New Generation Computing (NGC)

Special Issue Call for Papers

The New Generation Computing Journal welcomes contributions for a special issue:

 

Hybrid Ensemble Machine Learning for Complex and Dynamic Data

Guest editors

Contact

Bartosz Krawczyk, Wroclaw University of Technology, Poland
Bogdan Trawiński, Wroclaw University of Technology, Poland

bartosz.krawczyk@pwr.edu.pl
bogdan.trawinski@pwr.edu.pl

Objectives and topics

Hybrid and ensemble methods in machine learning have gained a great attention of scientific community over the last several years. Multiple learning models have been theoretically and empirically shown to provide significantly better performance than their single base models. Their most interesting application area lies in analyzing of complex, high dimensional and big data, that cannot be handle efficiently by single -model approaches. Another contemporary problem lies in providing efficient compound methods for tackling streams of data in dynamic and

non-stationary environments. This Special Issue of New Generation Computing, is devoted to both hybrid and ensemble methods in solving complex and non-stationary problems. The impact factor of NGC is 0.795. The papers within this issue will be a combination of open submission procedure and invitations sent after the success of the 6th Asian Conference on Intelligent Information and Database Systems (ACIIDS 2014) and especially, the Special Session on Multiple Model Approach to Machine Learning (MMAML 2014). We want to offer an exciting opportunity for researchers and practitioners to present their work and publish recent advances in this area.

 

The scope of the special issue includes the following topics:

  • Theoretical framework for ensemble methods
  • Ensemble learning algorithms: bagging, boosting, stacking, etc.
  • Hybridization of ensembles
  • Combined classifiers for big and high-dimensional data
  • Multiple Classifier Systems for im balanced classification
  • Ensembles for one-class classification
  • Mining data streams using ensemble methods
  • Ensemble methods for dealing with concept drift
  • Incremental, evolving, and online ensemble learning
  • Diversity, accuracy, interpretability, and stability issues
  • Classifier selection and ensemble pruning
  • Subsampling and feature selection in multiple model machine learning
  • Multi-objective ensemble learning
  • Assessment and statistical analysis of ensemble models
  • Applications of ensemble methods in business, engineering, medicine, etc.

International Reviewer Board (tentative)

·          Ethem Alpaydin, Bogaziçi University, Turkey

·          Abdelhamid Bouchachia, Bournemouth University, UK

·          Robert Burduk, Wroclaw University of Technology, Poland

·          Rung-Ching Chen, Chaoyang University of Technology, Taiwan

·          Suphamit Chittayasothorn, King Mongkut's Institute of Technology Ladkrabang, Thailand

·          Oscar Cordón, University of Granada, Spain

·          José Alfredo F. Costa, Federal University (UFRN), Brazil

·          Bogusław Cyganek, AGH University of Technology, Poland

·          Ireneusz Czarnowski, Gdynia Maritime University, Poland

·          Joao Gama, University of Porto, Portugal

·          Fernando Gomide, State University of Campinas, Brazil

·          Lawrence O. Hall, University of South Florida, USA

·          Francisco Herrera, University of Granada, Spain

·          Tzung-Pei Hong, National University of Kaohsiung, Taiwan

·          Konrad Jackowski, Wroclaw University of Technology, Poland

·          Przemysław Kazienko, Wrocław University of Technology, Poland

·          Mark Last, Ben-Gurion University of the Negev, Israel

·          Kun Chang Lee, Sungkyunkwan University, Korea

·          Edwin Lughofer, Johannes Kepler University Linz, Austria

·          Bogdan Trawiński, Wrocław University of Technology, Poland

·          Olgierd Unold, Wrocław University of Technology, Poland

·          Michał Woźniak, Wrocław University of Technology, Poland

·          Faisal Zaman, Dublin City University, Ireland

·          Zhongwei Zhang, University of Southern Queensland, Australia

·          Zhi-Hua Zhou, Nanjing University, China

·          Indre Zliobaite, Aalto University, Finland

Important dates

Expression of interest, submission of the tentative title via EasyChair: September 15, 2014
Submission of the paper for revision via EasyChair: November 15, 2014
First round of reviews: January 15, 2015
Revised version submission deadline: February 15, 2015
First round of reviews: March 15, 2015
Camera-ready copies of accepted papers due: April 15, 2015

Submission

The submission of the title is required to form the list of papers and should be send to the EasyChair service at https://www.easychair.org/conferences/?conf=hemlcdd2014; select “New Submission”, mark “Abstract Only” at the bottom. Since the abstract is not necessary that time, you may put any text in the Abstract field.

 

Authors are encouraged to send new, unpublished research results. However, in special cases extended works based on previously published conference papers can be considered. However, the journal submission must contain at least 50% new material and the title of the extended version must clearly and unmistakably differ from the title of the article presented at the conference.

 

The submission of the paper for the revision should be send in the electronic version (PDF) via EasyChair available at https://www.easychair.org/conferences/?conf=hemlcdd2014. To be fully considered for publication, papers must be received by the due date and meet the following requirements. Papers must be written in English and the maximal length of the final version should be 20 pages (incl. figures and tables) in the journal format. The electronic data of the final version of papers must be prepared in LaTeX according to the New Generation Computing guidelines.

 

All papers submitted will be reviewed by the independent reviewers. However, please note that this invitation does not mean your paper will be automatically accepted for publication.