Browsing by Author "Matos, S."
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- Embolic signals characterization using wavelet networksPublication . Matos, S.; Ruano, M. Graça; Ruano, Antonio; Evans, D. H.Cerebral embolism represents a major cause of stroke. While embolic signal can be detected using transcranial Doppler (TCD) ultrasound, there are limitations in this technique that makes it difficult to differentiate between gaseous and solid emboli and artifacts. In this paper, we report the application of emergent signal processing techniques in the analysis and classification of embolic signals. The Wavelet Neural Network (WNN) is used to approximate the signals and the parameters from the wavelets that best fit each signal are used as inputs to train a Neural Network (NN) for classifying them as normal signals, or gaseous or solid embolic signals.
- Neural network classification of cerebral embolic signalsPublication . Matos, S.; Ruano, M. Graça; Ruano, Antonio; Evans, D. H.The presence of circulating cerebral emboli represents an increased risk of stroke. The detection of such emboli is possible with the use of a transcranial Doppler ultrasound (TCD) system.
- Training neural networks and neuro-fuzzy systems: a unified viewPublication . Ruano, Antonio; Ferreira, P. M.; Cabrita, Cristiano Lourenço; Matos, S.Neural and neuro-fuzzy models are powerful nonlinear modelling tools. Different structures, with different properties, are widely used to capture static or dynamical nonlinear mappings. Static (non-recurrent) models share a common structure: a nonlinear stage, followed by a linear mapping. In this paper, the separability of linear and nonlinear parameters is exploited for completely supervised training algorithms. Examples of this unified view are presented, involving multilayer perceptrons, radial basis functions, wavelet networks, B-splines, Mamdani and TSK fuzzy systems.