Editorial

It is a matter of immense pleasure to introduce this special issue comprising extended versions of selected papers from the first Mediterranean Conference on Pattern Recognition and Artificial Intelligence (MedPRAI-2016) that was successfully held on 22–23 November 2016 at Tebessa Algeria. During the recent years, a tremendous growth has been witnessed in the volume of research being carried out in different areas of pattern classification and artificial intelligence. The significant increase in these research areas is mainly due to the wide variety of applications that have evolved to meet the new challenges of today as well as the next few decades. MedPRAI-2016 was aimed at providing an interdisciplinary forum of discussion to share the recent advancements in different areas of pattern recognition and artificial intelligence and was endorsed by the International Association of Pattern Recognition (IAPR). MedPRAI-2016 received a total of 101 research contributions out of which 28 highquality papers were accepted for presentation and publication. Authors of selected papers were invited to submit the extended versions and after a thorough and competitive paper review and selection process, six papers were selected to constitute this special issue. In the first paper, Ferdi and Layeb study the capacitated location-routing problem (CLRP). A greedy-randomised adaptive search procedure is proposed that reports promising results on several LRP instances. The second paper by Demim et al. presents a Decentralised Cooperative Simultaneous Localisation and Mapping (DCSLAM) solution based on 2D laser data using an Adaptive Covariance Intersection (ACI).The third paper titled ‘Hidden Markov random field model and Broyden–Fletcher– Goldfarb–Shanno algorithm for brain image segmentation’ investigates the combination of HMRF and BFGS to carry out segmentation on brain images. In the fourth paper, Menassel et al. exploit the Wolf Pack Algorithm for the fractal image compression. In comparison to exhaustive search; the presented technique not only reduces the encoding time but also reports high compression ratios. The fifth paper titled ‘Flexible Web services integration: a novel personalized social approach’ aims at composing web services that are highly relevant to user’s preferences. In addition to functional and non-function attributes, social networks of web services are incorporated in the dynamic web services. The last paper by Saidi et al. presents an instance selection method called EnsembleMargin Instance Selection (EMIS) algorithm. The effectiveness of the proposed selection scheme is validated through a series of experiments carried out on multiple real-world classification problems from the UCI Machine Learning repository. The editors would like to take this opportunity to thank the referees for their time and efforts in reviewing the papers and providing constructive feedback to the authors within the short stipulated time. We are also thankful to the authors for their contributions as well as their patience during the review process. Finally, we are grateful to Prof. Eric Dietrich, Editor in Chief, Journal of Experimental and Theoretical Artificial Intelligence, for the timely guidance and support as well as for providing us with the opportunity to edit this special issue. In closing, it has been a privilege to work on this special issue and we hope that readers will find this collection of papers valuable and useful.