BibTex:

    @Article{OJDB_2020v7i1n01_Poensgen,
        title     = {Quasi-Convex Scoring Functions in Branch-and-Bound Ranked Search},
        author    = {Peter Poensgen and
                     Ralf M{\"o}ller},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2020},
        volume    = {7},
        number    = {1},
        pages     = {1--11},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-2019092919333113374958},
        urn       = {urn:nbn:de:101:1-2019092919333113374958},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {For answering top-k queries in which attributes are aggregated to a scalar value for defining a ranking, usually the well-known branch-and-bound principle can be used for efficient query answering. Standard algorithms (e.g., Branch-and-Bound Ranked Search, BRS for short) require scoring functions to be monotone, such that a top-k ranking can be computed in sublinear time in the average case. If monotonicity cannot be guaranteed, efficient query answering algorithms are not known. To make branch-and-bound effective with descending or ascending rankings (maximum top-k or minimum top-k queries, respectively), BRS must be able to identify bounds for exploring search partitions, and only for monotonic ranking functions this is trivial. In this paper, we investigate the class of quasi-convex functions used for scoring objects, and we examine how bounds for exploring data partitions can correctly and efficiently be computed for quasi-convex functions in BRS for maximum top-k queries. Given that quasi-convex scoring functions can usefully be employed for ranking objects in a variety of applications, the mathematical findings presented in this paper are indeed significant for practical top-k query answering.}
    }

BibTex:

    @Article{OJDB_2020v7i1n02_Poensgen,
        title     = {Branch-and-Bound Ranked Search by Minimizing Parabolic Polynomials},
        author    = {Peter Poensgen and
                     Ralf M{\"o}ller},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2020},
        volume    = {7},
        number    = {1},
        pages     = {12--20},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-2020080219330783060411},
        urn       = {urn:nbn:de:101:1-2020080219330783060411},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {The Branch-and-Bound Ranked Search algorithm (BRS) is an efficient method for answering top-k queries based on R-trees using multivariate scoring functions. To make BRS effective with ascending rankings, the algorithm must be able to identify lower bounds of the scoring functions for exploring search partitions. This paper presents BRS supporting parabolic polynomials. These functions are common to minimize combined scores over different attributes and cover a variety of applications. To the best of our knowledge the problem to develop an algorithm for computing lower bounds for the BRS method has not been well addressed yet.}
    }

BibTex:

    @Article{OJDB_2019v6i1n01e_HiDeSt2018,
        title     = {Special Issue on High-Level Declarative Stream Processing},
        author    = {Patrick Koopmann and
                     Theofilos Mailis and
                     Danh Le Phuoc},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2019},
        volume    = {6},
        number    = {1},
        pages     = {1--4},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-2018122318332165752519},
        urn       = {urn:nbn:de:101:1-2018122318332165752519},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {Stream processing as an information processing paradigm has been investigated by various research communities within computer science and appears in various applications: realtime analytics, online machine learning, continuous computation, ETL operations, and more. The special issue on "High-Level Declarative Stream Processing" investigates the declarative aspects of stream processing, a topic of undergoing intense study. It is published in the Open Journal of Web Technologies (OJWT) (www.ronpub.com/ojwt). This editorial provides an overview over the aims and the scope of the special issue and the accepted papers.}
    }

BibTex:

    @Article{OJDB_2019v6i1n02_QianLiu,
        title     = {Provenance Management over Linked Data Streams},
        author    = {Qian Liu and
                     Marcin Wylot and
                     Danh Le Phuoc and
                     Manfred Hauswirth},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2019},
        volume    = {6},
        number    = {1},
        pages     = {5--20},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-2018122318333313711079},
        urn       = {urn:nbn:de:101:1-2018122318333313711079},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {Provenance describes how results are produced starting from data sources, curation, recovery, intermediate processing, to the final results. Provenance has been applied to solve many problems and in particular to understand how errors are propagated in large-scale environments such as Internet of Things, Smart Cities. In fact, in such environments operations on data are often performed by multiple uncoordinated parties, each potentially introducing or propagating errors. These errors cause uncertainty of the overall data analytics process that is further amplified when many data sources are combined and errors get propagated across multiple parties. The ability to properly identify how such errors influence the results is crucial to assess the quality of the results. This problem becomes even more challenging in the case of Linked Data Streams, where data is dynamic and often incomplete. In this paper, we introduce methods to compute provenance over Linked Data Streams. More specifically, we propose provenance management techniques to compute provenance of continuous queries executed over complete Linked Data streams. Unlike traditional provenance management techniques, which are applied on static data, we focus strictly on the dynamicity and heterogeneity of Linked Data streams. Specifically, in this paper we describe: i) means to deliver a dynamic provenance trace of the results to the user, ii) a system capable to execute queries over dynamic Linked Data and compute provenance of these queries, and iii) an empirical evaluation of our approach using real-world datasets.}
    }

BibTex:

    @Article{OJDB_2019v6i1n03_Schiff,
        title     = {Ontology-Based Data Access to Big Data},
        author    = {Simon Schiff and
                     Ralf M{\"o}ller and
                     {\"O}zg{\"u}r L. {\"O}zcep},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2019},
        volume    = {6},
        number    = {1},
        pages     = {21--32},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-2018122318334350985847},
        urn       = {urn:nbn:de:101:1-2018122318334350985847},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {Recent approaches to ontology-based data access (OBDA) have extended the focus from relational database systems to other types of backends such as cluster frameworks in order to cope with the four Vs associated with big data: volume, veracity, variety and velocity (stream processing). The abstraction that an ontology provides is a benefit from the enduser point of view, but it represents a challenge for developers because high-level queries must be transformed into queries executable on the backend level. In this paper, we discuss and evaluate an OBDA system that uses STARQL (Streaming and Temporal ontology Access with a Reasoning-based Query Language), as a high-level query language to access data stored in a SPARK cluster framework. The development of the STARQL-SPARK engine show that there is a need to provide a homogeneous interface to access both static and temporal as well as streaming data because cluster frameworks usually lack such an interface. The experimental evaluation shows that building a scalable OBDA system that runs with SPARK is more than plug-and-play as one needs to know quite well the data formats and the data organisation in the cluster framework.}
    }

BibTex:

    @Article{OJDB_2019v6i1n04_Obermeier,
        title     = {Multi-Shot Stream Reasoning in Answer Set Programming: A Preliminary Report},
        author    = {Philipp Obermeier and
                     Javier Romero and
                     Torsten Schaub},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2019},
        volume    = {6},
        number    = {1},
        pages     = {33--38},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-2018122318335923776377},
        urn       = {urn:nbn:de:101:1-2018122318335923776377},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {In the past, we presented a first approach for stream reasoning using Answer Set Programming (ASP). At the time, we implemented an exhaustive wrapper for our underlying ASP system, clingo, to enable reasoning over continuous data streams. Nowadays, clingo natively supports multi-shot solving: a technique for processing continuously changing logic programs. In the context of stream reasoning, this allows us to directly implement seamless sliding-window-based reasoning over emerging data. In this paper, we hence present an exhaustive update to our stream reasoning approach that leverages multi-shot solving. We describe the implementation of the stream reasoner's architecture, and illustrate its workflow via job shop scheduling as a running example.}
    }

BibTex:

    @Article{OJDB_2018v5i1n01_Kotiranta,
        title     = {Effectiveness of NoSQL and NewSQL Databases in Mobile Network Event Data: Cassandra and ParStream/Kinetic},
        author    = {Petri Kotiranta and
                     Marko Junkkari},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2018},
        volume    = {5},
        number    = {1},
        pages     = {1--13},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-2018122318330989940385},
        urn       = {urn:nbn:de:101:1-2018122318330989940385},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {Continuously growing amount of data has inspired seeking more and more efficient database solutions for storing and manipulating data. In big data sets, NoSQL databases have been established as alternatives for traditional SQL databases. The effectiveness of these databases has been widely tested, but the tests focused only on key-value data that is structurally very simple. Many application domains, such as telecommunication, involve more complex data structures. Huge amount of Mobile Network Event (MNE) data is produced by an increasing number of mobile and ubiquitous applications. MNE data is structurally predetermined and typically contains a large number of columns. Applications that handle MNE data are usually insert intensive, as a huge amount of data are generated during rush hours. NoSQL provides high scalability and its column family stores suits MNE data well, but NoSQL does not support ACID features of the traditional relational databases. NewSQL is a new kind of databases, which provide the high scalability of NoSQL while still maintaining ACID guarantees of the traditional DBMS. In the paper, we evaluation NEM data storing and aggregating efficiency of Cassandra and ParStream/Kinetic databases and aim to find out whether the new kind of database technology can clearly bring performance advantages over legacy database technology and offers an alternative to existing solutions. Among the column family stores of NoSQL, Cassandra is especially a good choice for insert intensive applications due to its way to handle data insertions. ParStream is a novel and advanced NewSQL like database and is recently integrated into Cisco Kinetic. The results of the evaluation show that ParStream is much faster than Cassandra when storing and aggregating MNE data and the NewSQL is a very strong alternative to existing database solutions for insert intensive applications.}
    }

BibTex:

    @Article{OJDB_2017v4i1n01_Lindstroem,
        title     = {An NVM Aware MariaDB Database System and Associated IO Workload on File Systems},
        author    = {Jan Lindstr{\"o}m and
                     Dhananjoy Das and
                     Nick Piggin and
                     Santhosh Konundinya and
                     Torben Mathiasen and
                     Nisha Talagala and
                     Dulcardo Arteaga},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2017},
        volume    = {4},
        number    = {1},
        pages     = {1--21},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-201705194662},
        urn       = {urn:nbn:de:101:1-201705194662},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {MariaDB is a community-developed fork of the MySQL relational database management system and originally designed and implemented in order to use the traditional spinning disk architecture. With Non-Volatile memory (NVM) technology now in the forefront and main stream for server storage (Data centers), MariaDB addresses the need by adding support for NVM devices and introduces NVM Compression method. NVM Compression is a novel hybrid technique that combines application level compression with flash awareness for optimal performance and storage efficiency. Utilizing new interface primitives exported by Flash Translation Layers (FTLs), we leverage the garbage collection available in flash devices to optimize the capacity management required by compression systems. We implement NVM Compression in the popular MariaDB database and use variants of commonly available POSIX file system interfaces to provide the extended FTL capabilities to the user space application. The experimental results show that the hybrid approach of NVM Compression can improve compression performance by 2-7x, deliver compression performance for flash devices that is within 5\% of uncompressed performance, improve storage efficiency by 19\% over legacy Row-Compression, reduce data writes by up to 4x when combined with other flash aware techniques such as Atomic Writes, and deliver further advantages in power efficiency and CPU utilization. Various micro benchmark measurement and findings on sparse files call for required improvement in file systems for handling of punch hole operations on files.}
    }

BibTex:

    @Article{OJDB_2017v4i1n02_Marten,
        title     = {Machine Learning on Large Databases: Transforming Hidden Markov Models to SQL Statements},
        author    = {Dennis Marten and
                     Andreas Heuer},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2017},
        volume    = {4},
        number    = {1},
        pages     = {22--42},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-2017100112181},
        urn       = {urn:nbn:de:101:1-2017100112181},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {Machine Learning is a research field with substantial relevance for many applications in different areas. Because of technical improvements in sensor technology, its value for real life applications has even increased within the last years. Nowadays, it is possible to gather massive amounts of data at any time with comparatively little costs. While this availability of data could be used to develop complex models, its implementation is often narrowed because of limitations in computing power. In order to overcome performance problems, developers have several options, such as improving their hardware, optimizing their code, or use parallelization techniques like the MapReduce framework. Anyhow, these options might be too cost intensive, not suitable, or even too time expensive to learn and realize. Following the premise that developers usually are not SQL experts we would like to discuss another approach in this paper: using transparent database support for Big Data Analytics. Our aim is to automatically transform Machine Learning algorithms to parallel SQL database systems. In this paper, we especially show how a Hidden Markov Model, given in the analytics language R, can be transformed to a sequence of SQL statements. These SQL statements will be the basis for a (inter-operator and intra-operator) parallel execution on parallel DBMS as a second step of our research, not being part of this paper.}
    }

BibTex:

    @Article{OJDB_2016v3i1n01_Menninghaus,
        title     = {High-Dimensional Spatio-Temporal Indexing},
        author    = {Mathias Menninghaus and
                     Martin Breunig and
                     Elke Pulverm{\"u}ller},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2016},
        volume    = {3},
        number    = {1},
        pages     = {1--20},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-201705194635},
        urn       = {urn:nbn:de:101:1-201705194635},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {There exist numerous indexing methods which handle either spatio-temporal or high-dimensional data well. However, those indexing methods which handle spatio-temporal data well have certain drawbacks when confronted with high-dimensional data. As the most efficient spatio-temporal indexing methods are based on the R-tree and its variants, they face the well known problems in high-dimensional space. Furthermore, most high-dimensional indexing methods try to reduce the number of dimensions in the data being indexed and compress the information given by all dimensions into few dimensions but are not able to store now - relative data. One of the most efficient high-dimensional indexing methods, the Pyramid Technique, is able to handle high-dimensional point-data only. Nonetheless, we take this technique and extend it such that it is able to handle spatio-temporal data as well. We introduce a technique for querying in this structure with spatio-temporal queries. We compare our technique, the Spatio-Temporal Pyramid Adapter (STPA), to the RST-tree for in-memory and on-disk applications. We show that for high dimensions, the extra query-cost for reducing the dimensionality in the Pyramid Technique is clearly exceeded by the rising query-cost in the RST-tree. Concluding, we address the main drawbacks and advantages of our technique.}
    }

BibTex:

    @Article{OJDB_2016v3i1n02_Werner,
        title     = {Runtime Adaptive Hybrid Query Engine based on FPGAs},
        author    = {Stefan Werner and
                     Dennis Heinrich and
                     Sven Groppe and
                     Christopher Blochwitz and
                     Thilo Pionteck},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2016},
        volume    = {3},
        number    = {1},
        pages     = {21--41},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-201705194645},
        urn       = {urn:nbn:de:101:1-201705194645},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {This paper presents the fully integrated hardware-accelerated query engine for large-scale datasets in the context of Semantic Web databases. As queries are typically unknown at design time, a static approach is not feasible and not flexible to cover a wide range of queries at system runtime. Therefore, we introduce a runtime reconfigurable accelerator based on a Field Programmable Gate Array (FPGA), which transparently incorporates with the freely available Semantic Web database LUPOSDATE. At system runtime, the proposed approach dynamically generates an optimized hardware accelerator in terms of an FPGA configuration for each individual query and transparently retrieves the query result to be displayed to the user. During hardware-accelerated execution the host supplies triple data to the FPGA and retrieves the results from the FPGA via PCIe interface. The benefits and limitations are evaluated on large-scale synthetic datasets with up to 260 million triples as well as the widely known Billion Triples Challenge.	}
    }

BibTex:

    @Article{OJDB_2016v3i1n03_Koch,
        title     = {XML-based Execution Plan Format (XEP)},
        author    = {Christoph Koch},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2016},
        volume    = {3},
        number    = {1},
        pages     = {42--52},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-201705194654},
        urn       = {urn:nbn:de:101:1-201705194654},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {Execution plan analysis is one of the most common SQL tuning tasks performed by relational database administrators and developers. Currently each database management system (DBMS) provides its own execution plan format, which supports system-specific details for execution plans and contains inherent plan operators. This makes SQL tuning a challenging issue. Firstly, administrators and developers often work with more than one DBMS and thus have to rethink among different plan formats. In addition, the analysis tools of execution plans only support single DBMSs, or they have to implement separate logic to handle each specific plan format of different DBMSs. To address these problems, this paper proposes an XML-based Execution Plan format (XEP), aiming to standardize the representation of execution plans of relational DBMSs. Two approaches are developed for transforming DBMS-specific execution plans into XEP format. They have been successfully evaluated for IBM DB2, Oracle Database and Microsoft SQL.}
    }

BibTex:

    @Article{OJDB-2015v2i1n01_Buchmann,
        title     = {Deriving Bounds on the Size of Spatial Areas},
        author    = {Erik Buchmann and
                     Patrick Erik Bradley and
                     Klemens B{\"o}hm},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2015},
        volume    = {2},
        number    = {1},
        pages     = {1--16},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-201705194566},
        urn       = {urn:nbn:de:101:1-201705194566},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {Many application domains such as surveillance, environmental monitoring or sensor-data processing need upper and lower bounds on areas that are covered by a certain feature. For example, a smart-city infrastructure might need bounds on the size of an area polluted with fine-dust, to re-route combustion-engine traffic. Obtaining such bounds is challenging, because in almost any real-world application, information about the region of interest is incomplete, e.g., the database of sensor data contains only a limited number of samples. Existing approaches cannot provide upper and lower bounds or depend on restrictive assumptions, e.g., the area must be convex. Our approach in turn is based on the natural assumption that it is possible to specify a minimal diameter for the feature in question. Given this assumption, we formally derive bounds on the area size, and we provide algorithms that compute these bounds from a database of sensor data, based on geometrical considerations. We evaluate our algorithms both with a real-world case study and with synthetic data.}
    }

BibTex:

    @Article{OJDB_2015v2i1n02_Elbushra,
        title     = {Causal Consistent Databases},
        author    = {Mawahib Musa Elbushra and
                     Jan Lindstr{\"o}m},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2015},
        volume    = {2},
        number    = {1},
        pages     = {17--35},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-201705194619},
        urn       = {urn:nbn:de:101:1-201705194619},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {Many consistency criteria have been considered in databases and the causal consistency is one of them. The causal consistency model has gained much attention in recent years because it provides ordering of relative operations. The causal consistency requires that all writes, which are potentially causally related, must be seen in the same order by all processes. The causal consistency is a weaker criteria than the sequential consistency, because there exists an execution, which is causally consistent but not sequentially consistent, however all executions satisfying the sequential consistency are also causally consistent. Furthermore, the causal consistency supports non-blocking operations; i.e. processes may complete read or write operations without waiting for global computation. Therefore, the causal consistency overcomes the primary limit of stronger criteria: communication latency. Additionally, several application semantics are precisely captured by the causal consistency, e.g. collaborative tools. In this paper, we review the state-of-the-art of causal consistent databases, discuss the features, functionalities and applications of the causal consistency model, and systematically compare it with other consistency models. We also discuss the implementation of causal consistency databases and identify limitations of the causal consistency model.}
    }

BibTex:

    @Article{OJDB_2015v2i1n03_Groppe,
        title     = {PatTrieSort - External String Sorting based on Patricia Tries},
        author    = {Sven Groppe and
                     Dennis Heinrich and
                     Stefan Werner and
                     Christopher Blochwitz and
                     Thilo Pionteck},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2015},
        volume    = {2},
        number    = {1},
        pages     = {36--50},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-201705194627},
        urn       = {urn:nbn:de:101:1-201705194627},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {External merge sort belongs to the most efficient and widely used algorithms to sort big data: As much data as fits inside is sorted in main memory and afterwards swapped to external storage as so called initial run. After sorting all the data in this way block-wise, the initial runs are merged in a merging phase in order to retrieve the final sorted run containing the completely sorted original data. Patricia tries are one of the most space-efficient ways to store strings especially those with common prefixes. Hence, we propose to use patricia tries for initial run generation in an external merge sort variant, such that initial runs can become large compared to traditional external merge sort using the same main memory size. Furthermore, we store the initial runs as patricia tries instead of lists of sorted strings. As we will show in this paper, patricia tries can be efficiently merged having a superior performance in comparison to merging runs of sorted strings. We complete our discussion with a complexity analysis as well as a comprehensive performance evaluation, where our new approach outperforms traditional external merge sort by a factor of 4 for sorting over 4 billion strings of real world data.}
    }

BibTex:

    @Article{OJDB-v1i2n01_Mortensen,
        title     = {Using Business Intelligence to Improve DBA Productivity},
        author    = {Eric A. Mortensen and
                     En Cheng},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2014},
        volume    = {1},
        number    = {2},
        pages     = {1--16},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-201705194595},
        urn       = {urn:nbn:de:101:1-201705194595},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {The amount of data collected and used by companies has grown rapidly in size over the last decade.  Business leaders are now using Business Intelligence (BI) systems to make effective business decisions against large amounts of data. The growth in the size of data has been a major challenge for Database Administrators (DBAs). The increase in the number and size of databases at the speed they have grown has made it difficult for DBA teams to provide the same level of service that the business requires they provide. The methods that DBAs have used in the last several decades can no longer be performed with the efficiency needed over all of the databases they administer. This paper presents the first BI system to improve DBA productivity and providing important data metrics for Information Technology (IT) managers. The BI system has been well received by Sherwin Williams Database Administrators.  It has i) enabled the DBA team to quickly determine which databases needed work by a DBA without manually logging into the system; ii) helped the DBA team and its management to easily answer other business users' questions without using DBAs' time to research the issue; and iii) helped the DBA team to provide the business data for unanticipated audit request.}
    }

BibTex:

    @Article{OJDB-v1i2n02_Abramova,
        title     = {Which NoSQL Database? A Performance Overview},
        author    = {Veronika Abramova and
                     Jorge Bernardino and
                     Pedro Furtado},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2014},
        volume    = {1},
        number    = {2},
        pages     = {17--24},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-201705194607},
        urn       = {urn:nbn:de:101:1-201705194607},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {NoSQL data stores are widely used to store and retrieve possibly large amounts of data, typically in a key-value format. There are many NoSQL types with different performances, and thus it is important to compare them in terms of performance and verify how the performance is related to the database type. In this paper, we evaluate five most popular NoSQL databases: Cassandra, HBase, MongoDB, OrientDB and Redis. We compare those databases in terms of query performance, based on reads and updates, taking into consideration the typical workloads, as represented by the Yahoo! Cloud Serving Benchmark. This comparison allows users to choose the most appropriate database according to the specific mechanisms and application needs.}
    }

BibTex:

    @Article{OJDB-v1i1n01_Grandi,
        title     = {Introductory Editorial},
        author    = {Fabio Grandi},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2014},
        volume    = {1},
        number    = {1},
        pages     = {1--2},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-201705194557},
        urn       = {urn:nbn:de:101:1-201705194557},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {The Open Journal of Databases (OJDB) is a new open access journal covering all aspects of database research and technology. In this editorial, the first issue of the journal is presented.}
    }

BibTex:

    @Article{OJDB-v1i1n02_Duchateau,
        title     = {Designing a Benchmark for the Assessment of Schema Matching Tools},
        author    = {Fabien Duchateau and
                     Zohra Bellahsene},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2014},
        volume    = {1},
        number    = {1},
        pages     = {3--25},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-201705194573},
        urn       = {urn:nbn:de:101:1-201705194573},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {Over the years, many schema matching approaches have been developed to discover correspondences between schemas. Although this task is crucial in data integration, its evaluation, both in terms of matching quality and time performance, is still manually performed. Indeed, there is no common platform which gathers a collection of schema matching datasets to fulfil this goal. Another problem deals with the measuring of the post-match effort, a human cost that schema matching approaches aim at reducing. Consequently, we propose XBenchMatch, a schema matching benchmark with available datasets and new measures to evaluate this manual post-match effort and the quality of integrated schemas. We finally report the results obtained by different approaches, namely COMA++, Similarity Flooding and YAM. We show that such a benchmark is required to understand the advantages and failures of schema matching approaches. Therefore, it could help an end-user to select a schema matching tool which covers his/her needs.}
    }

BibTex:

    @Article{OJDB-v1i1n03_Elbushra,
        title     = {Eventual Consistent Databases: State of the Art},
        author    = {Mawahib Musa Elbushra and
                     Jan Lindstr{\"o}m},
        journal   = {Open Journal of Databases (OJDB)},
        issn      = {2199-3459},
        year      = {2014},
        volume    = {1},
        number    = {1},
        pages     = {26--41},
        url       = {http://nbn-resolving.de/urn:nbn:de:101:1-201705194582},
        urn       = {urn:nbn:de:101:1-201705194582},
        publisher = {RonPub},
        bibsource = {RonPub},
        abstract = {One of the challenges of cloud programming is to achieve the right balance between the availability and consistency in a distributed database. Cloud computing environments, particularly cloud databases, are rapidly increasing in importance, acceptance and usage in major applications, which need the partition-tolerance and availability for scalability purposes, but sacrifice the consistency side (CAP theorem). In these environments, the data accessed by users is stored in a highly available storage system, thus the use of paradigms such as eventual consistency became more widespread. In this paper, we review the state-of-the-art database systems using eventual consistency from both industry and research. Based on this review, we discuss the advantages and disadvantages of eventual consistency, and identify the future research challenges on the databases using eventual consistency.}
    }