Estudo avaliativo de um algoritmo genético auto-organizável e multiobjetivo utilizando aprendizado de máquina para aplicações de telecomunicações

This paper presents an evaluative study about the effects of using a machine learning technique on the main features of a self-organizing and multiobjective genetic algorithm (GA). A typical GA can be seen as a search technique which is usually applied in problems involving no polynomial complexity. Originally, these algorithms were designed to create methods that seek acceptable solutions to problems where the global optimum is inaccessible or difficult to obtain. At first, the GAs considered only one evaluation function and a single objective optimization. Today, however, implementations that consider several optimization objectives simultaneously (multiobjective algorithms) are common, besides allowing the change of many components of the algorithm dynamically (self-organizing algorithms). At the same time, they are also common combinations of GAs with machine learning techniques to improve some of its characteristics of performance and use. In this work, a GA with a machine learning technique was analyzed and applied in a antenna design. We used a variant of bicubic interpolation technique, called 2D Spline, as machine learning technique to estimate the behavior of a dynamic fitness function, based on the knowledge obtained from a set of laboratory experiments. This fitness function is also called evaluation function and, it is responsible for determining the fitness degree of a candidate solution (individual), in relation to others in the same population. The algorithm can be applied in many areas, including in the field of telecommunications, as projects of antennas and frequency selective surfaces. In this particular work, the presented algorithm was developed to optimize the design of a microstrip antenna, usually used in wireless communication systems for application in Ultra-Wideband (UWB). The algorithm allowed the optimization of two variables of geometry antenna - the length (Ls) and width (Ws) a slit in the ground plane with respect to three objectives: radiated signal bandwidth, return loss and central frequency deviation. These two dimensions (Ws and Ls) are used as variables in three different interpolation functions, one Spline for each optimization objective, to compose a multiobjective and aggregate fitness function. The final result proposed by the algorithm was compared with the simulation program result and the measured result of a physical prototype of the antenna built in the laboratory. In the present study, the algorithm was analyzed with respect to their success degree in relation to four important characteristics of a self-organizing multiobjective GA: performance, flexibility, scalability and accuracy. At the end of the study, it was observed a time increase in algorithm execution in comparison to a common GA, due to the time required for the machine learning process. On the plus side, we notice a sensitive gain with respect to flexibility and accuracy of results, and a prosperous path that indicates directions to the algorithm to allow the optimization problems with "η" variables

For the win (FTW)! Contribuições de um serious game para o ensino-aprendizagem de argumentação

This is a qualitative and reflexive research with focus on digital literacy. Among the digital media that could support the teaching of argumentation in the Science & Technology and Information Technology undergraduate courses of the Federal University of Rio Grande do Norte, we chose a serious game as object of research. Given the object of study in the discipline of reading and writing II – argumentation and genre from the order of argumentative writing -, common to the undergraduate courses mentioned, we invest on the development of a serious game, named ArgumentACTION, because we believe that it may, in fact, become a promising didactic instrument. Therefore we intend to understand whether and how this game can help students develop their reading and writing skills more independently, specifically towards an argumentative order genre: the opinion piece. With this research, we intend to contribute to the teaching of the Portuguese language on three bases: extending theoretical scope, in order to generate greater intelligibility on the teaching-learning process of argumenting; proposing a new methodological possibility, with the incorporation of a serious games to teaching; perfecting the game with which we are working, in order to build – and make available – a more refined digital tool to subsidize the teaching and learning of reading and writing of opinion pieces. To do so, we use the following as theoretical-methodological: Studies of Literacy (KLEIMAN, 2012b; TINOCO, 2008; OLIVEIRA, 2010; GEE, 2009; 2010; ROJO, 2012), The Applied Linguistics (KLEIMAN, 1998; BUSH-LEE, 2009), The Philosophy of Language (BAKHTIN, VOLOSHINOV, 2012) and Critical Pedagogy (DEWEY, 2010). A group of students from the upper mentioned undergraduate courses collaborated with this research by playing and analyzing the game. They were also interviewed about their experience in this matter. From the data generated, we established the categories of analysis: decollection, interest, multimodality/multisemiosis and interactivity, agent of literacy, learning principles. The conclusions we obtained show that the investment in applications, especially games, can bring real benefits to the teaching/learning of the Portuguese language; moreover they reveal that the work on argumenting has much to gain with the incorporation of serious games; however the possible advantages depend on a focused teaching practice and constant improvements and updates of this type of interactive tool, as well as the pedagogical practice from those who use and develop the games.