Monitoramento por microcontrolador do cultivo de spirulina em fotobiorreator raceway

A oportunidade de produção de biomassa microalgal tem despertado interesse pelos diversos destinos que a mesma pode ter, seja na produção de bioenergia, como fonte de alimento ou servindo como produto da biofixação de dióxido de carbono. Em geral, a produção em larga escala de cianobactérias e microalgas é feita com acompanhamento através de análises físicoquímicas offline. Neste contexto, o objetivo deste trabalho foi monitorar a concentração celular em fotobiorreator raceway para produção de biomassa microalgal usando técnicas de aquisição digital de dados e controle de processos, pela aquisição de dados inline de iluminância, concentração de biomassa, temperatura e pH. Para tal fim foi necessário construir sensor baseado em software capaz de determinar a concentração de biomassa microalgal a partir de medidas ópticas de intensidade de radiação monocromática espalhada e desenvolver modelo matemático para a produção da biomassa microalgal no microcontrolador, utilizando algoritmo de computação natural no ajuste do modelo. Foi projetado, construído e testado durante cultivos de Spirulina sp. LEB 18, em escala piloto outdoor, um sistema autônomo de registro de informações advindas do cultivo. Foi testado um sensor de concentração de biomassa baseado na medição da radiação passante. Em uma segunda etapa foi concebido, construído e testado um sensor óptico de concentração de biomassa de Spirulina sp. LEB 18 baseado na medição da intensidade da radiação que sofre espalhamento pela suspensão da cianobactéria, em experimento no laboratório, sob condições controladas de luminosidade, temperatura e fluxo de suspensão de biomassa. A partir das medidas de espalhamento da radiação luminosa, foi construído um sistema de inferência neurofuzzy, que serve como um sensor por software da concentração de biomassa em cultivo. Por fim, a partir das concentrações de biomassa de cultivo, ao longo do tempo, foi prospectado o uso da plataforma Arduino na modelagem empírica da cinética de crescimento, usando a Equação de Verhulst. As medidas realizadas no sensor óptico baseado na medida da intensidade da radiação monocromática passante através da suspensão, usado em condições outdoor, apresentaram baixa correlação entre a concentração de biomassa e a radiação, mesmo para concentrações abaixo de 0,6 g/L. Quando da investigação do espalhamento óptico pela suspensão do cultivo, para os ângulos de 45º e 90º a radiação monocromática em 530 nm apresentou um comportamento linear crescente com a concentração, apresentando coeficiente de determinação, nos dois casos, 0,95. Foi possível construir um sensor de concentração de biomassa baseado em software, usando as informações combinadas de intensidade de radiação espalhada nos ângulos de 45º e 135º com coeficiente de determinação de 0,99. É factível realizar simultaneamente a determinação inline de variáveis do processo de cultivo de Spirulina e a modelagem cinética empírica do crescimento do micro-organismo através da equação de Verhulst, em microcontrolador Arduino.

A congestion control scheme based on fuzzy logic in wireless body area networks

One of the major challenges in healthcare wireless body area network (WBAN) applications is to control congestion. Unpredictable traffic load, many-to-one communication nature and limited bandwidth occupancy are among major reasons that can cause congestion in such applications. Congestion has negative impacts on the overall network performance such as packet losses, increasing end-to-end delay and wasting energy consumption due to a large number of retransmissions. In life-critical applications, any delay in transmitting vital signals may lead to death of a patient. Therefore, in order to enhance the network quality of service (QoS), developing a solution for congestion estimation and control is imperative. In this paper, we propose a new congestion detection and control protocol for remote monitoring of patients health status using WBANs. The proposed system is able to detect congestion by considering local information such as buffer capacity and node rate. In case of congestion, the proposed system differentiates between vital signals and assigns priorities to them based on their level of importance. As a result, the proposed approach provides a better quality of service for transmitting highly important vital signs.

Modified AHP for gene selection and cancer classification using type-2 fuzzy logic

This paper proposes a modification to the analytic hierarchy process (AHP) to select the most informative genes that serve as inputs to an interval type-2 fuzzy logic system (IT2FLS) for cancer classification. Unlike the conventional AHP, the modified AHP allows us to process quantitative factors that are ranking outcomes of individual gene selection methods including t-test, entropy, receiver operating characteristic curve, Wilcoxon test, and signal-to-noise ratio. The IT2FLS is introduced for the classification task due to its great ability for handling nonlinear, noisy, and outlier data, which are common problems in cancer microarray gene expression profiles. An unsupervised learning strategy using the fuzzy c-means clustering is employed to initialize parameters of the IT2FLS. Other classifiers such as multilayer perceptron network, support vector machine, and fuzzy ARTMAP are also implemented for comparisons. Experiments are carried out on three well-known microarray datasets: diffuse large B-cell lymphoma, leukemia cancer, and prostate. Rather than the traditional cross validation, leave-one-out cross-validation strategy is applied for the experiments. Results demonstrate the performance dominance of the IT2FLS against the competing classifiers. More noticeably, the modified AHP improves the classification performance not only of the IT2FLS but of all other classifiers as well. Accordingly, the proposed combination between the modified AHP and IT2FLS is a powerful tool for cancer classification and can be implemented as a real clinical decision support system that is useful for medical practitioners.

Enhancement of sensor data transmission by inference and efficient data processing

When wearable and personal health device and sensors capture data such as heart rate and body temperature for fitness tracking and health services, they simply transfer data without filtering or optimising. This can cause over-loading to the sensors as well as rapid battery consumption when they interact with Internet of Things (IoT) networks, which are expected to increase and de-mand more health data from device wearers. To solve the problem, this paper proposes to infer sensed data to reduce the data volume, which will affect the bandwidth and battery power reduction that are essential requirements to sensor devices. This is achieved by applying beacon data points after the inferencing of data processing utilising variance rates, which compare the sensed data with ad-jacent data before and after. This novel approach verifies by experiments that data volume can be saved by up to 99.5% with a 98.62% accuracy. Whilst most existing works focus on sensor network improvements such as routing, operation and reading data algorithms, we efficiently reduce data volume to reduce band-width and battery power consumption while maintaining accuracy by implement-ing intelligence and optimisation in sensor devices.

Automatic generation of assertions to detect potential security vulnerabilities in C programs that use union and pointer types

Type unions, pointer variables and function pointers are a long standing source of subtle security bugs in C program code. Their use can lead to hard-to-diagnose crashes or exploitable vulnerabilities that allow an attacker to attain privileged access over classified data. This paper describes an automatable framework for detecting such weaknesses in C programs statically, where possible, and for generating assertions that will detect them dynamically, in other cases. Exclusively based on analysis of the source code, it identifies required assertions using a type inference system supported by a custom made symbol table. In our preliminary findings, our type system was able to infer the correct type of unions in different scopes, without manual code annotations or rewriting. Whenever an evaluation is not possible or is difficult to resolve, appropriate runtime assertions are formed and inserted into the source code. The approach is demonstrated via a prototype C analysis tool.

A rule-based hybrid method for anomaly detection in online-social-network graphs

Detecting anomalies in the online social network is a significant task as it assists in revealing the useful and interesting information about the user behavior on the network. This paper proposes a rule-based hybrid method using graph theory, Fuzzy clustering and Fuzzy rules for modeling user relationships inherent in online-social-network and for identifying anomalies. Fuzzy C-Means clustering is used to cluster the data and Fuzzy inference engine is used to generate rules based on the cluster behavior. The proposed method is able to achieve improved accuracy for identifying anomalies in comparison to existing methods.

Damage assessment of composite plate structures with material and measurement uncertainty

Composite materials are very useful in structural engineering particularly in weight sensitive applications. Two different test models of the same structure made from composite materials can display very different dynamic behavior due to large uncertainties associated with composite material properties. Also, composite structures can suffer from pre-existing imperfections like delaminations, voids or cracks during fabrication. In this paper, we show that modeling and material uncertainties in composite structures can cause considerable problein in damage assessment. A recently developed C-0 shear deformable locking free refined composite plate element is employed in the numerical simulations to alleviate modeling uncertainty. A qualitative estimate of the impact of modeling uncertainty on the damage detection problem is made. A robust Fuzzy Logic System (FLS) with sliding window defuzzifier is used for delamination damage detection in composite plate type structures. The FLS is designed using variations in modal frequencies due to randomness in material properties. Probabilistic analysis is performed using Monte Carlo Simulation (MCS) on a composite plate finite element model. It is demonstrated that the FLS shows excellent robustness in delamination detection at very high levels of randomness in input data. (C) 2016 Elsevier Ltd. All rights reserved.

水泥回转窑热工控制模型研究及其仿真

水泥回转窑是建材工业发展的方向，我国是水泥生产大国，而国内回转窑与发达国家相差甚大，尤其在热工控制方面。由于水泥回转窑具有时变、分布参数和非线性特性，是一个典型的复杂过程，因而水泥回转窑控制系统是一个很有意义且困难的研究方向，本论文在借鉴国内外同类研究的基础上，提出了模糊专家系统控制模型，进行了深入地研究，并且对该模型进行了计算机仿真，希望通过这项研究，提高我国在水泥回转窑先进智能技术的控制水平。主要研究内容有：对水泥回转窑的热工过程进行了详细分析，对其不同控制方法进行全面的综述，对水泥回转窑实现控制的人工智能方法进行了全面的综述，并介绍了国内外的研究现状；研究了对水泥回转窑控制的模糊控制模型、专家系统设计方法，以及利用模糊控制与专家系统相结合的方法对水泥回转窑进行安全而有效控制的方法：研究了专家系统的实时性问题，提出了静态排列专家系统的推理时间模型、优化排列专家系统的时间估计模型与排列准则；利用计算机仿真方法，实现对水泥回转窑这种复杂而昂贵系统控制进行实验研究，以较低的代价实现对其分析。本论文的主研究成果如下：1. 详细研究了水泥回转窑的技术发展与结构演化过程，分析了水泥回转窑的热工过程以及影响水泥生产的各种因素，总结了影响水泥生产质量的主要因素与次要因素，确定了控制水泥回转窑的主要并且可测量的过程参数。2. 用推理全成方法研究模糊控制模型，实现从模糊的角度研究水泥回转窑的控制：从专家 系统角度研究水泥回转窑的控制问题，并提取了有关的专家系统控制规则；在模糊控制与专家系统的基础上，将水泥回转窑的模糊控制与专家系统相结合，利用层次化的控制器结构，底层为模糊控制器，顶层为专家系统，实现了水泥回转窑的安全与有效控制。3. 从定量的角度研究了专家系统的推理时间问题，给出了三种相应的时间估计模型，这不仅可以分析水泥回转窑系统中的专家系统的实时性，而且也可以分析一般专家系统的推理时间和问题。4. 本文提出的计算机仿真工具，为三组数据分别进行计算机仿真，以此研究水泥回转窑控制策略的性能以及对其动态过程进行分析，为水泥回转窑这样的复杂且昂贵的控制系统研究提供有效的手段。

Utilización de la lógica borrosa en la selección de personas e ideas para la participación en programas públicos de ayuda a la creación de empresas

[ES] Se propone en este trabajo un modelo de control borroso que ayude a filtrar y seleccionar las solicitudes de subvención que pueda recibir una institución pública en un programa de fomento para la creación y desarrollo de nuevas iniciativas empresariales. Creemos que la utilización de la lógica borrosa presenta ventajas sobre los procedimientos ordinarios ya que nos movemos en un escenario de actuación complejo y vago. El control borroso introduce el conocimiento de los expertos de un modo muy natural mediante variables lingüísticas y procesos de inferencia propios del lenguaje ordinario, lo que facilita la toma de decisiones en situaciones complejas. Nuestro modelo considera por un lado la idea empresarial y por otro la persona . Los indicadores y criterios que los expertos consideran relevantes para la evaluación de la subvención son modelados mediante variables lingüísticas y tratados como antecedentes y consecuentes de un motor de inferencia borroso, cuya salida nos proporciona la valoración final de la solicitud. Al final de nuestro trabajo resolvemos un caso práctico sencillo para aclarar el procedimiento.

Aplicação de Lógica Nebulosa para Previsão do Risco de Escorregamento de Taludes em Solo Residual.

A estabilidade de taludes naturais é um tema de grande interesse ao engenheiro geotécnico, face às significativas perdas econômicas, e até mesmo humanas, resultantes da ruptura de taludes. Estima-se que a deflagração de escorregamentos já provocou milhares de mortes, e dezenas de bilhões de dólares em prejuízos anuais em todo o mundo. Os fenômenos de instabilização de encostas são condicionados por muitos fatores, como o clima, a litologia e as estruturas das rochas, a morfologia, a ação antrópica e outros. A análise dos condicionantes geológicos e geotécnicos de escorregamentos proporciona a apreciação de cada um dos fatores envolvidos nos processos de instabilização de encostas, permitindo a obtenção de resultados de interesse, no que diz respeito ao modo de atuação destes fatores. O presente trabalho tem como objetivo a utilização da Lógica Nebulosa (Fuzzy) para criação de um Modelo que, de forma qualitativa, forneça uma previsão do risco de escorregamento de taludes em solos residuais. Para o cumprimento deste objetivo, foram estudados os fatores envolvidos nos processos de instabilização de encostas, e a forma como estes fatores se interrelacionam. Como experiência do especialista para a elaboração do modelo, foi analisado um extenso banco de dados de escorregamentos na cidade do Rio de Janeiro, disponibilizado pela Fundação Geo-Rio. Apresenta-se, neste trabalho, um caso histórico bem documentado para a validação do Modelo Fuzzy e análises paramétricas, realizadas com o objetivo verificar a coerência do modelo e a influência de cada um dos fatores adotados na previsão do risco de escorregamento. Dentre as principais conclusões, destaca-se a potencialidade da lógica nebulosa na previsão de risco de escorregamentos de taludes em solo residual, aparecendo como uma ferramenta capaz de auxiliar na detecção de áreas de risco.

Network Similarity Measures and Automatic Construction of Graph Models using Genetic Programming

A complex network is an abstract representation of an intricate system of interrelated elements where the patterns of connection hold significant meaning. One particular complex network is a social network whereby the vertices represent people and edges denote their daily interactions. Understanding social network dynamics can be vital to the mitigation of disease spread as these networks model the interactions, and thus avenues of spread, between individuals. To better understand complex networks, algorithms which generate graphs exhibiting observed properties of real-world networks, known as graph models, are often constructed. While various efforts to aid with the construction of graph models have been proposed using statistical and probabilistic methods, genetic programming (GP) has only recently been considered. However, determining that a graph model of a complex network accurately describes the target network(s) is not a trivial task as the graph models are often stochastic in nature and the notion of similarity is dependent upon the expected behavior of the network. This thesis examines a number of well-known network properties to determine which measures best allowed networks generated by different graph models, and thus the models themselves, to be distinguished. A proposed meta-analysis procedure was used to demonstrate how these network measures interact when used together as classifiers to determine network, and thus model, (dis)similarity. The analytical results form the basis of the fitness evaluation for a GP system used to automatically construct graph models for complex networks. The GP-based automatic inference system was used to reproduce existing, well-known graph models as well as a real-world network. Results indicated that the automatically inferred models exemplified functional similarity when compared to their respective target networks. This approach also showed promise when used to infer a model for a mammalian brain network.

Sistemas de gestión para el control de la cadena de abastecimiento que apropie características de los cubos OLAP como marco de aplicación en una empresa colombiana del sector de alimentos.

Se basa en un análisis teórico de los sistemas de información como lo es el almacenaje de datos, cubos OLAP e inteligencia de negocios. Seguidamente, se hace un análisis de los sectores económicos de Colombia con un especial interés sobre el sector de alimentos, de esta manera conceptualizar la empresa sobre la cual este trabajo se enfocara. Se encontrará un análisis del caso de éxito Summerwood Corporation, el cual brindará una justificación para la propuesta final presentada a la empresa Dipsa Food, Pyme dedicada a la producción de alimentos no perecederos ubicada en la ciudad de Bogotá D.C –Colombia, la cual tiene gran interés en cuanto al desarrollo de nuevas tecnologías que brinden información fidedigna para la toma de decisiones

Distributed intelligent management of active networks

This paper focuses on improving computer network management by the adoption of artificial intelligence techniques. A logical inference system has being devised to enable automated isolation, diagnosis, and even repair of network problems, thus enhancing the reliability, performance, and security of networks. We propose a distributed multi-agent architecture for network management, where a logical reasoner acts as an external managing entity capable of directing, coordinating, and stimulating actions in an active management architecture. The active networks technology represents the lower level layer which makes possible the deployment of code which implement teleo-reactive agents, distributed across the whole network. We adopt the Situation Calculus to define a network model and the Reactive Golog language to implement the logical reasoner. An active network management architecture is used by the reasoner to inject and execute operational tasks in the network. The integrated system collects the advantages coming from logical reasoning and network programmability, and provides a powerful system capable of performing high-level management tasks in order to deal with network fault.

Speed prediction for triggering vehicle activated signs

Accurate speed prediction is a crucial step in the development of a dynamic vehcile activated sign (VAS). A previous study showed that the optimal trigger speed of such signs will need to be pre-determined according to the nature of the site and to the traffic conditions. The objective of this paper is to find an accurate predictive model based on historical traffic speed data to derive the optimal trigger speed for such signs. Adaptive neuro fuzzy (ANFIS), classification and regression tree (CART) and random forest (RF) were developed to predict one step ahead speed during all times of the day. The developed models were evaluated and compared to the results obtained from artificial neural network (ANN), multiple linear regression (MLR) and naïve prediction using traffic speed data collected at four sites located in Sweden. The data were aggregated into two periods, a short term period (5-min) and a long term period (1-hour). The results of this study showed that using RF is a promising method for predicting mean speed in the two proposed periods.. It is concluded that in terms of performance and computational complexity, a simplistic input features to the predicitive model gave a marked increase in the response time of the model whilse still delivering a low prediction error.

Look-ahead intelligent energy management of a parallel hybrid electric vehicle

Improving fuel efficiency in vehicles can reduce the energy consumption concerns associated with operating the vehicles. This paper presents a model for a parallel hybrid electric vehicle. In the model, the flow of energy starts from wheels and spreads toward engine and electric motor. A fuzzy logic based control strategy is implemented for the vehicle. The controller manages the energy flow from the engine and the electric motor, controlling transmission ratio, adjusting speed, and sustaining battery's state of charge. The controller examines the vehicle speed, demand torque, slope difference, state of charge of battery, and engine and electric motor rotation speeds. It then determines the best values for continuous variable transmission ratio, speed, and torque. A slope window method is formed that takes into account the look-ahead slope information, and determines the best vehicle speed. The developed model and control strategy are simulated using real highway data relating to Nowra-Bateman Bay in Australia, and SAE Highway Fuel Economy Driving Schedule. The simulation results are presented and discussed. It is shown that the use of the proposed fuzzy controller reduces the fuel consumption of the vehicle.