Computational intelligence in time series forecasting

Introduction

    Time series forecasting has become more and more important in planning and decision making in various areas. With rapid advancement of IoT technology, more and more time series data are collected. How to forecast trends in these time series become highly desirable for optimal performance management, anomaly detection and decision making support. Computational intelligence plays an important role in time series forecasting. Among various computational intelligence techniques, heuristic optimisation techniques, deep learning network techniques, combination of heuristic optimisation and statistical techniques and hybrid of artificial intelligence are promising for real-world time series forecasting applications due to their attractive features, such as simplicity, learning capacity and fast convergence.

    This special session aims to provide a forum for researchers and practitioners to share their theoretical development and practical application of computational intelligence techniques in area of time series forecasting. The papers in this special session will offer a systematic overview of this field and provides innovative approaches to apply computational intelligence techniques in time series forecasting.

    The theme falls well within the scope of ISKE symposium -- a part of foundation of intelligent systems. It covers Artificial Neural Networks; Search, Optimization and Planning; Genetic and Swarm Computing; Pattern Recognition and Biological Inspired Computation.

Scope and Topics

The topics of interest include, but are not limited to:
  • Review of heuristic optimization techniques in time series forecasting
  • Heuristic global search algorithms
  • Genetic search algorithms
  • Swarm search algorithms
  • Applications of heuristic optimization techniques in time series forecasting
  • Biological inspired computation techniques
  • Deep learning algorithms for time series forecasting
  • Hybridization of heuristic optimization approaches and statistical approaches in time series forecasting
  • Review of hybrid artificial intelligence techniques in time series forecasting

Special Session Organisers

  • Dr. Haiyan Lu, Faculty of Engineering and Information Technology, Centre for Artificial Intelligence, University of Technology Sydney, E-mail: Haiyan.lu@uts.edu.au
  • Prof. Jianzhou Wang, Department of applied statistics, Dongbei University of Finance and Economics, E-mail: wjz@lzu.edu.cn

Submission

Papers reporting original research results and experience are solicited. Each paper should have no more than 8 pages, including references and Illustrations, written in IEEE conference proceedings format (See the templates available at: Paper Templates). Papers must be written in English and submitted electronically as a PDF/Word file at EasyChair: https://easychair.org/conferences/?conf=iske2017, and please select the Computational intelligence in time series forecasting. Submission of a paper should be regarded as an undertaking that, if the paper is accepted, at least one of the authors must attend the conference to present the paper.

Important Dates


1 Paper Submission Deadline: Aug 1, 2017
2 Notification Acceptance: Sep 1, 2017
3 Camera-ready Paper and Registration: Sep 25, 2017