Skip to Content

Computers, Volume 13, Issue 4

2024 April - 25 articles

Cover Story: Transformers have emerged as a major deep-learning architecture, with their diffusion spreading over a wide population due to some popular user-friendly interfaces, and their use extending from the original NLP domain to images and other forms of data. However, their user-friendliness has not translated into an equal degree of transparency.  Transformers maintain the level of opacity typically associated with deep-learning architectures. However, efforts are underway to add explainability to the features of transformers. In this paper, a review of the current status of those efforts and their observed trends is provided. The major explainability techniques are described by adopting a taxonomy based on the component of the architecture that is exploited to explain the transformer’s results. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list .
  • You may sign up for email alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.

Articles (25)

  • Article
  • Open Access
14 Citations
7,544 Views
30 Pages

5G is the fifth-generation technology standard for the new generation of cellular networks. Combining 5G and millimeter waves (mmWave) gives tremendous capacity and even lower latency, allowing you to fully enjoy the 5G experience. 5G is the successo...

  • Article
  • Open Access
36 Citations
18,234 Views
19 Pages

This paper investigates the evolving landscape of blockchain technology in renewable energy. The study, based on a Scopus database search on 21 February 2024, reveals a growing trend in scholarly output, predominantly in engineering, energy, and comp...

  • Article
  • Open Access
4 Citations
2,889 Views
25 Pages

In recent years, Sign Language Recognition (SLR) has become an additional topic of discussion in the human–computer interface (HCI) field. The most significant difficulty confronting SLR recognition is finding algorithms that will scale effecti...

  • Review
  • Open Access
2 Citations
4,169 Views
23 Pages

Smart Healthcare System in Server-Less Environment: Concepts, Architecture, Challenges, Future Directions

  • Rup Kumar Deka,
  • Akash Ghosh,
  • Sandeep Nanda,
  • Rabindra Kumar Barik and
  • Manob Jyoti Saikia

Server-less computing is a novel cloud-based paradigm that is gaining popularity today for running widely distributed applications. When it comes to server-less computing, features are available via subscription. Server-less computing is advantageous...

  • Article
  • Open Access
6 Citations
3,803 Views
16 Pages

The data economy has arisen in most developed countries. Instruments and tools to extract knowledge and value from large collections of data are now available and enable new industries, business models, and jobs. However, the current data market is a...

  • Article
  • Open Access
8 Citations
8,741 Views
24 Pages

This research article delves into the development of a reinforcement learning (RL)-based continuous authentication system utilizing behavioral biometrics for user identification on computing devices. Keystroke dynamics are employed to capture unique...

  • Article
  • Open Access
14 Citations
3,983 Views
21 Pages

A Holistic Approach to Use Educational Robots for Supporting Computer Science Courses

  • Zhumaniyaz Mamatnabiyev,
  • Christos Chronis,
  • Iraklis Varlamis,
  • Yassine Himeur and
  • Meirambek Zhaparov

Robots are intelligent machines that are capable of autonomously performing intricate sequences of actions, with their functionality being primarily driven by computer programs and machine learning models. Educational robots are specifically designed...

  • Article
  • Open Access
9 Citations
4,048 Views
25 Pages

Human Emotion Recognition Based on Spatio-Temporal Facial Features Using HOG-HOF and VGG-LSTM

  • Hajar Chouhayebi,
  • Mohamed Adnane Mahraz,
  • Jamal Riffi,
  • Hamid Tairi and
  • Nawal Alioua

Human emotion recognition is crucial in various technological domains, reflecting our growing reliance on technology. Facial expressions play a vital role in conveying and preserving human emotions. While deep learning has been successful in recogniz...

  • Review
  • Open Access
49 Citations
14,382 Views
26 Pages

Digital Twin and 3D Digital Twin: Concepts, Applications, and Challenges in Industry 4.0 for Digital Twin

  • April Lia Hananto,
  • Andy Tirta,
  • Safarudin Gazali Herawan,
  • Muhammad Idris,
  • Manzoore Elahi M. Soudagar,
  • Djati Wibowo Djamari and
  • Ibham Veza

The rapid development of digitalization, the Internet of Things (IoT), and Industry 4.0 has led to the emergence of the digital twin concept. IoT is an important pillar of the digital twin. The digital twin serves as a crucial link, merging the physi...

  • Article
  • Open Access
39 Citations
10,970 Views
16 Pages

Deepfakes are digital audio, video, or images manipulated using machine learning algorithms. These manipulated media files can convincingly depict individuals doing or saying things they never actually did. Deepfakes pose significant risks to our liv...

  • Article
  • Open Access
11 Citations
4,284 Views
14 Pages

Aspect-based sentiment analysis (ABSA) is a fine-grained type of sentiment analysis; it works on an aspect level. It mainly focuses on extracting aspect terms from text or reviews, categorizing the aspect terms, and classifying the sentiment polariti...

  • Article
  • Open Access
17 Citations
8,904 Views
19 Pages

Supervisory control and data acquisition (SCADA) systems enable industrial organizations to control and monitor real-time data and industrial processes. Migrating SCADA systems to cloud environments can enhance the performance of traditional systems...

  • Systematic Review
  • Open Access
2 Citations
2,037 Views
13 Pages

Neurophysiological measures have been used in the field of education to improve our knowledge about the cognitive processes underlying learning. Furthermore, the combined use of different neuropsychological measures has deepened our understanding of...

  • Article
  • Open Access
7 Citations
2,889 Views
20 Pages

To address the challenges associated with wind power integration, this paper analyzes the impact of distributed renewable energy on the voltage of the distribution network. Taking into account the fast control of photovoltaic inverters and the unique...

  • Article
  • Open Access
5 Citations
6,740 Views
20 Pages

Traditional hypervisor-assisted virtualization is a leading virtualization technology in data centers, providing cost savings (CapEx and OpEx), high availability, and disaster recovery. However, its inherent overhead may hinder performance and seems...

  • Article
  • Open Access
3 Citations
4,330 Views
25 Pages

GFLASSO-LR: Logistic Regression with Generalized Fused LASSO for Gene Selection in High-Dimensional Cancer Classification

  • Ahmed Bir-Jmel,
  • Sidi Mohamed Douiri,
  • Souad El Bernoussi,
  • Ayyad Maafiri,
  • Yassine Himeur,
  • Shadi Atalla,
  • Wathiq Mansoor and
  • Hussain Al-Ahmad

Advancements in genomic technologies have paved the way for significant breakthroughs in cancer diagnostics, with DNA microarray technology standing at the forefront of identifying genetic expressions associated with various cancer types. Despite its...

  • Article
  • Open Access
29 Citations
19,665 Views
34 Pages

An increasing demand for model explainability has accompanied the widespread adoption of transformers in various fields of applications. In this paper, we conduct a survey of the existing literature on the explainability of transformers. We provide a...

  • Review
  • Open Access
5 Citations
3,889 Views
23 Pages

Over the last decade, research on evolving computational thinking (CT) has garnered heightened attention. Assessing the publication tendencies and nucleus contents of investigations on progressing CT to direct future research initiatives, develop pol...

  • Article
  • Open Access
1,734 Views
13 Pages

We propose a monitoring system for detecting illicit and copyrighted objects in digital manufacturing (DM). Our system is based on extracting and analyzing high-dimensional data from blueprints of three-dimensional (3D) objects. We aim to protect the...

  • Article
  • Open Access
1 Citations
4,658 Views
17 Pages

Lite2: A Schemaless Zero-Copy Serialization Format

  • Tianyi Chen,
  • Xiaotong Guan,
  • Shi Shuai,
  • Cuiting Huang and
  • Michal Aibin

In the field of data transmission and storage, serialization formats play a crucial role by converting complex data structures into a byte stream that can be easily stored, transmitted, and reconstructed. Despite the myriad available serialization fo...

  • Article
  • Open Access
2 Citations
3,484 Views
15 Pages

This article provides an overview of count data and count models, explores zero inflation, introduces likelihood ratio tests, and explains how the Vuong test can be used as a model selection criterion for assessing overdispersion. The motivation of t...

  • Article
  • Open Access
2 Citations
1,803 Views
16 Pages

Problems related to privacy and security preservation are in the scope of the concerns of governments and policymakers because of their impact on fundamental rights. Users are called to act responsibly whenever they are potentially exposed to related...

  • Article
  • Open Access
2 Citations
2,464 Views
30 Pages

Temporal-Logic-Based Testing Tool Architecture for Dual-Programming Model Systems

  • Salwa Saad,
  • Etimad Fadel,
  • Ohoud Alzamzami,
  • Fathy Eassa and
  • Ahmed M. Alghamdi

Today, various applications in different domains increasingly rely on high-performance computing (HPC) to accomplish computations swiftly. Integrating one or more programming models alongside the used programming language enhances system parallelism,...

  • Review
  • Open Access
18 Citations
5,943 Views
27 Pages

A Qualitative and Comparative Performance Assessment of Logically Centralized SDN Controllers via Mininet Emulator

  • Mohammad Nowsin Amin Sheikh,
  • I-Shyan Hwang,
  • Muhammad Saibtain Raza and
  • Mohammad Syuhaimi Ab-Rahman

An alternative networking approach called Software Defined Networking (SDN) enables dynamic, programmatically efficient network construction, hence enhancing network performance. It splits a traditional network into a centralized control plane and a...

  • Article
  • Open Access
3 Citations
3,673 Views
21 Pages

Benchmarks play an essential role in the performance evaluation of novel research concepts. Their effectiveness diminishes if they fail to exploit the available hardware of the evaluated microprocessor or, more broadly, if they are not consistent in...

Get Alerted

Add your email address to receive forthcoming issues of this journal.

XFacebookLinkedIn
Computers - ISSN 2073-431X