The most of collected data samples from E-learning systems consist of correlated information caused by overlapping input instances, which decrease the classifier credibility and reliability. This paper presents an improved classification model based on Deep Learning and Principal Component Analysis (PCA) method as its use in reducing the dimensionality of data. By this task, we introduce the best learning process to extract just the useful parameters that describe students’ per-formances in an E-learning system. One of the primary goals of this technique is to help earlier in detecting the dropouts and discovering of students who need special attention, so that the teachers could provide the appropriate counseling at the right time. This study presents the proposal approach and its algorithms. In addition, it shows how deep neural network was modeled in the training phase, and how PCA helps in the elimination of correlated information in our dataset to increase the classifier performance. Finally, we introduce an example of an appli-cation of the method in a data mining scenario, find out more references for fur-ther information.
In this letter it is presented a Left-Handed Metamaterial design route based upon stacked arrays of screens made of complementary split rings resonators under normal incidence in the microwave regime. Computation of the dispersion diagram highlights the possibility to obtain backward waves provided the longitudinal lattice is small enough. The experimental results are in good agreement with the computed ones. The physics underlying the Left-Handed behavior is found to rely on electroinductive waves, playing the mutual capacitive coupling the major role to explain the phenomenon. Our route to Left-Handed metamaterial introduced in this paper based on stacking CSRRs screens can be scaled to millimeter and terahertz for future applications.
The online sources of the web, since years, are an extraordinarily important base of information and knowledge. Indeed, the web is one of the best access point to any type of information. For the users who want to share their knowledge, the wiki system is a powerful tool.
Nevertheless, any system has its limits. The investigation on the contributions performance of individual contributors is yet unexplored because it is partly related to the design of wikis which is considered for collaborative work. Consequently, this has made the assessment and evaluation of individual contributions a hard task.
In this research, we will attempt to emphasize the significance of distinguishing the relevant articles based on the opinions of contributors and their contributions. In this way, we will focus on the utilization of data mining using clusters analysis and k-means algorithm techniques.
A learner profile is key to personalize learning content. Nowadays learners use different applications and tools to learn (Formal and informal types). Indeed, the diversity of profiles, their content, their structure, their operation, and the actors concerned, limits possible interoperability. Hence, the need for a rich and an interoperable learner profile that describes all previous learning achievements or experiences. In this work, after a brief analysis of available standards in this area, an approach is proposed to build an interoperable learner model based on xAPI statements that combine the formal and informal experiences to enhance learning analytic and personalization. Then, we present a tool to transform collected data into our XML model proposed based on the IMS-LIP standard, and in the end, we explore his utility.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.