This paper proposes a new hybrid deep learning framework that combines search query data, autoencoders (AE) and stacked long-short term memory (staked LSTM) to enhance the accuracy of tourism demand prediction. We use data from Google Trends as an additional variable with the monthly tourist arrivals to Marrakech, Morocco. The AE is applied as a feature extraction procedure to dimension reduction, to extract valuable information and to mine the nonlinear information incorporated in data. The extracted features are fed into stacked LSTM to predict tourist arrivals. Experiments carried out to analyze performance in forecast results of proposed method compared to individual models, and different principal component analysis (PCA) based and AE based hybrid models. The experimental results show that the proposed framework outperforms other models.

Abstract-Computer Supported Collaborative Learning (CSCL) is a new mode of teaching and one of the popular approaches for learning process. It allows virtual interactions between groups by providing tools such as: chat, internal email and discussion forums. One of the major problems caused by this learning process is the neglect and isolation of learners in groups, and usually is the cause of a heterogeneous group through social, cognitive or emotional ways. The method used is based on the exploitation of traces left on the online learning platform by learners and groups. The data collected from the environment can be observed and exploited in order to build social and cognitive indicators. Our approach is to design a model which assists the tutor to rebuild groups who are not homogeneous in order to prevent their isolation and abandonment. Our model offers the tutor the opportunity to rebuild the groups in an automatic way and based on the characteristics of quantitative indicators of all learners. Our work allowed us to test our algorithm from a functional and technical point of view and also identifies real variables from a collaborative online learning. It also allowed us to evaluate six different indicators proposed for this experiment, showing that they may assist the tutor to rebuild many groups again. The results show us that after the rebuilding groups, there has been a lot of participation in the forum and a considerable number of shares and documents deposited to the forum for each group. This high frequency of interaction between learners, lead them to a fruitful collaboration, and a good quality work at the end.

E-learning, or learning via a computer or mobile device, is growing. It can take many forms, such as an annotated PowerPoint presentation, a tutorial, or an interactive role-playing game .The possibilities are endless. Today, 80% of companies and communities have done a number of interesting and effective e-learning solutions, and 30% of all professional training are e-learning courses. The development of these platforms is based mainly on different technologies. This technological diversity can make comparing or managing E-learning platforms difficult, and the choice of a given platform will be also complex. Therefore, to address this problem, this paper proposes a solution to generate a PSM model based on n-tier architecture from a PIM model. The language used is the QVT (Query View Transformation) transformation language.

No abstract

The e-learning study reflects a trend in the integration of information and communication technologies in universities. This trend evokes a new form of teaching and learning and a new form of relationship between students and teachers. In fact, information and communication technologies, such as e-learning, call into question the ways of thinking and the ways of acting of individuals in the representation of learning. This paradigm shift requires introspection and the renewal of skills. In the face of these changes, higher education institutes must develop and make essential the courses that allow students to adapt to the new demands of the labor market. on the other hand, information and communication technologies and computer networks, These objects from daily life, are part of the immediate environment that is both professional, educational and personal of each one. With the massive arrival of personal and accessible digital tools (computers, nomadic equipment such as mobile phones and digital tablets, etc…), multiple online spaces are emerging on the Internet (discussion forums, e-learning platforms, blogs, messaging, chats, social networks like Facebook, online information sharing sites, etc…). E-learning offers features that differentiate it from others media objects such as books or television. e-learning offers quick, even instant, access to a multitude of information sources. They make it possible to store them and facilitate the possibilities of networking between individuals and groups of individuals whatever the time and place. Access to the Internet information network is "universal". You only need to connect to a computer on the network to access almost this entire network. Access is also "simultaneous" because each Internet user exists on the network in the form of information by "his digital presence", by the data that he moves or deposits and the interactions caused. We can also say that access is independent of time and distance since it is a space permanently open to human activity. Developing an e-learning application for each technology requires a lot of human resources and technical knowledge. To solve this problem we propose a development of an e-learning application according to a model-driven architecture approach. This paper is a development of our work in paper [Srai,2020].