EducActiveCore: Computational Model to Educational Personalization Based on Multiagent and Context-Aware Computing

Abstract

Abstract. With the growth of online courses and, usage of mobile access allowing students execute educational activities in multiple locales, with variety of data and media content, new perspectives of educational support using different computing models can be observed. Some of most recent evolved computing models stand out in areas like Social Networks Analysis, Artificial Intelligence, Mobile Computing and Context-Aware Computing. Understanding the combination of these computing areas as complementary researches, this work investigates the applications of these computing technics to modeling an intelligent computational engine with educational personalization purposes. In this resume of a research in progress, a reduced implementation prepared as proof of concept simulating aspects of the target model, operates as centralized adaptive engine. The implemented engine, applied Artificial Neural Networks on classification tasks and routing recommendation. A group of 27 students participated in an experiment interacting with the adaptive engine using a mobile application provided. The mobile application allowed tracking of interface during usage flow by students, and provided to students the adaptive engine recommendation results. Around 59% of students confirmed the recommendation effectiveness of adaptive engine. In this experiment, at the end of each participation, students sent feedbacks about application features. The current results indicate the viability of computational model related to automation of classification tasks to environment identification and activity routing recommendation. In brief, the initial experiment presented encouraging results, indicating that the continuity of research could result in a useful tool to online educational platforms.

Intelligent Educational Assistant based on Multiagent System and Context-Aware Computing

“…In this experiment, we extended the mobile application implemented on prior experiments presented in Santos et al [3] to add a reduced set of Multiagent operations regarding to synchronize with Kernel, simulate the content search on context-aware environment, collect additional information about context and performs scheduling reservation on selected resources.…”

“…change of computation parameters or devices/resources coupled). Not detailed in this resume, the Neural Networks layer added to Kernel, its topology and data normalization method used on prediction process process of resources reservation, followed the basic method presented by Dos Santos et al 2017 [3].…”