache-assisted NOMA millimeter-wave (mmWave) vehicular networks, where mmWave channels experience double-Nakagami fading and the mmWave beamforming is subjected to beamsteering errors. We aim to optimize vehicular quality of service while maintaining fairness among vehicles, through the maximization of successful signal decoding probability for paired vehicles. A comprehensive analysis is carried out to understand the decoding success probabilities under various caching scenarios, leading to the development of optimal power allocation strategies for diverse caching conditions. Moreover, an optimal power allocation is proposed for the single-antenna case, for exploiting the cached data as side information to cancel interference. The robustness of our proposed scheme against variations in beamforming orientation is assessed by studying the influence of beamsteering errors. Numerical results demonstrate the effectiveness of the proposed cache-assisted NOMA scheme in enhancing cache utility and NOMA efficiency, while underscoring the performance gains achievable with larger cache sizes. Full article
Show Figures

Figure 1

Back to TopTop