Neural control of an autonomous robot

This article aims to apply the concepts associated with artificial neural networks (ANN) in the control of an autonomous robot system that is intended to be used in competitions of robots. The robot was tested in several arbitrary paths in order to verify its effectiveness. The results show that the robot performed the tasks with success. Moreover, in the case of arbitrary paths the ANN control outperforms other methodologies, such as fuzzy logic control (FLC).

Influence of environmental temperature and humidity on the acute ventilatory response to exercise in asthmatic adolescents

Asthma is a chronic inflammatory disorder of the respiratory airways affecting people of all ages, and constitutes a serious public health problem worldwide (6). Such a chronic inflammation is invariably associated with injury and repair of the bronchial epithelium known as remodelling (11). Inflammation, remodelling, and altered neural control of the airways are responsible for both recurrent exacerbations of asthma and increasingly permanent airflow obstruction (11, 29, 34). Excessive airway narrowing is caused by altered smooth muscle behaviour, in close interaction with swelling of the airway walls, parenchyma retractile forces, and enhanced intraluminal secretions (29, 38). All these functional and structural changes are associated with the characteristic symptoms of asthma – cough, chest tightness, and wheezing –and have a significant impact on patients’ daily lives, on their families and also on society (1, 24, 29). Recent epidemiological studies show an increase in the prevalence of asthma, mainly in industrial countries (12, 25, 37). The reasons for this increase may depend on host factors (e.g., genetic disposition) or on environmental factors like air pollution or contact with allergens (6, 22, 29). Physical exercise is probably the most common trigger for brief episodes of symptoms, and is assumed to induce airflow limitations in most asthmatic children and young adults (16, 24, 29, 33). Exercise-induced asthma (EIA) is defined as an intermittent narrowing of the airways, generally associated with respiratory symptoms (chest tightness, cough, wheezing and dyspnoea), occurring after 3 to 10 minutes of vigorous exercise with a maximal severity during 5 to 15 minutes after the end of the exercise (9, 14, 16, 24, 33). The definitive diagnosis of EIA is confirmed by the measurement of pre- and post-exercise expiratory flows documenting either a 15% fall in the forced expiratory volume in 1 second (FEV1), or a ≥15 to 20% fall in peak expiratory flow (PEF) (9, 24, 29). Some types of physical exercise have been associated with the occurrence of bronchial symptoms and asthma (5, 15, 17). For instance, demanding activities such as basketball or soccer could cause more severe attacks than less vigorous ones such as baseball or jogging (33). The mechanisms of exercise-induced airflow limitations seem to be related to changes in the respiratory mucosa induced by hyperventilation (9, 29). The heat loss from the airways during exercise, and possibly its post-exercise rewarming may contribute to the exercise-induced bronchoconstriction (EIB) (27). Additionally, the concomitant dehydration from the respiratory mucosa during exercise leads to an increased interstitial osmolarity, which may also contribute to bronchoconstriction (4, 36). So, the risk of EIB in asthmatically predisposed subjects seems to be higher with greater ventilation rates and the cooler and drier the inspired air is (23). The incidence of EIA in physically demanding coldweather sports like competitive figure skating and ice hockey has been found to occur in up to 30 to 35% of the participants (32). In contrast, swimming is often recommended to asthmatic individuals, because it improves the functionality of respiratory muscles and, moreover, it seems to have a concomitant beneficial effect on the prevalence of asthma exacerbations (14, 26), supporting the idea that the risk of EIB would be smaller in warm and humid environments. This topic, however, remains controversial since the chlorified water of swimming pools has been suspected as a potential trigger factor for some asthmatic patients (7, 8, 20, 21). In fact, the higher asthma incidence observed in industrialised countries has recently been linked to the exposition to chloride (7, 8, 30). Although clinical and epidemiological data suggest an influence of humidity and temperature of the inspired air on the bronchial response of asthmatic subjects during exercise, some of those studies did not accurately control the intensity of the exercise (2, 13), raising speculation of whether the experienced exercise overload was comparable for all subjects. Additionally, most of the studies did not include a control group (2, 10, 19, 39), which may lead to doubts about whether asthma per se has conditioned the observed results. Moreover, since the main targeted age group of these studies has been adults (10, 19, 39), any extrapolation to childhood/adolescence might be questionable regarding the different lung maturation. Considering the higher incidence of asthma in youngsters (30) and the fact that only the works of Amirav and coworkers (2, 3) have focused on this age group, a scarcity of scientific data can be identified. Additionally, since the main environmental trigger factors, i.e., temperature and humidity, were tested separately (10, 28, 39) it would be useful to analyse these two variables simultaneously because of their synergic effect on water and heat loss by the airways (31, 33). It also appears important to estimate the airway responsiveness to exercise within moderate environmental ranges of temperature and humidity, trying to avoid extreme temperatures and humidity conditions used by others (2, 3). So, the aim of this study was to analyse the influence of moderate changes in air temperature and humidity simultaneously on the acute ventilatory response to exercise in asthmatic children. To overcome the above referred to methodological limitations, we used a 15 minute progressive exercise trial on a cycle ergometer at 3 different workload intensities, and we collected data related to heart rate, respiratory quotient, minute ventilation and oxygen uptake in order to ensure that physiological exercise repercussions were the same in both environments. The tests were done in a “normal” climatic environment (in a gymnasium) and in a hot and humid environment (swimming pool); for the latter, direct chloride exposition was avoided.

Training control centers' operators in incident diagnosis and power restoration using intelligent tutoring systems

The activity of Control Center operators is important to guarantee the effective performance of Power Systems. Operators’ actions are crucial to deal with incidents, especially severe faults like blackouts. In this paper, we present an Intelligent Tutoring approach for training Portuguese Control Center operators in tasks like incident analysis and diagnosis, and service restoration of Power Systems. Intelligent Tutoring System (ITS) approach is used in the training of the operators, having into account context awareness and the unobtrusive integration in the working environment. Several Artificial Intelligence techniques were criteriously used and combined together to obtain an effective Intelligent Tutoring environment, namely Multiagent Systems, Neural Networks, Constraint-based Modeling, Intelligent Planning, Knowledge Representation, Expert Systems, User Modeling, and Intelligent User Interfaces.

A influência da hipertonia biomecânica VS neuronal na selecção das estratégias de intervenção em sujeitos com sequelas de acidente vascular encefálico no território da artéria cerebral média

Introdução: Após lesão do SNC o músculo pode perder a sua variabilidade e flexibilidade, tal como se verifica em indivíduos após AVE. A caracterização do tónus muscular tem sido um indicador a ter em atenção para o diagnóstico clínico. As alterações do tónus podem resultar de uma combinação de alterações neurais, como consequência dos processos inerentes à neuroplasticidade e alterações biomecânicas. Objectivo: Verificar quais as modificações no tónus muscular, segundo a escala de Tardieu, após a aplicação de um programa de reabilitação neuromotora baseado no conceito de Bobath em dois indivíduos com sequelas de AVE. Pretendeu-se também verificar as repercussões nas actividades funcionais. Participantes e métodos: Foram seleccionados dois indivíduos e aplicado um programa de reabilitação, durante onze semanas, e avaliados em dois momentos, antes da intervenção (PRE) e após a intervenção (APÓS). Aplicaram-se vários instrumentos de avaliação, nomeadamente a escala de Tardieu. O programa de reabilitação realizado baseou-se no conceito de Bobath. Resultados: Na escala de Tardieu, foi comum aos dois indivíduos melhorias a nível da qualidade de reacção muscular. Ambos os indivíduos apresentaram melhorias no controlo postural e equilíbrio, que se evidenciaram na CIF. Conclusão: Foi possível observar modificações no tónus muscular após aplicação de um programa de reabilitação e, consequentemente modificações na distribuição da carga na base de suporte, no alinhamento das estruturas articulares e musculares e na marcha. Ao longo da intervenção, observaram-se repercussões positivas em ambos os indivíduos, permitindo a estes realizar as AVDs com menor dificuldade

Agressividade e índice de Apgar

A agressividade é o comportamento que surge transversalmente como queixa isolada ou a par de outras queixas na maioria das crianças com e sem doença, que procuram apoio em saúde mental infantil. Nessas crianças, e a partir da recolha dos dados anamnesicos, tem-se verificado a constância de registo, no Livro do Bebé, de Índice de Apgar ≤ 9 ao primeiro minuto. Este estudo exploratório pretendeu analisar a hipótese teórica de que o Índice de Apgar abaixo de 10 ao primeiro minuto pode ser representativo de sofrimento fetal intraparto ou perinatal e assim fragilizar os circuitos neuronais das emoções tendo como consequência o surgimento, ao longo do desenvolvimento infantil e juvenil, de dificuldades na capacidade de gestão ou controlo das emoções, com comportamentos opositivos e/ou agressivos, como resposta defensiva de luta e fuga. Utilizou-se uma amostra de crianças inscritas no serviço de consulta externa de saúde mental infantil e juvenil, e verificou-se se as queixas de perturbação do comportamento com agressividade, formuladas no momento do acolhimento ao serviço, estão relacionadas com o Índice de Apgar ≤ 9 ao primeiro minuto e/ou com os registos de sofrimento fetal. Procurou-se, numa amostra aleatória de crianças sem queixa formulada no serviço de consulta externa de saúde mental infantil e juvenil, perceber as diferenças ou semelhanças dos registos de nascimento relativamente à amostra de crianças inscritas. Foi ainda auscultada a opinião dos profissionais dos serviços de obstetrícia e neonatologia – pediatria, mediante a aplicação de um questionário, no sentido de recolher as opiniões dos profissionais de saúde que lidam com o parto, que avaliam o Índice de Apgar dos recém – nascidos e que os seguem durante as primeiras horas ou dias de vida. Das conclusões a que chegamos, salienta-se que o sofrimento fetal intraparto pode ser predictor de dificuldades de controlo emocional traduzidas em alterações do comportamento com agressividade em situações de stress. Não se conclui que o Índice de Apgar ≤ 9 pode ser predictor de alterações do comportamento com agressividade em situações de stress, uma vez que os registos de ocorrências de sofrimento fetal intraparto e os registos do Índice de Apgar ao primeiro minuto são, na amostra de crianças com queixa, díspares, relacionando-se no entanto de modo estatisticamente significativo na amostra de crianças sem queixa. III No entanto, e apesar das dificuldades metodológicas, fica a certeza de haver mais percursos a percorrer nesta direcção para a compreensão dos distúrbios emocionais e a agressividade.

ANN-Based LMP forecasting in a distribution network with large penetration of DG

In recent years, power systems have experienced many changes in their paradigm. The introduction of new players in the management of distributed generation leads to the decentralization of control and decision-making, so that each player is able to play in the market environment. In the new context, it will be very relevant that aggregator players allow midsize, small and micro players to act in a competitive environment. In order to achieve their objectives, virtual power players and single players are required to optimize their energy resource management process. To achieve this, it is essential to have financial resources capable of providing access to appropriate decision support tools. As small players have difficulties in having access to such tools, it is necessary that these players can benefit from alternative methodologies to support their decisions. This paper presents a methodology, based on Artificial Neural Networks (ANN), and intended to support smaller players. In this case the present methodology uses a training set that is created using energy resource scheduling solutions obtained using a mixed-integer linear programming (MIP) approach as the reference optimization methodology. The trained network is used to obtain locational marginal prices in a distribution network. The main goal of the paper is to verify the accuracy of the ANN based approach. Moreover, the use of a single ANN is compared with the use of two or more ANN to forecast the locational marginal price.

Dynamic artificial neural network for electricity market prices forecast

This paper presents an artificial neural network applied to the forecasting of electricity market prices, with the special feature of being dynamic. The dynamism is verified at two different levels. The first level is characterized as a re-training of the network in every iteration, so that the artificial neural network can able to consider the most recent data at all times, and constantly adapt itself to the most recent happenings. The second level considers the adaptation of the neural network’s execution time depending on the circumstances of its use. The execution time adaptation is performed through the automatic adjustment of the amount of data considered for training the network. This is an advantageous and indispensable feature for this neural network’s integration in ALBidS (Adaptive Learning strategic Bidding System), a multi-agent system that has the purpose of providing decision support to the market negotiating players of MASCEM (Multi-Agent Simulator of Competitive Electricity Markets).

Decision support system with incomplete and domain incoherent information management

Many of the most common human functions such as temporal and non-monotonic reasoning have not yet been fully mapped in developed systems, even though some theoretical breakthroughs have already been accomplished. This is mainly due to the inherent computational complexity of the theoretical approaches. In the particular area of fault diagnosis in power systems however, some systems which tried to solve the problem, have been deployed using methodologies such as production rule based expert systems, neural networks, recognition of chronicles, fuzzy expert systems, etc. SPARSE (from the Portuguese acronym, which means expert system for incident analysis and restoration support) was one of the developed systems and, in the sequence of its development, came the need to cope with incomplete and/or incorrect information as well as the traditional problems for power systems fault diagnosis based on SCADA (supervisory control and data acquisition) information retrieval, namely real-time operation, huge amounts of information, etc. This paper presents an architecture for a decision support system, which can solve the presented problems, using a symbiosis of the event calculus and the default reasoning rule based system paradigms, insuring soft real-time operation with incomplete, incorrect or domain incoherent information handling ability. A prototype implementation of this system is already at work in the control centre of the Portuguese Transmission Network.

Intelligent supervisory control system for home devices using a cyber physical approach

Although we have many electric devices at home, there are just few systems to evaluate, monitor and control them. Sometimes users go out and leave their electric devices turned on what can cause energy wasting and dangerous situations. Therefore most of the users may want to know the using states of their electrical appliances through their mobile devices in a pervasive way. In this paper, we propose an Intelligent Supervisory Control System to evaluate, monitor and control the use of electric devices in home, from outside. Because of the transferring data to evaluate, monitor and control user's location and state of home (ex. nobody at home) may be opened to attacks leading to dangerous situations. In our model we include a location privacy module and encryption module to provide security to user location and data. Intelligent Supervising Control System gives to the user the ability to manage electricity loads by means of a multi-agent system involving evaluation, monitoring, control and energy resource agents.

Adaptable control for electrical generation at irregural wind speeds

The main aims of this work are the development and the validation of one generic algorithm to provide the optimal control of small power wind generators. That means up to 40 kW and blades with fixed pitch angle. This algorithm allows the development of controllers to fetch the wind generators at the desired operational point in variable operating conditions. The problems posed by the variable wind intensity are solved using the proposed algorithm. This is done with no explicit measure of the wind velocity, and so no special equipment or anemometer is required to compute or measure the wind velocity.

Genetic algorithm methodology applied to intelligent house control

In recent years the use of several new resources in power systems, such as distributed generation, demand response and more recently electric vehicles, has significantly increased. Power systems aim at lowering operational costs, requiring an adequate energy resources management. In this context, load consumption management plays an important role, being necessary to use optimization strategies to adjust the consumption to the supply profile. These optimization strategies can be integrated in demand response programs. The control of the energy consumption of an intelligent house has the objective of optimizing the load consumption. This paper presents a genetic algorithm approach to manage the consumption of a residential house making use of a SCADA system developed by the authors. Consumption management is done reducing or curtailing loads to keep the power consumption in, or below, a specified energy consumption limit. This limit is determined according to the consumer strategy and taking into account the renewable based micro generation, energy price, supplier solicitations, and consumers’ preferences. The proposed approach is compared with a mixed integer non-linear approach.

ANN based support for distributed energy resources scheduling in smart grids

The future scenarios for operation of smart grids are likely to include a large diversity of players, of different types and sizes. With control and decision making being decentralized over the network, intelligence should also be decentralized so that every player is able to play in the market environment. In the new context, aggregator players, enabling medium, small, and even micro size players to act in a competitive environment, will be very relevant. Virtual Power Players (VPP) and single players must optimize their energy resource management in order to accomplish their goals. This is relatively easy to larger players, with financial means to have access to adequate decision support tools, to support decision making concerning their optimal resource schedule. However, the smaller players have difficulties in accessing this kind of tools. So, it is required that these smaller players can be offered alternative methods to support their decisions. This paper presents a methodology, based on Artificial Neural Networks (ANN), intended to support smaller players’ resource scheduling. The used methodology uses a training set that is built using the energy resource scheduling solutions obtained with a reference optimization methodology, a mixed-integer non-linear programming (MINLP) in this case. The trained network is able to achieve good schedule results requiring modest computational means.