Collection Launch: Recent Advances in Information Fusion

PeerJ are excited to announce the launch of our most recent Conference Collection – Recent Advances in Information Fusion – featuring selected research presented at the 3rd International Conference on Data Science, E-learning and Information Systems 2021 (Data’21) held in Petra, Jordan, in April 2021.


The PeerJ Computer Science Conference Collection “Recent Advances in Information Fusion” is available to download here


This Conference Collection is concerned with an important area that has recently attracted the attention of Computer Science researchers: Information Fusion.

The term Information Fusion refers to the process of combining information from different sources with the goal of producing more complete, improved and precise information than that provided by each source separately. In the last few years, the Information Fusion paradigm has grown rapidly due to various factors such as the sustained increase in systems connectivity, and the advent and development of concepts such as the Internet of Things (IoT) and Big Data.

We developed this Conference Collection around the theme of Information Fusion to highlight the critical importance of this topic for continued progress in Computer Science.

Recent Advances in Information Fusion” is formed of four published articles, highlighted below, that have examined this issue in various applications, such as sentiment analysis in pandemics, hand-written Arabic text management, lean requirements traceability automation and open-source intelligence.

The aim of this Conference Collection is to explore the latest advances in Information Fusion related to new methods, architectures, technologies and applications that have emerged from the community. We hope the Information Fusion community will find this to be an informative and useful collection of articles.

Collection Editors

Prof. Shadi A. Aljawarneh
Jordan University of Science and Technology.

Prof. Juan Alfonso Lara Torralbo
School of Engineering , UDIMA Universidad a Distancia de Madrid, Spain.


Algorithm based on normal coordinate vectors with 16 segments for the data fusion from hand-written Arabic text implemented with MATLAB

Said S. Saloum, Iván García-Magariño​

Hand-written text recognition is useful for interpreting records in different fields such as healthcare, surgery and police in which professionals may avoid technical equipment and prefer writing notes on paper. In order to perform data fusion from different data sources, handwriting automatic recognition involves barriers such as different ways of writing letters and deformation due to many reasons. This work presents a novel handwriting recognition approach based on the application of coordinate vectors to find similarities in different kinds of deformations. In particular, it has been implemented using 16 segments in order to distinguish all the particularities in matching the new text considering a dataset with a machine-learning approach. The implementation of this approach with MATLAB shows promising results with accuracy of 92.8% for with ensemble and bagged trees, after analyzing 22 possible combinations of machine learning and processing techniques.

A machine-learning scraping tool for data fusion in the analysis of sentiments about pandemics for supporting business decisions with human-centric AI explanations

Swarn Avinash Kumar, Moustafa M. Nasralla, Iván García-Magariño​, Harsh Kumar

The COVID-19 pandemic is changing daily routines for many citizens with a high impact on the economy in some sectors. Small-medium enterprises of some sectors need to be aware of both the pandemic evolution and the corresponding sentiments of customers in order to figure out which are the best commercialization techniques. This article proposes an expert system based on the combination of machine learning and sentiment analysis in order to support business decisions with data fusion through web scraping. The system uses human-centric artificial intelligence for automatically generating explanations. The expert system feeds from online content from different sources using a scraping module. It allows users to interact with the expert system providing feedback, and the system uses this feedback to improve its recommendations with supervised learning.

The effect of ISO/IEC 27001 standard over open-source intelligence

Abdallah Qusef​, Hamzeh Alkilani​

The Internet’s emergence as a global communication medium has dramatically expanded the volume of content that is freely accessible. Through using this information, open-source intelligence (OSINT) seeks to meet basic intelligence requirements. Although open-source information has historically been synonymous with strategic intelligence, today’s consumers range from governments to corporations to everyday people. This paper aimed to describe open-source intelligence and to show how to use a few OSINT resources. In this article, OSINT (a combination of public information, social engineering, open-source information, and internet information) was examined to define the present situation further, and suggestions were made as to what could happen in the future. OSINT is gaining prominence, and its application is spreading into different areas. The primary difficulty with OSINT is separating relevant bits from large volumes of details. Thus, this paper proposed and illustrated three OSINT alternatives, demonstrating their existence and distinguishing characteristics. The solution analysis took the form of a presentation evaluation, during which the usage and effects of selected OSINT solutions were reported and observed. The paper’s results demonstrate the breadth and dispersion of OSINT solutions. The mechanism by which OSINT data searches are returned varies greatly between solutions. Combining data from numerous OSINT solutions to produce a detailed summary and interpretation involves work and the use of multiple disjointed solutions, both of which are manual. Visualization of results is anticipated to be a potential theme in the production of OSINT solutions. Individuals’ data search and analysis abilities are another trend worth following, whether to optimize the productivity of currently accessible OSINT solutions or to create more advanced OSINT solutions in the future.

Lean requirements traceability automation enabled by model-driven engineering

María-José Escalona, Nora Koch, Laura Garcia-Borgoñon

The benefits of requirements traceability, such as improvements in software product and process quality, early testing, and software maintenance, are widely described in the literature. Requirements traceability is a critical, widely accepted practice. However, very often it is not applied for fear of the additional costs associated with manual efforts or the use of additional tools. This article presents a “low-cost” mechanism for automating requirements traceability based on the model-driven paradigm and formalized by a metamodel for the creation and monitoring of traces and an integration process for traceability management. This approach can also be useful for information fusion in industry insofar that it facilitates data traceability. This article extends an existing model-driven development methodology to incorporate traceability as part of its development tool. The tool has been used successfully by several companies in real software development projects, helping developers to manage ongoing changes in functional requirements. One of those projects is cited as an example in the paper. The authors’ current work leads them to conclude that a model-driven engineering approach, traditionally used only for the automatic generation of code in a software development process, can also be used to successfully automate and integrate traceability management without additional costs. The systematic evaluation of traceability management in industrial projects constitutes a promising area for future work.



Interested in organising a PeerJ Collection for your next conference? Email us at 


You may also like...