23 September 2003 in IEEE Signal Processing Letters
An efficient technique for detecting explosive lung sounds (LS) (fine/coarse crackles and squawks) or bowel sounds (BS) in clinical auscultative recordings is presented. The technique is based on a fractal-dimension (FD) analysis of the recorded LS and BS obtained from controls and patients with pulmonary and bowel pathology, respectively. Experimental results demonstrate the efficiency of the proposed method, since it clearly detects the time location and duration of LS and BS, despite their variation either in time duration and/or amplitude. A noise stress test justifies the noise robustness of the FD-based detector, indicating its potential use in everyday clinical practice.
7 August 2002 in IEEE Transactions on Magnetics
In this paper, the application of radial basis function neural networks (RBFNNs) in inverse-scattering problems related to microwave medical imaging is proposed. The objective of the networks is to estimate the geometric and/or electromagnetic properties of tissues by processing the scattered-field measurements obtained during the illumination of the body by electromagnetic waves. The training of the RBFNNs is based on the orthogonal least-squares algorithm. This approach results in straightforward construction of the network, where both the size and the values of the free parameters of the network are obtained. The proposed methodology is applied to the estimation of the position and the size of proliferated marrow inside the bone of a limb. This application is closely related to the detection and monitoring of leukemia. Different measurement configurations are examined. The performance of the constructed networks in cases of noisy field measurements is also investigated.
16 May 2008 in IEEE Transactions on Geoscience and Remote Sensing
The shape reconstruction of a perfectly conducting 2-D scatterer by inverting transverse magnetic scattered field measurements is investigated. The reconstruction is based on evolutionary algorithms that minimize the discrepancy between measured and estimated scattered field data. A closed cubic B-spline expansion is adopted to represent the scatterer contour. Two algorithms have been examined the differential-evolution (DE) algorithm and the particle swarm optimization (PSO). Numerical results indicate that the DE algorithm outperforms the PSO in terms of reconstruction accuracy and convergence speed. Both techniques have been tested in the case of simulated measurements contaminated by additive white Gaussian noise.
24 February 2009 in IEEE Transactions on Magnetics
The design of thinned planar microstrip arrays under specific constraints concerning the impedance-matching condition of the array elements and the radiation pattern is presented. The radiation characteristics of the structure are extracted by applying the method-of-moments. The array design is based on a novel optimization method, which is a modified version of the boolean particle swarm optimization that employs velocity mutation (BPSO-vm). Apart from the optimization of the array geometry, the proposed method is applicable to other discrete-variable optimization problems. Moreover, the planar array design is coped with by means of other techniques, namely, a binary coded Genetic Algorithm, the binary Particle Swarm Optimization, and the Boolean PSO. The comparison of the above methods and the BPSO-vm shows the efficiency of the proposed technique.
23 June 2009 in IEEE Geoscience and Remote Sensing Letters
A comparison between differential evolution (DE) and particle swarm optimization (PSO) in solving 1-D small-scale inverse scattering problems is presented. In this comparison, the efficiency of both aforementioned optimization techniques is examined for permittivity and conductivity profile reconstruction problems. The comparison is carried out under the same conditions of initial population of candidate solutions and number of iterations. Numerical results indicate that both optimization methods are reliable tools for inverse scattering applications even when noisy measurements are considered. In the particular case of small-scale problems investigated in this letter, DE outperforms the PSO in terms of reconstruction accuracy. This is considered an indicative result and not generally applicable.
30 August 2010 in IEEE Transactions on Antennas and Propagation
TPTheseus G. Papadopoulos
A method for modeling time-domain wave propagation in dispersive Cole-Cole media is presented. The Cole-Cole model can describe the frequency dependence of the electromagnetic properties of various biological tissues with great accuracy over a wide frequency range and plays a key role in microwave medical imaging. The main difficulty in the time-domain modeling of Cole-Cole media is the appearance of fractional time derivatives. In the proposed method a Padé approximation is employed resulting in auxiliary differential equations of integer order. A finite-difference time-domain method is developed to solve the differential equations obtained. The comparison of analytical and calculated relative complex permittivity values over wideband frequency domain proves the validity of the method.