Cloud IntelligenceInformation Systems


Jérôme Darmont, Torben Bach Pedersen
Hardware and Architecture / Software / Information Systems


the Web, to possibly mix them with private data, to

Cloud Intelligence. The 2013 Call for Papers attracted 8 submissions from Africa, Asia, Europe and North America.

In the paper entitled “Efficient Skyline Query Processis and Christos

Doulkeridis address the problem of computing the skyline operations. They ork for skyline ging local skyline sets. A comparison study shows that the proposed techniques are more efficient and outperform

Contents lists available at ScienceDirect .else on

Information Systems 54 (2015) 309–3100306-4379 & 2015 Published by Elsevier Ltd.Each paper received 3 reviews by the distinguished Program Committee consisting of 15 leading researchers.

SpatialHadoop's default skyline algorithm significantly, especially in the case of large skyline output size., regular exchange forum for researchers, industry and practitioners, as well as all potential users of query processing, which can be parameterized by individual techniques related to filtering candidate points mer-BI concepts and analyses in large scale fashion, and to share the results world-wide.

The aim of the Cloud-I workshop series is to be an of big spatial datasets in SpatialHadoop

Hadoop that efficiently supports spatial propose a scalable and efficient framew, an extension of collaborative features that enable users to share and re-use analyze them with intelligible on-line tools with advanced sing in SpatialHadoop”, Dimitris PertePreface

Cloud Intelligence

This special section contains extended versions of the best papers from the 2nd International Workshop on

Cloud Intelligence (Cloud-I 2013), which was held on

August 26, 2013 in Riva del Garda, Italy, in conjunction with the 39th International Conference on Very Large

Databases (VLDB 2013).

Business intelligence (BI) is a broad field related to integrating, storing and analyzing data to help decisionmakers in many domains (from actual business fields to administration, health and environment) make better decisions. Front-end analytics methods include reporting, on-line analytical processing (OLAP), and data mining.

With the increasing success of cloud computing, cloud

BI “as a service” offerings have sparkled widely, both from cloud start-ups and major BI industry vendors. Beyond porting BI features into the cloud, which already implies numerous issues (e.g., Big Data/NoSQL database modeling and storage, data localization, security and privacy, performance, cost and usage models), this trend also poses new, broader challenges for making data analytics available to small and middle-size enterprises (SMEs), nongovernmental organizations, Web communities (e.g., supported by social networks), and even the average citizen; this vision presumably requiring a mixture of both private and open data.

Thus, Cloud Intelligence is not only a current technological and research challenge, but also an important economic and societal stake, since people increasingly demand open data, which they need to access easily from journal homepage: www

InformatiUltimately, it was decided to accept 4 papers, of which 3 were full 8-page papers and 1 was a shorter position paper. The topics of accepted papers mostly related to the optimization of data analytics within the MapReduce framework. The Cloud-I 2013 proceedings were published by ACM Press as part of the International Conference

Proceedings Series.

Two of the papers were selected by the Cloud-I Chairs based on both quality and potential, and the authors were invited to submit extended versions to this special section.

An open call for papers resulted in a further 3 submitted papers, for a total of 5 submitted papers. After a thorough refereeing process, including further revisions of all papers, the following 3 papers were finally accepted for appearing in this special section, listed in alphabetical order by the first author's last name.

In the paper entitled “Bloofi: Multidimensional Bloom

Filters”, Adina Crainiceanu and Daniel Lemire consider the use of Bloom filters in federated cloud environments. With hundreds of geographically distributed clouds participating in a federation, information needs to be shared by the semi-autonomous cloud providers. This can be done by encoding the information using Bloom filters and sharing the Bloom filters with a central coordinator. Bloofi, an efficiently constructed and maintained hierarchical index structure for Bloom filters, is thus proposed to speed-up the search process. Theoretical and experimental results show that Bloofi provides a scalable and efficient solution for searching through a large number of Bloom filters.


Finally, in the paper entitled “Tuning Small Analytics on

Big Data: Data Partitioning and Secondary Indexes in the

Hadoop Ecosystem”, Oscar Romero, Victor Herrero, Alberto

Abelló and Jaume Ferrarons propose the use of wellknown query optimization techniques on top of “brute force” MapReduce. More precisely, they study the feasibility of solving OLAP queries with Hadoop, the Apache project implementing MapReduce, while benefiting from secondary indexes and partitioning in HBase. They notably compare different access plans in terms of cost, with respect to resources, i.e., CPU, bandwidth and I/Os.

As Guest Editors of this special section and Chairs of

Cloud-I 2013, we would like to thank all the referees, both the Cloud-I 2013 PC members and the extra reviewers for the special section, for their careful and dedicated work.

We would also like to thank the Information Systems

Editors-in-Chief Gottfried Vossen and Dennis Shasha for their support. We hope you will enjoy the papers that follow and see them as bearing witness to the high quality of the Cloud-I workshop series.

Jérôme Darmont,

Université de Lyon, France

E-mail address:

Torben Bach Pedersen

Aalborg University, Denmark

E-mail address:

Preface / Information Systems 54 (2015) 309–310310