Rosaura Palma Orozco

IDENTIFICACIÓN DE SECUENCIAS DE AMINOÁCIDOS

Dentro del procesamiento de senales, la estimacion de parametros es necesaria para obtener coeficientes aplicables en algoritmos de clasificacion, optimizacion, prediccion o identificacion. Este ultimo, de interes en este trabajo, hace referencia a la reconstruccion de una senal, corregida a partir del error generado entre la senal deseada y la identificada.

n-Iterative Exponential Forgetting Factor for EEG Signals Parameter Estimation

Electroencephalograms (EEG) signals are of interest because of their relationship with physiological activities, allowing a description of motion, speaking, or thinking. Important research has been developed to take advantage of EEG using classification or predictor algorithms based on parameters that help to describe the signal behavior. Thus, great importance should be taken to feature extraction which is complicated for the Parameter Estimation (PE)–System Identification (SI) process. When based on an average approximation, nonstationary characteristics are presented. For PE the comparison of three forms of iterative-recursive uses of the Exponential Forgetting Factor (EFF) combined with a linear function to identify a synthetic stochastic signal is presented. The one with best results seen through the functional error is applied to approximate an EEG signal for a simple classification example, showing the effectiveness of our proposal.Electroencephalograms (EEG) signals are of interest because of their relationship with physiological activities, allowing a description of motion, speaking, or thinking. Important research has been developed to take advantage of EEG using classification or predictor algorithms based on parameters that help to describe the signal behavior. Thus, great importance should be taken to feature extraction which is complicated for the Parameter Estimation (PE)–System Identification (SI) process. When based on an average approximation, nonstationary characteristics are presented. For PE the comparison of three forms of iterative-recursive uses of the Exponential Forgetting Factor (EFF) combined with a linear function to identify a synthetic stochastic signal is presented. The one with best results seen through the functional error is applied to approximate an EEG signal for a simple classification example, showing the effectiveness of our proposal.

CLARIFICACIÓN DINÁMICA USANDO MODOS DESLIZANTES PARA SISTEMAS CON INCERTIDUMBRES

This collaboration presents a clarification based on sliding modes, applied into fuzzy logic membership function. The main idea includes instead of absolute value differences generated between the state and its average, the sliding mode without loss its properties. The transformation includes the functions that have the sign and its differences. The sign function is inversely proportional with the membership function slopes. Therefore, it is necessary pay attention in the membership function form and the sliding mode description. Key Words: fuzzy logic, sliding modes, clarification, membership functions, computational methods.

CLARIFICACIÓN BASADA EN LA FUNCIÓN DE PERTENENCIA INVERSA Y EL VECTOR UNITARIO

RESUMEN: Este articulo presenta un modelo de clarificacion en el sentido borroso, considerando que la funcion de pertenencia es invertible con respecto al estado del sistema y definiendola como proceso de identificacion sobre la respuesta acotada del sistema visto como caja negra. En este caso la herramienta necesaria es el vector unitario basado en los valores de la funcion de pertenencia. Especificamente, se considera en el a la diferencia de los valores absolutos entre el valor del estado y su media, en vez de la desigualdad del triangulo; permitiendo asi la clarificacion dado que se conoce la funcion de pertenencia. Dentro de las simulaciones en Matlab® se observa que la convergencia entre la senal deseada y la clarificada se da en casi todos los puntos, describiendo ilustrativamente como se va desarrollando el proceso de clarificacion; comparandose los resultados con los obtenidos por el metodo del centroide. En el funcional de error de las secuencias, convergen a una region que decrece a cero a traves del tiempo. Palabras Clave: logica borrosa, clarificacion, funciones de pertenencia, metodos computacionales, error cuadratico medio