Intelligent Data Analysis

An International Journal

Impact Factor
2023
1.7
CiteScore
2023
2.5

Volume

28, 6 issues

Latest issue

28:1 online 20 February 2024

Next issue

28:2 scheduled for April 2024

Back volumes

From volume 1, 1997

ISSN print

1088-467X

ISSN online

1571-4128

Aims & Scope

Intelligent Data Analysis provides a forum for the examination of issues related to the research and applications of Artificial Intelligence techniques in data analysis across a variety of disciplines. These techniques include (but are not limited to): all areas of data visualization, data pre-processing (fusion, editing, transformation, filtering, sampling), data engineering, database mining techniques, tools and applications, use of domain knowledge in data analysis, big data applications, evolutionary algorithms, machine learning, neural nets, fuzzy logic, statistical pattern recognition, knowledge filtering, and post-processing. In particular, papers are preferred that discuss the development of new AI-related data analysis architectures, methodologies, and techniques and their applications to various domains.

Papers published in this journal are geared heavily towards applications, with an anticipated split of 70% of the papers published being applications-oriented, research and the remaining 30% containing more theoretical research. Manuscripts should be submitted in PDF format only. Please prepare your manuscripts in single-space, and include figures and tables in the body of the text where they are referred to. For all enquiries regarding the submission of your manuscript please contact the IDA journal editor: editor1@ida-ij.com

Editorial Board

Editor-in-Chief

JM. Peña
Lurtis Ltd, Oxford
Wood Centre for Innovation Stansfeld Park, Quarry Rd
PO Box 1658, Oxford
Oxfordshire, OX4 9PW, United Kingdom

Center for Computer Simulation
Technical University of Madrid
Campus de Montegancedo / Scientific and Technological Park
N/N Montepríncipe Avenue
28660 Boadilla del Monte, Madrid, Spain
Email: jmpena@ida-ij.com

Founding Editor

A. Famili
1696 Des Sapins Gardens
Ottawa, ON K1C8E3
Canada

Editorial Board

Ahmad B. Al-Hasant
Faculty of Information Technology, Mutah University
Mu'tah, Jordan

Muthu Bala Anand
INTI International University, Malaysia
Department of Computer Science & Engineering,
Tagore Institute of Engineering and Technology, Attur, India

Márcio P. Basgalupp
Institute of Science and Technology, Federal University of Sao Paulo
Sao Paulo, Brazil

Elena Bellodi
Department of Engineering
University of Ferrara, Ferrara, Italy

Petr Berka
Department of Information and Knowledge Engineering, University of Economics
Prague, Czech Republic

Carmen Camara
Computer Science Department, Carlos III University of Madrid
Madrid, Spain

Mu-Yen Chen
Department of Engineering Science, National Cheng Kung University
Tainan, Taiwan

Lin Chi
Institute of Intelligent System, School of Software
Dalian University of Technology, Dalian, China

Boris Cule
Department of Cognitive Science and Artificial Intelligence, Tilburg University
Tilburg, the Netherlands

Wouter Duivesteijn
Department of Mathematics and Computer Science, Technische Universiteit Eindhoven
Eindhoven, Netherlands

Ad Feelders
Institute of Information & Computing Sciences, University of Utrecht
Utrecht, The Netherlands

Carlos Fernandez
Department of Computer Science and Information Technologies, University of A Coruña,
A Coruña, Spain

Benoît Frenay
Faculty of Computer Science / HuMaLearn / NaDI, Université de Namur
Namur, Belgium

Joao Gama
Artificial Intelligence and Computer Science Laboratory, University of Porto
Porto, Portugal

Jelena Graovac
Department of Computer Science, Faculty of Mathematics, University of Belgrade
Belgrade, Serbia

Achim G. Hoffmann
School of Computer Science & Engineering, University of South Wales
Sydney, NSW, Australia

Tamás Horváth
School of Computing Engineering and the Built Environment
Edinburgh Napier University, Edinburgh, Scotland, UK
Institute of Computer Science
Pavol Jozef Šafárik University, Košice, Slovakia.

Tzung-Pei Hong
Department of Computer Science and Information Engineering, National University of Kaohsiung
Kaohsiung, Taiwan

Juhua Hu
School of Engineering and Technology, University of Washington
Tacoma, WA, USA

Chien-Feng Huang
Department of Computer Science and Information Engineering, National University of Kaohsiung
Kaohsiung, Taiwan

Ivan Izonin
Department of Artificial Intelligence, Lviv Polytechnic National University
Lviv, Ukraine

Eric Jiang
Shiley-Marcos School of Engineering, University of San Diego
San Diego, CA, USA

Brian Keith N.
Department of Systems and Computer Engineering, Catholic University of the North
Antofagasta, Chile

Sung-Ho Kim
Division of Applied Mathematics, KAIST
Daejeon, South Korea

Frank Klawon
Department of Computer Science, Ostfalia University of Applied Sciences
Wolfenbuettel, Germany

Irena Koprinska
School of Computer Science, The University of Sydney
Camperdown, NSW, Australia

Viacheslav Kovtun
Department of Computer Control Systems, Vinnytsia National Technical University
Vinnytsia, Ukraine

Iurii Krak
Theoretical Cybernetics Department, Taras Shevchenko National University of Kyiv
Kyiv, Ukraine

Georg Krempl
Department of Information and Computing Sciences, Utrecht University
Utrecht, Netherlands

Ajay Kumar
Department of Information Technology, KIET Group of Institutions
Ghaziabad, India

Jerry Chun-Wei Lin
Department of Computing, Mathematics, and Physics, Western Norway University of Applied Sciences (HVL)
Bergen, Norway

Mingwei Lin
College of Computer and Cyber Security
Fujian Normal University, Fuzhou, China

Yingzi Lin
College of Engineering, Northeastern University
Boston, MA, USA

Shuai Liu
College of Information Science and Engineering
Hunan Normal University, Changsha, China

Haris M. Khalid
College of Engineering and Information Technology
University of Dubai, Dubai, United Arab Emirates

Priyan Malarvizhi Kumar
Department of Information Science, University of North Texas
Texas, USA

Andres Masegosa
Department of Computer Science, Aalborg University
Aalborg, Denmark

Andres Ponce de Leon
Department of Computer Science, University of Sao Paulo at Sao Carlos
Sao Carlos, Brazil

Pedro Lind
Department of Computer Science, Faculty of Technology, Art and Design, OSLOMET
Oslo, Norway

Gokul Prabhakar
Financial Services, Global Technology
Somerset, NJ, USA

Rita Ribeiro
Department of Computer Science, University of Porto & INESC TEC
Porto, Portugal

Fabrizio Riguzzi
Department of Mathematics and Computer Science, University of Ferrara
Ferrara, Italy

Alon Schclar
School of Computer Science, The Academic College of Tel-Aviv-Yaffo,
Tel Aviv, Israel

CB Sivaparthipan
Department of Computer Science, Tagore Institute of Engineering and Technology
Tamil Nadu, India

Leo Soheily Khah   
LiveRamp
Paris, France

Myra Spiliopoulou
Knowledge Management & Discovery Lab, Faculty of Computer Science Otto-von-Guericke University Magdeburg
Magdeburg, Germany

Gautam Srivastava
Department of Mathematics and Computer Science, Brandon University
Brandon, Canada

Einoshin Suzuki
Faculty of Information Science and Electrical Engineering, Kyushu University
Fukuoka, Japan

Marcin Szczuka
Institute of Mathematics, University of Warsaw
Warsaw, Poland

Chunwei Tian
School of Software, Northwestern Polytechnical University
Xi'an, China

Bhekisipho Twala
Artificial Intelligence & Data Science, Tshwane University of Technology
Republic of South Africa

Alejandro Vaisman
Information Engineering Department, Buenos Aires Institute of Technology
Buenos Aires, Argentina

Guiwu Wei
School of Business, Sichuan Normal University
Chengdu, China

De-Nian Yang
Institute of Information Science, Academia Sinica
New Taipei, Taiwan

Mingxin Yu
School of Instrument Science and Opto-Electronics Engineering, Beijing Information Science and Technology University
Beijing, China

Shuhan Yuan
Computer Science Department, Utah State University
Logan, UT, USA

De-Chuan Zhan
National Key Laboratory for Novel Software Technology, Nanjing University
Nanjing, China

Min-Ling Zhang
School of Computer Science and Engineering, Southeast University
Nanjing, China

Author Guidelines

SUBMISSION OF MANUSCRIPT

By submitting my article to this journal, I agree to the Author Copyright Agreement, the IOS Press Ethics Policy, and the IOS Press Privacy Policy.

Authors are requested to submit their manuscript electronically to the journal's editorial management system.

Authors are encouraged to use the IDA LaTeX style file and to follow the formatting rules explained in more detail below. MsWord users can prepare their paper as an unformatted double-spaced manuscript. When an article is accepted for publication the publisher will ensure that the article is typeset according to the journal style.

Intelligent Data Analysis invites the submission of research and application articles that comply with the aims and scope of the journal. In particular, articles that discuss development of new AI architectures, methodologies, and techniques and their applications to the field of data analysis are preferred. Manuscripts should be submitted in *.pdf format only. Please prepare your manuscripts in single-space, and include figures and tables in the body of the text where they are referred to. Manuscripts are received with the understanding that their content is unpublished material and is not being submitted for publication elsewhere. Further, it is understood that each co-author has made substantial contributions to the work described and that each accepts joint responsibility for publication.

Open access option
The IOS Press Open Library offers authors an open access option. By selecting the open access option, the article will be freely available from the moment it is published, also in the pre-press module. In the Open Library the article processing charges are paid in the form of an open access fee. Authors will receive an order form upon acceptance of their article. Open access is entirely optional.  

Publication types and fees

When an article is accepted for publication, authors are required to pay a publication fee that depends on the publication type:

  • Subscription-based publication (restricted access): US$450 / €450.
  • Open Access option (CC BY-NC 4.0): US$1500 / €1500.
  • Open Access option without the Non-Commercial clause (CC BY 4.0): US$2150/€2150.

Page charges do not apply to feature articles.

Required files
After the article has been accepted, the authors should submit the final version as source files, including a word processor file of the text, such as Word or LateX (If using LaTeX, please use the standard article.sty as a style file and also send a PDF version of the LaTeX file).

Colour figures
It is possible to have figures printed in colour, provided the cost of their reproduction is paid for by the author. See Preparation of Manuscripts for the required file formats.

PREPARATION OF MANUSCRIPTS

Organization of the paper and style of presentation
Manuscripts must be written in English. Authors whose native language is not English are advised to consult a professional English language editing service or a native English speaker prior to submission.

Manuscripts should be prepared with wide margins and double (single) spacing throughout, including the abstract, footnotes and references. Manuscripts should be submitted in *.pdf format only. Every page of the manuscript, including the title page, references, tables, etc., should be numbered. However, in the text no reference should be made to page numbers; if necessary, one may refer to sections. Try to avoid the excessive use of italics and bold face.

Manuscripts should be organized in the following order:

Title page

Body of text (divided by subheadings) + Tables, Figures and Figure captions

Acknowledgements

References

Headings and subheadings should be numbered and typed on a separate line, without indentation.

SI units should be used, i.e., the units based on the metre, kilogramme, second, etc.

Title page
The title page should provide the following information:

Title (should be clear, descriptive and not too long)

Name(s) of author(s); please indicate who is the corresponding author

Full affiliation(s)

Present address of author(s), if different from affiliation

Complete address of corresponding author, including tel. no., fax no. and e-mail address

Abstract; should be clear, descriptive, self-explanatory and not longer than 200 words, it should also be suitable for publication in abstracting services

Keywords

Tables

Figures and Tables

Number as Table 1, Table 2 etc, and refer to all of them in the text.

Figures and Tables should be included in the text in the exact location where they are referred to.

Each table should have a brief and self-explanatory title.

Column headings should be brief, but sufficiently explanatory. Standard abbreviations of units of measurement should be added between parentheses.

Vertical lines should not be used to separate columns. Leave some extra space between the columns instead.

Any explanations essential to the understanding of the table should be given in footnotes at the bottom of the table.

REFERENCES

Place citations as numbers in square brackets in the text. All publications cited in the text should be presented in an alphabetical list of references at the end of the manuscript in the following style:

[1] B. Newman and E.T. Liu, Perspective on BRCA1, Breast Disease 10 (1998), 3-10.
[2] D.F. Pilkey, Happy conservation laws, in: Neural Stresses, J. Frost, ed., Controlled Press, Georgia, 1995, pp. 332-391.
[3] E. Wilson, Active vibration analysis of thin-walled beams, Ph.D. Dissertation, University of Virginia, 1991.

Footnotes
Footnotes should only be used if absolutely essential. In most cases it is possible to incorporate the information in the text.

  • If used, they should be numbered in the text, indicated by superscript numbers and kept as short as possible.

Figures

Number figures as Fig. 1, Fig. 2, etc and refer to all of them in the text.

Each figure should be provided on a separate sheet. Figures should not be included in the text.

Colour figures can be included, provided the cost of their reproduction is paid for by the author.

For the file formats of the figures please take the following into account:

Line art should be have a minimum resolution of 600 dpi, save as EPS or TIFF

Grayscales (incl photos) should have a minimum resolution of 300 dpi (no lettering), or 500 dpi (when there is lettering); save as tiff

Do not save figures as JPEG, this format may lose information in the process

Do not use figures taken from the Internet, the resolution will be too low for printing

Do not use colour in your figures if they are to be printed in black & white, as this will reduce the print quality (note that in software often the default is colour, you should change the settings)

For figures that should be printed in colour, please send a CMYK encoded EPS or TIFF

Figures should be designed with the format of the page of the journal in mind. They should be of such a size as to allow a reduction of 50%.

On maps and other figures where a scale is needed, use bar scales rather than numerical ones, i.e., do not use scales of the type 1:10,000. This avoids problems if the figures need to be reduced.

Each figure should have a self-explanatory caption. The captions to all figures should be typed on a separate sheet of the manuscript.

Photographs are only acceptable if they have good contrast and intensity.

COPYRIGHT

Copyright of your article
Authors submitting a manuscript do so on the understanding that they have read and agreed to the terms of the IOS Press Author Copyright Agreement.

Article sharing
Authors of journal articles are permitted to self-archive and share their work through institutional repositories, personal websites, and preprint servers. Authors have the right to use excerpts of their article in other works written by the authors themselves, provided that the original work is properly cited. The consent for sharing an article, in whole or in part, depends on the version of the article that is shared, where it is shared, and the copyright license under which the article is published. Please refer to the IOS Press Article Sharing Policy for further information.

Quoting from other publications
Authors, when quoting from someone else's work or when considering reproducing figures or tables from a book or journal article, should make sure that they are not infringing a copyright. Although in general authors may quote from other published works, permission should be obtained from the holder of the copyright if there will be substantial extracts or reproduction of tables, plates, or other figures. If the copyright holder is not the author of the quoted or reproduced material, it is recommended that the permission of the author should also be sought. Material in unpublished letters and manuscripts is also protected and must not be published unless permission has been obtained. Submission of a paper will be interpreted as a statement that the author has obtained all the necessary permission. A suitable acknowledgement of any borrowed material must always be made.

PROOFS

The corresponding author will receive a PDF proof and is asked to check this proof carefully (the publisher will execute a cursory check only). Corrections other than printer's errors, however, should be avoided. Costs arising from such corrections will be charged to the authors.

PRE-PRESS 
The corrected proofs are published online in the journal's pre-press module and the article is fully citable by using its DOI number. This is not the final version. When the article is published in an issue, the final, updated version replaces the pre-press version.

PURCHASES

How to order reprints, a PDF file, journals, or IOS Press books
The corresponding author of a contribution to the journal will receive a complimentary PDF Author’s Copy of the article, unless otherwise stated. This PDF copy is watermarked and for personal use only. A free PDF copy will not be provided for conference proceedings and abstract issues. An order form for a PDF file without watermark, reprints or additional journal copies will be provided along with the PDF proof.

If you wish to order reprints of an earlier published article, please contact the publisher for a quotation. IOS Press, Fax: +31 20 687 0019. Email: editorial@iospress.nl.

An author is entitled to 25% discount on IOS Press books. See Author's discount (25%) on all IOS Press book publications.

KUDOS

Authors of published articles (non-prepress, final articles) will be contacted by Kudos. Kudos is a service that helps researchers maximize the impact and visibility of their research. It allows authors to enrich their articles with lay metadata, add links to related materials and promote their articles through the Kudos system to a wider public. Authors will receive no more than three emails: one invitation and a maximum of two reminders to register for the service and link the published article to their profile. Using and registering for Kudos remains entirely optional. For more information, please have a look at our authors section.

HOW TO PROMOTE YOUR WORK

Would you like some pointers on how to help your research achieve a wider reach and greater impact? Please consult our Promotional Toolkit for Authors for tips.

Please visit the IOS Press Authors page for further information.

Abstracted/Indexed in

Academic Search
ACM Digital Library
Business Source Complete
Cabell's Guide or Directory
Cambridge Scientific Abstracts
Compendex
CSA Illumina
DBLP Bibliography Server
EBSCO Databases
EBSCO Engineering Collection
Inspec IET
International Security & Counter-Terrorism Reference Center
io-port
PsycINFO
Science & Technology Collection
SciVerse Scopus
Ulrich's Periodicals Directory
Web of Science: Current Contents®/Engineering, Computing, and Technology
Web of Science: Journal Citation Reports/Science Edition
Web of Science: Science Citation Index Expanded (SciSearch®)

Open Access

By default, articles published in Intelligent Data Analysis are available only to institutions and individuals with access rights. However, the journal offers all authors the option to purchase open access publication for their article as part of the IOS Press Open Library. This means that the final published version will be freely available to anyone worldwide, indefinitely, under a Creative Commons license and without the need to purchase access to the article. This is also referred to as “gold” open access.

Gold open access pricing
Authors who choose gold open access publication will be subject to an article publication charge of €1500 / US$1500 for publication under the CC BY-NC 4.0 license or €2150 / US$2150 for publication under the CC BY 4.0 license. Pricing is exclusive of possible taxes. After an article is accepted for publication, the corresponding author will be informed regarding the open access option during the production stages, and will have the opportunity to purchase open access for their article. It could be that the open access fee of an article is waived completely due an institutional agreement IOS Press has with the corresponding authors' institution. Please check the institutional agreements page for details.

Green open access
Authors who do not make use of the gold open access option may still make their article freely available using self-archiving, also referred to as green open access. Authors may make their final accepted manuscript available for free download from their personal or institutional website or institutional archive. This model is free for the author.

Extra

Newsletter: Be sure to sign up to the IDA newsletter to receive alerts of new issues and other journal news. Sign up via this link: tiny.cc/IDAsignup.

Latest Newsletter: You can view the latest newsletter here

Special Issues

CURRENT SPECIAL ISSUES UNDER PREPARATION

To submit any contribution particularly addressed to any of the special issues please, include the address of the guest editors as well as the submissions@ida-ij.com and state the name of the special issue in both the subject and the body of the message.

The following special issues are under preparation:

  • Machine Learning Based Computational Bioinformatics for Healthcare Big Data
  • Image Mining and Knowledge Discovery for Business Applications
  • Deep Learning for Accident Prediction and Analysis Using Traffic Data

Machine Learning Based Computational Bioinformatics for Healthcare Big Data

In recent years, computational algorithms with machine learning have been widely employed in sectors such as construction, business, and healthcare. The usage of big data is also gaining more scope in healthcare. Thus, the advancements in technologies are used to the maximum potential in the healthcare sector to provide better service. However, the onset of the pandemic has increased the investments in healthcare and medicine to increase efficiency. It can also be seen that the accessibility and the comfortability of using healthcare services have increased exponentially with the introduction of these new techniques. The main objective of the advancements and innovations of technologies in healthcare is to improve the convenience of both the service provider and receiver. Increased awareness about health among people in tough times like this is also opening new opportunities for technologies like machine learning, big data and informatics in the healthcare sector.

Machine learning is one of the biggest growing fields in artificial intelligence. It allows the technological systems to find the solution to the problems without any human interaction. This special feature is of great help to big data in healthcare. The availability of large-scale data in healthcare can provide the machine learning algorithms with the required database to monitor and provide reliable solutions in healthcare. Firstly, automatic speech recognition and medical image analysis can be done with more accuracy using machine learning. Likewise, the integration of machine learning with computational bioinformatics can be used for protein sequence classification and image classifications. Added to that, these algorithms can also be employed in creating neural networks for brain imaging. The availability of different types of machine learning algorithms such as mRMR and mTBI makes it simple and easy to choose the required algorithm for specific tasks. Machine learning in computational bioinformatics also aids in providing better medical solutions by giving accurate medical analyses for physicians. In the administration of healthcare, machine learning can be used to identify insurance fraud, periodical monitoring of patients and drug discovery. All these advancements not only help in providing better healthcare in a community but also decrease diseases. Other usages of machine learning in healthcare big data include the prediction of diseases such as diabetes, Alzheimer’s, etc., heart disease monitoring and cancer treatments. Similarly, machine learning algorithms can be employed in all the fields of healthcare equipped with big data, including the analysis of DNA, monitoring metabolism and tracking the protein and genome sequences in the patients for better decision making. Thus, integrating different technologies can transform the healthcare sector to a whole new level. Original research and review articles in this area are encouraged in the following topic areas including, but are not limited to:

  • Gene-gene disease analysis with machine learning algorithms.
  • Role of computational bioinformatics in sequence analysis for healthcare.
  • Big data in healthcare for disease network analysis.
  • Contributions of machine learning in the healthcare sector.
  • Advantages of machine learning tools like Knime in big data analytics for healthcare.
  • Deep learning for better governance in the healthcare sector.
  • Recent trends in bioinformatics for healthcare.
  • Evolutionary researches in big data to aid the healthcare sector.
  • Role of big data and machine learning in testing and prediction of diseases.
  • Gene expression profiling using machine learning algorithms such as Weka.

Important Dates:

  • Paper Submission Deadline:     30.12.2022
  • Author Notification:                    27.03.2023
  • Revised Papers Submission:    25.05.2023
  • Final Acceptance:                      01.07.2023

Guest Editors Details:

Image Mining and Knowledge Discovery for Business Applications

In today’s world, business is recognized as one of the stimulating concerns for the progressive brainiac and dreamers to carry out their visions to happen really. The prime motive of different business organizations is to attain more development, which gradually leads to sustainable economic growth. This motive is achieved by planning proper business applications. It tends to be the governing property of business management by increasing productivity and enhancing innovative technologies that universally provide numerous growths in all business ecosystems.

Business creates greater chance and revolution, which changes the life of the people. Nowadays, business applications are generated using the new positive approach of grouping patterns. CIS (Core Information System) is one of the most critical factors for grouping patterns for business applications which provides extreme value to the particular business applications. The practice of knowledge discovery and image mining for business applications is to find the solutions through images and data. Image mining and knowledge discovery play an essential role in the knowledge extraction for new patterns and related data. The included image mining techniques involve device recognition, image extraction, image grouping, image clustering, and relationship rules mining. Image mining has been widely used in business sectors such as agricultural, industrial work, educational systems, space research, healthcare for diagnosing illness, and satellite stations. Similarly, knowledge discovery is a tool to solve problems in developing the business by making intelligent decisions. Marketing, banking and spam detection are essential segments in the corporate world. A knowledge discovery powered by image mining technology can effectively fulfil these segments. Furthermore, image mining and knowledge discovery for business applications find the procedure of automatically finding patterns, modifications, and interconnections in databases, and is a highly multidisciplinary sector constituting the convergence of various regulations such as database systems, machine learning, statistics, and computing for the business applications.

However, it is found clear that image mining and knowledge discovery for business applications is essential for the business users to run their firm so profitably by taking appropriate decisions with collective data information, it holds tremendous management challenges, inadequate knowledge for handling the applications, and complex application problems that have to be considered for the better result. Researchers and data analytics are invited to present an abstract text related to this ground. The special issue provides various opportunities to academicians to enhance business applications with advanced technologies.

Topics:

  • Recent progress in technology for high dimensional data in knowledge discovery for business applications
  • Future perspectives of image mining for effective and intelligent business applications
  • Need for highly automated and reliable data in image mining
  • An empirical study on advanced data mining technics in business applications
  • Exploring new innovative technique that exhibits the uniqueness of image data
  • Limitations and challenges faced in implementing image mining for business applications
  • Incorporation of new visualization technology for image mining for improved business environment
  • Problems and risk associated with management problems in knowledge discovery for business
  • Data image mining for business environment: Present and future opportunities

Important Dates:

  • Paper Submission Deadline:     30.01.2023
  • Author Notification:                    25.04.2023
  • Final Acceptance:                      26.09.2023

Guest Editors Details:

Deep Learning for Accident Prediction and Analysis Using Traffic Data

Road accident is a severe problem globally, leading to the major cause of preventable death across several countries. In general, road accidents are due to various concerns such as road conditions, vehicles, environment, road users, traffic, the way the users handle road traffics, and many more. The probability of road accidents increases every day with a growing rate of urbanization and metropolitan activities. As a result, road accidents can adversely cut off millions of lives with its accelerating frequency if left unaddressed. Though it is difficult, predicting the risk of road accidents is not completely impossible. Many countries collect accident records, weather forecasts, and road infrastructure data and make them publicly available to predict the risk of road accidents. Presently, many researchers worldwide are actively involved in designing and developing effective strategies for road accident prediction and prevention, but traffic accidents are still unavoidable.

To effectively counter this problem, predicting patterns involved with various factors causing road accidents and developing accurate prediction models for various accidental scenarios has become vital. Deep learning empowers many aspects of society. Based on of road accident prediction and analysis, deep learning forms the efficient solution in contrast to the traditional machine learning methodologies. It can efficiently deal with natural data in the raw form with multiple levels of abstraction. The use of deep learning for road accident prevention is not only limited to the analysis of historical accident records; indeed, it can predict the likelihood of the accidents in a real-time scenario with higher accuracy measures. There are several ways deep learning can enhance the process of accident prediction and analysis. This includes it can offer an appropriate roadway design, safe route planning, emergency vehicle allocation, offer interactive driving guidance to the road users, and enhance the potential of intelligent vehicles with vision techniques.

This special issue is specifically devoted to finding efficient ways of using deep learning to predict and analyze road traffic injuries. The prime focus is twofold. The first part deals with identifying and analyzing the possibility of risk factors from the historical data. And the second part deals with real-time accident prediction and prevention measures. Researchers and practitioners are most welcomed to present their novel and innovative solutions against this background.

Topics:

  • Recent progress in technology for high dimensional data in knowledge discovery for business applications
  • Future perspectives of image mining for effective and intelligent business applications
  • Need for highly automated and reliable data in image mining
  • An empirical study on advanced data mining technics in business applications
  • Exploring new innovative technique that exhibits the uniqueness of image data
  • Limitations and challenges faced in implementing image mining for business applications
  • Incorporation of new visualization technology for image mining for improved business environment
  • Problems and risk associated with management problems in knowledge discovery for business
  • Data image mining for business environment: Present and future opportunities

Important Dates:

  • Paper Submission Deadline:     28.12.2022
  • Author Notification:                    14.05.2023
  • Final Acceptance:                      15.07.2023

Guest Editors Details:

Latest Articles

Discover the contents of the latest journal issue:

A review on network representation learning with multi-granularity perspective
Lufeng Wang, Shun Fu, Jie Yang

Knowledge graph embedding in a uniform space
Shudong Chen, Da Tong, Rong Ma, Donglin Qi, Yong Yu

How graph features from message passing affect graph classification and regression?
Mahito Sugiyama, Masatsugu Yamada

TSAGNN: Temporal link predict method based on two stream adaptive graph neural network
Jing Guo, Yuhang Zhu, Haitao Li, Shuxin Liu, Yingle Li

Conversational recommender based on graph sparsification and multi-hop attention
Yuhao Wang, Yihao Zhang, Wei Zhou, Pengxiang Lan, Haoran Xiang, Junlin Zhu, Meng Yuan

Sustainable Development Goals

The content of this journal relates to SDG:

sdg symbolsdg symbolsdg symbolsdg symbolsdg symbolsdg symbolsdg symbolsdg symbolsdg symbolsdg symbolsdg symbolsdg symbol

Visit the SDG page for more information.

Supporting Diversity and Inclusion

This journal supports IOS Press' actions relating to the Sustainable Development Goals (SDGs) and commits to the Diversity and Inclusion Statement.

dark blue banner for IDA author geo data for SDGs

More information will be available in due course. Check the SDGs page for updates.

IDA news signup banner