Use of ARIMA mathematical analysis to model the implementation of expert system courses by means of free software OpenSim and Sloodle platforms in virtual university campuses

• Published in: Expert systems with applications Vol. 40; no. 18; pp. 7381 - 7390
• Main Authors: González Crespo, Rubén, Escobar, Roberto Ferro, Joyanes Aguilar, Luis, Velazco, Sandra, Castillo Sanz, Andrés G.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Ltd 15-12-2013; Elsevier
• Subjects: Applied sciences; ARIMA; Artificial intelligence; Avatars; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Computer systems performance. Reliability; Distance education; Exact sciences and technology; Expert systems; General aspects; Islands; Mathematical analysis; Mathematical models; Occupational training. Personnel. Work management; OpenSim; Pattern recognition. Digital image processing. Computational geometry; Servers; Sloodle; Software; Time series; OpenSim; Sloodle; Expert systems; Artificial intelligence; ARIMA; Cloud computing; Statistical analysis; Expert system; Time series; Computer animation; Virtual community; Modeling; Open source software; Remote teaching; Teaching; Graphics; University; Graphical interface; Virtual reality; World wide web; Occupation time; Internet; Web site; Computer server
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2013.06.054

•This paper presents a basic methodology for implementing an expert systems course.•This paper uses Open Simulator and Sloodle in virtual learning environments.•This paper shows a mathematical analysis model to apply an expert system course.•The paper shows the results into the statistical model and its relation to reality.
This paper describes the implementation of a virtual World based in GNU OpenSimulator. This program offers a great variety of Web 3.0 ways of work, as it makes possible to visit web sites using avatars created for that purpose. The Universities should be familiar with the creation of new metaverses. That is the reason why a new basic methodology for the creation of a course on expert systems within a metaverse in a virtual campus for e-learning. Besides the creation of a repository or island, it is necessary to make measurements of the performance of the server dedicated to host the system when the number of users of the application grows. In order to forecast the behavior of such servers, ARIMA based time series are used. The auto-correlogrames obtained are analyzed to formulate a statistical model, as close to reality as possible.