Allan R. S. Feitosa

Reconstruction of electrical impedance tomography images using genetic algorithms and non-blind search

The development and improvement of non-invasive imaging techniques have been increasing in the last decades, due to interests from both academy and industry. Electrical Impedance Tomography (EIT) is a noninvasive imaging technique that offers a vast field of possibilities due to its low cost, portability, and safety of handling. However, EIT image reconstruction is an ill-posed problem. Herein this work we present an EIT reconstruction method based on the optimization of the relative error of reconstruction using genetic algorithms employing elitist strategies. The initial set of solutions used by the elitist genetic algorithm includes a noisy version of the solution obtained from the backprojection algorithm, according to Saha and Bandyopadhyays criterion for non-blind initial search in optimization algorithms, in order to accelerate convergence and improve performance.

A modified differential evolution algorithm for the reconstruction of electrical impedance tomography images

It is a well-known fact that exposure of living tissues to ionizing radiation can result on several health problems, where cancer is probably the most complicated. This issue has been strengthening the efforts of both academy and industry to develop and improve non-invasive methods in the last decades. Electrical Impedance Tomography (EIT) is a non-invasive imaging technique that offers a vast field of possibilities due to its low cost, portability, and safety of handling. However, EIT image reconstruction is an ill-posed problem governed by Poissons Equation: there are no unique mathematical solution to solve this equation. Herein this work we present an EIT reconstruction method based on the optimization of the relative error of reconstruction using a modified differential evolution algorithm. Our approach was compared with genetic algorithms, classical differential evolution, and other modified differential evolution strategies. Results were quantitatively evaluated with ground-truth images using the relative mean squared error, showing that our results reached considerably low error magnitudes. Qualitative evaluation also indicated that our results were anatomically consistent.

Reconstruction of Electrical Impedance Tomography Using Fish School Search, Non-Blind Search, and Genetic Algorithm

Electrical Impedance Tomography (EIT) is a noninvasive imaging technique that does not use ionizing radiation, with application both in environmental sciences and in health. Image reconstruction is performed by solving an inverse problem and ill-posed. Evolutionary Computation and Swarm Intelligence have become a source of methods for solving inverse problems. Fish School Search (FSS) is a promising search and optimization method, based on the dynamics of schools of fish. In this article the authors present a method for reconstruction of EIT images based on FSS and Non-Blind Search (NBS). The method was evaluated using numerical phantoms consisting of electrical conductivity images with subjects in the center, between the center and the edge and on the edge of a circular section, with meshes of 415 finite elements. The authors performed 20 simulations for each configuration. Results showed that both FSS and FSS-NBS were able to converge faster than genetic algorithms.

Reconstruction of electrical impedance tomography images using chaotic self-adaptive ring-topology differential evolution and genetic algorithms.

The exposition of living tissues to ionizing radiation can result on several health problems, increasing the probability of cancer. Efforts from both academy and industry to develop and improve non-invasive methods have been increasing since the 1990s. Electrical Impedance Tomography (EIT) is a noninvasive imaging technique that offers a vast field of possibilities for imaging diagnostics, once it is a low cost, portable, and safe of handling technology. Nevertheless, EIT image reconstruction is an ill-posed problem: there are no unique mathematical solutions to solve the Equation of Poison. Herein this work we present an EIT reconstruction method based on the finite-element method and the optimization of the relative error of reconstruction using Self-Adaptive Ring-Topology Differential Evolution (SRDE) and its modified version using chaotic mutation factor (CSRDE). Our proposal was compared with genetic algorithms and classical differential evolution strategies, considering initial populations of 100 individuals. CSRDE-based experiments were ran using 70 agents evolving by SRDE and 30 chaotic mutated agents generated from the 30 worst agents. Results were quantitatively evaluated with ground-truth images using the relative mean squared error, demonstrating that our results using CSRDE reached considerably low error magnitudes. Qualitative evaluation also indicated that our results were anatomically consistent.

Reconstruction of electrical impedance tomography images using particle swarm optimization, genetic algorithms and non-blind search

The fields of non-invasive imaging and e-health have been increasing in the last decades, due to the need of avoiding to exposure living tissues to ionizing radiation, increasing monitoring levels of critical patients, and promoting the increasing of quality life. Furthermore, the use of image-reconstruction devices based on ionizing radiation can result on several health problems for patients in case non-calibrated apparatus is employed. These needs have been strengthening the efforts to improve non-invasive methods like Electrical Impedance Tomography (EIT), a low-cost, non-invasive, portable, and safe of handling imaging technique. However, EIT image reconstruction is still an open problem, due to its nature as an ill-posed problem governed by the Equation of Poison. Several numerical methods are used in order to solve this equation without generating anatomically inconsistent results. Evolutionary methods can be used as alternatives to Gauss-Newton and Backprojection well-known approaches, which frequently generate low-resolution blurred images. Herein this work we present an EIT reconstruction method based on the optimization of the relative error of reconstruction using particle swarm optimization with non-blind search. We studied two forms of initialization: totally random and including an imperfect but anatomically consistent solution based on Gauss-Newton reconstruction method, according to Saha and Bandyopadhyays criterion for non-blind initial search in optimization algorithms, in order to guide the iterative process to avoid anatomically inconsistent solutions. Our approach was compared with genetic algorithms. Results were quantitatively evaluated with ground-truth images using the relative mean squared error, showing that our results reached low error magnitudes. Qualitative evaluation also indicated that our results were morphologically consistent.

Hybrid Metaheuristics Applied to Image Reconstruction for an Electrical Impedance Tomography Prototype

Evolutionary computation has much scope for solving several important practical applications. However, sometimes they return only marginal performance, related to inappropriate selection of various parameters (tuning), inadequate representation, the number of iterations and stop criteria, and so on. For these cases, hybridization could be a reasonable way to improve the performance of algorithms. Electrical impedance tomography (EIT) is a non-invasive imaging technique free of ionizing radiation. EIT image reconstruction is considered an ill-posed problem and, therefore, its results are dependent on dynamics and constraints of reconstruction algorithms. The use of evolutionary and bioinspired techniques to reconstruct EIT images has been taking place in the reconstruction algorithm area with promising qualitative results. In this chapter, we discuss the implementation of evolutionary and bioinspired algorithms and its hybridizations to EIT image reconstruction. Quantitative and qualitative analyses of the results demonstrate that hybrid algorithms, here considered, in general, obtain more coherent anatomical images than canonical and non-hybrid algorithms.

SmartHome Energy Saving Using a Multi-objective Approach Based on Appliances Usage Profiles

The increasing number of electronic appliances in the houses and the huge human dependency on fossil fuel, bring the necessity of an efficient use of the available power sources. The Smart Home systems allow monitoring and controlling residential appliances. The proposed system works in residential energetic management using multi-objective techniques to recommend more economic appliances usage profiles than the actual usage profile of the user. However, these recommended profiles have to be similar to the user normal usage profile before the recommendation, allowing to make a reasonable recommendation. For the tested appliances, the NSGA-II technique has shown the best solutions. From the best results it was possible to get similar profiles to the normal use with until 90% of energy saving.

Reconstrução de Imagens de Tomografia por Impedância Elétrica Usando Cardume de Peixes, Busca Não-Cega e Algoritmo Genético

Valter A. F. Barbosa, Reiga R. Ribeiro, Allan R. S. Feitosa, Victor L. B. A. da Silva, Arthur D. D. Rocha, Rafaela C. Freitas, Ricardo E. de Souza, Wellington P. dos Santos Departamento de Engenharia Biomédica, Universidade Federal de Pernambuco, UFPE, Recife, Brasil Departamento de Engenharia da Computação, Universidade de Pernambuco, UPE, Recife, Brasil Emails: valter.augusto12@gmail, wellington.santos@ieee.org

Reconstrução de Imagens de TIE usando Simulated Annealing, Evolução Diferencial e Algoritmos Genéticos

Resumo — A reconstrução de imagem de Tomografia por Impedância Elétrica (TIE) consiste na resolução de um problema inverso e mal-posto governado pela Equação de Poisson, de modo que não existem soluções matemáticas únicas para sua resolução. Neste trabalho foram comparadas três técnicas de busca e otimização para a reconstrução das imagens de TIE, visando minimizar a função objetivo: Simulated Annealing (SA), Evolução Diferencial (ED) e Algoritmos Genéticos (AG). Os resultados de reconstrução foram gerados a partir de fantomas numéricos e avaliados tanto de forma quantitativa quanto qualitativa, levando em conta o erro de reconstrução e o custo computacional aproximado de cada algoritmo. Do ponto de vista da análise quantitativa, a reconstrução de TIE por ED obteve maior eficiência computacional quando comparada às demais técnicas, a saber, AG e SA. Quanto à avaliação qualitativa, foi evidenciado que os resultados foram anatomicamente consistentes e conclusivos para todas as técnicas estudadas, destacando-se a ED, cuja aplicação gerou imagens consideradas consistentes de acordo com os parâmetros estabelecidos, em apenas 50 iterações.

Reconstruction of electrical impedance tomography images using chaotic ring-topology particle swarm optimization and non-blind search

Non-invasive imaging and e-health have been increasing in the last decades, as a result of the efforts to generate diagnostic technology based on non-ionizing radiation. Electrical Impedance Tomography (EIT) is a low-cost, non-invasive, portable, and safe of handling imaging technique based on measuring the electric potentials generated by the application of currents in pairs of surface electrodes. Nevertheless, EIT image reconstruction is still an open problem, due to its nature as an ill-posed problem governed by the Equation of Poison. Several numerical methods are used in order to solve this equation without generating anatomically inconsistent results. Particle swarm algorithms can be used as alternatives to Gauss-Newton and Backprojection well-known approaches, which frequently generate low-resolution blurred images. Furthermore, Gauss-Newton convergence to anatomically consistent images is not guaranteed, needing to set constraints like the number of anatomical structures present on the image domain. Herein this work we present EIT reconstruction methods based on the optimization of the relative error of reconstruction using chaotic particle swarm algorithms with non-blind initial search. We studied two forms of initialization: totally random and including an imperfect but anatomically consistent noisy solution based on Gauss-Newton reconstruction method, according to Saha and Bandyopadhyays criterion for non-blind initial search in optimization algorithms, in order to guide the iterative process to avoid anatomically inconsistent solutions and avoid convergence to local minima. Results were quantitatively evaluated with ground-truth images using the relative mean squared error, showing that our results reached low error magnitudes. Qualitative evaluation also indicated that our results were morphologically consistent, mainly for classical PSO and ring-topology PSO with non-blind initial search.