Browsing by Author "Ruano, M. Graça"
Now showing 1 - 10 of 73
Results Per Page
Sort Options
- A hybrid autonomous robot navigation method based on artificial intelligence and soft computing techniquesPublication . Kiss, L.; Varkonyi-koczy, A. R.; Ruano, M. GraçaThe main problem to be solved for autonomous indoor robots is that the environment where they have to move safety is only partially known and possibly dynamically changing. In this paper a hybrid navigation method is proposed, using two techniques that deal with a priori information and sensory data separately, thus blending the intelligence and optimality of global navigation methods with the reactivity and low complexity of local ones. The first, global navigation module, based on a priori information, chooses intermediary goals for the local navigation module, for which the so called A* algorithm is used. The second part, carrying out the (local) navigation relying on sensory data, applies a fuzzy-neural representation of an improved potential field based guiding navigation tool. Vision based obstacle detection is implemented by difference detection based on a combination of RGB and HSV representations of the pixels. Copyright (C) 2003 IFAC.
- A radial basis function classifier for the automatic diagnosis of cerebral vascular accidentsPublication . Ruano, M. Graça; Hajimani, Elmira; Ruano, AntonioA Radial Basis Function Neural Network (RBFNN) based diagnosis system for automatic identification of Cerebral Vascular Accident (CVA) through analysis of Computer Tomographic images (CT) is presented. For the design of a neural network classifier, most published methods just focus on the feature selection aspect and do not consider any approach for determining a model structure that best fits the application at their hand. Moreover, considering the domain of lesion detection from brain tissues, their feature space rarely contains symmetry/asymmetry information with respect to ideal mid-sagittal line. Another issue is how to handle multiple conflicting objectives in the design process, such as the maximization of both specificity and sensitivity, enforcing as well generalization. To deal with these challenges, a Multi Objective Genetic Algorithm (MOGA) based approach is used to determine the architecture of the classifier, its corresponding parameters and input features subject to multiple objectives, as well as their corresponding restrictions and priorities.
- A scalable and open source linear positioning system controllerPublication . Medeiros, M. C.; Fernandes, A. J. A.; Teixeira, C. A.; Ruano, M. GraçaThis paper is on the implementation of a dual axis positioning system controller. The system was designed to be used for space-dependent ultrasound signal acquisition problems, such as pressure field mapping. The work developed can be grouped in two main subjects: hardware and software. Each axis includes one stepper motor connected to a driver circuit, which is then connected to a processing unit. The graphical user interface is simple and clear for the user. The system resolution was computed as 127 mu m with an accuracy of 2.44 mu m. Although the target application is ultrasound signal acquisition, the controller can be applied to other devices that has up to four stepper motors. The application was developed as an open source software, thus it can be used or changed to fit different purposes.
- A spectral estimator using parallel-processing for use in a doppler blood-flow instrumentPublication . Ruano, M. Graça; Nocetti, D. F. G.; Fish, P. J.; Fleming, P. J.The work described here is part of a research program aiming to increase the sensitivity to disease detection using Doppler ultrasound by reducing the effects to the measurement procedure on the estimation of blood velocity and detection of flow disturbance.
- Adaptive system for blood flow estimationPublication . da Cruz Silva Andrade Madeira e Carvalho de Moura, Maria Margarida; Leiria, A.; Ruano, M. GraçaAdaptive estimation of blood flow signals is performed resorting to a framework developed to support research on Doppler blood flow signals' analysis. Real time spectral estimation methods, real time performance evaluation and run-time adjustment of the estimation methods parameters are bound together allowing the system to adapt itself to varying signal characteristic that are caused by physiological reasons.
- Adaptive system for blood flow estimationPublication . da Cruz Silva Andrade Madeira e Carvalho de Moura, Maria Margarida; Leiria, A.; Ruano, M. GraçaAdaptive estimation of blood flow signals is performed resorting to a framework developed to support research on Doppler blood flow signals' analysis. Real time spectral estimation methods, real time performance evaluation and run-time adjustment of the estimation methods parameters are bound together allowing the system to adapt itself to varying signal characteristics that are caused by physiological reasons.
- Alternative parallel implementations of an AR-modified covariance spectral estimator for diagnostic ultrasonic blood flow studiesPublication . Ruano, M. Graça; Nocetti, D. F. G.; Fish, P. J.; Fleming, P. J.The work described here is part of a research program aiming to increase the sensitivity to desease detection using Doppler ultrasound by reducing the effects of the measurement procedure on the estimation of blood velocity and detection of flow disturbance. The paper presents a summary of autoregressive spectral estimation, focusing the attention on a specific estimator - the modified covariance method. This method has been realized in parallel to achieve a fast computer processing. The new parallel version of this algorithm has been developed and implemented on a multiprocessing transputer-based system. Two different approaches to the problem of parallel partitioning the algorithm into a number of tasks were considered - a fine and a medium grain task scheme. The medium grain scheme is mapped onto a transputer-based system, by means of a processor farm computational structure. Two approaches to this farm model were adopted: a linear and a tree topology. For different model parameters, performance measurements were obtained revealing that the tree topology offers a higher performance. © 1993.
- Characterization of temperature-dependent echo-shifts and backscattered energy induced by thermal ultrasoundPublication . Ruano, M. Graça; Teixeira, C. A.; Rahmati, Javid J.Existence of accurate temporal-spatial temperature models, which would enable non-invasive estimates, will promote ultrasound-based thermal therapy applications. These models should reflect the tissue temperature with a maximum absolute error of 0.5 ºC within 1 cm3. In-vitro experiments have been developed to evaluate the temperature variations induced by standard ultrasound therapeutic device emitting continuously on gel-based phantom and on pork meat tissue using three different emitting intensities (1, 1.5 and 2 W/cm3). Temperature estimates were performed based on raw RF data collected using a second ultrasound transducer (imaging transducer). This second transducer worked in pulse-echo mode, and was placed perpendicularly to the therapeutic transducer. In order to access the quality of the estimates, temperatures were acquired by five and by two thermocouples placed in the gel-based phantom and on the porcine sample, respectively. At every 10 seconds the temperature and one RF-line is stored in a PC for future processing. The possibility to estimate temperature was assessed by considering two RFline features: temporal echo-shifts produced by changes in speed-of-sound and medium expansion/contraction and by changes on the backscattered energy originated by medium inhomogeneities. On one hand, results prove that echo-shifts correlated with temperature in both types of medium (phantom and ex-vivo porcine muscle). On the other hand, analyzing the backscattered energies one may conclude that this measures correlates with temperature in the porcine sample and not on the phantom. This led us to conclude that the developed phantom is not appropriate for studying changes on backscattered energy with temperature. Energy analysis of the porcine sample confirms the non-uniform temperature variation due to the existence of a heterogeneous media with different sound propagation velocities.
- Comparative study of different Doppler spectrum estimator implementationsPublication . Madeira, M. M.; Tokhi, M. O.; Ruano, M. GraçaThis paper presents a comparative performance study of some parallel processing architectures aiming at real-time implementation of a blood flow spectral estimator. Three homogeneous and an heterogeneous architecture incorporating transputers, digital signal processors (DSP's) and a vector processor were considered. The performance of these architectures was evaluated and compared in terms of execution times and gradient measurements. Communication times among processing elements were also considered. Analysis of the results revealed that both the DSP's homogeneous architecture and the heterogeneous architecture met real-time requirements; the latter presenting better execution times with less communications time load.
- Configurable processing for real-time spectral estimationPublication . Madeira, M.; Bellis, S.; Ruano, M. Graça; Marnane, W.This paper presents a system for real-time implementation of the fourth order Modified Covariance spectral estimator, which, when used in conjunction with pulsed Doppler blood how detectors, has been shown to offer increased sensitivity in atherosclerotic disease detection. The computational burden incurred with the Modified Covariance method is considerably seater than that of the conventional FFT method. This has led to separate studies to evaluate the cost and performance of firstly, transputer/DSP based platforms and secondly application specific custom circuitry, for implementation of the algorithm in real-time. The advantages and disadvantages of each of these different approaches are reviewed in this paper resulting in the design of a combined custom/DSP based system. Copyright (C) 1998 IFAC.