Controlo de um robô autónomo através de redes neuronais

Neste trabalho pretende-se introduzir os conceitos associados às redes neuronais e a sua aplicação no controlo de sistemas, neste caso na área da robótica autónoma. Foi utilizado um AGV de modo a testar experimentalmente um controlo através de uma rede neuronal artificial. A grande vantagem das redes neuronais artificiais é estas poderem ser ensinadas a funcionarem como se pretende. A partir desta caraterística foram efetuadas duas abordagens na implementação do AGV disponibilizado. A primeira abordagem ensinava a rede neuronal a funcionar como o controlo por lógica difusa que foi implementado no AGV aquando do seu desenvolvimento. A segunda abordagem foi ensinar a rede neuronal artificial a funcionar a partir de dados retirados de um controlo remoto simples implementado no AGV. Ambas as abordagens foram inicialmente implementadas e simuladas no MATLAB, antes de se efetuar a sua implementação no AGV. O MATLAB é utilizado para efetuar o treino das redes neuronais multicamada proactivas através do algoritmo de treino por retropropagação de Levenberg-Marquardt. A implementação de uma rede neuronal artificial na primeira abordagem foi implementada em três fases, MATLAB, posteriormente linguagem de programação C no computador e por fim, microcontrolador PIC no AGV, permitindo assim diferenciar o desenvolvimento destas técnicas em várias plataformas. Durante o desenvolvimento da segunda abordagem foi desenvolvido uma aplicação Android que permite monitorizar e controlar o AGV remotamente. Os resultados obtidos pela implementação da rede neuronal a partir do controlo difuso e do controlo remoto foram satisfatórios, pois o AGV percorria os percursos testados corretamente, em ambos os casos. Por fim concluiu-se que é viável a aplicação das redes neuronais no controlo de um AGV. Mais ainda, é possível utilizar o sistema desenvolvido para implementar e testar novas RNA.

Efficient digital self-calibration of video-rate pipeline ADCs using white gaussian noise

Proceedings of IEEE, ISCAS 2003, Vol.I, pp. 877-880

Multiobjective optimization for node adaptation in the analysis of composite plates using a meshless collocation method

The bending of simply supported composite plates is analyzed using a direct collocation meshless numerical method. In order to optimize node distribution the Direct MultiSearch (DMS) for multi-objective optimization method is applied. In addition, the method optimizes the shape parameter in radial basis functions. The optimization algorithm was able to find good solutions for a large variety of nodes distribution.

GPU implementation of a hyperspectral coded aperture algorithm for compressive sensing

This paper presents a new parallel implementation of a previously hyperspectral coded aperture (HYCA) algorithm for compressive sensing on graphics processing units (GPUs). HYCA method combines the ideas of spectral unmixing and compressive sensing exploiting the high spatial correlation that can be observed in the data and the generally low number of endmembers needed in order to explain the data. The proposed implementation exploits the GPU architecture at low level, thus taking full advantage of the computational power of GPUs using shared memory and coalesced accesses to memory. The proposed algorithm is evaluated not only in terms of reconstruction error but also in terms of computational performance using two different GPU architectures by NVIDIA: GeForce GTX 590 and GeForce GTX TITAN. Experimental results using real data reveals signficant speedups up with regards to serial implementation.

Domestic Consumption Simulation and Management Using a Continuous Consumption Management and Optimization Algorithm

The recent changes concerning the consumers’ active participation in the efficient management of load devices for one’s own interest and for the interest of the network operator, namely in the context of demand response, leads to the need for improved algorithms and tools. A continuous consumption optimization algorithm has been improved in order to better manage the shifted demand. It has been done in a simulation and user-interaction tool capable of being integrated in a multi-agent smart grid simulator already developed, and also capable of integrating several optimization algorithms to manage real and simulated loads. The case study of this paper enhances the advantages of the proposed algorithm and the benefits of using the developed simulation and user interaction tool.

Geodupa - a geography-driven partial membership algorithm

Trabalho apresentado no âmbito do Mestrado em Engenharia Informática, como requisito parcial para obtenção do grau de Mestre em Engenharia Informática

Efficient Legendre spectral tau algorithm for solving two-sided space-time Caputo fractional advection-dispersion equation

In this paper we present the operational matrices of the left Caputo fractional derivative, right Caputo fractional derivative and Riemann–Liouville fractional integral for shifted Legendre polynomials. We develop an accurate numerical algorithm to solve the two-sided space–time fractional advection–dispersion equation (FADE) based on a spectral shifted Legendre tau (SLT) method in combination with the derived shifted Legendre operational matrices. The fractional derivatives are described in the Caputo sense. We propose a spectral SLT method, both in temporal and spatial discretizations for the two-sided space–time FADE. This technique reduces the two-sided space–time FADE to a system of algebraic equations that simplifies the problem. Numerical results carried out to confirm the spectral accuracy and efficiency of the proposed algorithm. By selecting relatively few Legendre polynomial degrees, we are able to get very accurate approximations, demonstrating the utility of the new approach over other numerical methods.

A module for the FTT-SE protocol in ns-3

Demo in Workshop on ns-3 (WNS3 2015). 13 to 14, May, 2015. Castelldefels, Spain.

Chaotic Phenomena and Performance Optimization in the Trajectory Control of Redundant Manipulators

Redundant manipulators have some advantages when compared with classical arms because they allow the trajectory optimization, both on the free space and on the presence of abstacles, and the resolution of singularities. For this type of manipulators, several kinetic algorithms adopt generalized inverse matrices. In this line of thought, the generalized inverse control scheme is tested through several experiments that reveal the difficulties that often arise. Motivated by theseproblems this paper presents a new method that ptimizes the manipulability through a least squre polynomialapproximation to determine the joints positions. Moreover, the article studies influence on the dynamics, when controlling redundant and hyper-redundant manipulators. The experiment confirm the superior performance of the proposed algorithm for redundant and hyper-redundant manipulators, revealing several fundamental properties of the chaotic phenomena, and gives a deeper insight towards the future development of superior trajectory control algorithms.

Algorithmic skeleton framework for the orchestration of GPU computations

Dissertação para obtenção do Grau de Mestre em Engenharia Informática

Analysis of the Dynamics and Origin of Epileptic Activity in Patients with Tuberous Sclerosis Evaluated for Surgery of Epilepsy

Objective: The epilepsies associated with the tuberous sclerosis complex (TSC) are very often refractory to medical therapy. Surgery for epilepsy is an effective alternative when the critical link between the localization of seizure onset in the scalp and a particular cortical tuber can be established. In this study we perform analysis of ictal and interictal EEG to improve such link. Methods: The ictal and interictal recordings of four patients with TSC undergoing surgery for epilepsy were submitted to independent component analysis (ICA), followed by source analysis, using the sLORETA algorithm. The localizations obtained for the ictal EEG and for the average interictal spikes were compared. Results: The ICA of ictal EEG produced consistent results in different events, and there was good agreement with the tubers that were successfully removed in three of the four patients (one patient refused surgery). In some patients there was a large discrepancy between the localization of ictal and interictal sources. The interictal activity produced more widespread source localizations. Conclusions: The use of ICA of ictal EEG followed by the use of source analysis methods in four cases of epilepsy and TSC was able to localize the epileptic generators very near the lesions successfully removed in surgery for epilepsy. Significance: The ICA of ictal EEG events may be a useful add-on to the tools used to establish the connection between epileptic scalp activity and the cortical tubers originating it, in patients with TSC considered for surgery of epilepsy.

Epidemiological profile of meningococcal disease in the State of Minas Gerais and in the Central, North, and Triângulo Mineiro regions, Brazil, during 2000-2009

INTRODUCTION: Infection by Neisseria meningitidis, termed as meningococcal disease, can cause meningococcal meningitis and septicemia with or without meningitis. Meningococcal disease is endemic in Brazil and has a high potential to cause large-scale epidemics; therefore, it requires the immediate notification of cases to the Information System for Notifiable Diseases (SINAN) in Brazil. The aim of this study was to describe an epidemiological profile using data from notified and confirmed cases in the State of Minas Gerais, Brazil, from January 2000 to December 2009, obtained from the investigation records of individuals with meningitis registered with SINAN. METHODS: This was a retrospective, population-based study. Descriptive analysis of the data was made using the simple and relative frequencies of the categorical variables in the investigation records. RESULTS: There were 1,688 confirmed patients in Minas Gerais of which 45.5% lived in the Central, North, and Triângulo Mineiro regions. The highest frequencies of cases were in the 1-4-years age group (26.3%), males (54.7%), caucasian (36.4%), and lived in an urban area (80%). In the patients with specified education, 650 (60.9%) patients had secondary education. Serogrouping of meningococci had been performed in 500 (29.6%) patients by age and gender; 285 (57%) belonged to serogroup C, 67 (13.4%) were in the 1-to 4-years age group, and 168 (33.6%) were male. CONCLUSIONS: The epidemiological profiles of patients in the Central, North, and Triângulo Mineiro regions were not significantly different from the profile of patients in Minas Gerais.

Eclectic feeding behavior of Lutzomyia (Nyssomyia) intermedia (Diptera, Psychodidae, Phlebotominae) in the transmission area of American cutaneous leishmaniasis, state of Paraná, Brazil

Introduction The blood meal source of sandflies provides valuable information about the vector/host interaction and allows for an understanding of American cutaneous leishmaniasis (ACL) transmission mechanisms. The aim of this study was to identify the blood meal sources of Lutzomyia (Nyssomyia) intermedia in an endemic area of leishmaniasis in Brazil's State of Paraná using a precipitin test. Methods Sandflies were collected in the rural locality of Epitácio Pessoa within the City of Adrianópolis, State of Paraná, in southern Brazil. A total of 864 female sandflies were captured, and 862 (99.8%) were identified as L. intermedia species. However, two unidentified specimens were considered to be part of the genus Lutzomyia. Results Among the females examined, 396 specimens presented reactions to a certain type of tested antiserum, and most (67.9%) reacted to the simple type. These sandflies fed mainly on the blood of birds, opossums, and rodents, but specimens that fed on the blood of humans, dogs, horses, cattle, and cats were also found. Among the cross-reactions found (32.1%), bird/rodent, bird/opossum, bird/dog, bird/human, and horse/dog cross-reactions were the most common. Conclusions These results demonstrate a tendency in the eclectic feeding behavior of L. intermedia and support its potential role as a vector for ACL in the study area.

EDP - A new estimation algorithm

The aim of this work project is to analyze the current algorithm used by EDP to estimate their clients’ electrical energy consumptions, create a new algorithm and compare the advantages and disadvantages of both. This new algorithm is different from the current one as it incorporates some effects from temperature variations. The results of the comparison show that this new algorithm with temperature variables performed better than the same algorithm without temperature variables, although there is still potential for further improvements of the current algorithm, if the prediction model is estimated using a sample of daily data, which is the case of the current EDP algorithm.

The role of temporary accommodation buildings for post-disaster housing reconstruction

The number of houses damaged or destroyed after disasters is frequently large, and re-housing of homeless people is one of the most important tasks of reconstruction programmes. Reconstruction works often last long and during that time, it is essential to provide victims with the minimum conditions to live with dignity, privacy, and protection. This research intends to demonstrate the crucial role of temporary accommodation buildings to provide spaces where people can live and gradually resume their life until they have a permanent house. The study also aims to identify the main problems of temporary accommodation strategies and to discuss some principles and guidelines in order to reach better design solutions. It is found that temporary accommodation is an issue that goes beyond the simple provision of buildings, since the whole space for temporary settlement is important. Likewise, temporary accommodation is a process that should start before a disaster occurs, as a preventive pre-planning. In spite of being temporary constructions, these housing buildings are one of the most important elements to provide in emergency scenarios, contributing for better recovery and reconstruction actions.