Search

Currently, one may find large repositories on the Internet that can be used as a source of resources for e-learning. In order to facilitate the use of these contents, they are organized as Learning Objects (LOs), which, in addition to the content itself, they hold several metadata to describe them. Due to the large volume of materials available, it becomes difficult to choose those LOs that best meet the needs of each individual. To suggest the most suitable LOs, we rely on Recommendation Systems, that are responsible to find and recommend the most useful items to students. In this context, the present work proposes a multiobjective optimization approach for the LOs recommendation problem. In this problem, there is a set of concepts to be taught, according to an Instructional Design, a repository of LOs, in which each LO addresses one or more concepts, and also pedagogical dependencies, that enforce certain concepts to be presented in advance to others. In this problem, we do not seek for solutions that necessarily cover all established concepts. In fact, we aim to obtain solutions that fulfill two distinct objectives, namely: i) lower cost, given by the sum of the cost of each LO present in the solution; ii) greater number of concepts covered, respecting the established pedagogical dependencies. To solve the problem, we used the NSGA-II, a multiobjective Genetic Algorithm implemented in the MOEA framework. The problem instances were artificially generated, simulating repositories of 1000 LOs, courses with 200 concepts, with up to 20 dependencies. The results obtained covered sets of different configurations of solutions, with different numbers of concepts covered and costs of the solutions, which brings greater possibilities to deliver content in accordance with the objectives, needs and reality of the students. [ABSTRACT FROM AUTHOR]

This work investigated the Artificial Intelligence planning for pedagogical actions sequencing, according to the student's profile. The actions represented the cognitive process given by Bloom's Taxonomy (BT) and the student profile was modeled by the Revised Approaches to Studying Inventory (RASI). To measure the suitability of a sequence to the student's profile, it was necessary to map these two theories, this mapping being one of the contributions of this study. Thus, the sequencing of actions was formulated as an optimization problem and developed through Genetic Algorithm. The proposition of the function to be optimized for this problem is also a contribution, since establishing criteria to evaluate pedagogical aspects has been a challenge for Informatics in Education. Experiments carried out had 41 participants who answered the RASI inventory and, after receiving and analyzing the sequences of actions generated by the planner proposed in this work, they also answered a satisfaction questionnaire about the sequence. The results obtained can be considered promising, demonstrating the feasibility of the research. [ABSTRACT FROM AUTHOR]

One field of the most fertile in the study of the strategies is the Theory of Games, which aims to capture the behavior of individuals in strategic situations. This paper aims to analyze the evolution of strategies of suppliers and borrowers credit by proposing two simultaneous and reflective games, making, for both, computational simulations. Two games were held simultaneously, where the results of an influence the pay-offs of each other. After 400 generations, it's believed that this is due to the complex interaction between the two groups of actors and is not seen as a setback by the authors of the study, whereas data on the evolution of strategies is fertile ground for valuable analysis on the interaction of actors in this study. The conclusions show the potential of techniques for analyzing and understanding the strategic behavior of SMCs in their relationship with suppliers of large companies. [ABSTRACT FROM AUTHOR]

Machine Learning (MA) has the concepts of development of computational techniques, construction of a system capable of acquiring automatic knowledge and decision making alone, have paradigms such as symbols, statistical, example and connectionist. Genetic Algorithm (GA) works with concepts on the field of evolutionary computation, are methods of optimization and seek inspiration in the mechanisms of evolution of species, with intuitive knowledge and deductive are key parts of the genetic algorithm. Without the pretension to present the historical chronology of the industry 4.0, AM and AG, the importance of concepts on the subject is verified, search through researches of scientific articles, didactic material and books, subjects for understanding of how one arrives in the industry 4.0. [ABSTRACT FROM AUTHOR]

The Chinese Postman Problem is an optimization problem that aims to cover all the arcs of a graph, minimizing the total distance traveled. Can be applied to non-directed graphs (two-way streets), directed (one-way streets) or mixed (some two-way streets and other one-way). These arch for the route is done by algorithms that generate approximate solutions. In this work we used a genetic algorithm for the construction of routes that approximate the optimal solution. The main objective is to minimize the cost of the course of collection and transportation solid waste in the city of Irati (PR), Brazil. The application of the algorithm was performed in a downtown area. Were used formapping, real data courtesy of City Hall officials. With the help of the online application Google Earth, we obtained the geographical coordinates of the vertices of the graph associated with the problem. The results generated by the genetic algorithm were compared with the optimal solution obtained by LINGO ® 12.0 software. These results were satisfactory for this mall instance of problems analyzed. [ABSTRACT FROM AUTHOR]