Pattern Discovery from Multi-Source Data (PDMSD)

in Special Issue   Posted on August 13, 2017 

Information for the Special Issue

Submission Deadline: Wed 31 May 2017
Journal Impact Factor : 3.255
Journal Name : Pattern Recognition Letters
Journal Publisher:
Website for the Special Issue:
Journal & Submission Website:

Special Issue Call for Papers:

Summary and Scope:

Advanced data acquisition technologies have been producing massive amounts of data in engineering sciences, and computer science. In addition to volume, data are naturally comprised of multiple representations in many real applications since only single-source data do not always meet all types of scenarios. For example, in image analysis, images are represented by local features and global features. Usually, different sources describe different characteristics of images. Thanks to the massive volume and multi-source structure of data, studies have shown that, it is very difficult to deal with multi-source data using conventional analysis tools. We have also noticed that pattern recognition from multi-source data is different activity than that from single-source data. Thus the understanding and analysis of multi-source data has been a very popular topic in machine learning and computer vision. Meanwhile the advent of multi-source data creates new challenges for current information technology.

In this special issue, we invite papers that address many of the challenges of pattern discovery from multi-source data. The list of possible topics includes, but not limited to:

– Pattern discovery of multi-source big database

  • Data analysis and pattern recognition in multi-source big database (associate analysis, clustering, synthesizing)
  • Distributed algorithms of multi-source big database
  • Data preprocessing (e.g., missing value imputation and feature selection)

– Pattern discovery of multi-modal multimedia data

  • Feature extraction (e.g., deep learning methods, local feature extraction methods, and global feature extraction methods)
  • Multi-modal multimedia tools and applications (e.g. storing, ranking, hashing, and retrieval)
  • Multi-modal multimedia understanding and analysis (e.g., supervised learning, unsupervised learning and semi-supervised learning)

– Pattern discovery of  multi-source medical image data

  • Segmentation method for medical image data
  • Medical image data retrieval
  • Data fusion of multi-source or multi-structure medical image data

Submission Guideline

Authors should prepare their manuscript according to the Guide for Authors available from the online submission page of Pattern Recognition Letters at Specifically, authors should find the acronym of the special issue visible to be selected as article type “SI:PDMSD”. The maximal length of the submissions should be less than 10 pages in the template of Pattern Recognition Letters which can be found in Moreover, all the submissions should be original and technically sound.

All papers will be peer-reviewed by at least two independent reviewers. Requests for additional information should be addressed to the guest editors.

Important Dates:

  • Paper submission period: May 1-31, 2017
  • First notification: July 15, 2017
  • First revision: September 15, 2017
  • Second notification: October 15, 2017
  • Second revision: November 15, 2017
  • Final decision: December 15, 2017
  • Publication date: Spring 2018 (Tentative)

Guest Editors:

  • Dr. Xiaofeng Zhu, The University of North Carolina at Chapel Hill  (
  • Dr. Jie Shao, University of Electronic Science and Technology of China (  
  • Dr. Jilian Zhang, Guangxi University of Finance and Economics, China ( 

Other Special Issues on this journal

Closed Special Issues