Overview

Every problem whether simple or complex can be computed by understanding the procedure of the approach to arrive a solution. In contrast, constraint programming approaches a problem by declaring all possible variables in constraints that can influence the system in achieving an accurate answer or solution. The most common way to optimize a constraint solver is to come up with additional information at the time of solving a problem that can be utilized to greatly reduce the search space. Since constraint programming is a robust technique which uses constraint based toolkits with enhanced functional and imperative programming capabilities. Besides the powerful implications of constraint programming, acquisition, reformulation and solving real-world situations needs integration or combination of intelligent medium.   

Integration of Constraint Programming with Artificial Intelligence (AI) and machine learning provides an optimizing solution to overcome the challenge and helps to increase the performance of constraint solver in terms of accuracy, efficiency, and effectiveness. The intelligent learning technology deal with the scientific study of algorithms and statistical models that constraint programming uses in order to perform specific tasks without using explicit step by step instructions but relying on the algorithms to explore the patterns behind and solve the problem. Also integrating the constraint programming with intelligence helps to learn mapping rules from previously mapped instances. This greatly helps to search the exact variable reducing the time to solve the problem.  

Intelligent learning platforms enhanced with data mining will identify the basic functions and patterns of the investigating problem, whereas constraint solving identifies the common ideologies behind solving the problem and other ways in optimizing the problem. Moreover, both machine learning and constraint-based solving problem are mutually beneficial to each other, here the constraint programming techniques can be solved using machine learning platform and machine learning uses constraint programming techniques to augment and strengthen the existing system.  

The integration of constraint programming with AI and Machine Learning can definitely be a novel and effective methods for solving large and complex problems. This Special Issue on ‘Integration of Constraint with AI and Machine Learning” provides an excellent research area and invite papers showcasing constraint programming techniques and its operational challenges and novel methods in integrating with artificial intelligence and machine learning platforms. 

Topics of Interests

Papers are welcomed on the following topics but not confined to:

√ Innovative Applications of Constraint Programming with Machine learning Techniques
√ Constraint Programming for Intelligent Backtracking using Artificial Intelligence
√ Computational Comparison of Optimization Methods using Constraint Programming and Machine learning
√ Storage Techniques for Mapped Instances using Machine Learning Techniques and Constraint Programming 
√ Intelligent Learning Framework for Constraint Solving and Parameter Selection
√ Local, Incomplete, Randomized Search Techniques for Constraint Programming
√ Perturbation vs. Refinement Model: A Constraint-based Approach Study
√ Challenges in Exploring the Inference of Constraint Model with Machine Learning Model 
√ Study on Real-time Applications using Intelligent Constraint Programming methods
√ Constraint Programming, AI and Machine Learning: A Comparative Study

List of Important Dates:
Manuscript Submission Deadline Date:          24th October, 2020
Authors Notification Date:                                25th December, 2020
Revised Papers Due Date:                                 15th March, 2021
Final notification Date:                                      18th  May, 2021

Guest Editors 

Priyan Malarvizhi Kumar, Postdoctoral Research Fellow, Middlesex University, UK, P.Malarvizhikumar@mdx.ac.uk, P.Malarvizhikumar@ieee.org
Hari Mohan Pandey, Lecturer, Department of Computer Science, Edge Hill University, UK,  Pandeyh@edgehill.ac.uk
Gautam Srivastava,  Associate Professor, Department of Mathematics & Computer Science, Brandon University,Canada, srivastavag@brandonu.ca