Author: CARLOS ALBERTO REYES GARCIA
In this paper we report the results obtained from experiments with a database of emotional speech in English in order to ﬁnd the most important acoustic features to estimate Emotion Primitives which determine the emotional content on speech. We are interested in exploiting the potential beneﬁts of continuous emotion models, so in this paper we demonstrate the feasibility of applying this approach to annotation of emotional speech and we explore ways to take advantage of this kind of annotation to improve the automatic classiﬁcation of basic emotions.
In this paper, a hybrid methodology based on Support Vector Regression for wind speed forecasting is proposed. Using the autoregressive model called Time Delay Coordinates, feature selection is performed by the Phase Space Reconstruction procedure. Then, a Support Vector Regression model is trained using univariate wind speed time series. Parameters of Support Vector Regression are tuned by a genetic algorithm. The proposed method is compared against the persistence model, and autoregressive models (AR, ARMA, and ARIMA) tuned by Akaike's Information Criterion and Ordinary Least Squares method. The stationary transformation of time series is also evaluated for the proposed method. Using historical wind speed data from the Mexican Wind Energy Technology Center (CERTE) located at La Ventosa, Oaxaca, M exico, the accuracy of the proposed forecasting method is evaluated for a whole range of short termforecasting horizons (from 1 to 24 h ahead). Results show that, forecasts made with our method are more accurate for medium (5e23 h ahead) short term WSF and WPF than those made with persistence and autoregressive models.
An automatic synthesis method based on the application of genetic algorithms (GAs) is described for the synthesis of voltage followers (VFs), which are designed using CMOS integrated circuit technology of 0.35μm. It is shown the usefulness of the nullor element to model the ideal behavior of the VF, and to codify its topology using a chromosome which is divided into four genes: gene of small-signal (genSS), gene of synthesis of the MOSFET (genSMos), gene of bias (genBias), and gene of synthesis of current mirrors (genCM); this last one to synthesize ideal current sources used in the biasing of the circuits with CMOS current mirrors.
The proposed synthesis method has been programmed in MatLab, and it uses T-SPICE to evaluate the fitness of the VFs at the transistor level of abstraction. In this manner, the method selects the more appropriated VFs by elitism. Finally, it is shown the behavior of the GA to synthesize practical VFs. As a result, it is shown the synthesis of eight CMOS compatible VFs, and their applications are briefly discussed.
Se describe un método de síntesis automática basado en la aplicación de algoritmos genéticos (GAs) para la síntesis de seguidores de voltaje (VFs), los cuales son diseñados usando tecnología CMOS de circuitos integrados de 0.35μm. Se demuestra la utilidad del elemento anulador para modelar el comportamiento ideal del VF, y para codificar su topología usando un cromosoma que es dividido en cuatro genes: gen de pequeña señal (genSS), gen de síntesis del MOSFET (genSMos), gen de polarización (genBias), y gen de síntesis de espejos de corriente (genCM); este último para sintetizar las fuentes de corriente ideales utilizadas en la polarización de los circuitos por espejos de corriente CMOS.
El método de síntesis propuesto se ha programado en MatLab, y usa T-SPICE para evaluar la aptitud de los VFs en el nivel de abstracción de transistor. De esta manera, el método selecciona los VFs más apropiados por elitismo. Finalmente, se muestra el comportamiento del GA para sintetizar VFs prácticos. Como resultado, se muestra la síntesis de ocho VFs compatibles con CMOS, y sus aplicaciones se discuten brevemente.
Evolutionary electronics Circuit synthesis Voltage follower Nullor Electrónica evolutiva Síntesis de circuitos Seguidor de voltaje Anulador CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA FÍSICA ELECTRÓNICA
This paper presents a Web 2.0 Learning Environment, for a systematic creation of adaptive and intelligent tutoring systems. Authoring contents is made by a community of users including teachers and students. The tutoring systems adapt the contents according to the best learning style using self-organizing maps (SOMs). The SOM was trained for classifying Felder–Silverman learning styles. The most important advantage of these unsupervised neural networks is that they do not require an external teacher for presenting a training set. The approach was implemented under an authoring tool that allows the production of personalized learning material to be used under collaborative and mobile learning environments. The tutoring systems together with the neural network can also be exported to mobile devices. We present different results to the approach working under the authoring tool.
Intelligent tutoring systems collaborative learning/Cooperative/collaborative learning Authoring tools and methods Learning communities CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA MATEMÁTICAS CIENCIA DE LOS ORDENADORES CIENCIA DE LOS ORDENADORES
In the infant cry analysis, the identiﬁcation of qualitative features is of great importance, because this provides relevant information to differentiate between normal and pathological cries, which makes important their identiﬁcation. Qualitative infant cry analysis has been done until now by medical per- sonal through visual inspection of spectrograms and by the auditory study of the cry recordings. In this way, the success of the process depends on the subjective perception of the inspector besides being a very slow task. The information extracted from the perceptive observation of the crying waves recordings is then used as a help to emit diagnosis. With the idea of helping to make the whole process easier and faster we are developing a method to automatically identify, measure and highlight selected qualitative features in infant cry recordings. The processing of this identiﬁer starts with the automatic discovery of infant cry units, which is performed by the use of a threshold applied to the energy of the signal along with another threshold applied to eliminate inspiratory cry segments, when not needed. From all the detected cry units, the process automatically identiﬁes melodic shape, shifts, glides and noise concentra- tion. In this work, we present, besides a quick review of related works, and a description of the perceptive analysis to help diagnosis, the process implementation, some experiments as well as the experimental results obtained.
Infant cry analysis Automatic cry units detection Automatic qualitative features identiﬁcation CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA MATEMÁTICAS CIENCIA DE LOS ORDENADORES CIENCIA DE LOS ORDENADORES
ESTEBAN TLELO CUAUTLE IVICK GUERRA GOMEZ MIGUEL AURELIO DUARTE VILLASEÑOR LUIS GERARDO DE LA FRAGA GEORGINA FLORES BECERRA GERARDO REYES SALGADO CARLOS ALBERTO REYES GARCIA GUSTAVO RODRIGUEZ GOMEZ (2010)
During the last decade, evolutionary algorithms (EAs) have shown its usefulness for solving multi-objective optimization problems. In the field of analog Integrated Circuits (ICs), they provide a set of feasible solutions for the optimal synthesis and sizing of different kinds of linear and nonlinear circuits, namely: amplifiers, filters and oscillators. The optimization of these circuits can enhance the performance for signal processing applications in electronics. In this study we present the state of the art in applying EAs for the synthesis and sizing of analog ICs. A survey of the main people working in this field and recent major advances and discoveries are summarized. Some insights on the behavior of EAs in the optimal design automation of analog ICs are given. Finally, several open research problems are listed mainly devoted to improve the electronic design automation tools for analog ICs by applying EAs.
Electronic design automation Evolucionary electronics Evolucionary algorithms Circuit synthesis Circuit sizing Genetic algorithm Non-sorting genetic algorithm Multi-objective evolutionary algorithm Unity-gain cell Current conveyor CMOS integrated circuits CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA FÍSICA ELECTRÓNICA ELECTRÓNICA
Hugo Jair Escalante Balderas Manuel Montes y Gómez Jesús Antonio González Bernal María del Pilar Gómez Gil Leopoldo Altamirano Robles CARLOS ALBERTO REYES GARCIA CAROLINA RETA CASTRO ALEJANDRO ROSALES PEREZ (2012)
Objective: Acute leukemia is a malignant disease that affects a large proportion of the world population. Different types and subtypes of acute leukemia require different treatments. In order to assign the correct treatment, a physician must identify the leukemia type or subtype. Advanced and precise methods are available for identifying leukemia types, but they are very expensive and not available in most hospitals in developing countries. Thus, alternative methods have been proposed. An option explored in this paper is based on the morphological properties of bone marrow images, where features are extracted from medical images and standard machine learning techniques are used to build leukemia type classifiers. Methods and materials: This paper studies the use of ensemble particle swarm model selection (EPSMS), which is an automated tool for the selection of classification models, in the context of acute leukemia classification. EPSMS is the application of particle swarm optimization to the exploration of the search space of ensembles that can be formed by heterogeneous classification models in a machine learning toolbox. EPSMS does not require prior domain knowledge and it is able to select highly accurate classification models without user intervention. Furthermore, specific models can be used for different classification tasks. Results: We report experimental results for acute leukemia classification with real data and show that EPSMS outperformed the best results obtained using manually designed classifiers with the same data. The highest performance using EPSMS was of 97.68% for two-type classification problems and of 94.21% for more than two types problems. To the best of our knowledge, these are the best results reported for this data set. Compared with previous studies, these improvements were consistent among different type/subtype classification tasks, different features extracted from images, and different feature extraction regions. The performance improvements were statistically significant.Weimproved previous results by an average of 6% and there are improvements of more than 20% with some settings. In addition to the performance improvements, we demonstrated that no manual effort was required during acute leukemia type/subtype classification.
Conclusions: Morphological classification of acute leukemia usingEPSMSprovides an alternative to expensive diagnostic methods in developing countries. EPSMS is a highly effective method for the automated construction of ensemble classifiers for acute leukemia classification, which requires no significant user intervention. EPSMS could also be used to address other medical classification tasks.
Ensemble learning Swarm optimization Full model selection Morphological classification Analysis of bone marrow cell images Acute leukemia classification CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA MATEMÁTICAS CIENCIA DE LOS ORDENADORES CIENCIA DE LOS ORDENADORES
CARLOS RODRIGO SUBIRIA CUETO FRANCISCO ALFONSO LARQUE SAAVEDRA MARIA DE LA LUZ REYES VEGA Laura A. de la Rosa Laura Elena Santana Contreras MARCELA GAYTAN MARTINEZ ALMA ANGELICA VAZQUEZ FLORES JOAQUIN RODRIGO GARCIA ALBA YADIRA CORRAL AVITIA JOSE ALBERTO NUÑEZ GASTELUM Nina del Rocío Martínez-Ruiz (2019)
The wheat flour tortilla (WFT) is a Mexican food product widely consumed in the world, despite lacking fiber and micronutrients. Ramón seed flour (RSF) is an underutilized natural resource rich in fiber, minerals and bioactive compounds that can be used to improve properties of starchy foods, such as WFT. The study evaluated the impact of partial replacement of wheat flour with RSF on the physicochemical, sensory, rheological and nutritional properties and antioxidant capacity (AC) of RSF-containing flour tortilla (RFT). Results indicated that RFT (25% RSF) had higher dietary fiber (4.5 times) and mineral (8.8%; potassium 42.8%, copper 33%) content than WFT. Two sensory attributes were significantly different between RTF and WFT, color intensity and rollability. RFT was soft and it was accepted by the consumer. Phenolic compounds (PC) and AC were higher in RFT (11.7 times, 33%–50%, respectively) than WFT. PC identification by ultra-performance liquid chromatography quadrupole time of flight mass spectrometry (UPLC-QTOF-MS) showed that phenolic acids esterified with quinic acid, such as chlorogenic and other caffeoyl and coumaroyl derivatives were the major PC identified in RSF, resveratrol was also detected. These results show that RSF can be used as an ingredient to improve nutritional and antioxidant properties of traditional foods, such as the WFT.
Luis Luis Pellegrin OCTAVIO LOYOLA GONZALEZ JOSE ORTIZ BEJAR MIGUEL ANGEL MEDINA PEREZ ANDRES EDUARDO GUTIERREZ RODRIGUEZ Eric Sadit Téllez Avila MARIO GRAFF GUERRERO SABINO MIRANDA JIMENEZ Daniela Moctezuma MAURICIO ALFONSO GARCIA LIMON ALICIA MORALES REYES CARLOS ALBERTO REYES GARCIA Eduardo Morales Manzanares Hugo Jair Escalante (2019)
This paper describes the design of the 2017 RedICA: Text-Image Matching (RICATIM) challenge, including the dataset generation, a complete analysis of results, and the descriptions of the top-ranked developed methods. The academic challenge explores the feasibility of a novel binary image classification scenario, where each instance corresponds to the concatenation of learned representations of an image and a word. Instances are labeled as positive if the word is relevant for describing the visual content of the image, and negative otherwise. This novel approach of the image classification problem poses an alternative scenario where any text-image pair can be represented in such space, so any word could be considered for describing an image. The proposed methods are diverse and competitive, showing considerable improvements over the proposed baselines.
FRANCISCO LIZCANO FERNANDEZ Víctor Manuel Reynoso Angulo GUSTAVO ERNESTO EMMERICH ISAAC JAVIER SANTIAGO CASTILLO José Roberto Rojas Quincosa Hilda Naessens FRANCISCO JAVIER DUARTE JOVE ROGERIO RAMIREZ GIL MARIA MARGARITA ARGUELLES GOMEZ GABRIELA YOLANDA CASTAÑON GARCIA JUAN ANTONIO TAGUENCA BELMONTE LUIS JAVIER SELFA CASADOS ANGELICA CAZARIN MARTINEZ MARTHA GLORIA MORALES GARZA JONATHAN ROMERO GRANADOS CARLOS ALBERTO FLORES HERNANDEZ Marco Antonio Calderón Mólgora MA. AIDE HERNANDEZ GARCIA FERNANDO DIAZ PEREZ ANDRES REYES RODRIGUEZ Hugo Alejandro Borjas García ULISES PAVEL MARTINEZ ROMERO ALICIA GOMEZ LOPEZ ALBERTO MARTIN ALVAREZ ALEJANDRO PALOMO GARRIDO VERONICA DE LA TORRE OROPEZA OSCAR DAVID RIVERA GARRIDO LAURA ELENA ARELLANO RIVERA LOURDES CONSUELO PACHECO LADRON DE GUEVARA (2015)
Este libro, que tiene por objetivo analizar la calidad de las elecciones celebradas entre 2006 y 2011 para ocupar la titularidad del Poder Ejecutivo de las 14 entidades federativas de la República Mexicana que conforman las regiones Centro y Centro-occidente de este país, ha sido elaborado por investigadores pertenecientes a la Red Nacional de Investigación sobre la Calidad de la Democracia en México (Renicadem), la cual cuenta con un equipo de investigación en cada una de las entidades federativas del país. A su vez, esta Red constituye una de las cuatro líneas temáticas que componen la red temática del Conacyt “Sociedad civil y calidad de la democracia”. Con todo, la presente obra puede considerarse, en dos sentidos, como el resultado parcial de estudios realizados por investigadores que conforman la mencionada Renicadem. Por un lado, trata sólo de una de las varias dimensiones que esta Red ha establecido como necesarias para analizar la calidad de la democracia: la calidad electoral (otras dimensiones, que se encuentran en proceso de investigación, son calidad de vida, rendición de cuentas y Estado de derecho). También es parcial porque no abarca la totalidad de la República Mexicana, sino únicamente a las 14 entidades indicadas.