Topical Collection on ‘Babel Fish’ for Feature-driven Machine Learning: From Financial Services to Healthcare

Aims

This Topical Collection on the ‘Babel Fish’ for Feature-driven Machine Learning (ML) seeks for publications highlighting novel practical or potential applications of feature-driven ML to use cases including but not limited to financial services, wherein it has been a proven technology in industry, to more cutting-edge applications in healthcare, public sector, engineering, and education. There is a considerable body of literature on feature extraction and selection algorithms that could enable feature-driven ML for specific applications; however, it presents either theoretical mathematical algorithms that do not lead to tangible applications or approaches that lack feasibility in the field of interest, not being reusable in other domains either.

Scope

We welcome submissions of original research articles involving methods outlined in the 'Objectives' encompassing both real-life applications and those experiments or simulations showing potential and feasibility for real-life applications. Although the topics can be those mentioned in the ‘Aims’ or even broader, preference will be given to those applications involving mental health and psychiatry for healthcare-related articles, as well as capital investment, trading and cybersecurity for the financial services-related studies.

Objectives

The feature-driven applications presented should leverage one or more of the following to help in solving either classification or regression problems: feature selection, feature extraction, feature engineering. The problems defined should be generalised enough for the solutions developed to be so too, such that they have been or can be applied in other domains as well. The feature-driven approaches must lead to the following requirements being met in the resulting ML-based decision support systems: accuracy, completeness, reliability and explainability, i.e., ease of interpretability from a user standpoint, e.g., clinicians for healthcare-related applications, business professionals for financial services-related ones.

Topics of interest

We invite the submission of high-quality papers related to one or more of the following topics:

  • Machine Learning for feature extraction
  • Machine Learning for feature engineering
  • Machine Learning for feature selection
  • Hybrid feature engineering
  • Feature-driven Machine Learning for Financial Services - in particular, to improve capital investment, trading and for cybersecurity
  • Feature-driven Machine Learning for Healthcare - in particular, to support personalised treatments and predict treatment response for patients with mental health disorders
  • Feature-driven Machine Learning for Public Sector
  • Feature-driven Machine Learning for Engineering
  • Feature-driven Machine Learning for Education
  • Feature-driven Machine Learning for Enhanced Pattern Recognition
  • Feature-driven Machine Learning for Image and Video Classification
  • Feature-driven Machine Learning for Isolated and Continuous Speech Processing
  • Feature-driven Machine Learning for Text Classification
  • Feature-driven Machine Learning for Anomaly Detection
  • Ensembles of Feature-driven Machine Learning approaches

Guest Editors

Luca Parisi (Lead Guest Editor), Coventry University and University of Bradford, UK, parisil@coventry.ac.uk
Alin Ungureanu, Chelmer Ltd., New Zealand, alin@chelmer.co.nz
Lee Andrew Kissane, Tokyo Mental Health, International Medical K.K. and American Clinic Tokyo, Japan, andrew@tokyomentalhealth.com
Richard Tranter, Mid North Coast Local Health District, Australia, richard.tranter@health.nsw.gov.au

Provisional Deadlines

Deadline for submissions: extended to 28th  February 2021
Deadline for review:          30th March 2021
Decisions:                            9th April 2021
Deadline for revised version by authors: 13th  May 2021
Deadline for 2nd review:   27th May 2021
Final decisions:                  11th June 2021

Peer Review Process

All the papers will go through a double blind review process and will be reviewed by at least two reviewers. A thorough check will be done and the guest editors will check any significant similarity between the manuscript under consideration and any published paper or submitted manuscripts of which they are aware. In such case, the article will be directly rejected without proceeding further. Guest editors will make all reasonable effort to receive the reviewer’s comments and recommendation on time.

The submitted papers must provide original research that has not been published nor currently under review by other venues. Conference papers should be clearly identified by the authors at the submission stage and an explanation should be provided about how such papers have been extended.  At least 30% of new content is expected.

Submission Guideline 

Submissions for the special issue should follow the submission format and guidelines of the journal at https://www.springer.com/journal/521/submission-guidelines.
Each manuscript should not exceed 16 pages in length (inclusive of figures and tables).

Authors should select ‘‘Babel Fish’ for Feature-driven Machine Learning to Maximise Societal Value' during the submission step 'Additional Information'.

Manuscripts must be submitted to the journal online system at https://www.editorialmanager.com/ncaa/default.aspx. All papers will be refereed by experts in the field based on originality, significance, quality and clarity. Every submitted paper will be reviewed by at least two reviewers. The final acceptance is the Editor-in-Chief's decision.