Germán Castellanos

Learn More
Heuristical algorithms can reduce the computational complexity. Such methods require of some stopping criteria (cost function). Some of these cost functions are based on statistics like univariate and multivariate methods of analysis. Dimensional reduction techniques such as principal component analysis (PCA) allow to find a lower dimension transformed(More)
The follow-up of some cardiac diseases may be achieved by ECG-holter record analysis. A heartbeat clustering method can be used to reduce the usually high computational cost of such holter analysis. This study describes a method aimed at cardiac arrhythmia recognition based on this approach, by means of unsupervised inspection of morphologically similar(More)
Hidden Markov models have shown promising results for identification of spike sources in Parkinson's disease treatment, e.g., for deep brain stimulation. Usual classification criteria consist in maximum likelihood rule for the recognition of the correct class. In this paper, we present a different classification scheme based in proximity analysis. For this(More)
IntroductIon In the treatment of children with fixed Cleft Lip and Palate (CLP), problems such as hipponasality and hypernasality, which are related to vocal emission and resonance, might appear. Nevertheless, according to the report presented in Castellanos et al. (2006), hy-pernasality is more frequently found than hipponasality (90% vs. 10%). The(More)
Identificación de modelos dinámicos no lineales variantes en el tiempo en problemas mal condicionados correspondientes a la estimación de la actividad neuronal a partir de señales EEG Identificación de modelos dinámicos no lineales variantes en el tiempo en problemas mal condicionados correspondientes a la estimación de la actividad neuronal a partir de(More)
Importance of the resonance frequencIes of the vocal tract In estImatIng artIculatory posItIons Abstract — Acoustic-to-Articulatory inversion, which seeks to estimate an articulator position using the acoustic information in the speech signal, offers several potential applications in the field of speech processing. In this context, it is important to use(More)
HMMs are statistical models used in a very successful and effective form in speech recognition. However, HMM is a general model to describe the dynamic of stochastic processes; therefore it can be applied to a huge variety of biomedical signals. Usually, the HMM parameters are estimated by means of MLE (Maximum Likelihood Estimation) criterion.(More)
—A methodology based on acoustic analysis of digitized phonocar diogr aphic signals (PCG) is pr esented, or iented to detection of car diac mur mur s or iginated by valvular pathologies. Initially, a filtr ation system based on the wavelet tr ansfor m is developed to r educe the distur bances that usually appear in the acquisition stage, adjusting the sound(More)
Here, a lip posture recognition and segmentation system by means of tuning adjustable parameter models, is shown. For segmentation, deformable templates are used, and for feature extraction a variational model of lip contours is implemented. Both models are tuned by canonical genetic algorithms yielding performances up to 86.5% and 76.6% respectively.