Arnaud Castelltort

Fuzzy Queries over NoSQL Graph Databases: Perspectives for Extending the Cypher Language

When querying databases, users often wish to express vague concepts, as for instance asking for the cheap hotels. This has been extensively studied in the case of relational databases. In this paper, we propose to study how such useful techniques can be adapted to NoSQL graph databases where the role of fuzziness is crucial. Such databases are indeed among the fastest-growing models for dealing with big data, especially when dealing with network data (e.g., social networks). We consider the Cypher declarative query language proposed for Neo4j which is the current leader on this market, and we present how to express fuzzy queries.

Representing history in graph-oriented NoSQL databases: A versioning system

Graph databases are taking more and more importance, especially for social networking. For instance, organizations can implement graph databases to represent and query data such as Person1 is CEO of Organization1. NoSQL graph databases (e.g., Neo4j) have been designed to deal with such data. However, managing history is not yet possible in an easy manner while being critical in many applications. Tracking changes is indeed one of the main functionalities in databases (especially Relational BD) and should not be forsaken in NoSQL graph DB. For instance, queries like “list all the people who have been CEO of Organization1” or “list all the functions People1 has been taken in his career” are important. In this paper, we thus propose a novel representation of historical graph data and tools to implement it as a plug-in of existing NoSQL graph systems.

Extracting Fuzzy Summaries from NoSQL Graph Databases

Linguistic summaries have been studied for many years and allow to sum up large volumes of data in a very intuitive manner. They have been studied over several types of data. However, few works have been led on graph databases. Graph databases are becoming popular tools and have recently gained significant recognition with the emergence of the so-called NoSQL graph databases. These databases allow users to handle huge volumes of data (e.g., scientific data, social networks). There are several ways to consider graph summaries. In this paper, we detail the specificities of NoSQL graph databases and we discuss how to summarize them by introducing several types of linguistic summaries, namely structure summaries, data structure summaries and fuzzy summaries. We present extraction methods that have been tested over synthetic and real database experimentations.

Exploiting NoSQL Graph Databases and in Memory Architectures for Extracting Graph Structural Data Summaries

NoSQL graph databases have been introduced in recent years for dealing with large collections of graph-based data. Scientific data and social networks are among the best examples of the dramatic increase of the use of such structures. NoSQL repositories allow the management of large amounts of data in order to store and query them. Such data are not structured with a predefined schema as relational databases could be. They are rather composed by nodes and relationships of a certain type. For instance, a node can represent a Person and a relationship Friendship. Retrieving the structure of the graph database is thus of great help to users, for example when they must know how to query the data or to identify relevant data sources for recommender systems. For this reason, this paper introduces methods to retrieve structural summaries. Such structural summaries are extracted at different levels of information from the NoSQL graph database. The expression of the mining queries is facilitated by the use of two frame-works: Fuzzy4S allowing to define fuzzy operators and operations with Scala; Cypherf allowing the use of fuzzy operators and operations in the declarative queries over NoSQL graph databases. We show that extracting such summaries can be impossible with the NoSQL query engines because of the data volume and the complexity of the task of automatic knowledge extraction. A novel method based on in memory architectures is thus introduced. This paper provides the definitions of the summaries with the methods to automatically extract them from NoSQL graph databases only and with the help of in-memory architectures. The benefit of our proposition is demonstrated by experimental results.

Handling scalable approximate queries over NoSQL graph databases: Cypherf and the Fuzzy4S framework

NoSQL databases are currently often considered for Big Data solutions as they offer efficient solutions for volume and velocity issues and can manage some of complex data (e.g., documents, graphs). However, fuzzy approaches are often not efficient on such frameworks. Thus this article introduces a novel approach to define and run approximate queries over NoSQL graph databases using Scala by proposing the Fuzzy4S framework and the Cypherf fuzzy declarative query language. NoSQL Graph databases are currently gaining more and more interest and are applied in many real world applications. The Fuzzy4S framework is defined with an open DSL (Domain Specific Language) allowing it to define scalable approximate queries at an abstract level. Cypherf is an extension of Cypher which runs over the Neo4J NoSQL graph databases. This work consists of a complete approach embedding the whole chain from end-user declarative query level to implementation issues within the database engine. We provide both the formal definitions for defining approximate graph NoSQL queries and the experimental results which demonstrate the interest and efficiency of our proposition.

Multimapping Design of Complex Sensor Data in Environmental Observatories

Environmental resources (e.g., air quality, water quantity) are needed to understand fundamental questions such as global change. Such resources are often collected from sensors, including humans acting as sensors. Tools have emerged to manage such data in the form of time series and, in particular, the Sensor Observation Service (SOS) which offers a framework based on predefined relational database schema. Environmental observatories can be built using such frameworks, allowing to address specific key scientific questions by collecting and sharing large-scale environmental data. However, the strict schema of SOS database makes it difficult to integrate some data that cannot be directly mapped to the schema. Guidelines and best practices are offered in the literature in order to reuse standards from the Semantic Web but they do not cover all needs. In particular, they do not help to reflect the fact that a single environmental database can lead to several SOS models. Since being aware of these multiple possibilities is crucial for a better use of the observatories, we argue that some extensions of the existing works are required. In this paper, we thus propose an extension of existing vocabularies to achieve this goal. Our contribution is illustrated on the real case of the Lebanese-French O-LiFE environmental observatory.

Rogue behavior detection in NoSQL graph databases

Rogue behaviors refer to behavioral anomalies that can occur in human activi- ties and that can thus be retrieved from human generated data. In this paper, we aim at showing that NoSQL graph databases are a useful tool for this pur- pose. Indeed these database engines exploit property graphs that can easily represent human and object interactions whatever the volume and complexity of the data. These interactions lead to fraud rings in the graphs in the form of sophisticated chains of indirect links between fraudsters representing successive transactions (money, communications, etc.) from which rogue behaviours are detected. Our work is based on two extensions of such NoSQL graph databases. The first extension allows the handling of time-variant data while the second one is devoted to the management of imprecise queries with a DSL (to define flexible operators and operations with Scala) and the Cypherf declarative flex- ible query language over NoSQL graph databases. These extensions allow to better address and describe sophisticated frauds. Feasibility have been studied to assess our proposition.

Fuzzy Historical Graph Pattern Matching A NoSQL Graph Database Approach for Fraud Ring Resolution

Graphs have been studied and used for many years as they allow to represent in an efficient manner real data such as biological or social data. Graph databases have recently emerged within the NoSQL framework and are implemented in systems like Neo4J, OrientDB, etc. Recent works have shown that the management of history is crucial in such systems. In this paper, we show how such historical graph databases can be queried in order to retrieve fraud rings, also known as fraud cycles. Frauds are indeed often based on sophisticated chains of successive transactions (money, communications, etc.). We thus claim that the indirect link between fraudsters can be retrieved by considering historical NoSQL graph databases. We study how the model of historical NoSQL databases can be extended for better address this goal and we propose the associated queries that have been tested on a synthetical database.

Discovering Ordinal Attributes Through Gradual Patterns, Morphological Filters and Rank Discrimination Measures

This paper proposes to exploit heterogeneous data, i.e. data described by both numerical and categorical features, so as to gain knowledge about the categorical attributes from the numerical ones. More precisely, it aims at discovering whether, according to a given data set, based on information provided by the numerical attributes, some categorical attributes actually are ordinal ones and, additionally, at establishing ranking relations between the category values. To that aim, the paper proposes the 3-step methodology OSACA, standing for Order Seeking Algorithm for Categorical Attributes: it first consists in extracting gradual patterns from the numerical attributes, to identify rich ranking information about the data; it then applies mathematical morphology tools, more precisely alternated filters, to induce an associated order on the categorical attributes. The third step evaluates the quality of the candidate rankings through an original measure derived from the rank entropy discrimination.

NoSQL Graph-based OLAP Analysis

OLAP is a leading technology for analysing data and decision making. It helps the users to discover relevant information from large databases. Graph OLAP has been studied for several years in the OLAP framework. In existing work, the authors study how to import graph data into OLAP cube models but no work has explored yet the feasability to exploit graph structures to store analytical data. As graph databases are more and more used through NoSQL implementations (e.g., social and biological networks), in this paper we aim at providing an original model for managing cubes into NoSQL graphs. We show how cubes can be represented in graphs and how these structures can then be used for graph OLAP queries to support decision making.