Social Networking increases allowed the spreading of cyberbullying worldwide. The latter invaded cyberspace, kids and adolescents are no more safe in their virtual playgrounds. Indeed, online bullying is attracting considerable concern due to the societal and health issues it causes, ranging from depression, anxiety, and low self-esteem to sui cide attempts. Automatic cyberbullying detection is becoming a vital factor in protecting individuals’ lives. It has received much attention in the last decade. Researchers use machine learning and deep learning models to detect online bullying content. An automatic cyberbullying detection model would flag any bullying text as efficiently as possible. Yet, several challenges lie ahead for the development of such a robust model. Our study discerned class imbalance and bullying text representation as being the major issues concerning cyberbullying classification. In this context, we tried to handle the class imbalance problem through data augmentation, cost-sensitive learning, and lever- aging a Computer Vision loss function for the task. Moreover, we consider a prominent solution for bullying content representation, which consists of fine-tuning Pre-trained Language Models for cyberbullying detection and using these latter as feature extractors for Multichannel ConvNets and Bidirectional LSTMs. The results show the effectiveness of the proposed models, which outperform several past works and provide high Recall values (78%–96%) on English and Arabic datasets.

Deep learning-based disease diagnosis applications are essential for accurate diagnosis at various disease stages. However, using personal data exposes traditional centralized learning systems to privacy concerns. On the other hand, by positioning processing resources closer to the device and enabling more effective data analyses, a distributed computing paradigm has the potential to revolutionize disease diagnosis. Scalable architectures for data analytics are also crucial in healthcare, where data analytics results must have low latency and high dependability and reliability. This study proposes a microservices-based approach for IoT data analytics systems to satisfy privacy and performance requirements by arranging entities into fine-grained, loosely connected, and reusable collections. Our approach relies on federated learning, which can increase disease diagnosis accuracy while protecting data privacy. Additionally, we employ transfer learning to obtain more efficient models. Using more than 5800 chest X-ray images for pneumonia detection from a publically available dataset, we ran experiments to assess the effectiveness of our approach. Our experiments reveal that our approach performs better in identifying pneumonia than other cutting-edge technologies, demonstrating our approach's promising potential detection performance.

Developing Scientific Reasoning (SR) competencies at an early age, are challenging to meet expectation of the 4th sustainable development goal. Hence, educators and educational decision-makers try to embed these competencies into such subjects as the arts, language, technology, economics, mathematics and science, using an inter-disciplinary approach. In this context, this paper proposes a fuzzy knowledge-based solution to build practical pupils, educators, and decision-makers recommender system to support the development of SR competencies in a data driver manner. Our system consists of:(1) inferring and computational module that calculates in a fuzzy manner the global appreciation to each SR-competencies. (2) recommendation module that aims to help learners, educators and decision makers to assess the degree of development of SR competencies and to get alternative suggestion of remediation. The proposed solution has been tested on the last two levels of science education in four Tunisian elementary schools in different regions. A preliminary analysis showed that the learning process should be more focused on Tunisian pupil's profile, and that investigation and collaborative based learning should be applied further in Tunisian classroom.

With the frequent occurrence of natural and man-made disasters, emergency management has become an active research field aiming at saving lives and reducing environmental and economic losses. Due to the complexity of crisis situations, emergency managers need to be assisted in making critical and effective decisions. Case-based reasoning (CBR) methodology has been widely adopted to support emergency decision makers in their tasks. This paper presents a comprehensive literature review of recent emergency management CBR systems reported in peer-reviewed journals and ICCBR conference proceedings between 2000 and 2020. Recent development trends of emergency management CBR systems are identified in terms of their purposes, application contexts and techniques used for their development. Finally, opportunities to improve emergency management CBR systems are outlined.

To reduce the spread of COVID-19 pandemic, educational institutions were closed in all countries. This closure deteriorated the level of all learners and resulted in a considerable disturbance of the education system. In this context, distance learning was the best solution. This paper reports the findings obtained Likert scale survey on April 2020 sent to learners and teachers of the Tunisian universities. In this survey, the interviewees were asked about their opinions concerning e-learning in the new situation resulting from covid19 crisis. After describing the existing learner models, we present the findings provided by examining the impact of the learning situation on the learner model. Learners and teachers were asked to capture four profile dimensions: interaction, involvement, motivation and emotions during the COVID -19 health crisis. The analysis of the obtained results show that a new learning situation influences negatively the learner model, which proves the importance of considering the situational dimension in such a learner model.

Summary In recent years, cloud computing has become a priority for organizations that seek to facilitate the management of their increasingly complex information systems (IS) that includes different components: data, services, business processes and hardware. With the large number of cloud providers, the selection of cloud services for each IS component remains a challenge because each one has its own requirements in terms of quality of service which may be different from each other. Cloud providers preferences are generally different from those of organizations, hence the need for a negotiation process. In this article, we propose a framework on which the negotiations between organizations and cloud providers will be based. In this framework, we use rough set theory to predict provider preferences. This method plays an important role in improving the results of negotiations and allows to speed up this process since the preferences of the providers will be known. Additionally, we propose an improvement to an existing negotiation strategy in order to further speed up negotiation process and increase organization utility. Experiments show the effectiveness of our approach in terms of utility, time and success rate.

Gamification used in e-learning platforms is considered as a very valuable process forasmuch as it helps students to focus on their study manner, improve their educational experiences, boost their motivation and engagement and facilitate the learning mechanism. However, the one-size-fits-all approach could be inadequate for all learners. Whereas learners are educated regardless of their concerns, cognitive capacities, learning styles, attitudes, and personalities, which are all unique to them. Adaptive gamification has emerged, focusing on adaptive learning and cognitive science research and is providing personalized learning according to what the learner has for skills and interests. In this article, we present a personalized gamification model based on ontologies. The potential of our model is that it combines, at the same time, adaptive learning and adaptive gamification. Also, it considers both player context and learner context to adapt learning scenarios. The first implementation steps of our proposed approach will be presented in this article.

Recently, Convolutional Neural Networks (CNNs) have made a great performance for remote sensing image classification. Plant recognition using CNNs is one of the active deep learning research topics due to its added-value in different related fields, especially environmental conservation and natural areas preservation. Automatic recognition of plants in protected areas helps in the surveillance process of these zones and ensures the sustainability of their ecosystems. In this work, we propose an Enhanced Randomly Initialized Convolutional Neural Network (ERI-CNN) for the recognition of columnar cactus, which is an endemic plant that exists in the Tehuacán-Cuicatlán Valley in southeastern Mexico. We used a public dataset created by a group of researchers that consists of more than 20000 remote sensing images. The experimental results confirm the effectiveness of the proposed model compared to other models reported in the literature like InceptionV3 and the modified LeNet-5 CNN. Our ERI-CNN provides 98% of accuracy, 97% of precision, 97% of recall, 97.5% as f1-score, and 0.056 loss.

In today’s digital world, counter-terrorism is considered as one of the highest priorities in defense departments worldwide. Organizations are investing in the development of new tools that harness advanced information technology to detect and counter terrorism through in-depth analysis of online data, especially online social networks (OSNs). A militant terrorist groups are exploiting these networks in the aim to promote their organizations and recruit more naive people inside their dangerous communities, the most used social network by these groups is Twitter. However, the existing approaches are not very efficient or they do not study the behaviors of these malicious users and they only rely on textual data provided by the users. In this paper, we propose a novel computational model using various machine learning and recommender systems techniques for detecting and predicting the influence of terrorists’ behaviors on social networks from their text-posted and image-posted content, as well as building social graphs of terrorist networks that are helpful for any further social network analysis.

Travel demand modeling requires micro-data of populations at household and person levels as a key input. Unfortunately, due to privacy constraints and the high cost of surveys, such data is often unavailable. To overcome this limit, populations can be synthesized to create disaggregated and complete representations of the studied population from real samples. Within this framework, Volunteered Geographic Information (VGI) is very promising to enrich the input sample and consequently to improve the goodness-of-fit of the resulting synthetic populations. An approach based on an evolutionary algorithm (EPSA) was previously introduced to generate a synthetic population with progressive inputs fed by VGI. However, it does not perfectly address the problem of assigning results to their locations. To solve this problem, we present a new Improved Evolutionary Population Synthesis Approach (IEPSA) based on a three-dimensional stable matching algorithm. Experimental results show the high efficiency of the proposed solution.

In the context of Product lines, the collaborative configuration process gets complicated when the configuration decisions of involved stakeholders are contradictory, which may lead to conflicting situations. Although considerable research has been devoted to collaborative configuration, little attention has been paid to conflict resolution. Moreover, most of existing approaches rely on a systematic process which constraint decisions of some stakeholders. In this paper, we propose a new collaborative configuration approach which allows conflict resolution based on stakeholders preferences expressed through a set of substitution rules. Based on such preferences, we delete the minimal set of conflicting configuration decisions which are identified using the Minimal Correction Subsets (MCSs) computing algorithm. An illustrating example and a tool prototype are presented to evaluate the applicability of our approach.

The increase in electronic devices and social media use has allowed face-to-face bullying integrate the cyber space. Cyberbullying is an increasing problem that affects its victims worldwide both mentally and physically. Acting upon this phenomenon is of highly importance. Several researches were conducted on cyberbullying classification in English language and less on Arabic. In this paper, we conducted a series of experiments using neural network models (Convolutional and Recurrent Neural Networks) and pre-trained word embeddings in an attempt to classify cyberbullying instances on an Arabic channel news comments dataset. Best models achieved 0.84 F1-score on a balanced version of the aforementioned dataset.

With the multiple occurrences of natural and man-made disasters, supporting emergency decision makers (EDMs) in crisis response is primordial. Case-based reasoning (CBR) is a fitting problem-solving paradigm to solve crisis response issues. The performance of the CBR method depends on the steps of case representation and case retrieval. This paper firstly proposes the use of an ontology in order to represent crisis response cases. Then, it develops a two-stage case retrieval method. This latter firstly matches crisis events in order to generate a set of potential similar cases and then matches crisis impacts to obtain a set of the most similar cases. In addition, the proposed case retrieval method integrates cumulative prospect theory (CPT) in similarity measurement for the purpose of taking into account the psychological behavior of the EDM in the process of case retrieval. Finally, a case study using flood crisis real cases is used to illustrate our proposed method.

E-learning is constantly growing and seems to be essential in this rapidly changing world. Continually improving learners ‘experience, gamifying e-learning appeared with one objective: of motivation, attendance and progress of e-learners. One size of gamification isn’t suitable for all learners. Learners do not interact with gamification element or gamification environment in the same way which brings the appearance of personalized gamification which has proven its effectiveness to improve learner engagement, motivation and learning results. To understand which mechanisms and dynamics create pleasure, several concepts revolve around to personalized gamification. A learner in the context of adaptive gamification has different changing aspects like personalities, needs, values and motivations, we are going to combine those aspects with learner experience to adapt gamification process. The objective of this paper is to propose a representation of adaptive gamification domain knowledge into an ontology. To evaluate AGE-Learn† ontology, we adopt a criteria-based evaluations approach.

Data quality has become an important issue. This issue becomes more and more important in medicine area, where the need for effective decision making is high. In this context, the need for data cleaning to improve data quality is becoming crucial. Duplicate records elimination is a challenging data cleansing task. In this paper, we present a duplicate records elimination approach to improve the quality of data. We propose a deep learning-based approach for duplicate records detection using a sentence embeddings model. Also, we propose an algorithm for duplicated records correction. Then, we apply the proposed duplicate records elimination approach to analyse the effect of data cleaning on the quality of decisions. We evaluate our proposal on heart disease problem using Cleveland heart disease dataset. Experiments show that the classification performance improves upon the application of the duplicate records elimination approach on datasets compared to that of datasets with duplicate records.

As with normal learners, disabled learners should also benefit from technology and more specifically accessible technologies. The design and implementation of learning solutions adapted to the needs of these learners are the major challenges faced by situation-aware ubiquitous learning systems. The learning process guidance is one of the most important forms of adaptation. This is why our study will focus on guidance work and those dedicated to disabled learners. The aim of this paper is to give an overview of the state-of-art in situation-aware ubiquitous learning systems. To do so, the study adopts a classification framework based on four different views (awareness, adaptation, guidance and u-accessibility). The framework has been used six ubiquitous learning systems dealing with guidance and / or learning for disabled and/or non-disabled learners.

Duplicate record detection is a crucial task for data cleaning. Records representation is among the main challenges of this task. Word embeddings models have been widely applied in an attempt to improve records representation. However, despite the improvements made by word embeddings to enhance the semantic aspect, duplicate record detection results is still insufficient In this paper, we present a duplicate record detection approach based on sentence embeddings, where each attribute is viewed as a sentence. First, universal sentence encoder model is used to embed the values of records' attributes into embeddings vectors. Afterwards, based on the created vectors, similarity vectors between the record pairs are computed. Finally, support vector machine algorithm is used to classify the similarity vectors. Experiments on two datasets (Cora and Restaurant) show that our proposal outperforms state-of-the-art baselines and leads to significant improvements in duplicate record detection effectiveness.

Port scanning is a cyber-network attack allows cyber terrorists to gather valuable information about target hosts namely defense, governmental and banks servers by trying to identify instantly open ports, which correspond to specific services on the cloud, such as HTTP, DNS, and email. The basic role of Intrusion Detection Systems (IDSs) is to monitor networks and systems for malicious activities, policy violations attacks and unauthorized information gathering activities. In this paper, we proposed a TCP port scanning detection framework, based on fuzzy logic controller, which uses fuzzy rules base and the Mamdani inference method. The proposed platform is a Fuzzy IDS as a Service, which enables network administrators and cyber security specialists to follow in real time the network traffic behavior, i.e., the Port Scanning Criticity Level (PSCL). A SaaS dynamic dashboard is implemented to quickly and efficiently identify malicious port scanning activities. Experimentations and evaluations showed the efficiency of the proposed system in multilevel port scanning detection compared to Snort and the related IDS systems.

Service-oriented architecture (SOA) is known to be characterized by its openness, its agility and its composability. Such architecture includes autonomous, interoperable and potentially reusable services, which are implemented as Web Services (WS). When deployed in the Cloud Environment, security threats may increase at the WS level, raising some security challenges, such as vulnerability discovery and trust or availability violation. Addressing security issues require complex tasks that should be treated separately with associated concerns. To deal with this problem, we refer here to an alternative architecture known as Micro-Services Architecture (MSA) which is based on the principle of decomposing large and complex software projects into many atomic sub-projects. In Addition, to control, manager and ensure that vulnerabilities are appropriately treated and the expected security objectives are achieved, we find that the governance of Web Service security is inevitably required. Hence, we suggest here a Web Service security governance approach aims to reduce the security flaws and to enhance trust between web services. This approach consists in combining micro-services by using a sub-set of GDPR (EU General Data Protection Regulation (GDPR) replaces the Data Protection Directive 95/46/EC and was designed to harmonize data privacy laws across Europe, to protect and empower all EU citizens data privacy and to reshape the way organizations across the region approach data privacy.) rules and a set of defined security policies. This approach allows guessing the dedicated micro-service referring to user security requirements.

Stemming process is one of the important pre-processing steps in different natural language process tasks such as text mining and information retrieval. Yet, stemming process can be considered as a difficult step to realize according to the used language. In fact, due to the complex morphology of Arabic language, stemming results can be influenced. Thus, several algorithms have been proposed in order to overcome stemming problems. In this paper, we investigate different stemming algorithms by presenting a comparative study in the field of Arabic topic identification.

International audience

Data lakes have recently emerged as an alternative solution to costly traditional data warehouse solutions. To exploit data lakes, however, there is a need for means that assist users in combining and integrating data stored within a data lake. In this paper, we position ourselves in the recurrent context where a user has a local dataset that is not sufficient for processing the queries that are of interest to him/her. We show how data lakes, or more specifically the service lakes, since we are focusing on data providing services, can be leveraged to answer user queries, taking into account the quality of the services and respecting the (time and monetary) budget set by the user.

Cloud applications are increasingly available, and the cloud must provide a multitude of services to cover the requirements of diverse users. Likewise, the number of web services has increased, and users may find themselves lost in the array of complex services. Consequently, it has become difficult for users to find the best services to meet their needs. In this context, cloud service discovery is an important challenge that has received increasing attention. In the cloud environment, services are openly accessible, which can lead to potential risks. Security in cloud services thus is necessary and can be identified through many attributes. In this study, we examine privacy attributes, which at present are the most bargain property in the cloud environment, and present a few mechanisms, including access control. With a specific goal to encourage cloud investigation by the user, we propose a refined cloud services discovery tool based on a user model that includes privacy-preserving access control. This user model is a combination of user context and security context and is designed with the aim of disentangling the demonstrating task.

The emergence of web 2.0 virtual spaces, namely social networks and social media, enables terrorist organizations to flourish and advance their cyber malicious activities by posting criminal contents, exchanging information and polarizing new members. Thus, there is an immense need for the development of effective approaches to understand cyber terrorist organizations structures, working strategies, and operation tactics. A terrorist community is a set of subgroups, which share many properties but differ on others, such as degree of activity and roles. The identification of these sub-communities is a key task not only to understand the topology of these organizations but also to discover their operation methods. In this paper, we propose a cyber community detection approach based on Constrained Evidential C-Means (CECM) algorithm which is an adequate evidential clustering method that can be applied to detect cyber terrorist subgroups. Based on Must-link and Cannot-link constraints, objects (network members) can be classified into various sub-classes Cn, such as military, finance and local leaders committees. The membership of nodes to clusters (sub-communities) is described by Belief functions. Clustering results show the efficiency of our evidential constrained approach not only in classifying cyber terrorist actors into the aforementioned communities, but also in allocating a degree of membership for each member to each class.

Topic Segmentation is one of the pillars of Natural Language Processing. Yet there is a remarkable research gap in this field, as far as the Arabic language is concerned. The purpose of this article is to improve Arabic Topic Segmentation (ATS) by inquiring into two segmenters: ArabC99 and ArabTextTiling. This study is carried out on two independent levels: the pre-processing level and the segmentation level. These levels represent the basic steps of topic segmentation. On the pre-processing level, we examine the effect of using different Arabic stemming algorithms on ATS. We find out that Light10 is more appropriate for the pre-processing step. Based on this conclusion, we proceed to the second level by proposing two Arabic segmenters called ArabC99-LS-LSA and ArabTextTiling-LS-LSA. These latter use external semantic knowledge related to the Latent Semantic Analysis (LSA). Based on the evaluation results, we notice that LSA provides improvements in this field. Hence, the main outcome of this article emphasizes the multilevel improvement of ATS based on Light10 and LSA.

In a Web services (WS) composition process, identifying the relevant sequence of services that meets the end user requirements remains an important issue. WS semantic enrichment process helps in solving this issue to cope with data heterogeneity, and facilitate their discovery and integration. This process should support personalization that takes into account user context. Currently, this personalization is not sufficient. In fact, it needs to be extended until the realization step. Besides, it requires many human interventions. The main characteristics of services based architecture, which are deployment and distribution, may open important security flaws. Personalization should then include protection against threats that could be encountered. WS composition must be made in a careful way, and security integration is neccesary.Starting from the beginning of runtime phase of a composition process, this paper suggests an on-the-fly approach which aims to: 1) Personalize the scheduling of all linked semantic Web services (SWS) according to their relevance degree based on user context ontology. 2) Try to improve the security level of each SWS and their composition according to usage and based on a security ontology and security patterns.

Recently, terrorist risks are continuing to increase in the form of terrorist acts due to various and simultaneous factors. This subject is of great scientific interest and importance because our society is vulnerable and we have a low level of protection against terrorism. This paper aims at developing a decision support model, called jCatt (jCOLIBRI against terrorist attacks). The preventive model is based on acquiring and reusing past attacks historically solved to assist a decision maker. It helps to understand each terrorist attack situation and to propose possible solutions in the form of preventive and / or corrective measures. It is composed of two main parts: knowledge models described by an ontology, and a reasoning process based on Case-Based Reasoning (CBR). In this paper, we present the development environment used, the architecture and in particular the various components of our model as well as the phases of the reasoning cycle.

Hashtags are crucial social data that are useful for multiple purposes, such as tweets' classification, indexing, content categorization, search or recommendation. Hashtags recommendation on Twitter is an important issue, seeing the importance of this social data and the need of social users to be provided with personalized information that fits their interests. Users recommendation is also an eminent task as it allows a user to broaden his network by users with similar interests. This work focuses on how hashtags can be analyzed for recommendation purposes. First, we present a state of the art reviewing social analysis, users and hashtags' recommendation. We then present a new architecture of hashtags and users recommender system based on hashtags' semantic analysis. This proposal is based on ontology as a semantic resource. We build social user profiles, analyze hashtags and study their contextual and temporal cooccurrence. We then propose two novel ranking schemes. The first is HF-IUTF scheme that weights hashtags in the user profile. We use it to rank and filter the representative hashtags of each user's social profile. The second contribution is HF-IGHF scheme: Given a group of users, this method identifies the hashtags representative of the group. We apply spectral clustering algorithm to obtain similar clusters. We can then recommend similar users of the same cluster and representative new and recent hashtags of users in the cluster. The originality of this architecture is the way user profiles will be semantically indexed and analyzed, and ranking schemes that are independent of the way the similarity group is built.

Today, operational and business agility within organizations need to be improved to deal with the new challenges and seize the opportunities. Cloud computing is proving to be the key to achieve these goals. This technology allows to meet the organizations requirements and to benefit from virtually unlimited resources. However, the migration of information systems from the organization to a cloud environment is not trivial and requires considerable effort. The organization must follow a comprehensive process to ensure the migration of its information system. An exhaustive analysis and planning is required to ensure successful migration. Different cloud migration processes are proposed. However, we notice the lack of a migration process that is based on a detailed analysis of the information system and all its components, and that takes into account all the issues encountered during the migration. For this reason, in this work we propose a methodology to assess information systems components in order to help organizations make decisions during their journey towards cloud migration.

Studies on u-accessibility for learners with special needs have been the subject of many researches in recent years. The works identified in the literature are developed to solve the u-accessibility and divided into two categories: Web accessibility works and assistive technologies works. The work of web accessibility presents guidelines and recommendations for the design of accessible websites while assistive technologies works, facilitate the use of computers and other devices according to the learner's disability; however, these works need to have a clear view and an overview of how systems intended assure uaccessibility for learners with disabilities. This study details a multidimensional descriptive view of u-accessibility in contextaware ubiquitous learning systems for learners with special needs through seven different views. Each view captures a particular aspect of u-accessibility, learning and guidance. Then a set of facets is associated with each particular aspect in order to study, understand and describe it appropriately. This work would be helpful for context-aware u-learning system developers in order to have a clear understanding of u-accessibility and learning process guidance for learners with special needs in such systems and highlight the guidelines to be applied and the means used to satisfy the needs as well as the requirements of the learner and the application. Last but not least, the framework provides a first step towards a common understanding of u-accessibility in context-aware learning systems for disabled learners.

Identify the serious games that best meet the needs and expectations of teachers and pedagogical objectives of their courses remains a necessity about the integration of serious games in the learning process. Indeed, several serious games have developed in recent years, and it is often difficult for a teacher, not a computer scientist in particular, to find and choose a game that meets its specific needs. Our aim is to develop models and tools to support teachers/trainers in their choice of serious games through knowledge extraction of educational objectives, considering user feedback and their traces of interaction with the game.

Common personalization approaches involve re-ranking search results. In such way, documents likely to be preferred by the user are presented higher. In this paper, we focus on research-paper retrieval. We propose a scientometric re-ranking approach based on the scientometric preferences of a particular researcher. The researcher creates its own definition of document quality by the mean of scientometric indicators. These indicators are the base of the scientometric score calculation, which serves to results re-ranking. The originality of our approach was the incorporation of different scientometric indicators into researcher’s preferences which have significantly improved ranking performance.

The vector representations of words are very useful in different natural language processing tasks in order to capture the semantic meaning of words. In this context, the three known methods are: LSA, Word2Vec and GloVe. In this paper, these methods will be investigated in the field of topic segmentation for both languages Arabic and English. Moreover, Word2Vec is studied in depth by using different models and approximation algorithms. As results, we found out that LSA, Word2Vec and GloVe depend on the used language. However, Word2Vec presents the best word vector representation yet it depends on the choice of model.

The emergence of social networks and the communication facilities they offer have generated an enormous informational mass. This social content is used in several research and industrial works and has had a great impact in different processes. In this paper, we present an overview of social information use in Information Retrieval (IR) and Recommendation systems. We first describe several user profile models using social information. A special attention is given to the following points: the analysis of the different user profiling models incorporating social content in Information Retrieval (IR) and in social recommendation methods. We distinguish between the models using social signals and relations, and the models using temporal information. We also present current and future challenges and research directions to enhance IR and recommendation process. We then describe our proposed model of social polarized and temporal user profile building and use in social recommendation context. Our proposal tries to address open challenges and establish a new model of user profile that fits information needs in recommender systems.

Cloud computing has made a revolution in the way in which IT services are delivered to organizations. For organizations, have an effective and efficient IS migration process is important to ensure a successful process. Certainly, several migration processes have been proposed but we notice the lack of a general and well detailed migration process that ensures cloud migration and integrates an economic model that increases the profits of the organization in terms of cost and performance. To fill this gap, we propose a cloud migration process which allows automating the cloud service selection and deployment by using the brokerage model. The broker will help the organization to select the cloud provider that meets its requirements, and manage the provisioning and the execution of cloud services. This paper will be dedicated to explain and detail the first phase of this process which is the assessment phase. This phase represents the basis of the whole process and has a very important role in the success of the migration project. The assessment phase will be applied in a concrete example based on the information system of the company Sigma Conseil.

Situation awareness is an emerging concept in ubiquitous environments, particularly the learning ones. Situation-aware systems aim to infer the user's situation from detected context. Given the fact that detected context information pieces are prone to sensors' quality, recent quality-awarecentred researches are basically interested in the evaluationof the quality of context (QoC). However, so far no attentionhas been paid to improve system awareness of the identifiedu-learning situation quality. In this paper, a new proposal for evaluating quality of situation (QoSi) is detailed. The proposition aims to compute QoSi by combining QoC of context elements used to describe the identified situation. QoC are weighted according to the weights attributed to the context elements on which the identified situation depends once all context elements do not have the same importance to describe the inferred situation. Illustrative example is given to show the applicability of the proposed solution in evaluating QoSi of Cooperative Data Collecting u-learning situation and its usage in learning resource recommendation.

Recently, the social network has revolutionized the interaction and information exchange between users. Several works have been committed to unify the social network domain, particularly the medical domain through introducing ontology-based modeling of medical social network. Nevertheless, few researches focused on modeling the social network using ontology from the medical side. To overcome this drawback, we propose, in this paper, a medical social network ontology which includes definitions of main entities and describes major attributes of medical social network concepts aiming at sharing common understanding of this domain.

Situation identification has become a major issue for situation-aware ubiquitous learning environments. The identification process aims to infer learner's situation by aggregating detected context information pieces. Most recent situation identification approaches are basically focused on crisp ontological modelling and reasoning. Given the fact that crisp ontology is not able to deal with context information imperfection, a new approach for situation identification based on fuzzy ontology is proposed in this work. The proposition aims to evaluate for any observed runtime situation a certainty degree relative to the recognition of a typical u-learning situation, known as situation pattern. The pattern relative to the highest certainty degree is triggered as the most appropriate pattern to the observed learning situation. Experimental results are given to show the applicability of the proposed solution for u-learning situation identification under imperfection and to show to what extend fuzzy ontology out performs crisp one.

With the evolution of teaching modalities and the high integration of the technology in the learning processes, teachers proceed to the design of learning situations in order to plan and formalize their educational experiences and share them with students and other teachers. Various academic and community initiatives of experience sharing and resulting learning scenarios repositories have emerged. This leads us to discuss the learning scenarios reuse issue, which becomes an essential practice for capitalization. Since the learning contexts are continuously changing, it could represent an obstacle to the reuse and the appropriation of learning scenarios. It therefore becomes important to consider the context dimension to assist teachers in the scenarios reuse situations. This paper deals firstly with the proposition of an approach to model learning scenarios context. Based on this modeling approach, this paper is interested in the retrieval of learning scenarios that most fit a target learning situation context by presenting a context similarity algorithm matching contextual models. The retrieval is based on contextual indexes related to scenarios. The indexing process is consolidated by the observation of the prior user-experiences of learning scenarios. An authoring tool is then presented integrating the context modeling approach and the detailed algorithm. Simulations of the implemented tool and related results are detailed within this paper.

There was a growing interest in the development of CSCL (Computer Supported Collaborative Learning) environments over the last decade. Despite the plethora of tools available, they ignore the cultural differences between learners. In fact, especially, in the case of distant learning, these environments may bring together learners from different socio-cultural backgrounds that have acquired different socio-cultural values and behaviors and developed different needs, points of view and learning styles. Thus, CSCL environments need to be socio-culturally adapted to each learner’s culture. The main goal of this paper is to emphasize the need of socio-cultural aware collaborative learning, to present our proposed ontology-driven adaptation approach to meet this need, its operationalization and its experimental validation. Results and limits are discussed at the end of the paper.

In this paper, we aim to cover works that are related to the process of transforming requirements into UML diagrams, from the first works which were manual techniques in 1976, to automatic tools in 2015. In this context, we try to exhibit different approaches and to indicate their strength as well as their shortcomings. This work will help us to evaluate existing approaches and propose other alternatives for Requirement Engineering. The objective of this paper is to present an overview of various works dedicated to requirement analysis and a comparative study of these works. Also, we tried to discuss the combination of Artificial Intelligence with Requirement Engineering.

Real-time applications managing a large number of real-time data require the use of Real-time Database Management Systems (RTDBMS) to meet temporal constraints of both real-time data and transactions. However, a RTDBMS has a dynamic workload and may be frequently overloaded since the arrival times and workloads of user transactions are unpredictable. Therefore, Quality of Service management solutions have been proposed to guarantee the stability of RTDBMS even during unpredictable overload periods. While effective, the design and reuse of these solutions is challenging because they are not formally modeled and there is no tool neither a methodology that helps us design such solutions. To address these issues, the authors propose a design framework based on the Model-Driven Engineering approach providing a modeling architecture, a strategic methodology and a software tool to support modeling and reusing such solutions. The framework is implemented and tested for a real Qos management solution.

Summary Software development life cycle is a structured process, including the definition of user requirements specification, the system design, and programming. The design task comprises the transfer of natural language specifications into models. The class diagram of Unified Modeling Language has been considered as one of the most useful diagrams. It is a formal description of user's requirements and serves as inputs to the developers. The automated extraction of UML class diagram from natural language requirements is a highly challenging task. This paper explains our vision of an automated tool for class diagram generation from user requirements expressed in natural language. Our new approach amalgamates the statistical and pattern recognition properties of natural language processing techniques. More than 1000 patterns are defined for the extraction of the class diagram concepts. Once these concepts are captured, an XML Metadata Interchange file is generated and imported with a Computer‐Aided Software Engineering tool to build the corresponding UML class diagram. Copyright © 2015 John Wiley & Sons, Ltd.

The BASAR project offers a repository of blended learning scenarios. This project aims to reuse and capitalize good teaching practices. A teacher-designer would have the ability to choose a scenario that matches his needs, to be modified, used and refined. Specializing the scenario to a given context often improves the learning quality. On the other hand, it increases the difficulty to reuse it in a different context. Knowing the appropriate contexts for a scenario is essential for better reusing a part of this scenario or all of it (granularity). So, how can we characterize the learning scenarios with their most appropriate contexts based on the observation of the learning sessions progress in order to enhance scenario retrieval? This paper proposes a multi-faceted approach to index learning scenarios using the context trees formalism. The main objective of this indexing is to facilitate the learning scenarios design by and for reuse.

Question Answering systems aim at providing answers to natural language questions and provide a solution to the problem of response accuracy. This paper describes a visual QA framework based on ontolgoies, that relies on two main components: question analysis component and answer extraction component. Our goal consists on performing an efficient question answering by: (1) Improving the representation of the question's structure using question ontology and typed attributed graphs, (2) Improving the results of question reformulation using domain ontologies and lexicosyntactic patterns (3) Extracting answers based on the question graph, lexico-syntactic patterns and score computation and (4)Offering a visual representation of the graphs and ontologies. Our framework has been implemented and evaluated.

Service-Oriented Computing (SOC) is a new computing paradigm that utilizes service to support the development of rapid, low-cost and easy composition. SOC promotes creation of new services by composition. In the composition process, requirements are described by requestor and Web service offered by the provider, a provider is the owner of service his role is to create service and publish it to make it available to customers and partners. A number of Web services compositions approaches have been presented to satisfy the end user's requirements. Interactive Web services compositions (IWSC) creates new value by adapting the end-user's requirements, the end-user corresponds to the person requesting the service and who will search and invoke the service. With the emergence of collective intelligence (CI), IWSC allows a better end-user's satisfaction. In this paper, we propose a new approach that supports Collective intelligence for satisfying the actor's requirements that suggests a model to help the web services composition. Our approach uses the beneficial roles of collaboration as a key for future services composition. It uses also the interactivity between the actors, user interaction during a service composition will contribute in the satisfaction degree of the actors.

Collaborative learning environments bring together learners from different cultures and social contexts, around a common task. These learners interact both with each other and with computers. Hence, a dual problem arises: how to model and integrate socio-cultural factors that characterize these learners? How to design and develop culture-aware collaborative learning environments? This paper addresses both issues by describing an ontology based socio-cultural adaptation approach and its operationalization leading to the implementation of a culture-aware-web-based collaborative system. The adaptation of the collaborative learning environment is performed according to the socio-cultural profile of each learner.

Ontologies have proven their utility in the area of Information Retrieval. However, building and updating ontologies manually is a long and tedious task. Moreover, crisp ontologies are not capable to support uncertain information. One interesting solution is to integrate fuzzy logic into ontology to handle vague and imprecise information. This paper presents a method for individual fuzzy ontology building. The key aspects in our proposal are: (1) an automatic building of an individual fuzzy ontology; (2) a query reformulation based, on the one hand, on the weights associated with the concepts and all existing relations in the fuzzy ontology and, on the other hand, on users' preferences, (3) an update of the membership concepts and relations' values after each users search, and (4) the use of the proposed fuzzy ontology and service ontology to individually classify documents by services. Our method has endured a twofold evaluation. Firstly, we have evaluated the impact of the update and the weights' variations on the search results. Secondly, we have studied how the query reformulation has led to a quality results improvement, both in terms of precision and recall.

In the context of Software Product Line (SPL) reuse paradigm, one of the most widely used models is the feature model. It describes the set of products in an SPL in terms of their features and the relationships among them. A feature is an externally desired service by the system. While features concern functional aspects, non-functional features must also be considered which have impact on the quality of the SPL derived systems. For this purpose, Extended feature models are proposed in the literature. In order to verify the consistency of such models, several techniques are proposed. We adopt a formal approach that represents Extended Feature Models and reason about them for proving consistency and other operations. In this paper, we show the impact of non-functional attributes on the analysis operations of feature models. In this work, we have resumed analysis operations of feature models listed in the literature. Moreover, we studied the effect of adding the non-functional attributes on these operations by giving examples. So this has enabled us to emphasize the presence of three types of constraints namely: constraint value, constraint attribute-attribute and constraint feature-attribute.

Decision making has become a strategic need for any business. Indeed, it is among the priorities of capital business. The establishment of decision information systems facilitates the data exploitation and analysis. We distinguish data warehouses as the core system of business intelligence to ensure the structuring and analysis of multidimensional data. Consequently, the design of data warehouses has become a major problem, leading to the development of appropriate approaches to implement data warehouses. In this paper, we propose an approach to design and to construct data warehouses based on a descriptive statistics technique for the analysis of multidimensional data in the Principal Components Analysis (PCA). The findings of this article appear in two main areas: (i) a conceptual model data warehouse, (ii) an algorithm for the determination of measures and dimensions. A case study is used to validate our proposal.

Research in ubiquitous learning (U-learning) has gained attention of a large number of researchers and a number of ubiquitous learning systems are now available in the literature. Majority of these systems have been developed to resolve a specific problem in a given context; their development approaches do not dictate ubiquitous context usage requirements to fill in. U-learning systems developers need to have a clear and a general view of how their intended systems make use of the ubiquitous context. This paper introduces a comprehensive view of context usage through three different view-points inspired from Dowson’s work (Dowson, 1993) each one capturing a particular aspect of context handling. Then a set of facets is associated to each given aspect in order to study, understand and appropriately describe it. The findings of this research are aimed to provide context-aware u-learning system developers a clear understanding of the context usage in such systems and help in underlining the requirements of the u-learning environment. This research is also aimed to help in comparing and evaluating context-aware u-learning systems according to the descriptive system views.

The work developed in the context of this article stems from the thesis work in progress (done in RIADI labs. at the National School of Computer Sciences, Tunisia in collaboration with the Research Unit of Evaluation of Automated Transport Systems and Safety IFSTTAR, French). The works treat the problem of knowledge management of a critical area, that of security and in particular the railroad accidents. The goal is to provide methodological support and tools to support the capitalization and exploitation of produced knowledge and/or used by domain experts. We have proposed an approach based on domain ontology and Case-based Reasoning CBR. We will present as part of this article, the first realized works in our approach.

The new paradigm for distributed computing over the Internet is that of Web services (WSs). One of the key ideas of this new paradigm is the ability to create value-added Service-Based Applications (SBAs) by composing pre-existing services. Building SBAs necessitates the discovery and the selection of the most appropriate WSs that fit closely users' functional and non-functional requirements. Due to the large number of WSs that are advertised over public and private registries and the various functional and non-functional capabilities that are required by users, discovery and selection of WSs have become a real challenge nowadays. In this paper, we present a WS composition approach that is built upon both perspectives: intentional and operational. In the intentional perspective, we propose to model users' requirements for SBAs using the MAP formalism and specify the required WSs using an Intentional Service Model (ISM). In the operational perspective, we propose to discover the required WSs by querying the service search engine Service-Finder and select the most appropriate WSs by using many-valued concept lattices. To validate our approach, we use an analytical technique that is the monitoring to verify that the selected WSs assure the required users' non-functional capabilities.

Choosing the shortest path for real-time flows is insufficient. Respecting the deadline cannot be insured nor guaranteed neither with exhausted energy resource nor with overloaded intermediate mobile nodes. The main problem is to choose the reliable, efficient and correct routing protocol to route real-time flows with respect to their deadlines within MANET constraints. This paper introduces the Energy Delay aware based on Dynamic Source Routing, ED-DSR. ED-DSR efficiently utilizes the network resources such as the intermediate node energy and load in order to balance traffic load. It ensures both timeliness and energy efficiency by avoiding low-power and busy intermediate node. Simulation results, using NS simulator, improve that the protocol increases the volume of delivered packets in-time (around 50% for the data flows with strict deadline and around 63% with non-strict deadline), prolongs the network lifetime (up to 66%) and shortens the end-to-end delay.

COTS-Based Software Development has emerged as an approach aiming to improve a number of drawbacks found in the software development industry. The main idea is the reuse of well-tested software products, known as Commercial-Off-The-Shelf (COTS) components, that will be assembled together in order to develop larger systems. The potential benefits of this approach are mainly its reduced costs and shorter development time, while ensuring the quality. One of the most critical activities in COTS-based development is the identification of the COTS candidates to be integrated into the system under development. Nowadays, the Web is the most used means to find COTS candidates. Thus, the use of search engines turns out to be crucial. This paper deals with existing search engines especially proposed to find COTS components satisfying some needs on the Web. It presents a state of the art and practice of search engines followed by a study assessing to which extent they are able to accomplish their objectives.

This paper presents the results of our innovative approach for the realization of a model driven development framework for modeling context-aware adaptive learning activities within Context-aware and adaptive learning environments. Its core element consists of a domain specific visual modeling language called CAAML (Context-aware Adaptive Activities Modeling Language). After, we present the developed authoring tool based on CAAML language and that aims to support pedagogical designers to model context-aware adaptive learning activities and transform them into executable models represented in IMS-LD.

In this paper, we propose a new constraint to select materialized webviews. The webview materialization is a term used to represent the transformation of dynamic web data into equivalent static web data. That is the creation of a static instance of a dynamic web page, at a certain point in time. Our new selection constraint consists of limiting the number of sources of materialized webviews. Our first aim is to reduce the update frequency of the materialized webview. This will decrease the access cost to the data sources which may be distant. Secondly, we aim to guarantee the stability of the profit and the materialization load of the materialization plan (the set of materialized webviews) during the selection period. That is we will reduce the probability of early violation of the selection constraints or early materialization loss of the selected plan. Our experiment results show that for small values of the source constraint, our approach can improve the average profit of materialization by more than 15%. Also, when the number of candidate webviews is high, the query response time is improved by applying our solution.

Nowadays, to survey and guarantee the security policy in networks, the administrator uses different network security components, such as firewalls and intrusion detection systems (IDS). For a perfect interoperability between these components in the network, these latter must be configured properly to avoid misconfiguration anomalies between them. However, there are a set of anomalies between alerting rules in the IDS and filtering rules in firewalls, that degrade the network security policy. In this paper, we will present a mobile agent based architecture to detect misconfigurations between these distributed components and generate a new set of rules free of errors. A case study will illustrate the effectiveness of our approach.

Firewalls are core elements in network security. However, detecting anomalies, particularly in distributed firewalls has become a complex task. Mobile agents promise an interesting approach for communications between different distributed systems specially Web services applications. In this work, we propose a firewall anomaliespsila detection system based on interactions between the Web services and the mobile agents technologies. Then, we highlight the trumps of this approach compared to the client/server model.

Firewalls are core elements in network security. However detecting anomalies, particularly in distributed firewalls has become a complex task. Mobile agents promise an interesting approach for communications between different distributed systems. The main challenge when deploying mobile agent environments pertains to security issues concerning mobile agents and their executive platform. In this work, we propose a firewall anomalies' detection system using a secure mobile agents approach where protection is based on the cooperation of a trust agent running inside a trust host.

In this paper we present the main existing approaches of management quality of service (QoS) in Real-Time database management systems (RTDBMS) which are based on the feedback control scheduling. We propose a generic model of these approaches composed by three layers: Models, Parameters and Policies. We aim to help designers of real time applications to rapidly design a feedback control based QoS management approach by reusing, configuring and adapting our model to their requirements.

Building secure software is about taking security into account during all phases of software development. This practice is missing in, widely used, traditional developments due to domain immaturity, newness of the field and process complexity. Software development includes two views, a product view and a process view. Product view defines what the product is, whereas process view describes how the product is developed. Here we are concerned with the process view. Modelling the process allows simulate and analyze a software development process, which can help developers better understand, manage and optimize the software development process. In this paper we present our approach S2D-ProM, for Secure Software Development Process Model, which is a strategy oriented process model. This latter, capture steps and strategies that are required for the development of secure software and provide a two level guidance. The first level guidance is strategic helping developers choosing one among several strategies. The second level guidance is tactical helping developers achieving their selection for producing secure software. The proposed process model is easily extensible and allows building customized processes adapted to context, developer's finalities and product state. This flexibility allows the environment evolving through time to support new securing strategies.

Web Services security is a major concern in the web engineering domain. Several approaches emphasizing Secure Web Services Design (SWSD) process have been proposed. However, they provide a little guidance as to what developers should do exactly to conduct this highly intellectual process. SWSD practices cannot be defined independently of the situation in which they are applied. To address this challenge, we propose an approach for guiding the construction and execution of situational SWSD methods by reengineering and integrating different existing SWSD method components suited to the specific situation on hand.

SWSD practices cannot be defined independently of the situation in which they are applied. To address this challenge, we propose an approach for guiding the construction and execution of situational SWSD methods by reusing and integrating different existing SWSD method components suited to the specific situation on hand.

Summary form only given. This paper discusses that in order to help development with reusable software components, various reuse libraries should be available for users, components retrieval, use and comprehension should be facilitated and relations between components should be considered. To achieve this goal, we propose a reuse infrastructure-IRL which preferences various reuse libraries in order to make them available for users all over the world and to facilitate their access, 2) supplies components reuse guidelines, samples and/or demos to facilitate their comprehension and use and 3) extracts components relationships to facilitate their composition and integration. IRL infrastructure is based on a component meta-model and a search process. The meta-model represents a meta-library associated with IRL and encapsulates different views of a reusable component. The search process is strategic and supplies different search techniques which can be applied to search for components independently of their source libraries search techniques. This infrastructure provides an ontology which represents components meta-knowledge. This ontology provides, in one hand a unified vocabulary for various reuse libraries by which ambiguities on the components semantics are removed. On the other hand, this ontology facilitates components search and filling in the meta-library associated with IRL infrastructure. In this paper, the IRL infrastructure is presented, and an experimentation evaluating it is discussed.

Summary form only given. COTS-based development (CBD) is gaining ground on traditional development given the benefits it provides. Several methods are proposed to support one or more CBD process steps. However, in practice many problems are faced. These problems are mainly related to the lack of CBD environments, and the difficulty of choosing the appropriate method in each step and then properly applying it. In this paper, we propose a meta-model for the CBD process. To generate it, we use the map process meta-model which allows to specify decision-oriented processes. The proposed CBD meta-model has as intentions the main CBD process steps and as strategies the different types of existing methods allowing to achieve a process step. It exhibits a strategic level capturing knowledge about existing methods. It provides therefore choice guidance of the appropriate method according to the current situation. Besides, it allows the developer to construct his/her customized process depending on the application to develop, his/her preferences and experience with the methods. The use of this meta-model is illustrated through a case study.

The product line engineering approaches (PLE) to software development are promising in matter of quality, productivity and time-to-market. Some results achieved in industry can prove that. But managers need quantitative models reassuring them concerning the important initial investment they are going to commit. This paper reports on the need for such economic models for reuse as well as the underlying supported tools. Thus, we introduce a new software cost estimation model for product line engineering that we denote as SoCoEMo-PLE. This model is based on two previous models: the integrated cost estimation model for reuse in general and Poulin's model for PLE. In fact, we present a new model, which takes into account PLE software development cycle approach and takes some features of the two previous cost estimation models. The tool supporting SoCoEMo-PLE is described and an UML modeling is presented. Results of a preliminary experiment in the use of the model and the tool are reported.

COTS-based development (CBD) process consists in five main steps including identifying COTS products candidates, selecting the most appropriate one and assembling it with the other components. In practice, this process is not yet obvious to follow. Many methods are proposed to support one or several steps of the process. But, which method to use and how to apply it still remains problematic. The MAP is a process meta-model proposed to support methods specification and their enactment. We have already used the MAP to express the CBD process, and the MAP was also used to express PORE, a COTS selection method. In this paper, we propose to generalize the use of the MAP to express both the CBD process and COTS related methods, especially selection ones. As a result, the developer is guided in the process of choosing the appropriate method and its application.

Commercial off-the-shelf (COTS) components are more and more used in the new applications development. They promise to reduce cost and risks, and to ensure software higher quality. However, in practice, many problems are faced during the evaluation, selection and integration. Major causes of these problems are due to the lack of knowledge about COTS products, the ignorance of the available methods of evaluation, selection and integration, and the lack of guidance for choosing between these methods. Therefore, a COTS-based development environment (CEDE) turns out to be essential. In this perspective, we propose a survey of COTS characterizations and propose an extended model. The use of these attributes in a CEDE is specified by a scenario denoted by a multimodel process known as map formalism. The same development process is then illustrated with a map scenario focusing on the different types of selection/integration existing methods.

Understanding software development process has always been a great challenge in the software engineering field. Actual engineering has many aspects and processes that need to be well understood and modeled. We focus on simulating the development process according to two complementary points of view: method and application engineering views. We use a formalism to represent the process model, which is the map. Maps are dynamic: they provide several non-deterministic strategies to achieve given intentions from given products. Navigation in a map is dynamic. We design and develop an agent-based simulator where its main components are environment and actors: the environment which is composed of the map structure being simulated and the product being developed; software engineers are modeled as autonomous agents able to select sections and achieve intentions. By agent cloning, we were able to develop exhaustive and concurrent multi-process and multiproduct building. Our simulation supports engineers in building their maps and validating process models by giving an exhaustive and simultaneous navigation through one map. Maps incoherencies have been detected and flexibility assessed.

Data warehouses have appeared in answer to the new requirements of database technologies. With them appeared some automated techniques like knowledge discovery in databases (KDD), data mining (DM) and online analytical processing (OLAP), which have registered a great demand in relational, transactional and finally in geographical databases. We give a survey of the state of the art of this research field. We mention the principles of data warehouses defining the context of geographical information, and present models used to build the data warehouse. Then, the tools permitting exploration of data warehouses and considered as tools for decision making are introduced. An evaluation of the technique of generalization is carried out using incendiary data. On the other hand, we expose a suggestion to manage incendiary data by cubic representation.

The recent development of communication networks and multimedia system provides users with the availability of a huge amount of information making worse the problem of information overload [9]. The evolution of system design is necessary becoming more user centred, and more personally involving. A review of survey studies on Internet users since 1993 confirms that a greater percentage of people are becoming online citizens, and professionals are integrating more online components into their work process. A review of the experimental literature on Internet user's reveals that there is intense interest in humanising the online environment by integrating affective and cognitive components [8].