Mourad Ykhlef

Fixpoint Calculus for Querying Semistructured Data

The paper proposes two query languages for semistructured data G-Fixpoint and G-While whose expressive power is comparable to Fixpoint and While respectively. These languages are multi-sorted like logic languages integrating fixpoint path expressions.

Association mining of dependency between time series using Genetic Algorithm and discretisation

Association rule mining is one of the most popular data-mining techniques used to find associations existing between a set of objects or data. A time series is a sequence of observations stamped over the time; Time-series analysis has been used in a variety of applications like: business and health. The application of association mining to time series is very promising. The purpose of this article is to propose a new fast algorithm to discover the association that can exist between two time series. We use discretisation to segment time series to a number of shapes, and we classify these shapes to pre-defined shape classes to generate association rules using Genetic Algorithm (GA).

GQLX: a new graphical query language for XML data

XML (eXtensible Markup Language) is used in many contexts of modern information technology to facilitate sharing of information between heterogeneous data sources and inter-platform applications. So, the ability to efficiently query XML data becomes increasingly important. Some XML graphical query languages for XML data have been proposed but they are either too complex or too limited in use. In this paper, we propose a new graphical query language for querying and restructuring XML data, which we call GQLX. GQLX is developed on the base of G-XML data model. The paper presents the basic capabilities of GQLX through a sequence of examples of increasing complexity. We also discuss the semantic part of GQLX.

An Effective Semantic Event Matching System in the Internet of Things (IoT) Environment

IoT sensors use the publish/subscribe model for communication to benefit from its decoupled nature with respect to space, time, and synchronization. Because of the heterogeneity of communicating parties, semantic decoupling is added as a fourth dimension. The added semantic decoupling complicates the matching process and reduces its efficiency. Our proposed algorithm clusters subscriptions and events according to topic and performs the matching process within these clusters, which increases the throughput by reducing the matching time from the range of 16–18 ms to 2–4 ms. Moreover, the accuracy of matching is improved when subscriptions must be fully approximated, as demonstrated by an over 40% increase in F-score results. This work shows the benefit of clustering, as well as the improvement in the matching accuracy and efficiency achieved using this approach.

Toward Information Diffusion Model for Viral Marketing in Business

Current obstacles in the study of social media marketing include dealing with massive data and real-time updates have motivated to contribute solutions that can be adopted for viral marketing. Since information diffusion and social networks are the core of viral marketing, this article aims to investigate the constellation of diffusion methods for viral marketing. Studies on diffusion methods for viral marketing have applied different computational methods, but a systematic investigation of these methods has limited. Most of the literature have focused on achieving objectives such as influence maxi-mization or community detection. Therefore, this article aims to conduct an in-depth review of works related to diffusion for viral marketing. Viral marketing has applied to business-to-consumer transactions but has seen limited adoption in business-to-business transactions. The literature review reveals a lack of new diffusion methods, especially in dynamic and large-scale networks. It also offers insights into applying various mining methods for viral marketing. It discusses some of the challenges, limitations, and future research directions of information diffusion for viral marketing. The article also introduces a viral marketing informa-tion diffusion model. The proposed model attempts to solve the dynamicity and large-scale data of social networks by adopting incremental clustering and a stochastic differential equation for business-to-business transactions.

A New Hybrid Algorithm to Solve Winner Determination Problem in Multiunit Double Internet Auction

Solving winner determination problem in multiunit double auction has become an important E-business task. The main issue in double auction is to improve the reward in order to match the ideal prices and quantity and make the best profit for sellers and buyers according to their bids and predefined quantities. There are many algorithms introduced for solving winner in multiunit double auction. Conventional algorithms can find the optimal solution but they take a long time, particularly when they are applied to large dataset. Nowadays, some evolutionary algorithms, such as particle swarm optimization and genetic algorithm, were proposed and have been applied. In order to improve the speed of evolutionary algorithms convergence, we will propose a new kind of hybrid evolutionary algorithm that combines genetic algorithm (GA) with particle swarm optimization (PSO) to solve winner determination problem in multiunit double auction; we will refer to this algorithm as AUC-GAPSO.

A New Strategic Risk Reduction For Risk Management

AbstractRisk Management is one of the key cares of any organization strategic management; proper benefit of risk management is finding risks and their solutions. In this article, we will suggest a new Strategic Risk Reduction technique for producing optimal risk reduction strategies; which reduce risk exposure for expected income by allowing several countermeasures per risk rather than one countermeasure as previous works did. Our Strategic Risk Reduction will be optimized using Ant Colony Optimization approach.

Querying and restructuring XML data by graphical query language

Purpose – The rapid development of Extensible Markup Language (XML) from a mere data exchange format to a universal syntax for encoding domain specific information increases the need of new query languages specifically visualized to address the characteristics of XML. Such languages should be able not only to extract information from XML documents, but also to apply powerful restructuring operators, based on a well‐defined semantics. Moreover, XML queries should be natural to write and understand, as also end‐users are expected to access the large XML information bases supporting their businesses. The purpose of this paper is to propose a new graphical query language for XML (GQLX) for querying and restructuring XML data.Design/methodology/approach – The methodology emphasizes on GQLXs development, which is based on G‐XML data model syntax to express a wide variety of XML queries, ranging from simple selection to expressive data transformations involving grouping, aggregation and sorting. GQLX has an ope...

A novel spreading framework using incremental clustering for viral marketing

Mining online social network has been a target for many recent studies in the literature. However, a limited have been aimed for the purpose of viral marketing. In this paper, a proposing of a novel spreading framework for viral marketing by using incremental clustering and activity network is presented. This framework ensures optimization in terms of cost and time by concentrating only on the most active users in online social network. Incremental clustering typically works at certifying that the viral marketing process is applied in the most updated network since many changes would occur in the networks especially in the nodes connections. Generally, the framework divides the overall community into clusters each of which has its interest. In addition, it ensures the overlapping between clusters when users having more than one interest. Activity network, on the other hand, excludes the least active nodes or the ones with limited connections. This way will consume less cost and time comparing to cover all nodes (active and inactive).

An Artificial Immune System for job recommendation

Artificial Immune System is a novel computational intelligence technique inspired by immunology has appeared in the recent few years and takes inspiration from the immune system in order to develop new computational mechanisms to solve problems in a broad range of domain areas. This paper presents a problem oriented approach to design an immunizing solution for job recommendation problem. We will describe the immune system metaphors that are relevant to job recommender system. Then, discuss the design issues that should be taken into account such as, the features of the problem to be modeled, the data representation, the affinity measures, and the immune process that should be tailored for the problem. Finally, the corresponding computational model is presented.