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

Length of stay in a neonatal intensive care unit and its association with low rates of exclusive breastfeeding in very low birth weight infants

OBJECTIVE: To identify the inpatient maternal and neonatal factors associated to the weaning of very low birth weight (VLBW) infants. METHODS: One hundred nineteen VLBW (<1500 g) infants were monitored from July 2005 through August 2006, from birth to the first ambulatory visit after maternity discharge. This maternity unit uses the Kangaroo Method and the Baby Friendly Hospital Initiative. Out of 119 VLBW infants monitored until discharge, 88 (75%) returned to the facility, 22 (25%) were on exclusive breastfeeding (EB), and 66 (75%) were weaned (partial breastfeeding or formula feeding). RESULTS: Univariate analysis found an association between weaning and lower birth weight, longer stays in the neonatal intensive care unit (NICU), and longer hospitalization times, in addition to more prolonged enteral feeding and birth weight recovery period. Logistic regression showed length of NICU stay as being the main determinant of weaning. CONCLUSION: The negative repercussion on EB of an extended stay in the NICU is a significant challenge for health professionals to provide more adequate nutrition to VLBW infants.

Length of stay in a neonatal intensive care unit and its association with low rates of exclusive breastfeeding in very low birth weight infants

OBJECTIVE: To identify the inpatient maternal and neonatal factors associated to the weaning of very low birth weight (VLBW) infants. METHODS: One hundred nineteen VLBW (<1500 g) infants were monitored from July 2005 through August 2006, from birth to the first ambulatory visit after maternity discharge. This maternity unit uses the Kangaroo Method and the Baby Friendly Hospital Initiative. Out of 119 VLBW infants monitored until discharge, 88 (75%) returned to the facility, 22 (25%) were on exclusive breastfeeding (EB), and 66 (75%) were weaned (partial breastfeeding or formula feeding). RESULTS: Univariate analysis found an association between weaning and lower birth weight, longer stays in the neonatal intensive care unit (NICU), and longer hospitalization times, in addition to more prolonged enteral feeding and birth weight recovery period. Logistic regression showed length of NICU stay as being the main determinant of weaning. CONCLUSION: The negative repercussion on EB of an extended stay in the NICU is a significant challenge for health professionals to provide more adequate nutrition to VLBW infants.

Desenvolvimento de monopolos quase-espirais para aplicações em sistemas UWB

This work is the analysis of a structure of the microstrip antenna designed for application in ultra wide band systems (Ultra Wideband - UWB). This is a prospective analytical study where they tested the changes in the geometry of the antenna, observing their suitability to the proposed objectives. It is known that the UWB antenna must operate in a range of at least 500 MHz, and answer a fractional bandwidth greater than or equal to 25%. It is also desirable that the antenna meets the specifications of track determined by FCC - Federal Communication Commission, which regulates the system in 2002 designating the UWB bandwidth of 7.5 GHz, a range that varies from 3.1 GHz to 10, 6 GHz. by setting the maximum power spectral density of operation in -41.3 dB / MHz, and defining the fractional bandwidth by 20%. The study starts of a structure of geometry in the form of stylized @, which evolves through changes in its form, in simulated commercial software CST MICROWAVE STUDIO, version 5.3.1, and then tested using the ANSOFT HFSS, version 9. These variations, based on observations of publications available from literature referring to the microstrip monopole planar antennas. As a result it is proposed an antenna, called Monopole Antenna Planar Spiral Almost Rectangular for applications in UWB systems - AMQEUWB, which presents simulated and measured results satisfactory, consistent with the objectives of the study. Some proposals for future work are mentioned