Uma implementação paralela híbrida para o problema do caixeiro viajante usando algoritmos genéticos, GRASP e aprendizagem por reforço

The metaheuristics techiniques are known to solve optimization problems classified as NP-complete and are successful in obtaining good quality solutions. They use non-deterministic approaches to generate solutions that are close to the optimal, without the guarantee of finding the global optimum. Motivated by the difficulties in the resolution of these problems, this work proposes the development of parallel hybrid methods using the reinforcement learning, the metaheuristics GRASP and Genetic Algorithms. With the use of these techniques, we aim to contribute to improved efficiency in obtaining efficient solutions. In this case, instead of using the Q-learning algorithm by reinforcement learning, just as a technique for generating the initial solutions of metaheuristics, we use it in a cooperative and competitive approach with the Genetic Algorithm and GRASP, in an parallel implementation. In this context, was possible to verify that the implementations in this study showed satisfactory results, in both strategies, that is, in cooperation and competition between them and the cooperation and competition between groups. In some instances were found the global optimum, in others theses implementations reach close to it. In this sense was an analyze of the performance for this proposed approach was done and it shows a good performance on the requeriments that prove the efficiency and speedup (gain in speed with the parallel processing) of the implementations performed

Uma contribuição à solução do problema dos k-servos usando aprendizagem por reforço

Neste trabalho é proposto um novo algoritmo online para o resolver o Problema dos k-Servos (PKS). O desempenho desta solução é comparado com o de outros algoritmos existentes na literatura, a saber, os algoritmos Harmonic e Work Function, que mostraram ser competitivos, tornando-os parâmetros de comparação significativos. Um algoritmo que apresente desempenho eficiente em relação aos mesmos tende a ser competitivo também, devendo, obviamente, se provar o referido fato. Tal prova, entretanto, foge aos objetivos do presente trabalho. O algoritmo apresentado para a solução do PKS é baseado em técnicas de aprendizagem por reforço. Para tanto, o problema foi modelado como um processo de decisão em múltiplas etapas, ao qual é aplicado o algoritmo Q-Learning, um dos métodos de solução mais populares para o estabelecimento de políticas ótimas neste tipo de problema de decisão. Entretanto, deve-se observar que a dimensão da estrutura de armazenamento utilizada pela aprendizagem por reforço para se obter a política ótima cresce em função do número de estados e de ações, que por sua vez é proporcional ao número n de nós e k de servos. Ao se analisar esse crescimento (matematicamente, ) percebe-se que o mesmo ocorre de maneira exponencial, limitando a aplicação do método a problemas de menor porte, onde o número de nós e de servos é reduzido. Este problema, denominado maldição da dimensionalidade, foi introduzido por Belmann e implica na impossibilidade de execução de um algoritmo para certas instâncias de um problema pelo esgotamento de recursos computacionais para obtenção de sua saída. De modo a evitar que a solução proposta, baseada exclusivamente na aprendizagem por reforço, seja restrita a aplicações de menor porte, propõe-se uma solução alternativa para problemas mais realistas, que envolvam um número maior de nós e de servos. Esta solução alternativa é hierarquizada e utiliza dois métodos de solução do PKS: a aprendizagem por reforço, aplicada a um número reduzido de nós obtidos a partir de um processo de agregação, e um método guloso, aplicado aos subconjuntos de nós resultantes do processo de agregação, onde o critério de escolha do agendamento dos servos é baseado na menor distância ao local de demanda

Classificação de padrões através de um comitê de máquinas aprimorado por aprendizagem por reforço

Reinforcement learning is a machine learning technique that, although finding a large number of applications, maybe is yet to reach its full potential. One of the inadequately tested possibilities is the use of reinforcement learning in combination with other methods for the solution of pattern classification problems. It is well documented in the literature the problems that support vector machine ensembles face in terms of generalization capacity. Algorithms such as Adaboost do not deal appropriately with the imbalances that arise in those situations. Several alternatives have been proposed, with varying degrees of success. This dissertation presents a new approach to building committees of support vector machines. The presented algorithm combines Adaboost algorithm with a layer of reinforcement learning to adjust committee parameters in order to avoid that imbalances on the committee components affect the generalization performance of the final hypothesis. Comparisons were made with ensembles using and not using the reinforcement learning layer, testing benchmark data sets widely known in area of pattern classification

Roteamento em Redes de Sensores Sem Fios Com Base Em Aprendizagem Por Reforço

The use of wireless sensor and actuator networks in industry has been increasing past few years, bringing multiple benefits compared to wired systems, like network flexibility and manageability. Such networks consists of a possibly large number of small and autonomous sensor and actuator devices with wireless communication capabilities. The data collected by sensors are sent directly or through intermediary nodes along the network to a base station called sink node. The data routing in this environment is an essential matter since it is strictly bounded to the energy efficiency, thus the network lifetime. This work investigates the application of a routing technique based on Reinforcement Learning s Q-Learning algorithm to a wireless sensor network by using an NS-2 simulated environment. Several metrics like energy consumption, data packet delivery rates and delays are used to validate de proposal comparing it with another solutions existing in the literature

Fibras de licuri: um reforço vegetal alternativo de compósitos poliméricos

This research is based, at first, on the seeking of alternatives naturals reinforced in place of polymeric composites, also named reinforced plastics. Therein, this work starts with a whole licuri fiber micro structural characterization, as alternative proposal to polymeric composites. Licuri fiber is abundant on the Bahia state flora, native from a palm tree called Syagrus Coronata (Martius) Beccari. After, it was done only licuri fiber laminar composite developing studies, in order to know its behavior when impregnated with thermofix resin. The composite was developed in laminar structure shape (plate with a single layer of reinforcement) and produced industrially. The layer of reinforcement is a fabric-fiber unidirectional of licuri up in a manual loom. Their structure was made of polyester resin ortofitálica (unsaturated) only reinforced with licuri fibers. Fiber characterization studies were based on physical chemistry properties and their constitution. It was made by tension, scanning electron microscopy (SEM), x-ray diffraction (RDX) and thermal analyses (TG and DTA) tests, besides fiber chemistry analyses. Relating their mechanical properties of strength and hardness testing, they were determined through unit axial tension test and flexion in three points. A study in order to know fiber/matrix interface effects, in the final composites results, was required. To better understand the mechanical behavior of the composite, macroscopic and microscopic optical analysis of the fracture was performed

Utilização de RNA´s na construção do diagrama de vida constante de probabilidade de materiais compósitos

The static and cyclic assays are common to test materials in structures.. For cycling assays to assess the fatigue behavior of the material and thereby obtain the S-N curves and these are used to construct the diagrams of living constant. However, these diagrams, when constructed with small amounts of S-N curves underestimate or overestimate the actual behavior of the composite, there is increasing need for more testing to obtain more accurate results. Therewith, , a way of reducing costs is the statistical analysis of the fatigue behavior. The aim of this research was evaluate the probabilistic fatigue behavior of composite materials. The research was conducted in three parts. The first part consists of associating the equation of probability Weilbull equations commonly used in modeling of composite materials S-N curve, namely the exponential equation and power law and their generalizations. The second part was used the results obtained by the equation which best represents the S-N curves of probability and trained a network to the modular 5% failure. In the third part, we carried out a comparative study of the results obtained using the nonlinear model by parts (PNL) with the results of a modular network architecture (MN) in the analysis of fatigue behavior. For this we used a database of ten materials obtained from the literature to assess the ability of generalization of the modular network as well as its robustness. From the results it was found that the power law of probability generalized probabilistic behavior better represents the fatigue and composites that although the generalization ability of the MN that was not robust training with 5% failure rate, but for values mean the MN showed more accurate results than the PNL model

Estudo da fibra de coco como reforço em tijolo de solocimento

To take care of to the demand of the new constructions in the low income communities and to develop the production of a strengthened alternative brick with staple fibers of coconut, capable to contribute mainly with the recycling of the green and mature coconut in the urban and agricultural lexes, this research was developed, to confection bricks of soil-cement with coconut fiber. Ecologically correct material and of low cost, since the greenhouse use of or oven for burning will be manufactured without. The study it presents a set of tables and graphs that prove good indices found in the values of the density, water absorption, axial compressive strength and isolation term acoustics, with evidential results that make possible the production in industrial character with press mechanics or the place of the workmanship with manual form. The preparation of coconut staple fibers was made of natural form without use of chemical products not to deprive of characteristics the properties mechanical physicist-chemistries and of the same ones. The sixty bricks produced in simple and manual press had been carried through in four lots of fifteen units. The mixture of aggregates was made in four different traces composites for: ground erinaceous, cement, fiber of dry coconut and water; the bricks had been compact in the press and cured in natural way under an area covered during the minimum time of seven days

Desenvolvimento de têxteis técnicos para reforço de compósitos poliméricos

Materials denominated technical textiles can be defined as structures designed and developed with function to fulfill specific functional requirements of various industrial sectors as are the cases of the automotive and aerospace industries. In this aspect the technical textiles are distinguished from conventional textile materials, in which the aesthetic and of comfort needs are of primordial importance. Based on these considerations, the subject of this dissertation was established having as its main focus the study of development of textile structures from aramid and glass fibers and acting in order to develop the manufacture of composite materials that combine properties of two different structures, manufactured in an identical operation, where each structure contributes to improving the properties of the resulting composite material. Therefore were created in laboratory scale, textile structures with low weight and different composition: aramid (100%), glass (100%) and aramid /glass (65/35%), in order to use them as a reinforcing element in composite materials with polyester matrix. These composites were tested in tension and its fracture surface, evaluated by MEV. Based on the analysis of mechanical properties of the developed composites, the efficiency of the structures prepared as reinforcing element were testified by reason of that the resistance values of the composites are far superior to the polyester matrix. It was also observed that hybridization in tissue structure was efficient, since the best results obtained were for hybrid composites, where strength to the rupture was similar to the steel 1020, reaching values on the order of 340 MPa

Método simplificado para manutenção da concentração sangüínea de propofol em nível aproximadamente constante, associado ao óxido nitroso no paciente pediátrico

JUSTIFICATIVA E OBJETIVOS: A manutenção de concentração sangüínea alvo-controlada em níveis aproximadamente constantes do propofol é uma técnica que pode ser empregada de modo simplificado na sala de cirurgia. A finalidade desta pesquisa é comparar clínica e laboratorialmente a infusão de propofol em crianças usando os atributos farmacocinéticos de Short e de Marsh. MÉTODO: Foram estudados 41 pacientes com a idade de 4 a 12 anos, de ambos os sexos, estado físico ASA I ou II, distribuídos em dois grupos S (20 pacientes) e M (21 pacientes). No Grupo S utilizaram-se os atributos farmacocinéticos de Short, e no Grupo M, os atributos farmacocinéticos de Marsh. A indução anestésica foi feita com bolus de alfentanil 30 µg.kg-1, propofol 3 mg.kg-1 e pancurônio, 0,08 mg.kg-1 por via venosa. Procedeu-se a intubação traqueal e a manutenção com N2O/O2 (60%) em ventilação controlada mecânica. No grupo S a infusão de propofol foi de 254 (30 min) seguido de 216 µg.kg-1.min-1 por mais 30 min. No grupo M a infusão de propofol foi de 208 (30 min) seguido de 170 µg.kg-1.min-1 por mais 30 min. Através do atributo farmacocinético específico a cada grupo a meta foi a obtenção da concentração-alvo de 4 µg.kg-1 de propofol. Foram colhidas três amostras sangüíneas (aos 20, 40 e 60 minutos) para a dosagem do propofol pelo método da Cromatografia Líquida de Alta Performance. RESULTADOS: Os Grupos S e M foram considerados similares quanto à idade, altura, peso e sexo (p > 0,05). Não houve diferença estatística significativa entre os dois grupos estudados para os parâmetros: PAS, PAD, FC, FiN2O, SpO2 da hemoglobina e P ET CO2 no final da expiração. A comparação entre grupos no número de bolus repetidos de alfentanil não foi estatisticamente significativa. O índice bispectral (BIS) não apresentou diferença estatisticamente significativa entre M0 (vigília) e os demais momentos em ambos os grupos. Os valores Medianos da Performance do Erro (MPE) e os valores Medianos Absolutos da Performance do Erro (MAPE) mostraram diferenças estatísticas significativas entre os grupos no momento 60. Valores medianos da concentração sangüínea de propofol (µg.kg-1) mostraram diferenças estatísticas significativas entre M e S no momento 60 e entre os momentos 40 e 60 no grupo S. CONCLUSÕES: A anestesia com propofol usando os atributos farmacocinéticos de Marsh (Grupo M) apresentou menor erro no cálculo da concentração-alvo de propofol de 4 µg.kg-1. Além disso, utiliza menor quantidade de propofol para obter resultados clínicos semelhantes. Por todas essas qualidades deve ser a preferida para uso em crianças ASA I e com idades entre 4 e 12 anos.

Influencia da elevacao sustentada da pressao arterial sobre a dP/dt do ventriculo esquerdo mantendo-se constante a pressao diastolica do ventriculo esquerdo

Purpose - To evaluate the influence of sustained elevations of arterial pressure on dP/dt values, which the left ventricular end diastolic pressure was kept constant. Methods - Thirteen anesthetized dogs, mechanically ventilated and submitted to thoracotomy and pharmacological autonomic block (atropine - 0.5 mg/kg IV + oxprenolol - 3 mg/kg IV) were studied. The arterial pressure elevation was obtained by mechanical constriction of the descending thoracic aorta. Analyses were made in control (C) situation and after two successives increments of arterial pressure, sustained for 10min, called hypertension 1 (H1) and hypertension 2 (H2), respectively. The end diastolic left ventricular pressure was kept constant by utilization of a perfusion system connected to the left atria. Results - Heart rate did not change (C: 125 ± 13.9bpm; H1: 125 ± 13.5bpm; H2: 123 ± 14.1bpm; p > 0.05); the LVSP increased (C: 119 ± 8.1mmHg; H1: 142 ± 7.9mmHg; H2: 166 ± 7.7mmHg; p < 0.01); the AoDP increased (C: 89 ± 11.6mmHg; H1: 99 ± 9.5mmHg; H2: 120 ± 11.8mmHg; p < 0.01); the LVEDP (C: 6.2 ± 2.48mmHg; H1: 6.3 ± 2.43mmHg; H2: 6.1 ± 2.51mmHg; p > 0.05) and the dP/dt (C: 3068 ± 1057.1mmHg/s; 3112 ± 995.7mmHg/s; H2: 3086 ± 979.5mmHg/s; p > 0.05) did not change. Conclusion - dP/dt values are not influenced by a sustained elevation of arterial pressure, when the end diastolic left ventricular pressure is kept constant.

Respostas comportamentais de vacas holandesas, com acesso à sombra constante ou limitada

The experiment was carried out at Piracicaba, São Paulo, Brazil, from January to February 1993, with the objective of evaluating the behavior responses of Holstein cows, with constant or limited access to shade. The experimental design used was completely randomized. Twenty four dairy cows were used, at different lactation stages and production levels, kept in two free stall barns, with or without protection against solar radiation in south-east and north-west edge. The behavior parameters studied were: alimentation, rumination, rest time and frequency and water ingestion frequency. The protection of the free stall barn didn't affect the behavior responses. The alimentation, rumination and rest time, daily, were 3.4, 7.0 e 9.0 hours, respectively. The highest alimentation frequencies were before and after milking. The rumination was mainly during nocturnal period; the rest was more frequent during the period with higher solar radiation. The animals stayed more time in the shelter (13.4 vs 2.5 h/day). The highest daily water ingestion frequencies were in the hot time and next milking, mainly.

Efeito da cadência de pedalada sobre as respostas metabólica e cardiovascular durante o exercício incremental e de carga constante em indivíduos ativos

The main purpose of this study was to analyze the effect of the pedaling cadence (500 × 100 rpm) on the heart rate (HR) and the blood lactate response during incremental and constant workload exercises in active individuals. Nine active male individuals (20.9 ± 2.9 years old; 73.9 ± 6.5 kg; 1.79 ± 0.9 m) were submitted to two incremental tests, and to 6-8 constant workload tests to determine the intensity corresponding to the maximal steady state lactate (MLSSintens) in both cadences. The maximal power (Pmax) attained during the incremental test, and the MLSSintens were significantly lower at 100 rpm (240.9 ± 12.6 W; 148.1 ± 154.W) compared to 50 rpm (263.9 ± 18.6 W; 186.1 ± 21.2 W), respectively. The HRmax did not change between cadences (50 rpm = 191.1 ± 8.8 bpm; 100 rpm = 192.6 ± 9.9 bpm). Regardless the cadence, the HRmax percentage (70, 80, 90, and 100%) determined the same lactate concentrations during the incremental test. However, when the intensity was expressed in Pmax percentage or in absolute power, the lactate and the HR values were always higher at highest cadences. The HR corresponding to MLSSintens was similar between cadences (50 rpm = 162.5 ± 9.1 bpm; 100 rpm = 160.4 ± 9.2 bpm). Based on these results, it can be conclude that regardless the cadence employed (50 × 100 rpm), the use of the HR to individualize the exercise intensity indicates similar blood lactate responses, and this relationship is also kept in the exercise of constant intensity performed at MLSSintens. On the other hand, the use of the Pmax percentages depend on the cadence used, indicating different physiological responses to a same percentage.

Efecto de una inmigracion constante mantenida durante 50 anos en poblaciones estables y cuasi-estables modelos

Incluye Bibliografía

Retificador trifásico de 18 pulsos com estágio CC controlado por histerese constante

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)