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

Simulação das temperaturas diárias na cidade de Natal-rn

Information retrieval is of paramount importance in all areas of knowledge. Regarding the temperatures of Natal, they were simulated and analyzed. Thus, it was possible to recover, with some accuracy, the temperatures of days they were not collected. For this we constructed a software that displays the temperature value at each moment in the city. The program was developed in Delphi using interpolated polynomial function of third degree. The equations were obtained in Excel and data were collected at the Instituto Nacional de Pesquisas Espaciais (INPE). These functions were changed from a correction factor in order to provide values to temperatures between those who were not collected. Armed with this program you can build tables and charts to analyze the temperatures for certain periods of time. The same analysis was done by developing mathematical functions that describes the temperatures. With the data provided by this software is possible to say which are the hours of highest and lowest temperatures in the city, as the months have indexes with the highest and lowest temperatures.

A influência da criopreservação nas células mesenquimais indiferenciadas do ligamento periodontal de humanos análise comparativa in vitro

Cryopreservation is a process where cells or biological tissues are preserved by freezing at very low temperatures and aims to cease reversibly, in a controlled manner, all the biological functions of living tissues, i.e., maintain cell preservation so that it can recover with high degree of viability and functional integrity. This study aimed to evaluate the influence of cryopreservation on the mesenchymal stem cells originating from the periodontal ligament of human third molars by in vitro experiments. Six healthy teeth were removed and the periodontal cells grown in culture medium containing α-MEM supplemented with antibiotics and 15% FBS in a humidified atmosphere with 5% CO2 at 37° C. Cells isolated from each sample were divided into two groups: Group I - immediate cell culture (not fresh cryopreserved cells) and Group II - cell cryopreservation, during a period of 30 days. Analyses of rates of cell adhesion and proliferation in different groups were performed by counting the cells adhered to the wells, in intervals of 24, 48 and 72 hours after the start of cultivation. The number of cells in each well was obtained by counting viable cells with the use of hemocytometer and the method of exclusion of cells stained by trypan blue. The difference between groups for each of the times was analyzed by Wilcoxon test. Regarding the temporal evolution for each group, analysis was done by Friedman's test to verify the existence of differences between times and, when it existed, the Wilcoxon penalty was applied. The results showed no statistically significant difference between the two groups analyzed in this study. Therefore, we conclude that the cryopreservation process, after a period of 30 days, did not influence the cell type studied, and there was no difference in growth capacity in vitro between the groups