Application of computational intelligence to engineering

Computational Intelligence (CI) includes four main areas: Evolutionary Computation (genetic algorithms and genetic programming), Swarm Intelligence, Fuzzy Systems and Neural Networks. This article shows how CI techniques overpass the strict limits of Artificial Intelligence field and can help solving real problems from distinct engineering areas: Mechanical, Computer Science and Electrical Engineering.

Music and evolutionary computation

This paper presents a brief history of the western music: from its genesis to serialism and the Darmstadt school. Also some mathematical aspects of music are then presented and confronted with music as a form of art. The question is, are these two distinct aspects compatible? Can computers be of real help in automatic composition? The more appealing algorithmic approach is evolutionary computation as it offers creativity potential. Therefore, the Evolutionary Algorithms are then introduced and some results of GAs and GPs application to music generation are analysed.

Optimal offering strategies for wind power producers considering uncertainty and risk

This paper provides a two-stage stochastic programming approach for the development of optimal offering strategies for wind power producers. Uncertainty is related to electricity market prices and wind power production. A hybrid intelligent approach, combining wavelet transform, particle swarm optimization and adaptive-network-based fuzzy inference system, is used in this paper to generate plausible scenarios. Also, risk aversion is explicitly modeled using the conditional value-at-risk methodology. Results from a realistic case study, based on a wind farm in Portugal, are provided and analyzed. Finally, conclusions are duly drawn.

Short-term electricity prices forecasting in a competetive market by a hybrid Pso-Anfis approach

In this paper, a novel hybrid approach is proposed for electricity prices forecasting in a competitive market, considering a time horizon of 1 week. The proposed approach is based on the combination of particle swarm optimization and adaptive-network based fuzzy inference system. Results from a case study based on the electricity market of mainland Spain are presented. A thorough comparison is carried out, taking into account the results of previous publications, to demonstrate its effectiveness regarding forecasting accuracy and computation time. Finally, conclusions are duly drawn.

Day-ahead Resource Scheduling Including Demand Response for Electric Vehicles

The energy resource scheduling is becoming increasingly important, as the use of distributed resources is intensified and massive gridable vehicle (V2G) use is envisaged. This paper presents a methodology for day-ahead energy resource scheduling for smart grids considering the intensive use of distributed generation and V2G. The main focus is the comparison of different EV management approaches in the day-ahead energy resources management, namely uncontrolled charging, smart charging, V2G and Demand Response (DR) programs i n the V2G approach. Three different DR programs are designed and tested (trip reduce, shifting reduce and reduce+shifting). Othe r important contribution of the paper is the comparison between deterministic and computational intelligence techniques to reduce the execution time. The proposed scheduling is solved with a modified particle swarm optimization. Mixed integer non-linear programming is also used for comparison purposes. Full ac power flow calculation is included to allow taking into account the network constraints. A case study with a 33-bus distribution network and 2000 V2G resources is used to illustrate the performance of the proposed method.

Negotiation mechanism for self-organized scheduling system with collective intelligence

Current Manufacturing Systems challenges due to international economic crisis, market globalization and e-business trends, incites the development of intelligent systems to support decision making, which allows managers to concentrate on high-level tasks management while improving decision response and effectiveness towards manufacturing agility. This paper presents a novel negotiation mechanism for dynamic scheduling based on social and collective intelligence. Under the proposed negotiation mechanism, agents must interact and collaborate in order to improve the global schedule. Swarm Intelligence (SI) is considered a general aggregation term for several computational techniques, which use ideas and inspiration from the social behaviors of insects and other biological systems. This work is primarily concerned with negotiation, where multiple self-interested agents can reach agreement over the exchange of operations on competitive resources. Experimental analysis was performed in order to validate the influence of negotiation mechanism in the system performance and the SI technique. Empirical results and statistical evidence illustrate that the negotiation mechanism influence significantly the overall system performance and the effectiveness of Artificial Bee Colony for makespan minimization and on the machine occupation maximization.

Otimização de placas compósitas laminadas utilizando redes neuronais e enxames de partículas

Trabalho Final de mestrado para obtenção do grau de Mestre em engenharia Mecância

Simulated Annealing Approach Applied to the Energy Resource Management Considering Demand Response for Electric Vehicle

The aggregation and management of Distributed Energy Resources (DERs) by an Virtual Power Players (VPP) is an important task in a smart grid context. The Energy Resource Management (ERM) of theses DERs can become a hard and complex optimization problem. The large integration of several DERs, including Electric Vehicles (EVs), may lead to a scenario in which the VPP needs several hours to have a solution for the ERM problem. This is the reason why it is necessary to use metaheuristic methodologies to come up with a good solution with a reasonable amount of time. The presented paper proposes a Simulated Annealing (SA) approach to determine the ERM considering an intensive use of DERs, mainly EVs. In this paper, the possibility to apply Demand Response (DR) programs to the EVs is considered. Moreover, a trip reduce DR program is implemented. The SA methodology is tested on a 32-bus distribution network with 2000 EVs, and the SA results are compared with a deterministic technique and particle swarm optimization results.

Análise de desempenho de algoritmos de otimização para extração de parâmetros em modelos semicondutores de potência

Apresenta-se nesta tese uma revisão da literatura sobre a modelação de semicondutores de potência baseada na física e posterior análise de desempenho de dois métodos estocásticos, Particle Swarm Optimizaton (PSO) e Simulated Annealing (SA), quando utilizado para identificação eficiente de parâmetros de modelos de dispositivos semicondutores de potência, baseado na física. O conhecimento dos valores destes parâmetros, para cada dispositivo, é fundamental para uma simulação precisa do comportamento dinâmico do semicondutor. Os parâmetros são extraídos passo-a-passo durante simulação transiente e desempenham um papel relevante. Uma outra abordagem interessante nesta tese relaciona-se com o facto de que nos últimos anos, os métodos de modelação para dispositivos de potência têm emergido, com alta precisão e baixo tempo de execução baseado na Equação de Difusão Ambipolar (EDA) para díodos de potência e implementação no MATLAB numa estratégia de optimização formal. A equação da EDA é resolvida numericamente sob várias condições de injeções e o modelo é desenvolvido e implementado como um subcircuito no simulador IsSpice. Larguras de camada de depleção, área total do dispositivo, nível de dopagem, entre outras, são alguns dos parâmetros extraídos do modelo. Extração de parâmetros é uma parte importante de desenvolvimento de modelo. O objectivo de extração de parâmetros e otimização é determinar tais valores de parâmetros de modelo de dispositivo que minimiza as diferenças entre um conjunto de características medidas e resultados obtidos pela simulação de modelo de dispositivo. Este processo de minimização é frequentemente chamado de ajuste de características de modelos para dados de medição. O algoritmo implementado, PSO é uma técnica de heurística de otimização promissora, eficiente e recentemente proposta por Kennedy e Eberhart, baseado no comportamento social. As técnicas propostas são encontradas para serem robustas e capazes de alcançar uma solução que é caracterizada para ser precisa e global. Comparada com algoritmo SA já realizada, o desempenho da técnica proposta tem sido testado utilizando dados experimentais para extrair parâmetros de dispositivos reais das características I-V medidas. Para validar o modelo, comparação entre resultados de modelo desenvolvido com um outro modelo já desenvolvido são apresentados.

Estado da Arte da Computação Evolutiva Aplicada à Eletrónica

A Computação Evolutiva enquadra-se na área da Inteligência Artificial e é um ramo das ciências da computação que tem vindo a ser aplicado na resolução de problemas em diversas áreas da Engenharia. Este trabalho apresenta o estado da arte da Computação Evolutiva, assim como algumas das suas aplicações no ramo da eletrónica, denominada Eletrónica Evolutiva (ou Hardware Evolutivo), enfatizando a síntese de circuitos digitais combinatórios. Em primeiro lugar apresenta-se a Inteligência Artificial, passando à Computação Evolutiva, nas suas principais vertentes: os Algoritmos Evolutivos baseados no processo da evolução das espécies de Charles Darwin e a Inteligência dos Enxames baseada no comportamento coletivo de alguns animais. No que diz respeito aos Algoritmos Evolutivos, descrevem-se as estratégias evolutivas, a programação genética, a programação evolutiva e com maior ênfase, os Algoritmos Genéticos. Em relação à Inteligência dos Enxames, descreve-se a otimização por colônia de formigas e a otimização por enxame de partículas. Em simultâneo realizou-se também um estudo da Eletrónica Evolutiva, explicando sucintamente algumas das áreas de aplicação, entre elas: a robótica, as FPGA, o roteamento de placas de circuito impresso, a síntese de circuitos digitais e analógicos, as telecomunicações e os controladores. A título de concretizar o estudo efetuado, apresenta-se um caso de estudo da aplicação dos algoritmos genéticos na síntese de circuitos digitais combinatórios, com base na análise e comparação de três referências de autores distintos. Com este estudo foi possível comparar, não só os resultados obtidos por cada um dos autores, mas também a forma como os algoritmos genéticos foram implementados, nomeadamente no que diz respeito aos parâmetros, operadores genéticos utilizados, função de avaliação, implementação em hardware e tipo de codificação do circuito.

Africanized honeybee stings: how to treat them

INTRODUCTION: In 1956, Africanized honeybees (AHB) migrated from Brazil to other regions of the Western Hemisphere, including South, Central, and North America, except for Canada. Despite being productive, they are highly aggressive and cause fatal accidents. This study aimed to evaluate patients at the Clinical Hospital of Botucatu Medical School (HC-FMB) and to propose treatment guidelines. METHODS: From 2005 to 2006, the clinical and laboratorial aspects of 11 patients (7 male and 4 female) and the anatomopathological aspects of one patient who had died in 2003 were analyzed. RESULTS: The age of the surviving patients varied from 5 to 87 years, with a mean of 42.5 years. The majority of accidents occurred in the afternoon, and the number of stings ranged from 20 to 500. The principal signs and symptoms were pain and local inflammatory signs, nausea, tachycardia, and vomiting. Biochemical findings presented increased levels of creatine phosphokinase, lactate dehydrogenase, and aspartate/alanine aminotransferase. An 11-year-old male patient died upon entering the attic of a two-storey building where he was attacked by a swarm, receiving more than 1,000 stings. He was sent to HC-FMB where he was treated, but he died 24h later. Observed at the autopsy were erythematous-purpuric skin lesions besides necrosis at the sting locations, rhabdomyolysis, focal myocardial necrosis, tubular hydropic degeneration and focal tubular acute necrosis of the kidneys, myoglobinuria, and centrolobular necrosis in the liver. CONCLUSIONS: Accidents caused by multiple AHB stings always constitute a medical emergency. As there is no specific antivenom, we have developed guidelines, including first aid, drugs, and the proper removal of stingers.

Towards effective control of P2P traffic aggregates in network infrastructures

Nowadays, many P2P applications proliferate in the Internet. The attractiveness of many of these systems relies on the collaborative approach used to exchange large resources without the dependence and associated constraints of centralized approaches where a single server is responsible to handle all the requests from the clients. As consequence, some P2P systems are also interesting and cost-effective approaches to be adopted by content-providers and other Internet players. However, there are several coexistence problems between P2P applications and In- ternet Service Providers (ISPs) due to the unforeseeable behavior of P2P traffic aggregates in ISP infrastructures. In this context, this work proposes a collaborative P2P/ISP system able to underpin the development of novel Traffic Engi- neering (TE) mechanisms contributing for a better coexistence between P2P applications and ISPs. Using the devised system, two TE methods are described being able to estimate and control the impact of P2P traffic aggregates on the ISP network links. One of the TE methods allows that ISP administrators are able to foresee the expected impact that a given P2P swarm will have in the underlying network infrastructure. The other TE method enables the definition of ISP friendly P2P topologies, where specific network links are protected from P2P traffic. As result, the proposed system and associated mechanisms will contribute for improved ISP resource management tasks and to foster the deployment of innovative ISP-friendly systems.

Combining non-dominance, objective-order and spread metric to extend firefly algorithm to multi-objective optimization

In this paper, we propose an extension of the firefly algorithm (FA) to multi-objective optimization. FA is a swarm intelligence optimization algorithm inspired by the flashing behavior of fireflies at night that is capable of computing global solutions to continuous optimization problems. Our proposal relies on a fitness assignment scheme that gives lower fitness values to the positions of fireflies that correspond to non-dominated points with smaller aggregation of objective function distances to the minimum values. Furthermore, FA randomness is based on the spread metric to reduce the gaps between consecutive non-dominated solutions. The obtained results from the preliminary computational experiments show that our proposal gives a dense and well distributed approximated Pareto front with a large number of points.

A firefly dynamic penalty approach for solving engineering design problems

Firefly Algorithm is a recent swarm intelligence method, inspired by the social behavior of fireflies, based on their flashing and attraction characteristics [1, 2]. In this paper, we analyze the implementation of a dynamic penalty approach combined with the Firefly algorithm for solving constrained global optimization problems. In order to assess the applicability and performance of the proposed method, some benchmark problems from engineering design optimization are considered.

Bases para o estudo da genética de populações dos Hymenoptera em geral e dos Apinae sociais em particular

This paper deals with problems on population genetics in Hymenoptera and particularly in social Apidae. 1) The studies on populations of Hymenoptera were made according to the two basic types of reproduction: endogamy and panmixia. The populations of social Apinae have a mixed method of reproduction with higher percentage of panmixia and a lower of endogamy. This is shown by the following a) males can enter any hive in swarming time; b) males of Meliponini are expelled from hives which does not need them, and thus, are forced to look for some other place; c) Meliponini males were seen powdering themselves with pollen, thus becoming more acceptable in any other hive. The panmixia is not complete owing to the fact that the density of the breeding population as very low, even in the more frequent species as low as about 2 females and 160 males per reproductive area. We adopted as selection values (or survival indices) the expressions according to Brieger (1948,1950) which may be summarised as follows; a population: p2AA + ²pq Aa + q2aa became after selection: x p2AA + 2pq Aa + z q²aa. For alge-braics facilities Brieger divided the three selective values by y giving thus: x/y p2 AA + y/y 2 pq Aa + z/y q²aa. He called x/y of RA and z/y of Ra, that are survival or selective index, calculated in relation to the heterozygote. In our case all index were calculated in relation to the heterozygote, including the ones for haploid males; thus we have: RA surveval index of genotype AA Ra surveval index of genotype aa R'A surveval index of genotype A R'a surveval index of genotype a 1 surveval index of genotype Aa The index R'A ande R'a were equalized to RA and Ra, respectively, for facilities in the conclusions. 2) Panmitic populations of Hymenoptera, barring mutations, migrations and selection, should follow the Hardy-Weinberg law, thus all gens will be present in the population in the inicial frequency (see Graphifc 1). 3) Heterotic genes: If mutation for heterotic gene ( 1 > RA > Ra) occurs, an equilibrium will be reached in a population when: P = R A + Ra - 2R²a _____________ (9) 2(R A + Ra - R²A - R²a q = R A + Ra - 2R²A _____________ (10) 2(R A + Ra - R²A - R²a A heterotic gene in an hymenopteran population may be maintained without the aid of new mutation only if the survival index of the most viable mutant (RA) does not exced the limiting value given by the formula: R A = 1 + √1+Ra _________ 4 If RA has a value higher thah the one permitted by the formula, then only the more viable gene will remain present in the population (see Graphic 10). The only direct proof for heterotic genes in Hymenoptera was given by Mackensen and Roberts, who obtained offspring from Apis mellefera L. queens fertilized by their own sons. Such inbreeding resulted in a rapid loss of vigor the colony; inbred lines intercrossed gave a high hybrid vigor. Other fats correlated with the "heterosis" problem are; a) In a colony M. quadrifasciata Lep., which suffered severely from heat, the percentage of deths omong males was greater .than among females; b) Casteel and Phillips had shown that in their samples (Apis melifera L). the males had 7 times more abnormalities tian the workers (see Quadros IV to VIII); c) just after emerging the males have great variation, but the older ones show a variation equal to that of workers; d) The tongue lenght of males of Apis mellifera L., of Bombus rubicundus Smith (Quadro X), of Melipona marginata Lep. (Quadro XI), and of Melipona quadrifasciata Lep. Quadro IX, show greater variationthan that of workers of the respective species. If such variation were only caused by subviables genes a rapid increasse of homozigoty for the most viable alleles should be expected; then, these .wild populations, supposed to be in equilibrium, could .not show such variability among males. Thus we conclude that heterotic genes have a grat importance in these cases. 4) By means of mathematical models, we came to the conclusion tht isolating genes (Ra ^ Ra > 1), even in the case of mutations with more adaptability, have only the opor-tunity of survival when the population number is very low (thus the frequency of the gene in the breeding population will be large just after its appearence). A pair of such alleles can only remain present in a population when in border regions of two races or subspecies. For more details see Graphics 5 to 8. 5) Sex-limited genes affecting only females, are of great importance toHymenoptera, being subject to the same limits and formulas as diploid panmitic populations (see formulas 12 and 13). The following examples of these genes were given: a) caste-determining genes in the genus Melipona; b) genes permiting an easy response of females to differences in feeding in almost all social Hymenoptera; c) two genes, found in wild populations, one in Trigona (Plebéia) mosquito F. SMITH (quadro XII) and other in Melipona marginata marginata LEP. (Quadro XIII, colonies 76 and 56) showing sex-limited effects. Sex-limited genes affecting only males do not contribute to the plasticity or genie reserve in hymenopteran populations (see formula 14). 6) The factor time (life span) in Hymenoptera has a particular importance for heterotic genes. Supposing one year to be the time unit and a pair of heterotic genes with respective survival indice equal to RA = 0, 90 and Ra = 0,70 to be present; then if the life time of a population is either one or two years, only the more viable gene will remain present (see formula 11). If the species has a life time of three years, then both alleles will be maintained. Thus we conclude that in specis with long lif-time, the heterotic genes have more importance, and should be found more easily. 7) The colonies of social Hymenoptera behave as units in competition, thus in the studies of populations one must determine the survival index, of these units which may be subdivided in indice for egg-laying, for adaptive value of the queen, for working capacity of workers, etc. 8) A study of endogamic hymenopteran populations, reproduced by sister x brother mating (fig. 2), lead us to the following conclusions: a) without selection, a population, heterozygous for one pair of alleles, will consist after some generations (theoretically after an infinite number of generation) of females AA fecundated with males A and females aa fecundated with males a (see Quadro I). b) Even in endogamic population there is the theoretical possibility of the presence of heterotic genes, at equilibrium without the aid of new mutations (see Graphics 11 and 12), but the following! conditions must be satisfied: I - surveval index of both homozygotes (RA e Ra) should be below 0,75 (see Graphic 13); II - The most viable allele must riot exced the less viable one by more than is permited by the following formula (Pimentel Gomes 1950) (see Gra-fic 14) : 4 R5A + 8 Ra R4A - 4 Ra R³A (Ra - 1) R²A - - R²a (4 R²a + 4 Ra - 1) R A + 2 R³a < o Considering these two conditions, the existance of heterotic genes in endogamic populations of Hymenoptera \>ecames very improbable though not - impossible. 9) Genie mutation offects more hymenopteran than diploid populations. Thus we have for lethal genes in diploid populations: u = q2, and in Hymenoptera: u = s, being u the mutation ratio and s the frequency of the mutant in the male population. 10) Three factors, important to competition among species of Meliponini were analysed: flying capacity of workers, food gathering capacity of workers, egg-laying of the queen. In this connection we refer to the variability of the tongue lenght observed in colonies from several localites, to the method of transporting the pollen in the stomach, from some pots (Melliponi-ni storage alveolus) to others (e. g. in cases of pillage), and to the observation that the species with the most populous hives are almost always the most frequent ones also. 11) Several defensive ways used for Meliponini to avoid predation are cited, but special references are made upon the camouflage of both hive (fig. 5) and hive entrance (fig. 4) and on the mimetism (see list in page ). Also under the same heading we described the method of Lestrimelitta for pillage. 12) As mechanisms important for promoting genetic plasticity of hymenopteran species we cited: a) cytological variations and b) genie reserve. As to the former, duplications and numerical variations of chromosomes were studied. Diprion simile ATC was cited as example for polyploidy. Apis mellife-ra L. (n •= 16) also sugests polyploid origen since: a) The genus Melipona, which belongs to a" related tribe, presents in all species so far studied n = 9 chromosomes and b) there occurs formation of dyads in the firt spermatocyte division. It is su-gested that the origin of the sex-chromosome of Apis mellifera It. may be related to the possible origin of diplo-tetraploidy in this species. With regards to the genie reserve, several possible types of mutants were discussed. They were classified according to their survival indices; the heterotic and neutral mutants must be considered as more important for the genie reserve. 13) The mean radius from a mother to a daghter colony was estimated as 100 meters. Since the Meliponini hives swarm only once a year we may take 100 meters a year as the average dispersion of female Meliponini in ocordance to data obtained from Trigona (tetragonisca) jaty F. SMITH and Melipona marginata LEP., while other species may give different values. For males the flying distance was roughly estimated to be 10 times that for females. A review of the bibliography on Meliponini swarm was made (pg. 43 to 47) and new facts added. The population desity (breeding population) corresponds in may species of Meliponini to one male and one female per 10.000 square meters. Apparently the males are more frequent than the females, because there are sometimes many thousands, of males in a swarm; but for the genie frequency the individuals which have descendants are the ones computed. In the case of Apini and Meliponini, only one queen per hive and the males represented by. the spermatozoos in its spermateca are computed. In Meliponini only one male mate with the queen, while queens of Apis mellijera L. are fecundated by an average of about 1, 5 males. (Roberts, 1944). From the date cited, one clearly sees that, on the whole, populations of wild social bees (Meliponini) are so small that the Sewall Wright effect may become of great importance. In fact applying the Wright's formula: f = ( 1/aN♂ + 1/aN♀) (1 - 1/aN♂ + 1/aN♀) which measures the fixation and loss of genes per generation, we see that the fixation or loss of genes is of about 7% in the more frequent species, and rarer species about 11%. The variation in size, tergite color, background color, etc, of Melipona marginata Lep. is atributed to this genetic drift. A detail, important to the survival of Meliponini species, is the Constance of their breeding population. This Constance is due to the social organization, i. e., to the care given to the reproductive individuals (the queen with its sperm pack), to the way of swarming, to the food storage intended to control variations of feeding supply, etc. 14) Some species of the Meliponini are adapted to various ecological conditions and inhabit large geographical areas (e. g. T. (Tetragonisca jaty F. SMITH), and Trigona (Nanno-trigona testaceicornis LEP.) while others are limited to narrow regions with special ecological conditions (e. g. M. fuscata me-lanoventer SCHWARZ). Other species still, within the same geographical region, profit different ecological conditions, as do M. marginata LEP. and M. quadrifasciata LEP. The geographical distribution of Melipona quadrifasciata LEP. is different according to the subspecies: a) subsp anthidio-des LEP. (represented in Fig. 7 by black squares) inhabits a region fron the North of the S. Paulo State to Northeastern Brazil, ,b) subspecies quadrifasciata LEP., (marked in Fig. 7 with black triangles) accurs from the South of S. Paulo State to the middle of the State of Rio Grande do Sul (South Brazil). In the margined region between these two areas of distribution, hi-brid colonies were found (Fig. 7, white circles); they are shown with more details in fig. 8, while the zone of hybridization is roughly indicated in fig. 9 (gray zone). The subspecies quadrifasciata LEP., has 4 complete yellow bands on the abdominal tergites while anthidioides LEP. has interrupted ones. This character is determined by one or two genes and gives different adaptative properties to the subspecies. Figs. 10 shows certains meteorological isoclines which have aproximately the same configuration as the limits of the hybrid zone, suggesting different climatic adaptabilities for both genotypes. The exis-tance of a border zone between the areas of both subspecies, where were found a high frequency of hybrids, is explained as follows: being each subspecies adapted to a special climatic zone, we may suppose a poor adaptation of either one in the border region, which is also a region of intermediate climatic conditions. Thus, the hybrids, having a combination of the parent qualities, will be best adapted to the transition zone. Thus, the hybrids will become heterotic and an equilibrium will be reached with all genotypes present in the population in the border region.