Topical Collection on Data Fusion in the era of Data Science: From Big Data to Even Bigger

Scope

We are facing an evolution in the way traditional Business Intelligence (BI) operations are conducted, bringing it closer to Data Science. In applying innovative techniques to old problems, however, we must be careful to distinguish between those that are advances in Machine Learning research and concrete results.

Machine Learning offers the possibility to automate processes, even sophisticated ones, without having to explicitly program a computer, but letting the rules and structures emerge from the available data.

First, the amount of data must be sufficient to support the algorithms and distinguish the value signal from the background noise.  However, there are many possible models and approaches in order to accomplish this task. The choice of the most suitable models depends crucially on the type of problem and data available, and the world of research (the state of the art) offers some preliminary indications in this regard.

Data Science thus places itself at the intersection of theory and practice to explore, define and structure the most effective models and processes to arrive at the set objective.

A new challenge is certainly characterized by what is called Data Fusion, that is combining and exploiting heterogeneous data sources, and that of mastering a datum (but also a project) evolving over time.

Remembering that the availability of (good) data is the main bottleneck in applying Machine Learning procedures, Data Fusion is therefore promising because it allows problems to be dealt with that otherwise would not be solvable.

The aim of this theme issue is to explore the state-of-the-art, methodologies and applications related to all aspects of Data Fusion in the era of Data Science. Review or summary articles — for example a critical evaluation of the state of the art, or an insightful analysis of established and upcoming technologies — may be accepted if they demonstrate academic rigor and relevance.

Topics of interest include (but not limited to)

  • Big Data Fusion
  • Data Fusion Algorithms
  • Data Stream processing for Data Fusion
  • Data Fusion in Data Science Tasks
  • Data Fusion in the Internet of Things
  • Bio-Inspired Data Fusion
  • Data Fusion Applications: Medicine, Economics, Cultural Heritage, etc.
  • Multimedia Data Fusion
  • Analytics for Data Fusion
  • Data Visualizations techniques for Data Fusion

Guest Editorial Team

Francesco Piccialli  (lead Guest Editor), University of Naples Federico II, Italy, francesco.piccialli@unina.it
Gwanggil Jeon, Incheon University, Republic of Korea, gjeon@inu.ac.kr
Sahil Garg, École de Technologie Supérieure, Montreal, Canada, sahil.garg@ieee.org
Giampaolo Casolla, University of Naples Federico II, Italy, giampaolo.casolla@unina.it

Schedule

Submissions Deadline:            July 1, 2020
First Reviews Due:                   September 1, 2020
Revision Due:                          October 15, 2020
Second Reviews Due/Notification: November 15, 2020
Final Manuscript Due:             December 31, 2020

Submission Format and Review Guidelines

Authors are solicited to submit complete unpublished articles and follow the guidelines set out by Neural Computing and Applications (NCAA).
Each article for submission should be formatted according to the style and length limit of NCAA. Please refer to “Submission guidelines” on the website: https://www.springer.com/521
All submissions will be peer-reviewed by independent reviewers and selected based on originality, scientific quality and relevance to this special issue. Manuscripts should be submitted online at https://www.editorialmanager.com/ncaa/default.aspx  and follow the "Submit A Manuscript" link on that page. When submitting your manuscript please select the article type "S.I.: Data Fusion in the era of Data Science".