Search

Mobile learning is considered a new phase of e-learning which gives the opportunity to learn more effectively and efficiently. In addition, the use of mobile devices for leaning is more sophisticated and more useful. The m-learning has become available anywhere and anytime for all students and professors. Moreover, the features of these mobile devices include ease of use in every place and time, very reasonable cost for students, and the ability to communicate through the internet or mobile networks, encouraging the development of many kinds of methods and systems. Now, a huge number of applications, in several domains, are oriented to this kind of mobile device. Researchers have been exploiting this technology to enhance the knowledge of learner (especially foreign languages learning). In this paper, the author proposed an educational system that provides the opportunity for students to learn English language outside the classroom and encourages them to get actively involved in their own learning processes.

Massive Open Online Courses (MOOCs) are increasingly used by learners to acquire knowledge and develop new skills. MOOCs provide a trove of data that can be leveraged to better assist learners, including behavioral data from built-in collaborative tools such as discussion boards and course wikis. Data tracing social interactions among learners are especially interesting as their analyses help improve MOOCs' effectiveness. We particularly perform sentiment analysis on such data to predict learners at risk of dropping out, measure the success of the MOOC, and personalize the MOOC according to a learner's behavior and detected emotions. In this paper, we propose a novel approach to sentiment analysis that combines the advantages of the deep learning architectures CNN and LSTM. To avoid highly uncertain predictions, we utilize a Bayesian neural network (BNN) model to quantify uncertainty within the sentiment analysis task. Our empirical results indicate that: 1) The Bayesian CNN-LSTM model provides interesting performance compared to other models (CNN-LSTM, CNN, LSTM) in terms of accuracy, precision, recall, and F1-Score; and 2) there is a high correlation between the sentiment in forum posts and the dropout rate in MOOCs. [ABSTRACT FROM AUTHOR]

The use of electronic environment in our life has become inevitable fact. In the educational field, the learners find many difficulties to attend a classical mode of learning (in class) that obliges them to be present according to daily schedule. Thus, the E-learning allows the process of learning anywhere and any when. However, the absence of the teacher, in the E-learning process, leads to the isolation of the learners. Generally, these learners have different backgrounds, preferences, needs, objectives, intellectual abilities and personal characteristics; and they do not understand and acquire the knowledge using the same courses and the same learning styles. Several aspects influence the effective learning process. Thus, different concepts, views and models of learning styles exist in literature. Many models and classifications of learning styles were proposed according to several angles of view. For this aim, we propose an educational system that provides the accurate learning content and use the most appropriate learning style that meets the needs and preference of each learner (personalized learning). Our system provides several learning styles for the learners; however, the essential task is to find the best course and learner style for each learner according to his characteristics. The adaptation of the content and styles allows the dynamicity in the learning process and gives a new chance for many kinds of learners to enhance their knowledge in personal manner. Moreover, the modeling of our system using multi-agents system increases its interaction and flexibility. [ABSTRACT FROM AUTHOR]

In reconfigurable manufacturing systems (RMSs), the structure of the system can be changed during its execution. This reconfiguration can be triggered by several motivations: a new requirement in the production process, avoiding some problems caused by machines breakdowns, etc. RMSs are characterised by their flexibility which guarantees productivity and efficiency. However, their design is more complicated and needs new techniques and paradigms. The use of high level Petri nets (PNs) offers the ability to design these systems and to analyse their properties. In this article, the authors apply reconfigurable object nets (RONs) for the modelling, simulation and analysis of RMSs. Indeed, a formal method is proposed, where the reconfiguration process is specified explicitly as a graph transformation, the simulation is realised using the RON-tool, and the analysis exploits the TINA-tool (timed nets analyser tool). [ABSTRACT FROM AUTHOR]

Nowadays, development of application that supports cooperative works has attracted recent attention. Thus, several approaches and methods were proposed to reach this aim. In this context, we propose a new solution to the problem of collective work that presents a result of hybridization of several cooperative approaches, as follows: the non-communicative approach to minimizing the required time to perform a cooperative activity and conflict resolution approach based competency for improving the quality of cooperative works. Therefore, we propose a cooperation framework fault tolerant called CoMAS (Cooperative Multi-Agent System) brings preemption resources to cooperating agents (CA) in case of failure to prevent the blocking and ensure the survival of the system. Moreover, we study the case of cooperative authoring systems for e-learning to examine the behavior of our framework with a cooperative activity. Finally, our cooperation approach provides a generic and extensible solution that covers the whole cycle of a cooperation process. [ABSTRACT FROM AUTHOR]

In Reconfigurable Manufacturing Systems (RMSs), the structure of the system can be changed during execution of the system. This reconfiguration can be motivated by a new requirement in the production process, or to avoid some problems caused by machines breakdowns. These systems offer a high flexibility leading to more productivity and efficiency. However, their design is more complicated implying new techniques and paradigms. The use of formal high level Petri Nets offers the ability to design these systems and to analyse or prove their properties. In this paper, we apply Reconfigurable Object Nets (RONs) for the modelling, simulation and analysis of reconfigurable manufacturing systems. We propose a formal approach, where the reconfiguration is specified as graph transformations, the simulation is realized using the RON-tool, and the analysis exploits some software tools such as TINA-tool and PIPE-tool. [ABSTRACT FROM AUTHOR]

The objective of this paper is to present an experience of virtual class on Facebook. Authors have started this project months ago. This virtual group is named: "programming with java" (in French: "Programmer avec Java", accessible at the address: https://www.facebook.com/groups/232171016900671/). The group was principally dedicated to 2nd year computer science's students at Biskra University (2011-2012 scholar years) (www.univ-biskra.dz). The growth of the group attracted more students in other levels, and many teachers get involved in the animation of the virtual class. In the following sections, authors will discuss the chronological events: creation and first results, recent results and evolutions, and encountered limits of virtual class as Facebook groups. [ABSTRACT FROM AUTHOR]

There have been significant developments in the development of computing and communication technology. Classical teaching methods are very slow and students are obliged to be present at specific times, which may be inconvenient for the majority of learners. Thus, so-called Elearning emerged via the Internet, whose aims are to reduce the time required to learn, as well as mitigate some drawbacks of traditional education. In E-learning, learners are free to choose when they wish to learn and determine their own personal schedules. Another important is how to adapt course content to the intellectual and social characteristics of learners and their individual backgrounds, which is one of the main tasks of online educational systems. The technology of our multiagent system is relevant in this area. [ABSTRACT FROM AUTHOR]

Mobile learning is considered a new phase of e-learning which gives the opportunity to learn more effectively and efficiently. In addition, the use of mobile devices for leaning is more sophisticated and more useful. The m-learning has become available anywhere and anytime for all students and professors. Moreover, the features of these mobile devices include ease of use in every place and time, very reasonable cost for students, and the ability to communicate through the internet or mobile networks, encouraging the development of many kinds of methods and systems. Now, a huge number of applications, in several domains, are oriented to this kind of mobile device. Researchers have been exploiting this technology to enhance the knowledge of learner (especially foreign languages learning). In this paper, the author proposed an educational system that provides the opportunity for students to learn English language outside the classroom and encourages them to get actively involved in their own learning processes. [ABSTRACT FROM AUTHOR]

Nowadays, a wide range of systems are becoming structurally dynamic, variably interconnected, and highly complex. The use of classical formal approaches, such as Petri nets, in the design of such systems becomes neither convenient nor sufficient. Indeed, they cannot handle, in a natural way, the dynamic structure and the growing complexity of modern systems. Introducing reconfigurability in Petri nets, as well as generalized stochastic Petri nets increases the modeling power, but decreases the applicability of analysis techniques. In fact, several properties become undecidable In this paper, we extend generalized stochastic Petri nets to a reconfigurable formalism, while maintaining verifiability with reduced complexity. The proposed approach identifies a set of properties that are preserved after reconfiguration. These properties are decidable with reduced time and space complexity. The use of the proposed formalism is illustrated through a running example. • A new Petri nets based formalism is proposed for reconfigurable systems. • The new formalism handles two aspects: stochastic time and reconfigurability. • Improved Net Rewriting Systems and Generalized Stochastic Petri Nets are combined. • A new approach for the performance evaluation is proposed and exploited. • The formalism is exploited in an Reconfigurable Manufacturing Systems case study. [ABSTRACT FROM AUTHOR]