The International Journal of Database Management Systems (IJDMS)

Journal URL https://airccse.org/journal/ijdms/index.html Volum URL https://airccse.org/journal/ijdms/current2021.html   TEXT ADVERTISEMENTS ANALYSIS USING CONVOLUTIONAL NEURAL NETWORKS Authors AbdulwahedAlmarimi and Asmaa Salem ABSTRACT  In this paper, we describe the developed model of the Convolutional Neural Networks CNN to a classification of advertisements. The developed method has been tested on both texts (Arabic and Slovak texts).The advertisements are chosen on a classified advertisements websites as short texts. We evolved a modified model of the CNN, we have implemented it and developed next modifications. We studied their influence on the performing activity of the proposed network. The result is a functional model of the network and its implementation in Java and Python. And analysis of model results using different parameters for the network and input data. The results on experiments data show that the developed model of CNN is useful in the domains of Arabic and...

  Paper Title Considering Structural and Vocabulary Heterogeneity in XML Query: FPTPQ and Holistic Evaluation Authors Brice Nguefack1, Maurice Tchoupé Tchendji1 and Thomas Djotio Ndie2, 1University of Dschang, Cameroon, 2University of Yaoundé I, Cameroun Abstract ---------- The integration of XML data sources which have different schemas/DTD can originate structural and vocabular heterogeneity. In this context, it is difficult to write satisfiable queries. As a solution, many Information Systems focus on building approximate evaluation techniques for exact queries. As a project, we build flexible and preference XML query languages and associated evaluation algorithms. In this paper, we propose the Flexible Preference Tree Pattern Query (FPTPQ), a new TPQ that allows multiple items/names (resp. paths) for the same node, in order to integrate (resp. to locate) all the different instances of the database nodes. The FPTPQ enable to have preference nodes and ordering operators among lab...