Adolfo Guzman Arenas | Instituto Politécnico Nacional (original) (raw)

Papers by Adolfo Guzman Arenas

congreso de la SEMANA IBEROAMERICANA DE INGENIERÍA ELECTRÓNICA de la UAM, 2024

A nivel global, la población enfrenta problemas de salud que afectan la calidad de vida y aumenta... more A nivel global, la población enfrenta problemas de salud que afectan la calidad de vida y aumentan las muertes. La academia y las instituciones de salud han investigado para descubrir nuevos tratamientos y prevenir enfermedades mediante programas estratégicos. Esta investigación examina la relación entre los servicios de salud otorgados a pacientes con enfermedades no transmisibles y la población en las entidades federativas de México, utilizando técnicas y herramientas de ciencia de datos. Se llevan a cabo dos análisis: a) un análisis de correlación lineal utilizando el índice de correlación de Pearson para evaluar la accesibilidad de los servicios de salud relacionados con enfermedades no transmisibles, y b) un análisis de correlación espacial utilizando el Índice Global de Moran y el Indicador de Asociación Espacial Local (LISA) para identificar patrones de agrupación en la prevalencia de los servicios de salud relacionados con Neoplasias.

Pattern Analysis and Applications, 2024

In the realm of 3D image processing, accurately representing the geometric nuances of line curves... more In the realm of 3D image processing, accurately representing the geometric nuances of line curves is crucial. Building upon the foundation set by the Slope Chain Code (SCC), which adeptly represents intricate two-dimensional curves using an array capturing the exterior angles at each vertex, this study introduces an innovative 3D encoding method tailored for polygonal curves.
This 3D encoding employs parallel slope and torsion chains, ensuring invariance to common transformations like translations, rotations, and uniform scaling, while also demonstrating robustness against mirror imaging and variable starting points. A hallmark feature of this method is its ability to compute tortuosity, a descriptor of curve complexity or winding nature. By applying this technique to biomedical engineering, we delved into the flagellar beat patterns of human sperm. These insights underscore the versatility of our 3D encoding across diverse computer
vision applications.

Keywords: 3D tortuosity, Slope Chain Code, 3D sperm flagellar beat

Jornada de Ciencia y Tecnología Aplicada, 2022

La dependencia de gobierno que da servicios de salud gratuitos a las personas que carecen de empl... more La dependencia de gobierno que da servicios de salud gratuitos a las personas que carecen de empleo formal, ha publicado el resumen histórico nacional de los servicios requeridos, en un lapso de 18 años. La herramienta "Análisis histórico de servicios de salud" permite la visualización de datos catalogados por la Clasificación Internacional de Enfermedades, en su décima edición. Las visualizaciones muestran los principales servicios médicos con mayor número de egresos otorgados a nivel nacional por género, en los que, por género masculino se encuentran traumatismos, envenenamientos, sistema digestivo, sistema génitourinario y neoplasias, mientras que en el género femenino se encuentran las categorías de sistema digestivo, neoplasias y sistema génitourinario. También muestran las categorías principales causantes de defunciones, en rangos de edades. Un rango interesante es "personas mayores de 66 años" donde las principales categorías son el sistema circulatorio, el sistema respiratorio y el sistema digestivo. Se visualizan los principales servicios otorgados a varios estados de México y se observa que siguen un patrón de servicios a nivel nacional.

Palabras clave: servicios de salud, base de datos, ciencia de datos, visualización, preprocesamiento de datos, análisis histórico

Jornada de Ciencia y Tecnología Aplicada, 2022

Los exámenes de desempeño-contexto EXCALE y PLANEA nos permiten obtener información interesante d... more Los exámenes de desempeño-contexto EXCALE y PLANEA nos permiten obtener información interesante de las variables relevantes o bien, de aquéllas que están correlacionadas con el desempeño del alumno en el área de Matemáticas. Las evaluaciones de los años 2005, 2008, 2012, 2015 y 2017 muestran que el porcentaje de alumnos evaluados como "Por debajo del básico" y "Avanzado" tienen una tendencia positiva, mientras que los alumnos colocados en "Básico" y "Medio" tienen una tendencia negativa. Las reglas de asociación obtenidas de variables relevantes que se han mantenido a nivel nacional de los alumnos con un buen desempeño son constantes y existen patrones que resisten el paso de los años, como es el caso de la variable relevante "aspiración académica". Para estudiantes con desempeño "Medio" y "Básico", dicha regularidad no existe, además de observarse dificultades para la clasificación de estos alumnos con los algoritmos J48 y Naive Bayes.

Palabras clave: Algoritmos de clasificación, Educación, Minería de datos, reglas de asociación, variables relevantes

USO DE LA GAMIFICACIÓN COMO UNA ESTRATEGIA NEURODIDÁCTICA, 2023

La UPIICSA en su interés de implementar nuevas estrategias neurodidácticas decidió impulsar este ... more La UPIICSA en su interés de implementar nuevas estrategias neurodidácticas decidió impulsar este estudio. El estudio está enfocado a explorar la utilización de la gamificación como una estrategia neurodidáctica con estudiantes de las carreras de Ciencias e Ingeniería en Informática invitándolos a participar en un quiz sobre la historia de la computación. El objetivo del estudio era conocer la actitud y respuesta de los estudiantes ante este tipo de actividades y su efecto en el aprendizaje. Conocer mediante la aplicación de una encuesta al terminar el quiz, cómo se sintieron, si les gustó participar y lo más importante, si habían ampliado sus conocimientos sobre el tema y si de esta forma se les había facilitado el aprendizaje y les había parecido divertido. El tamaño de la muestra fue de 105, de los cuales 88 aceptaron el reto y 68 de ellos lograron completar el quiz con éxito. Se utilizó software libre para crear el quiz Qbitts, integrado por 25 preguntas seleccionadas aleatoriamente con cinco posibles respuestas de un banco de 150 reactivos, adaptado de una aplicación de CodingNepal. Los resultados obtenidos muestran que a los estudiantes participantes en el quiz les pareció una actividad interesante, divertida, que puso a prueba su memoria de corto y largo plazo y que motivó a 41 de ellos a tratar de alcanzar las 25 respuestas correctas, aunque el reto era llegar a 20. La mayoría de los participantes declaró que les permitió aumentar sus conocimientos sobre la historia de la computación de una manera lúdica.

Palabras clave: gamificación, neurodidáctica, neuroeducación, quiz.

Seguimiento de personas en multicámaras., 2023

The increase in the number of video cameras in recent years has generated such an amount of infor... more The increase in the number of video cameras in recent years has generated such an amount of information that its manual analysis becomes virtually impossible, which opens the need for a method to process this information automatically and support the tasks
that these entail concerning security reasons.
A video-surveilled space is mostly composed of more than one video camera which are positioned in such a way that they cover the largest possible area and allow the correct identification of persons through different videos.
In this work we developed a system with the ability to track people in a multi-camera system, generating position trajectories of each camera maintaining the same identity throughout different areas.
To perform this task, modules were developed for detecting people in frames of each video in parallel, estimating their position given their past trajectory as well as a global memory module for exchanging identities and information across different video cameras, among other techniques to reduce uncertainty in frames and fragmentation of identities.
The system was tested with two proprietary datasets created using videos from the Centro de Investigación en Computación del IPN, showing robustness concerning video duration, number of transitions as well as person detection, reaching 87% and 86% accuracy concerning detection and values of 60.17% and 48.9% in MOTA, indicating the good performance of the system as well as the difficulty proposed with the developed datasets.

El incremento de videocámaras en los últimos años ha generado una cantidad de información tal que su análisis manual se vuelve virtualmente imposible, lo que abre la necesidad de un método para procesar esta información de manera automática y apoyar en las tareas que estas conllevan con respecto a motivos de seguridad.
Un espacio vídeo vigilado en su mayoría se compone de más de una videocámara, las cuales se posicionan de tal manera que abarquen la mayor área posible y que permiten la correcta identificación de personas a través de distintos vídeos.
En este trabajo se desarrolló un sistema con la capacidad de realizar el seguimiento de personas en un sistema multicámaras, generando trayectorias de posición de cada una manteniendo una misma identidad a lo largo de distintas zonas.
Para realizar esta tarea se desarrollaron módulos para la detección de personas en fotogramas de cada vídeo de manera paralela, la estimación de su posición dada su trayectoria pasada así como un módulo de memoria global para el intercambio de identidades e información a través de distintas videocámaras, entre otras técnicas para reducir la incertidumbre en fotogramas y la fragmentación de identidades.
El sistema fue puesto a prueba con dos conjuntos de datos propios creados utilizando vídeos del Centro de Investigación en Computación del IPN, mostrando una robustez con respecto a la duración de los vídeos, el número de transiciones así como la detección de las personas, alcanzando un 87& y 86% de exactitud con respecto a la detección y valores de 60.17& y 48.9% en MOTA, señalando el buen desempeño del sistema así como la dificultad propuesta con los conjuntos de datos desarrollados.

CIENCIA 7 4-3, julio de 2023, págs. 80-7, 2023

ChatGPT fue diseñado para producir lenguaje humano bastante natural; pregúntele lo que sea y reci... more ChatGPT fue diseñado para producir lenguaje humano bastante natural; pregúntele lo que sea y recibirá una respuesta como si la hubiera escrito alguien más, algo parecido a tener una conversación. Esta novedosa herramienta de inteligencia artificial impresiona rápidamente, pero muchas personas han señalado que tiene algunas dificultades serias.
En este artículo explico su funcionamiento, peligros y usos.

M. Sc. Thesis, CIC IPN Mexico, 2023

Depression is a common illness throughout the world. Approximately 280 million people around the ... more Depression is a common illness throughout the world. Approximately 280 million people around the world have depression, according to the World Health Organization (2021). The increasing capacities and more sensors in personal devices such as the telephone, smart bracelets, and watches have generated significant interest in the area of health due to the information from the data these devices passively generate. Research using digital phenotyping to predict indicators of mental illness, such as depression and stress, has increased.

In the present work, the analysis and exploration of different machine learning and deep learning models used to predict the levels of depression of students from the data obtained through mobile devices are shown. We used linear models and artificial neural networks to predict the results; Depression levels were analyzed and compared based on the PHQ-9 exam. The PHQ-9 is a clinical exam used to detect depression and consists of 9 questions. The score has a range from 0 to 27. The characteristics we used for the models were obtained by preprocessing the data from the mobile sensors. The results obtained for the linear regression models were 7.7 Root Mean Squared Error RMSE for the classic linear regressor (Ordinary Least Square); the results of this model with Ridge regularization were 2.8 RMSE and with Lasso 2.8 RMSE. The best model was the Neural Network Architecture with 2.7 RMSE.

Feature Selection Ordered by Correlation -FSOC, 2023

Data sets have increased in volume and features, yielding longer times for classification and tra... more Data sets have increased in volume and features, yielding longer times for classification and training. When an object has many features, it often occurs that not all of them are highly correlated with the target class, and that significant correlation may exist between certain pair of features. An adequate removal of "useless" features saves time and effort at data collection, and assures faster learning and classification times, with little or no reduction in classification accuracy. This article presents a new filter type method, called FSOC (Feature Selection Ordered by Correlation), to select, with small computational cost, relevant features. FSOC achieves this reduction by selecting a subset of the original features. FSOC does not combine existing features to produce a new set of fewer features, since the artificially created features mask the relevance of the original features in class assignment, making the new model difficult to interpret. To test FSOC, a statistical analysis was performed on a collection of 36 data sets from several repositories some with millions of objects. The classification percentages (efficiency) of FSOC were similar to other feature selection features. Nevertheless, when obtaining the selected features, FSOC was up to 42 times faster than other algorithms such as Correlation Feature Selection (CFS), Fast Correlation-Based Filter (FCFB) and Efficient feature selection based on correlation measure (ECMBF).

Expert Systems with Applications, 2007

Seguimiento de personas en multicámaras, 2023

The increase in the number of video cameras in recent years has generated such an amount of infor... more The increase in the number of video cameras in recent years has generated such an amount of information that its manual analysis becomes virtually impossible, which opens the need for a method to process this information automatically and support the tasks that these entail concerning security reasons.
A video-surveilled space is mostly composed of more than one video camera which are positioned in such a way that they cover the largest possible area and allow the correct identification of persons through different videos.
In this work we developed a system with the ability to track people in a multi-camera system, generating position trajectories of each camera maintaining the same identity throughout different areas.
To perform this task, modules were developed for detecting people in frames of each video in parallel, estimating their position given their past trajectory as well as a global memory module for exchanging identities and information across different video cameras, among other techniques to reduce uncertainty in frames and fragmentation of identities.
The system was tested with two proprietary datasets created using videos from the Centro de Investigación en Computación del IPN, showing robustness concerning video duration, number of transitions as well as person detection, reaching 87% and 86% accuracy concerning detection and values of 60.17% and 48.9% in MOTA, indicating the good performance of the system as well as the difficulty proposed with the developed datasets.

Tesis (Maestría en Ciencias de la Computación), Instituto Politécnico Nacional, CIC, 2017, 1 arch... more Tesis (Maestría en Ciencias de la Computación), Instituto Politécnico Nacional, CIC, 2017, 1 archivo PDF, (119 páginas). tesis.ipn.m

Tesis del Centro de Investigación en Computación del IPN, 2022

RESUMEN Actualmente se generan elevados volúmenes de información derivados de la actividad cient... more RESUMEN

Actualmente se generan elevados volúmenes de información derivados de la actividad científica. Aunado a esto, la evolución del conocimiento científico en todas sus áreas de investigación y específicamente en las áreas de la computación y afines, está en constante transformación. Partiendo de esto, se tiene la necesidad de analizar y esquematizar esta información generadas, para obtener conclusiones sobre su avance, evolución y generación.

El presente documento realiza un análisis y evalación, de las temáticas dominantes en las publicaciones del CIC-IPN que se han desarrollado hasta el 2020. Las 690 tesis feron obtenidas de los repositorios digitales del IPN. Para la evaluación del sistema, 100 tesis se clasificaron de manera manual previamente con base a la ontología multijerárquica que sugiere ACM (Association for Computing Machinery, por sus siglas en inglés) para el campo de la computación, sirviendo como Golden Standard. La clasificación de la tesis es utilizando el sistema desarrollado CLASSONTO, que permite clasificar basándose en un árbol de conocimiento. El sistema ocupa una votación y propagación del voto, para la identificación de temáticas, además de un procesamiento de textos. El árbol de conocimiento en el que se basa es enriquecido, por lo que lo convierte en un sistema de mejora continua.

Los resultados obtenidos muestran las clasificaciones de cada tesis, permitiendo inferir qué temas trata cada una. De igual manera se hace un análisis y evaluación de los resultados con respecto al tiempo, visualizando el desarrollo de temáticas a través del tiempo.

Esta investigación es de particular interés, pues servirá como una referencia para evaluar la producción científica del CIC, fomentando su estudio y catalogación.

Palabras clave: clasificación jerárquica, ontologías, modelado de temas.

Clasificación ACM: 8.5.5.8 Clustering and classification; 11.3.1 Natural Language Processing; 12.8.2 Publishing; 11.4.1.2.4 Topic modeling; 8.5.1.6 Ontologies.

Pattern Recognition, 1980

EN ENTREVISTA REALIZADA POR LA GACETA, EL PASADO LUNES, EL DOCTOR ADOLFO GUZMAN ARENAS INDICO QUE... more EN ENTREVISTA REALIZADA POR LA GACETA, EL PASADO LUNES, EL DOCTOR ADOLFO GUZMAN ARENAS INDICO QUE LAS FORMULAS DESARROLLADAS EN EL INSTITUTO DE INVESTIGACION EN MATEMATICAS APLICADAS Y SISTEMAS (IIMAS), EN EL RENGLON ELECTRONICO, ABREN NUEVAS PERSPECTIVAS PARA DETECTAR, CONOCER Y DETECTAR CON UN MARGEN MINIMO DE ERROR, LOS RECURSOS NATURALES DE MEXICO. ADOLFO GUZMAN ARENAS, JEFE DEL DEPARTAMENTO DE COMPUTACION DEL IIMAS, ENFATIZO QUE DICHO INSTITUTO DESARROLLA TECNOLOGIA Y HERRAMIENTAS ADECUADAS A LAS NECESIDADES ESPECIFICAS DEL PAIS, ACABANDO ASI CON EL MITO DE QUE MEXICO NO PUEDE IMPLEMENTAR TECNICAS PROPIAS

Atmósfera, 2016

This article proposes a methodology to discover patterns in observed climatologic data, particula... more This article proposes a methodology to discover patterns in observed climatologic data, particularly temperatures and rainfall, in subnational political division units using an automatic classification algorithm (a decision tree produced by the C4.5 algorithm). Thus, the patterns represent classification trees, assuming that: (1) every political division unit contains at least one climatological station, and (2) the recording periods of the stations are relatively similar in duration and in their initial and ending years. A series of classification models are produced by using different subsets from an experimental dataset. This dataset contains information from 3606 climatological stations in Mexico with recording periods whose durations, initial and ending years are diverse. The target (dependent) variable in all these models is the name of the political unit (i.e., the state). The predictors are 36 monthly features per each climatological station: 12 features corresponding to a m...

congreso de la SEMANA IBEROAMERICANA DE INGENIERÍA ELECTRÓNICA de la UAM, 2024

Pattern Analysis and Applications, 2024

Keywords: 3D tortuosity, Slope Chain Code, 3D sperm flagellar beat

Jornada de Ciencia y Tecnología Aplicada, 2022

Palabras clave: servicios de salud, base de datos, ciencia de datos, visualización, preprocesamiento de datos, análisis histórico

Jornada de Ciencia y Tecnología Aplicada, 2022

Palabras clave: Algoritmos de clasificación, Educación, Minería de datos, reglas de asociación, variables relevantes

USO DE LA GAMIFICACIÓN COMO UNA ESTRATEGIA NEURODIDÁCTICA, 2023

Palabras clave: gamificación, neurodidáctica, neuroeducación, quiz.

Seguimiento de personas en multicámaras., 2023

CIENCIA 7 4-3, julio de 2023, págs. 80-7, 2023

M. Sc. Thesis, CIC IPN Mexico, 2023

Feature Selection Ordered by Correlation -FSOC, 2023

Expert Systems with Applications, 2007

Seguimiento de personas en multicámaras, 2023

The increase in the number of video cameras in recent years has generated such an amount of infor... more The increase in the number of video cameras in recent years has generated such an amount of information that its manual analysis becomes virtually impossible, which opens the need for a method to process this information automatically and support the tasks that these entail concerning security reasons.
A video-surveilled space is mostly composed of more than one video camera which are positioned in such a way that they cover the largest possible area and allow the correct identification of persons through different videos.
In this work we developed a system with the ability to track people in a multi-camera system, generating position trajectories of each camera maintaining the same identity throughout different areas.
To perform this task, modules were developed for detecting people in frames of each video in parallel, estimating their position given their past trajectory as well as a global memory module for exchanging identities and information across different video cameras, among other techniques to reduce uncertainty in frames and fragmentation of identities.
The system was tested with two proprietary datasets created using videos from the Centro de Investigación en Computación del IPN, showing robustness concerning video duration, number of transitions as well as person detection, reaching 87% and 86% accuracy concerning detection and values of 60.17% and 48.9% in MOTA, indicating the good performance of the system as well as the difficulty proposed with the developed datasets.

Tesis del Centro de Investigación en Computación del IPN, 2022

RESUMEN Actualmente se generan elevados volúmenes de información derivados de la actividad cient... more RESUMEN

Esta investigación es de particular interés, pues servirá como una referencia para evaluar la producción científica del CIC, fomentando su estudio y catalogación.

Palabras clave: clasificación jerárquica, ontologías, modelado de temas.

Clasificación ACM: 8.5.5.8 Clustering and classification; 11.3.1 Natural Language Processing; 12.8.2 Publishing; 11.4.1.2.4 Topic modeling; 8.5.1.6 Ontologies.

Pattern Recognition, 1980

Atmósfera, 2016

Ontology fusion, text to concepts. Knowledge extraction. Knowledge acquisition

The fusion of several ontologies (data structures representing concepts and their relatioships; s... more The fusion of several ontologies (data structures representing concepts and their relatioships; semantic networks) will allow a computer to gradually increase knowledge obtained from several places. For instance, from text documents. We have done work on ontology fusion, and in the parsing or "translation" of text documents to ontologies (that permit precise representation of the information contained in the documents). This work is reported in the following documents.

"74. Guzmán, A. (1987) Existing and Projected Functionalities of CYC. Technical Report ACA-AI-331-87 (P). Artificial Intelligence Laboratory, MCC. MCC/ACA Confidential and Proprietary.

111. Olivares, J, Demetrio Aguirre, A., Domínguez Ayala, María, and Guzmán Arenas, A (1999) Distributed collaboration among purposeful agents. Proceedings of the Forum “Computing, from theory to practice.” Pages 210-219. CIC, May 26-28. ISBN 970-18-3012-1. Also: Proceedings of the II Workshop of Artificial Intelligence, TAINA-99, 39-53. October. Edited by CIC. ISBN 970-18-3554-9. Also: CIC Technical Report, red series, No. 67, October. ISBN 970-18-3847-5 Also: Proceedings of the International Congress on Computing, CIC-99. Pedro Galicia, ed. CIC. ISBN 970-18-3697-9. In Spanish.

*125. Adolfo Guzmán, Jesús Olivares, Araceli Demetrio and Carmen Domínguez (2000) Interaction of purposeful agents that use different ontologies. Lecture Notes in Artificial Intelligence 1793, 557-573. MICAI 2000: Advances in A. I. Osvaldo Cairo, Enrique Sucar, Francisco J. Cantu (eds). Springer Verlag.2 Also: CIC Technical Report 46, Blue Series, January 2000. ISBN 970-18-4132-8.

126. Jesús Olivares, Carmen Domínguez, Araceli Demetrio, and Adolfo Guzmán. (2000) A model for agents in interaction spaces, and the specification of its interpreter. CIC Technical Report #7, red series, February. In Spanish.

128 Adolfo Guzmán, Jesús Olivares, Araceli Demetrio and Carmen Domínguez (2000). An introduction to purposeful agents sharing different ontologies. Invited paper for InterSymp 2000 Twelfth International Conference on Systems Research, Informatics and Cybernetics. July 31-August 4, 2000. Baden-Baden, Germany. The International Institute for Advanced Studies in Systems Research and Cybernetics, and Society for Applied Systems Research. This is an abridged version of paper #125.

*143. Guzmán, A., Domínguez, C., and Olivares, J. (2002) Reacting to unexpected events and communicating in spite of mixed ontologies In Lecture Notes in Artificial Intelligence 2313, 377-386, Springer Verlag, Heidelberg.2 ISBN 3-540-43475-5; ISSN 0302-9743. MICAI 2002, April.
*150. Guzman, A., and Olivares, J. (2004) Finding the Most Similar Con¬cepts in two Different Onto¬logies. Lecture Notes in Artificial Intelligence LNAI 2972, Springer-Verlag. 129-138. ISSN 0302-9743.

158. Jesus Olivares-Ceja, Adolfo Guzman. (2004) Multipurpose Agent Model and its Interpreter. Unpublished manuscript.

*159. Jesus M. Olivares-Ceja, Adolfo Guzman-Arenas. (2004) Concept similarity measures the understanding between two agents. Lecture Notes in Computer Science 3136 (Springer Verlag) 182-194.

*168. Adolfo Guzman-Arenas, Jesus M. Olivares-Ceja (2006) Measuring the understanding between two agents through concept similarity. Journal Expert Systems with Applications 30, 4 577-591, Elsevier.

170. Alma-Delia Cuevas, Adolfo Guzman-Arenas. (2005) Improving the Search in Ontology OB for the Concept most Similar to cA in OA. Unpublished manuscript.

173. Alma-Delia Cuevas, Adolfo Guzman. (2006) Automatic merging of knowledge using ontologies. Research in Computer Science, Special issue on Data Mining and Information Systems. ICDIS 06 (CIC),3-14. CIC-IPN México. ISSN 1870-4069.

175. Alma-Delia Cuevas, Adolfo Guzman. (2006) A language and algorithm for automatic merging of ontologies. 15th International Conference on Computing (CIC 06), 180-185. IEEE Computer Society. ISBN-13: 978-0-7695-2708-6; ISBN-10: 0-7695-2708-6. IEEE Computer Society Order Number P2708. Short version of #176.

*176. Alma-Delia Cuevas, Adolfo Guzman. (2008) A language and algorithm for automatic merging of ontologies. Chapter of the book Handbook of Ontologies for Business Interaction, Peter Rittgen, ed. IGI Global (formerly Idea Group Inc.), USA. 381-404.

177. Alma-Delia Cuevas, Adolfo Guzman. OM fuses Ontologies without Human Intervention. Unpublished manuscript.

180. Alma-Delia Cuevas, Adolfo Guzman-Arenas. (2007) Fusing knowledge with ontologies. Unpublished manuscript. In Spanish.

*181. Alma-Delia Cuevas, Adolfo Guzman-Arenas. (2009) Fusing interesting topics in the Web. Ingeniería, Investigación y Tecnología vol X, No. 1, pages 63-73.

183. Adolfo Guzman, Alma-Delia Cuevas. (2010) Automatic fusion of knowledge stored in ontologies. Intelligent Decision Technologies 4, 1, 5-19. DOI: 10.3233/IDT-2010-0066

185. Alma-Delia Cuevas, Adolfo Guzman-Arenas (2009) Automatic interchange of knowledge between business ontologies. Withdrawn from Proceedings of Intelligent Decision Support Technologies 2009, Japan. This is a shorter version, suited for a Congress, of paper #183.

187. Adolfo Guzman-Arenas, Alma-Delia Cuevas (2010) Knowledge accumulation through automatic merging of ontologies. Journal Expert Systems with Applications 37, 1991-2005 doi:10.1016/j.eswa.2009.06.078

194. Adolfo Guzman-Arenas and Ramon Brena. (2011) Approximate methods in Semantics for the Internet: An introductory map to Quantitative Semantics. In “Quantitative Semantics and Soft Computing Methods for the Web: Perspectives and Applications”, Ramon F. Brena and Adolfo Guzman-Arenas, editors. IGI Global.

197. Israel Toledo, Gilberto Martínez-Luna, Adolfo Guzman-Arenas. (2012) Automatic building of an ontology from a corpus of text documents using data mining tools. Journal of Applied Research and Technology 10, 3, 398-404.

199. Ramon Brena and Adolfo Guzman-Arenas. (2011) “Quantitative Semantics and Soft Computing Methods for the Web: Perspectives and Applications”, Ramon F. Brena and Adolfo Guzman-Arenas, editors. IGI Global.

200. Diana Villanueva, Alma-Delia Cuevas, Omar Juárez, Adolfo Guzmán-Arenas (2013). Using frames to disambiguate propositions, Journal Expert Systems with Applications 40, 598-610."

201 I. Toledo-Gómez, E. Valtierra-Romero, A. Guzmán-Arenas, A. Cuevas-Rasgado, L. Martínez-Segundo. (2014) AnaPro, tool for identification and resolution of direct anaphora in Spanish. Journal of Applied Research and Technology 12, 1, 14-40.

201a. Lopez-Yebra, Gabriela; Guzman-Arenas, Adolfo; Cuevas-Rasgado, Alma. (submitted) SERCDD. Knowledge extraction and representation from descriptive Spanish documents. Computational Intelligence.

207. Benina Velázquez, Jesús Olivares, Miguel Patiño, Adolfo Guzmán-Arenas (2015) Integración de fuentes heterogéneas de datos textuales. Polibits 51, Will be published probably in Jan-Jun 2015.

More Info: The above papers can be downloaded from several places.
* In academia.edu, under the page of "Adolfo Guzman Arenas" (https://ipn.academia.edu/AdolfoGuzman/ or academia.edu/AdolfoGuzman). Search for "Adolfo Guzman Arenas". You may be asked to suscribe. Try it, it is free!
* From my web page: http://alum.mit.edu/www/aguzman
* If above fails, write to me: aguzman (at) ieee (dot) org (that is @ all).
Also, those places will contain, probably, newer documents about the same topics.

CONFUSION AND INCONSISTENCY AMONG NON-NUMERIC VALUES

The confusion among two concepts (two linguistic values, two non-numeric values, such as dog and ... more The confusion among two concepts (two linguistic values, two non-numeric values, such as dog and cat, or Christian and Catholic) can be measured on a tree. If I ask for a dog and they give me a Doberman, there is some error, but not much. conf(Doberman, dog) will quantify it. It is not a distance, but it obeys the law of the triangle. The inconsistency of a set of assertions on an attribute whose values are non-numeric can also be measured. The range of both functions is between 0 and 1. These functions allow replacement, retrieval or use of "approximate" values (using an orange instead of a lemon) with controlled (measured) error. We report this work in the following documents.

146. Serguei Levachkine, A. Guzman-Arenas (2007) Hierarchy as a new data type for qualitative variables. Journal Expert Systems with Applications 32, 3, 899-910.

*151. Guzman, A., and Levachkine, S. (2004) Hierarchies Measuring Qualitative Variables. Lecture Notes in Computer Science LNCS 2945 (Computational Linguistics and Intelligent Text Processing), Springer-Verlag. 262-274. ISSN 0372-9743.

*152. Guzman, A., and Levachkine, S. (2004) Graduated errors in approximate queries using hie¬rarchies and ordered sets. Lecture Notes in Artificial Intelligence LNAI 2972, Springer-Verlag. 139-148. ISSN 0302-9743.

153. Serguei Levachkine and Adolfo Guzman-Arenas. (2004) Relatedness of the elements of a hierarchy partitioned by percentages. Unpublished manuscript.

153b. Serguei Levachkine and Adolfo Guzman-Arenas. (2004) Relatedness of the elements of a hierarchy through its universalization and specialization. Unpublished manuscript.

*164. Victor Polo de Gyves, Adolfo Guzman, Serguei Levachkine (2005) Extending databases to precision-controlled retrieval of qualitative information. Lecture Notes in Computer Science 3563 (Springer Verlag 2005) 21-32.

167. Sergei Levachkine, Adolfo Guzman-Arenas, Victor Polo de Gyves (2005) The semantics of confusion in hierarchies: from theory to practice. In Contributions to ICCS 05 13th International Conference on Conceptual Structures: common semantics for sharing knowledge, July 18-22 2005, Kassel, Germany. 94-107.

171a. Adolfo Guzman-Arenas, Sergei Levachkine and Victor-Polo de-Gyves, Measuring the confusion between two qualitative values organized in hierarchies. Submitted to Journal on Data Semantics.

174. Adriana Jiménez, Adolfo Guzman. (2006) Measuring inconsistency over a hierarchy of qualitative facts. Research in Computer Science, Special issue on Data Mining and Information Systems. ICDIS 06 (CIC),15-30. CIC-IPN Mexico. ISSN 1870-4069.

178. Adolfo Guzman-Arenas, Adriana Jimenez. Obtaining the consensus and inconsistency among a set of qualitative facts. Unpublished manuscript. (Outline of how to solve the first five problems in Inconsistency)

186. Adolfo Guzman-Arenas, Adriana Jimenez, (2010) Obtaining the consensus and inconsistency among a set of assertions on a qualitative attribute. Journal Expert Systems with Applications 37, 158-164. doi:10.1016/j.eswa.2009.05.010

189. Adolfo Guzman-Arenas, Alma-Delia Cuevas, Adriana Jimenez. (2011) The centroid or consensus of a set of objects with qualitative attributes. Expert Systems with Applications 38 (2011) 4908-4919.

193. Adolfo Guzman-Arenas and Alma-Delia Cuevas. (2011) Clustering via centroids a bag of qualitative values and measuring its inconsistency. Chapter of the book “Quantitative Semantics and Soft Computing Methods for the Web: Perspectives and Applications”, Ramon F. Brena and Adolfo Guzman-Arenas, editors. IGI Global.

198. Adolfo Guzmán-Arenas, Alma-Delia Cuevas, (2011) Quantitative Measures of confusion and inconsistency for symbolic values, unpublished manuscript."

BIBLIODIGITAL, A DISTRIBUTED DIGITAL LIBRARY (texts and images)

BiblioDigital (C) is a library of digital documents (texts, images, sound --just any binary file,... more BiblioDigital (C) is a library of digital documents (texts, images, sound --just any binary file, in fact) that resides in the web. It is formed by several "local" digital libraries (repositories). Looking for a document can be done by the words it contains, the author, the title, etc. Search occurs simultaneously in all the repositories. In fact, we avoid searching, keeping instead, an inverted index. BiblioDigital is described in the following documents:

*155. Adolfo Guzman-Arenas and Victor-Polo de Gyves. (2004) A distributed digital text accessing and acquisition system. BiblioDigital. (C) SoftwarePro International. Lecture Notes in Computer Science 3061, 274-283. (Springer Verlag 2004), ISSN 0302-9743.

163. Victor Polo de Gyves y Adolfo Guzmán (2005) Bibliodigital. Network to share distributed information. Bulletin of the National Systems of Statistics and Geographic Information 1, 1, 73-80. May. INEGI. In Spanish.

EVA --Educación virtual, cursos por internet, educación en línea

We have built EVA, a computer-based engine to deliver on line courses (virtual education, interne... more We have built EVA, a computer-based engine to deliver on line courses (virtual education, internet courses, virtual learning). It is described in the following documents:

"102. Gustavo Núñez, Leonid Sheremetov, Jesús Martínez, Adolfo Guzmán, Álvaro Albornoz. (1998) The EVA Teleteaching Project - the concept and the first experience in the development of Virtual Learning Spaces. In Teleteaching’98 Distance Learning, Training and Education: Proc. of the 15th IFIP World Computer Congress ‘The Global Information Society on the way to the next Millen¬nium’, Gordon Davies (ed). Vienna and Budapest, Aug. 31-Sept. 4, Part II, 769-778.

*105. Adolfo Guzmán and Gustavo Núñez (1998) Virtual Learning Spaces in distance education; tools for the EVA Project. Journal Expert Systems with Applications, 15, 34, 205-210. Oct. Elsevier.

121. Leonid Sheremetov, Gustavo Núñez, Adolfo Guzmán. (1999) Artificial Intelligence and computational agent technologies in education: The EVA Project. Academia, year 4, No. 23, 45-53 (First part), Sep.-Oct. In Spanish.

122. Leonid Sheremetov, Gustavo Núñez, Adolfo Guzmán. (1999) Artificial Intelligence and computational agent technologies in education: The EVA Project. Academia, year 4, No. 24, 58-63 (second part), Nov.-Dic. In Spanish.

132. Adolfo Guzmán and Leonid Sheremetov (2000) Applying EVA to tailored virtual, distance, on-line education via Internet. CIC Technical Report, blue series, No. 73.

*133. Leonid Sheremetov and Adolfo Guzmán (2002) EVA: An Interactive Web-Based Collaborative Learning Environment. Computers and Education 39, 161-182. Special issue on “Multimedia in Engineering Education and Training.” Elsevier Science.
135. Gustavo Núñez, Leonid Sheremetov, Adolfo Guzmán (2000) The EVA Project. Academia 5, 28, 55-62, July-August. In Spanish."

Data mining, data bases, business intelligence, big data

Our work in data bases (and their use or exploitation), information management, information syste... more Our work in data bases (and their use or exploitation), information management, information systems, and data mining is described in these documents:

88c. Guzmán, A. (1994) ANASIN. Intelligent analyzer and synthetizer of information. Technical Report. User Manual. IDASA. Mexico City. In Spanish.

88d. A. Guzmán Arenas, Gilberto Martínez Luna. (1994) Design of the summarizer/transmitter system for CFE. IDASA, Mexico City. In Spanish.

*89. Guzmán, A. (1995) K-D trees as supervised classifiers and to replace expert systems. Proceedings of the International Congress on Pattern Recognition. ICIMAF, Havana, Cuba. In Spanish.

*92. Guzmán A. (1996) Data miners. Soluciones Avanzadas No. 34, Mexico City, June 15. Also: ARCHIPIÉ¬LAGO. Vol. 2 No. 9, pages 19ff. Nov.-Dec. In Spanish.

*97. Guzmán A. (1997) State of the art and the practice in Data Mining. Analysis and Critic. Proceedings of the II Iberoamerican Workshop on Pattern Recognition, 367-376. Havana, Cuba. March 24-28. Also: CIC Technical Report Informe Técnico del CIC, green series, No. 3, March 1998. In Spanish.

107. Adolfo Guzmán, Gilberto Martínez Luna (1999) Data mining with search for behavioral patterns. Bulletin of Informatics Policies, Year XXII, 2, 13-30. INEGI, Aguascalientes, Mexico. Also: CIC Technical Report, red series, No. 16, March 1998. In Spanish.

109. García, A., Guzmán Arenas, A., Martínez Luna, G., and Núñez Esquer, G (1998) Supervised classification. Induction of decision trees. K-D algorithm. Proceedings of the International Congress in Computing. CIC 98, 602-614. Mexico City. Nov. ISBN 970-18-1916-0. In Spanish.

110. Guzmán, A (1999) Tools for the distributed enterprise. Proceedings of the Forum “Computing, from theory to practice”, pages 5-14. May 26-28. CIC. ISBN 970-18-3012-1. In Spanish.

112. García, A., Guzmán Arenas, A., amd Martínez Luna, G. (1999) Anasin: Data mining with search for behavioral patterns. Proceedings of the Forum “Computing, from theory to practice.” Pages 15-28. Mexico City, May 26-28. ISBN 970-18-3012-1 Also: Proceedings of the International Congress in Computing CIC-99. Pedro Galicia, ed. ISBN 970-18-3697-9. Pages 528-540. Same publication as #107 (duplicated citation). In Spanish.

113. Guzmán, A. (1999) Data mining and data warehousing. Proceedings of the National Symposium on Computation SICOM 99, 5-13. Villahermosa, Tabasco. June 7-11. ISBN 970-18-3046-6. In Spanish.

136. Gilberto Martínez, Adolfo Guzmán (2000). Search for behavioral patterns in data cubes. 2nd International Workshop on Data Mining, Colegio de Postgraduados y Centro de Investigación en Computación. Texcoco, Edo. Mex., México. Págs. 163-179, septiembre. In Spanish.

147. Mirna López, Antonio Martínez Alcántara, Adolfo Guzmán (2002) Heuristic rules: alternatives for refining interesting association rules. Unpublished manuscript, Mayo 2002. In Spanish.

148. Martínez Luna G. L., Guzmán Arenas A., Mikhail Alexandrov. (2004) Incremental model of mining with curve fitting. In The IASTED International Conference on Databases and Applications, DBA 2004, as part of the Twenty-Second IASTED International Multi-Conference on Applied Informatics. Innsbruck, Austria, February 17-19, 2004.

149. Martínez Luna G. L., Guzmán Arenas A., Alexandrov M. (2003) Data mining model with curve fitting. Proceedings of the International Congress in Computing CIC-2003. Pages 73-82, ISBN 970-36-0098-0. In Spanish.

149b. Martínez Luna G. L., Guzmán Arenas A., Alexandrov M. (2003) Data mining model with curve fitting. X International Congress of Research in Computer Science CIICC 2003, Oaxtepec, Morelos. CE191. Eduardo Godínez, Gilberto Martínez-Luna, Adolfo Guzman-Arenas, (2010) SATC Tool for Analysis of the Evolution of Scientific Knowledge. II International Conference on Computer Technology and Development, ICCTD 2010, 2-4Nov., pages 42-46.
NIDET, SEP. Pages 5-14. ISBN 968-5823-02-2. In Spanish.

160. Martínez-Luna G. L., Guzmán-Arenas A, Alexandrov-Aronovich M. (2004) Incremental data mining model with curve fitting in data cubes. Unpublished manuscript. In Spanish.

161. Martínez-Luna G. L., Guzmán-Arenas A., Sossa-Azuela H, Vázquez-Gallo M., Cedeño-Nicolas J. (2004) Corroboration and formation of theories from antropological and archeological data. Applications of data analysis . Unpublished manuscript. In Spanish.

162. Martínez-Luna G. L., Guzmán-Arenas A., Vázquez-Gallo M., Camacho-González G.M., Hernández-García O., Cedeño-Nicolas J. (2004) Information systems for queries to archeological research. Unpublished manuscript. In Spanish.

166. Adolfo Guzman-Arenas. (2004) Data mining model with curve fitting. Proceedings of the IV Meeting of the Mexican Mathematics Society. Page 125. Abstract of #165. In Spanish.

179. Alejandro Botello, Adolfo Guzman-Arenas, Renato Barrera. (2007) Query resolution in independent databases by partial integration. International Congress on Data Mining and Information Systems, ICDIS 2007. CIC-IPN, Mexico.

*182. Adolfo Guzman, Claudia Nogueron, Alicia Martinez. (2008) Generation of interesting knowledge using data mining: a user-oriented approach. Polish Journal of Environmental Studies, vol. 17, No. 4C, pages 116-123.

184. Gilberto Martinez-Luna, Adolfo Guzmán-Arenas. (2008) Antecumen. Prototype of a tool for data analysis with cubes in main memory. World Conference on Information and Computing Technology 2008. In Spanish.

191. Eduardo Godínez, Gilberto Martínez-Luna, Adolfo Guzman-Arenas, (2010) SATC Tool for Analysis of the Evolution of Scientific Knowledge. II International Conference on Computer Technology and Development, ICCTD 2010, 2-4Nov., pages 42-46.

204. Rodolfo Vilchis, Gilberto Martínez, Adolfo Guzman-Arenas (submitted). Visualization of the largest number of properties of multivariate objects using meta-dimensional grouping. Expert Systems with Applications.

Clasitex -- text analysis. What are the main topics of a written document?

How to find the main topics or themes contained in a written document. What a document is about. ... more How to find the main topics or themes contained in a written document. What a document is about. It requires disambiguation of nouns and verbs. Anaphora (third person pronouns) resolution. Our work in this are is contained in the following documents:

98. Guzmán A. (1997) Finding the main topics in a Spanish article. Soluciones Avanzadas. Vol. 5, no. 47, pages 58-63, part I, July 15. Part II: vol. 5, no. 49, pages 66-71, September 15. Also in: Proceedings of the International Symposium in Computation 36-45, CIC. A short version of this article appears in Bulletin of the Mexican Society of Computer Science I, 1, 14-16, winter of 1999. Also: CIC Technical Report, blue series, No. 7, March 1998. In Spanish.*99. Guzmán, A. (1998) Finding the main themes in a Spanish document. Journal Expert Systems with Applications, Vol. 14, No. 1/2, 139-148, Jan./Feb.

99b. Adolfo Guzman. (1998) Clasitex+: A semantic analyzer for Spanish articles. InterSymp’98, 10th International Conference on System Research, Informatics and Cybernetics. Baden-Baden, Germany, 1998.

*101. Beatriz Beltrán Martínez, Adolfo Guzmán Arenas, Francisco Martínez Trinidad, José Ruiz Shulcloper. (1998) Clasitex+: a tool for text analysis. Proceedings of the III Iberoamerican workshop on Pattern Recognition, TIARP-98, 369-379. CIC. Also: CIC Technical Report, green series, No. 22, ISBN 970-18-1549-1. In Spanish.

*101b. Martínez-Trinidad J.F., Beltrán-Martínez B., Guzmán A.A., & Ruíz-Shulcloper J. (1998). CLASITEX+: A Tool for Knowledge Discovery from Texts. Lecture Notes in Artificial Intelligence 1510: 459-467. Springer-Verlag. Also in: Proceedings of the Principles of Data Mining and Knowledge Discovering Conference.

108. Alexander Gelbukh, Grigori Sidorov, Adolfo Guzman (1999) Text categorization using a hierarchical topic dictionary. IJCAI-99, International Joint Conference on Artificial intelligence, Workshop on Text Mining, 234-246, Stockholm, Sweden, July 31 to August 6.

115. A. Gelbukh, G. Sidorov, and A. Guzmán-Arenas. (1999) A method of describing document contents through topic selection. Proc. Of the 6th International Symposium on String Processing and Information Retrieval, SPIRE 99 and CRIWG 99. Cancun, Mexico, September 22-24. Pages 73-80. IEEE Computer Society Order No. PR00268. (IEEE Computer Society, Los Alamitos, CA) IEEE Orden Plan Catalog No. PR00268. ISBN 0-7695-0268-7. Library of Congress 99-64139.

*116. A. Gelbukh, G. Sidorov, and A. Guzmán-Arenas. (1999) Use of a weighted topic hierarchy for document classification. Text, Speech, Dialogue, 133-138. Pilsen, Chech Republic, September 13-17. Also: In Lecture Notes in Artificial Intelligence 1692, Text, Speech and Dialogue, Václav Matousek, Pavel Mautner et al (eds). Springer Verlag.2 Pages 133-138. Abstract: http://link.springer.de/link/service/series/0558/bibs/1692/16920133.htm

117. A. Gelbukh, G. Sidorov, and A. Guzmán-Arenas. (1999) Document comparison with a weighted topic hierarchy. DEXA-99, 10-th International Conference on Database and Expert System applications, Workshop on Document Analysis and Understanding for Document Databases, 566-570. Florence, Italy, August 30 to September 3. IEEE Computer Society, Los Alamitos, CA.

118. A. Gelbukh, G. Sidorov, A. Guzmán-Arenas. (1999) System for exploring and classifying documents with a dictionary of terms. Article in Russian. Proceedings of Knowledge, Dialogue, Solution. Yalta, Ukraine, September 13-18. (KDS-99).

124. Manuel Montes-y-Gómez, Aurelio López-López, Alexander F. Gelbukh, Grigori Sidorov, Adolfo Guzmán-Arenas. (1999) Text Mining: new techniques and applications. Text Mining Workshop at IJCAI-99, the Sixteenth International Joint Conference on Artificial Intelligence, Stockholm, Sweden, 31 July - 6 August 1999. Also: CIC Technical Report No. 34, Blue Series, August.

124b. A. Gelbukh, G. Sidorov, and A. Guzmán-Arenas. (2000) Topical summarization with a weighted concept tree. Selected Papers of CIC 1999, A. Guzmán, R. Menchaca (eds). CIC. ISBN 970-18-4250-2. Pages 45-52. This is a revised version of paper # 116

139. Alexander Gelbukh, Grigori Sidorov, and Adolfo Guzman-Arenas. (2001) Document Indexing With a Concept Hierarchy. NDDL-2001, 1st International Workshop on New Developments in Digital Libraries at ICEIS-2001, International Conference on Enterprise Information Systems, Setúbal, Portugal. Also in New Developments in Digital Libraries, Pedro Isaías (Ed.) ICEIS Press Setúbal, Portugal. Pages 47-54. ISBN 972-98050-4-0

144. A. Gelbukh, G. Sidorov, A. Guzman-Arenas. (2002) Simple Method for Hierarchical Conceptual Indexing of Documents Using Relational Data Model. In Advances in Information Science and Soft Computing, Alexander Zemliak, Nikos E. Mastorakis (Eds.), WSEAS Press. Pages 134-139. ISBN 960-8052-60-2. Conference: 2nd WSEAS ISA (Information Science and Applications 2002). Also: CIC Technical Report 101 (Red), May 2002.

*145. Alexander Gelbukh, Grigori Sidorov, Adolfo Guzmán-Arenas. (2002) Relational Data Model in Document Hierarchical Indexing, Lecture Notes in Computer Science 2389, 259-269.

*169. A. Gelbukh, G. Sidorov, and A. Guzman-Arenas. (2005) Document Indexing with a Concept Hierarchy. Computación y Sistemas VIII, No. 4, 281-292."

170. Alma-Delia Cuevas, Adolfo Guzman-Arenas. (2005) Improving the Search in Ontology OB for the Con-cept most Similar to cA in OA. Unpublished manuscript.

200. Diana Villanueva, Alma-Delia Cuevas, Omar Juárez, Adolfo Guzmán-Arenas (2013). Using frames to disambiguate propositions, Journal Expert Systems with Applications 40, 598-610.

Pattern Recognition, classification, clustering

Finding patterns or repetitive structures in data. Pattern recognition, supervised classifiers, u... more Finding patterns or repetitive structures in data. Pattern recognition, supervised classifiers, unsupervised classifiers (clustering). Remote sensing. Our work is reported in these documents:

26. Guzmán, A. (1975) P.R. Project. Report of activities and results. Stage 0. Technical Report P.R.-72-2A, October. IIMAS. In this report I describe the Remote Sensing Project. In Spanish.

27. Guzmán, A. (1975) Remote sensing by computers: Equipment, programs, and applications. Technical Report PR-75-2, November. IIMAS. In Spanish

29. Guzmán, A. (1976) Applications of Pattern Recognition to Computer Analysis of Aerial Images. Proceedings of MEXICON 76, IEEE. Mexico City. In Spanish.

*31. Guzmán, A. Seco, Rosa and Sánchez, Victor Germán. (1976) Analysis of LANDSAT Images for Crop Identification in Mexico. Proceedings of the International Conference on Information Science and Systems, 361-366. University of Patras, Greece. August 19-24. Results are described of the identification of wheat, cotton and other crops in tne NortEast of Mexico, in Stage I of Project PR. Also: Technical Report Vol. 7 No. 135. IIMAS.

32. Guzmán, A. (1976) Remote Sensing in UNAM. Proceedings of the II Meeting for use of satellite data. Comisión Nacional del Espacio Exterior (National Outer Space Committee), SCT. Mexico City. It describes the efforts and research in Remote Sensing and Image Processing in UNAM. In Spanish.

32b. R. Barrera, J. Becerra, R. Castillo, M. Díaz, V. Guerra, A. Guzmán, A. Jinich, J. López, E. Llera, J. Ludlow, R. Seco, V. Sánchez. (1977) Detection and quantifying of agricultural resources through computer analysis of images taken from airplane and satellite. Technical Report 8, No. 157, IIMAS. In Spanish.

*37. Barrera, R., Guzmán A., Ginich, A., Radhakrishnan, T. (1981) Design of a High Level Language (L) for Image Processing. In Languages and Architectures for Image Processing, M. J. B. Duff y S. Levialdi (eds.). Academic Press, 25-40 Also available as a Technical Report PR-78-22 (Orange Series 165), IIMAS.

96b. A. Guzmán, J. Ruiz, H. Sossa, M. Lazo, Juan Luis Díaz de León (eds). (1997) Proc. II Iberoamerican Workshop on Pattern Recognition, TIARP 97. CIC. ISBN 968-29-9892-1. In Spanish.

*100. Ruiz Shulclóper, José; Guzmán, A. and Martínez Trinidad, Francisco. (1999) Logic-combinatorial apprach to Pattern Recognition: Supervised classifiers. Editorial Politécnica. ISBN 970 18 2384 1.

*127. Francisco Martínez-Trinidad and Adolfo Guzmán. (2001) The logical combinatorial approach to Pattern Recognition, an overview through selected works. Pattern Recognition 34 (2001), 741-751. Also: CIC Technical Report #91, blue series, ISBN 970-18-6469-7

193. Adolfo Guzman-Arenas and Alma-Delia Cuevas. (2011) Clustering via centroids a bag of qualitative values and measuring its inconsistency. Chapter of the book “Quantitative Semantics and Soft Compu-ting Methods for the Web: Perspectives and Applications”, Ramon F. Brena and Adolfo Guzman-Arenas, editors. IGI Global.

205. Javier Arellano-Verdejo, Adolfo Guzmán-Arenas, Salvador Godoy-Calderón and Ricardo Barrón Fernán-dez. (2014) Efficiently Finding the Optimum Number of Clusters in a Dataset with a new Hybrid Cellular Evolutionary Algorithm. Computación y Sistemas vol. 2, No. 4, April-June, pages 313-328

206. Javier Arellano-Verdejo, Enrique Alba, Adolfo Guzman-Arenas, Salvador Godoy-Calderon. Efficiently Finding the Optimum Number of Clusters in a Dataset with a new Hybrid Differential Evolution Algorithm: DELA. Submitted to Soft Computing.

Parallel hardware design, construction of multiprocessors

Design of digital hardware. Parallel processing. Computer architectures. Design and construction ... more Design of digital hardware. Parallel processing. Computer architectures. Design and construction of a data flow machine that processes Lisp programs in parallel. Design of a computer to measure flow of fluids in large pipes. Our work is reported here.

*30. Guzmán, A. and Segovia, Raymundo. (1976) A Parallel Reconfigurable LISP Machine. Proceedings of the International Conference on Information Science and Systems, 207-211. August 19-24. University of Patras, Greece. It describes the architectures and features of a new type of computer, that uses Lisp as its machine language and performs as much parallel processing as the program flow allows. Also available as a Technical Report Vol. 7, No. 133. IIMAS.

*36. Guzmán, A. (1979) Heterarchical reconfigurable architectures for parallel digital processing with high level languages. Proceedings of the International Conference in Informatics and Office Equipment. Mexico City. In Spanish.

38. Guzmán A. (1979) Heterarchical architectures for parallel processing of digital images. AHR Technical Report AHR-79-3 (PR-79-23), IIMAS. Also: Proceedings of the II International Seminar on the use of Remote Sensing. Mexico City.

*42. Guzmán A. (1979) Distributed computing as an alternative for the future. Informática 46, 23-32. Also: Technical Report AHR-79-6, IIMAS. Also: Teledato, opus 132, IX-1982, 23-31. Publicaciones Telecomex. In Spanish.

45. Guzmán A., Lyons, L. , et. al. (1980) The AHR computer: Construction of a processing with Lisp as its main language. Technical Report AHR-80-10, IIMAS. In Spanish.

*47. Guzmán A. (1981) A Parallel Heterarchical Machine for High Level Language Processing. In Languages and Architectures for Image Processing. M. J. B. Duff y S. Levialdi (eds). Academic Press. 230-244. Also: Proc. 1981 International Conference on Parallel Processing, 64-71.

*48. Guzmán A. (1981) A Heterarchical Multi-microprocessor Lisp Machine. Proceedings of the 1981 IEEE Workshop on Computer Architectures for Pattern Analysis and Image Database Management. Hot Springs, VA. 309-317. IEEE Publication #81CH-1697-2.

*49. Guzmán A., Lyons, L. et. al. (1981) Construction of a multiprocessor that uses Lisp. Part I: Theory of operation of an AHR machine. Proceedings of the VII Congress of the National Academy of Engineering (Mexico). Oaxaca, Mexico. In Spanish.

*50. Guzmán A., Lyons, L. et. al. (1981) Construction of a multiprocessor that uses Lisp. Part II: Architecture of the AHR Machine. Proceedings of the VII Congress of the National Academy of Engineering (Mexico). Oaxaca, Mexico. In Spanish.

*51. Guzmán, A. (1982) Mexican Computer for Parallel Processing. Información Científica y Tecnológica, Vol. 3, No. 48, 42-43. In Spanish.

*52. Guzmán, A. (1982) A multi-microprocessor that executes pure Lisp in parallel. Proc. 15th Hawaii International Conference on System Sciences, Vol. 1, 368-377.

53. Norkin, Kemer and Guzmán, Adolfo. (1982) Design and construction of an heterarcnical parallel machine. Final Report of Project AHR. Technical Report AHR-82-21, AHR Laboratory, IIMAS.

54. Guzmán, A.; Gerzso, J. Miguel; Norkin, Kemer B. and Kuprianov, Boris. (1982) The PS-2000 SIMD computer: functional description and instruction set. Technical Report AHR-82-23, AHR Laboratory, IIMAS.

*56. Guzmán A., Gerzso, M., Norkin, K. B., and Vilenkin, S. Y. (1985) The Conversion via Software of a SIMD Processor into a MIMD Processor. PS-2000, an Array Processor, becomes AHR, a general purpose Lisp machine. In Computer Architectures for Spatially Distributed Data, H. Freeman and G. G. Pieroni (eds), Springer-Verlag. 121-137.

61. Norkin, K. B., and Guzmán, A. (1985) Functional specifications and preliminary design of HECTOR, a heterarchy of microprocessors. Technical Report, EE Dept., CINVESTAV. In Spanish.

63. Guzmán A.; Gerzso, M.; Norkin, K.; Logunova, N.; Vilenkin, S.; and Kuprianov, B. (1983) Functional design of a Lisp interpreter for the PS-2000 SIMD Computer. Technical Report AHR-83-24, IIMAS.

*66. Guzmán A. (1982) A Multiprocessor that executes Pure Lisp in Parallel. Proc. 15th Hawaii International Conference on System Sciences, V. 1, 368-377.

*67. Guzmán A. (1988) AHR: A Parallel Computer for Pure Lisp. In Parallel Computation and Computers for Artificial Intelligence, J. S. Kowalik (ed.), 201-222. Kluwer. Also: MCC Technical Report PP 355 86.

68. McGehearty, P., and Guzmán A. (1986) Hierarchical Parallel Architectures for Symbolic Processing. MCC. Technical Report PP-387-86.

69. Guzmán A., Krall, E. J., McGehearty, P. F., and Bagherzadeh, N. (1987) Measurement of Symbolic Applications on a Parallel Architecture. Technical Report PP-076-87, MCC.

*70. Guzmán A., Krall, E. J., McGehearty, P. F., and Bagherzadeh, N. (1987) Performance of Symbolic Applications on a Parallel Architecture. Technical Report PP-163-87, MCC. Also: International Journal of Parallel Programming, 16, 3, 183-214, June.

*71. Guzmán A., and Hermenegildo, M. (1987) Constructs and Evaluation Strategies for Intelligent Speculative Parallelism –Armageddon revisited. Technical Report PP-220-87, MCC. Also: Proceedings of the ACM 1988 Sixteen Annual Computer Science Conference 558-566, Atlanta, Ga. February.

*75. Guzmán A., Krall, E. J., McGehearty, P.F. y Bagherzadeh, N. (1987) The Effect of Application Characteristics on Performance in a Parallel Architecture. Technical Report ACA-262-87, MCC. Also: Proceedings of the Twenty First Hawaii International Conference on System Sciences, January 1988. Honolulu, Hawaii.

*76. Ramón D. Acosta and Adolfo Guzmán. (1991) An environment for functional and performance prototyping of parallel programs. Collected Papers of the 1991 Workshop on Hardware/Software CoDesign, XIII, International Conference on Software Engineering, Technical Report No. MCC-CAD-156-91, MCC, May.

134. Adolfo Guzman (2000) Families of “any time” algorithms and methods to compose them. Proceedings of the International Congress on Computing, CIC 2000. November. Pages 30-43. ISBN 970-18-5540-X. In Spanish.

156. Adolfo Guzmán. (2003) Design of a flow computer using the DSP 5509. Report AGA 03.02.28. Project 280157. Centro de Investigación Aplicada y Tecnología, A.C. (CIATEQ, or Center for Applied Research and Technology), Querétaro, Mexico. In Spanish.

157. Adolfo Guzmán. (2003) Flow computer with two processors DSP “Texas Instruments” model TMS320C5509A. Report AGA 03.06.26, Project 280157. It replaces Report AGA 03.06.05. CIATEQ, Querétaro, México. In Spanish.

*171. Adolfo Guzmán Arenas (2008) Design and construction of parallel Mexican computers. In “Descubrimiento y Aportaciones Científicas Mexicanas en el Siglo Veinte” (Discovers and scientific Mexican contributions during the XX Century), Octavio Paredes, Sergio Estrada Orihuela (Eds.), Fondo de Cultura Económica. 350-359. ISBN 978-968-16-8634-5. In Spanish.

Geographic Information Systems, Geoprocessing, Map representation, digital terrain models

Geographic data bases, geographic information systems, geoprocessing. Digital terrain models. Our... more Geographic data bases, geographic information systems, geoprocessing. Digital terrain models. Our work is described in these documents:

"*23. Guzmán, A. and Bribiesca, E. (1974) Use of a geographic data base. Proceedings of the I Panamerican Congress and III National Congress of Photogrammetry, Photointerpretation and Geodesics. Mexico City. In Spanish.

24. Bribiesca, E., and Guzmán, A. (1974) User’s manual for the exploitation of a geographic data base. Technical report CCAL 74 17, IBM Latin American Scientific Center. Mexico City. In Spanish.

25. Guzmán, A. (1975) Use of computers for regional planning. Proceedings of the 1st Annual Meeting of the National Academy of Sciences (Mexico). It describes our experiences in regional planning using CETENAL geographic data base. (See reference 24). In Spanish.

*35. Gómez, Dora and Guzmán, A. (1979) A digital Model for Three-dimensional Surface Representation. Journal of Geoprocessing 1, 53-70. Elsevier Publishing Co. (This journal no longer exists). Also: Proceedings of an International Conference “Computer Mapping for Resource Analysis”, a CoGeoData Conference. Kansas Geological Survey, University of Kansas, and Instituto de Geografía de la UNAM, 183-204, Mexico, 1978.

*43. Guzmán A. (1980) Reconfigurable Geographic Data Bases. In Pattern Recognition in Practice. E. S. Gelsema and Laveen N. Kanal (eds), 99-112, North Holland."

188. Ernesto Bribiesca, Adolfo Guzman. (2012) Enclosing Trees. Pattern Analysis and Applications 15:1-17.

192. Ernesto Bribiesca, Adolfo Guzman-Arenas, Luis A. Martínez. (2011) Representation of 3-D objects using enclosing trees. In Computational Intelligence Techniques in Handling Image Processing and Pattern Recognition, S. Ramakrishnan & Ibrahiem M. M. El Emary (Eds.), Lambert Academic Publishing, Germany. 227-252.

Form comparison. Quantifying the similarity between two shapes. Shapes of lines, of surfaces, of solid objects. Discrete shapes. Voxelized objects

Measuring the similarity between two shapes or forms. Shape comparison. Shape description. Shapes... more Measuring the similarity between two shapes or forms. Shape comparison. Shape description. Shapes of lines. Shapes of surfaces. Shapes of solid objects. Voxelized objects. Polyhedra. Polygons. Storing shapes economically. Shape unicity. Our work is described in these documents:

"*33. Bribiesca. E., y Guzmán, A. (1978) Shape Description and Shape Similarity Measurement for Two-dimensional Regions. Proceedings of the Fourth International Conference on Pattern Recognition, Kyoto, Japan. 608-612. Also available as Technical Report PR-78-18 (Orange Series 9, 166), IIMAS. Also: Journal of Geoprocessing, Vol. 1, No. 2, 129-144 (1980) (This journal no longer exists).

34. Bribiesca, E. and Guzmán, A. (1978) Shape numbers: a notation to describe pure form and to measure resemblance and difference among shapes. Technical Report PR-78-20 (Orange Series 178), IIMAS. In Spanish.

*39. Bribiesca, E. and Guzmán A. (1980) How to Describe Pure Forms and how to Measure Differences in Shapes using Shape Numbers. Invited paper to the IEEE Conference on Pattern Recognition and Image Processing. Chicago, USA. Also in Pattern Recognition, Vol 12, No. 2, 101-112. This article won the Seventh Annual Pattern Recognition Award, awarded by the Pattern Recognition Society in November 1981, as the best article of the year.

72. Guzmán A. (1987) Canonical Shape description for 3-D Stick Bodies. Technical Report ACA-254-87, MCC.

73. Guzmán, A. (1987) Shape Description in CYC. Technical Report AI-x-87(P), Artificial Intelligence Laboratory, MCC. MCC/ACA Confidential and Proprietary.

188. Ernesto Bribiesca, Adolfo Guzman. (2012) Enclosing Trees. Pattern Analysis and Applications 15:1-17.

203. Luis Martinez, Ernesto Bribiesca, Adolfo Guzman. (2013). Voxel-based object representation by means of edging trees. 17th International Conference on Image Processing, Computer Vision, & Pattern Recognition, July 22-25, Las Vegas, USA.

Digital image processing. Image understanding. Identifying objects in a visual image or scene

Scene analysis. Image understanding. Image processing. What are the objects in a given scene or i... more Scene analysis. Image understanding. Image processing. What are the objects in a given scene or image? These documents describe our work in this area.

8. Guzmán, A. (1966) Polybrick: Adventures in the domain of parallelepipeds. Memorandum Project MAC, MAC M 308 (AI Memo 96) MIT. Mayo.

9. Guzmán, A. (1967) Scene Analysis Using the Concept of Model. Report 67-0133, Computer Corporation of America. Cambridge, Mass., USA. January. AD-652-017.

10. Guzmán, A. (1967) A primitive Recognizer of Figures in a Scene. Memorandum Project MAC, MAC M 342 (AI Vision Memo 119) MIT, January.

11. Guzmán, A. Some Aspects of Pattern Recognition by Computer. (1967) Master’s Thesis, Department of Electrical Engineering, MIT., February. AD-656-041. Also available as a Project MAC Technical Report, MAC TR 37.

15. Guzmán, A. (1967) Decomposition of a Visual Scene into Bodies. Project MAC Memorandum MAC M 357 (AI Memo 139). MIT, September.

*16. Guzmán, A. (1968) Decomposition of a Visual Scene into Three-dimensional Bodies. Proceedings of the AFIPS Fall Joint Computer Conference. Vol. 33, First Part. 291-304. December. Also available as Project MAC Memorandum MAC M 391 (AI Memo 161). Also in Computer Methods in Image Analysis. J. K. Aggarwal, R. O. Duda y A. Rosenfeld (eds.). IEEE Press. 1977. 324-337.

*17. Guzmán, A. Analysis of Scenes by Computer: Recognition and Identification of Objects. In Interpretation and Classification of Images. Grasselli, Antonio (ed.) Academic Press. 243-276. Chapter 12.

*18. Guzmán, A. (1969) Object Recognition: Discovering the Parallelepipeds in a Visual Scene. Proceedings of the Second Hawaii International Conference on Systems Sciences. Universidad de Hawaii, Honolulu, Hawaii, 479-482. January. Western Periodicals Co.

19. Guzmán, A. (1968) Computer Recognition of Three-dimensional Objects in a Visual Scene. Ph.D. Thesis, Electrical Engineering Department, M.I.T., December. Also available as Project MAC Technical Report MAC TR 59. 287 pages. AD-692-200.

*20. Guzmán, A. (1970) Analysis of Curved Line Drawings Using Context and Global Information. In Machine Intelligence VI. D. Michie y B. Meltzer (eds.), Edinburg University Press. 325-375. ISBN 0 85224 195 X.

29. Guzmán, A. (1976) Applications of Pattern Recognition to Computer Analysis of Aerial Images. Proceed-ings of MEXICON 76, IEEE. Mexico City. In Spanish.

*31. Guzmán, A. Seco, Rosa and Sánchez, Victor Germán. (1976) Analysis of LANDSAT Images for Crop Iden-tification in Mexico. Proceedings of the International Conference on Information Science and Sys-tems, 361-366. University of Patras, Greece. August 19-24. Results are described of the identification of wheat, cotton and other crops in tne NortEast of Mexico, in Stage I of Project PR. Also: Technical Report Vol. 7 No. 135. IIMAS, 1976.

*33. Bribiesca. E., y Guzmán, A. (1978) Shape Description and Shape Similarity Measurement for Two-dimensional Regions. Proceedings of the Fourth International Conference on Pattern Recognition, Kyoto, Japan. 608-612. Also available as Technical Report PR-78-18 (Orange Series 9, 166; 1978), IIMAS. Also: Journal of Geoprocessing, Vol. 1, No. 2, 129-144 (1980) (This journal no longer exists).

*37. Barrera, R., Guzmán A., Ginich, A., Radhakrishnan, T. (1981) Design of a High Level Language (L) for Image Processing. In Languages and Architectures for Image Processing, M. J. B. Duff y S. Levialdi (eds.). Academic Press, 25-40. Also available as a Technical Report PR-78-22 (Orange Series 165; 1981), IIMAS.

72. Guzmán A. (1987) Canonical Shape description for 3-D Stick Bodies. Technical Report ACA-254-87, MCC.

188. Ernesto Bribiesca, Adolfo Guzman. (2012) Enclosing Trees. Pattern Analysis and Applications 15:1-17.

Languages for non-numerical manipulation.

Symbol manipulation languages. Programming languages. Our work is described in these documents: ... more Symbol manipulation languages. Programming languages. Our work is described in these documents:

1. Guzmán, A. (1964) The structure of the Fortran Language. Proceedings of the I Latin American Congress of Electronic Computation in Education CeNaC. Mexico. In Spanish.

4. Guzmán, A. (1965) CONVERT-Design of a language for symbol manipulation, and its corresponding interpreter. (In Spanish, English and Braille). B. Sc. thesis. ESIME-IPN.

*5. Guzmán, A. (1966) TRACE and HUSMEA: two Lisp functions for debugging. Cien-cias de la Información y Computación 1, June. In Spanish.

6. Guzmán, A. and McIntosh, H.V. (1966) A Program Feature for CONVERT. Memorandum MAC M 305 (AI Memo 95). Project MAC, MIT. April.

*7. Guzmán, A. and McIntosh H.V. (1966) CONVERT. Communications of the ACM 9, 8, 604-415. August. Also available as Memo MAC M 316 (AI Memo 99), M.I.T. June 1966.

12. McIntosh, H. V. and Guzmán, A. (1967) A Miscellaney of CONVERT Programming. Project MAC Memorandum MAC M 346 (AI Memo 130), MIT. April.

*13. Guzmán, A. and McIntosh H.V. (1967) Comments on ‘All Paths Through a Maze’. Proceedings of the IEEE. Vol. 55 No. 8, 1525-27. August.

*14. Guzmán, A. and McIntosh, H.V. (1969) Patterns and Skeletons in CONVERT. In The Programming Language LISP: Its Operations and Applications, Vol. II; Berkeley, E. C. y Bobrow, D. G. (Eds). MIT Press, Cambridge, Mass.

77. Guzmán, A. (1991) Unified Step Language (USL). Technical Report, International Software Systems, Austin, Tx.

78. Guzmán, A. (1991) Process supervision, control and evaluation using an augmented SDDS. Technical Report, International Software Systems, Austin, Tx.

79. Guzmán, A. (1991) Compilation of schema objects into flat Ada structures. Technical Report, International Software Systems, Austin, Tx.

80. Guzmán, A. (1991) Flexibility and efficiency via operations' particularization. Technical Report ISSI-91-005, International Software Systems, Austin, Tx.

81. Guzmán, A. (1991) Graphic queries and updates for 2-step. Technical Report ISSI-91-003, International Software Systems, Austin, Tx.

*82. Guzmán A., and Yin, Weiping. (1991) Interconnection of software tools or applications, considered as black boxes. Proceedings of the Fourth International Symposium on Artificial Intelligence, Cancún, Mexico, November.

85. Guzmán, A. (1992) Design and construction of applications using objects. Course notes in Spanish. Fourth International Winter School in Selected Computer Topics. Mérida, Yucatán. 60 pages.

86. Guzmán, A. (1993) Distributed Applications. Course notes in Spanish. © 1993, SoftwarePro International.
86bis. Guzmán, A. (1993) Design of a general system for tracking. Proceedings of the International Symposium on Computing, CeNac, Nov. 10-13. In Spanish.

M. Sc. thesis, Centro de Investigación en Computación, Instituto Politécnico Nacional, México, 2023

Resumen. En el presente trabajo se estudia la detección de indicadores de salud mental en persona... more Resumen. En el presente trabajo se estudia la detección de indicadores de salud mental en personas con esquizofrenia a partir de datos sensados pasivamente de teléfonos celulares con algoritmos de aprendizaje automático. Utilizando los datos generados en un estudio realizado en 2015 con personas que padecen esquizofrenia, se aborda el problema de la detección del bienestar mental con nuevas técnicas propias del área del aprendizaje automático, usando como referencia los resultados obtenidos por este primer estudio.
El documento comienza con una introducción general sobre el sensado pasivo, la detección de indicadores de salud mental con técnicas computacionales y los objetivos. Posteriormente, en el capítulo 2, se discuten los trabajos previos en donde, de manera similar, se han aplicado algoritmos de aprendizaje automático para el modelo de diversos problemas mentales. Por otra parte, en el marco teórico (capítulo 3), se introducen los fundamentos teóricos de las tećnicas y algoritmos empleados para este trabajo. Se decidió incluir un capítulo completo para describir el conjunto de datos y todas las tareas de preprocesamiento y análisis que se llevaron a cabo por la gran importancia que tuvieron en los experimentos, este corresponde al capítulo 4. En el capítulo 5, la metodología, se presentan todos los experimentos realizados así como los resultados obtenidos, sin discutirlos a detalle por ser la parte central del capítulo 6, discusión de resultados. Finalmente, en el último capítulo, conclusiones y trabajo futuro, se destacan los resultados obtenidos y las consecuencias en investigaciones futuras sobre el estudio de la salud mental con aprendizaje automático.
A pesar de que la detección de indicadores de salud mental se trata de un problema bastante complejo, uno de los principales aportes de esta investigación sugiere que el bienestar mental en personas con esquizofrenia puede ser modelado con una precisión aceptable con algunas pocas variables obtenidas a partir de los sensores de teléfonos celulares y con algoritmos de aprendizaje explicables de eficiente implementación.

Abstract. The present work studies the detection of mental health indicators in people with schizophrenia from passively sensed data from cell phones with machine learning algorithms. Using data generated in a study conducted in 2015 with people suffering from schizophrenia, we address the problem of detecting mental well-being with new techniques from the area of machine learning, using the results obtained by this first study as a reference.
The paper begins with a general introduction on passive sensing, the detection of mental health indicators with computational techniques and the objectives. Subsequently, in Chapter 2, previous works where, in a similar way, machine learning algorithms have been applied to model various mental problems are discussed. On the other hand, in the theoretical framework (Chapter 3), the theoretical foundations of the tećnics and algorithms employed for this work are introduced. It was decided to include a complete chapter to describe the data set and all the preprocessing and analysis tasks that were carried out because of the great importance they had in the experiments, this corresponds to chapter 4. In chapter 5, the methodology, all the experiments performed are presented as well as the results obtained, without discussing them in detail because it is the central part of chapter 6, discussion of results. Finally, the last chapter, conclusions and future work, highlights the results obtained and the implications for future research on the study of mental health with machine learning.
Although the detection of mental health indicators is a rather complex problem, one of the main contributions of this research suggests that mental well-being in people with schizophrenia can be modeled with acceptable accuracy with a few variables obtained from cell phone sensors and with explanatory learning algorithms of efficient implementation.

Ph. D. Thesis, Centro de Investigación en Computación, Instituto Politécnico Nacional , 2020

Introducción: La Diabetes Mellitus tipo 2 (DM2) es una enfermedad crónica que en los últimos años... more Introducción: La Diabetes Mellitus tipo 2 (DM2) es una enfermedad crónica que en los últimos años se ha incrementado en forma importante a nivel mundial, y específicamente en México ha habido un incremento en la obesidad, y consecuentemente de la DM2 y sus complicaciones. Para identificar si los pacientes con DM2 tienen un adecuado control glucémico se requiere la determinación de hemoglobina glicada (Hb𝐴𝐴1𝑐𝑐) cada 3 meses. Para evitar las complicaciones se requiere de un control glucémico adecuado, esto a través de cambio en el estilo de vida y tratamiento farmacológico. En los últimos 10 años se han agregado tratamientos farmacológicos de nueva generación. Una de las áreas de las Ciencias de la Computación (CS) es la Minería de Datos (DM), la cual se apoya del Aprendizaje de Máquina (ML). Los algoritmos de clasificación de ML pueden ser útiles para identificar a sujetos con DM2 con adecuado e inadecuado control glucémico a través de la Hb𝐴𝐴1𝑐𝑐, y para identificar factores relacionados a un adecuado control glucémico en sujetos que ya cuentan con el diagnóstico de DM2.
Objetivos: Utilizando técnicas de minería de datos y clasificación, identificar a los pacientes con DM2 que tengan alta probabilidad de descontrol glucémico a través de glucosa, perfil de lípidos y variables clínicas, considerando el porcentaje de Hb𝐴𝐴1𝑐𝑐 como el valor de referencia. Comparar la efectividad de 3 tipos de tratamientos farmacológicos para mejorar el control glucémico a tres meses de seguimiento en pacientes con DM2.
Metodología: Se obtuvieron 2 bases de datos de pacientes con DM2. Estas bases de datos a través de distintos métodos de limpieza se consolidaron en una base global. De esta base global, con la finalidad de identificar a los pacientes con descontrol glucémico a través de datos generales y perfil de lípidos se consideró a los pacientes que tenían determinación de Hb𝐴𝐴1𝑐𝑐 en forma trasversal obteniendo un total de 3777 mediciones de estos pacientes. Con esta base transversal se utilizaron árboles de decisión y algoritmos con enfoque “una cláusula a la vez” (OCAT, One Clause A Time) para la generación de reglas que describieran a los sujetos con y sin control glucémico. Con la finalidad de identificar los factores que pudieran predecir la modificación en el control glucémico posterior a por lo menos 6 meses de seguimiento se consolidó una base de datos con pacientes que tuvieran 2 mediciones de Hb𝐴𝐴1𝑐𝑐, obteniendo un total de 2169 sujetos. Con esta base longitudinal se dividieron a los sujetos en 3 grupos inicialmente (tratamiento habitual, gliflozina e inhibidores de la dipeptidil peptidasa-4 [iDPP4]) y posteriormente en 2 grupos (tratamiento habitual vs tratamiento de nueva generación). Los desenlaces que se analizaron fueron control, descontrol o sin modificación del control glucémico, y posteriormente se analizaron los desenlaces como reducción o aumento de la Hb𝐴𝐴1𝑐𝑐. Se utilizaron análisis de componentes principales y máquinas de soporte vectorial para determinación de los efectos de los tratamientos.
Resultados: En el modelo transversal el enfoque OCAT obtuvo mayor número de reglas con soporte mayor al 5% y alta precisión (mayor al 94%) para identificar a los sujetos con descontrol glucémico (con hasta 12 cláusulas en la regla); de estas reglas, dos se confirmaron como útiles a través de un modelo de regresión logística identificando un OR (Odds Ratio o razón de momios) de hasta 2.9 con significancia estadística. Dichas reglas son: 1.- Aquellos pacientes que sí usan insulina 2.- Mujeres con peso<=118.5kg, triglicéridos<=432mg/dl y Creatinina sérica<=0.97mg/dl. La clasificación por árboles sólo obtuvo una regla con soporte mayor al 5%, la cual tuvo una precisión de 98% y OR superior a 244 con significancia estadística: Un paciente con descontrol glucémico es aquel con edad<=70, sin uso de Gliflozina ni iDPP-4. En el modelo longitudinal para identificar si los diferentes tratamientos impactaban sobre la modificación del control glucémico, se observó a través de las máquinas de soporte vectorial que los sujetos que recibían gliflozina o iDPP-4 tuvieron un mayor control glucémico en comparación al grupo que sólo tuvo tratamientos tradicionales. Sin embargo, no se logró identificar diferencias significativas entre los pacientes que recibieron gliflozina e iDPP-4, a pesar de utilizar diferentes criterios de desenlaces entre los sujetos. A través de emparejamiento por puntaje de propensión, se identificó que la Gliflozina es 288% más efectiva que el iDPP-4.

Identificación de secuencias auditivas con big data, 2021

El presente trabajo de tesis aborda el problema del reconocimiento auditi- vo. Una canción contie... more El presente trabajo de tesis aborda el problema del reconocimiento auditi- vo. Una canción contiene música, pero también contiene partes donde solo existe voz, o una secuencia de sonidos (no forzosamente generados por un instrumento) que crean atmósferas. Para poder identificar correctamente es- tas secuencias se crea un modelado de huella a partir del contenido de las mismas, y almacenadas en una bodega que las relacione al archivo que las generó, permitirá que al extraer estas huellas de una muestra de audio pueda encontrarse el archivo reproducido, y recuperar toda la información que se tiene de él en la bodega.

Con este fin, se implementa un Sistema Identificador de Audio (SIA), hacien- do uso de un modelo de huellas usado por una aplicación bastante popular como lo es Shazam. Se hace uso de distintas tecnologías que permitan alma- cenar las huellas obtenidas con este modelo, con el fin de obtener pruebas de desempeño y factibilidad de implementación con una gran cantidad de canciones. Además, se propone y se pone a prueba una forma alternativa que busca acelerar el tiempo de búsqueda en la bodega sin perder exactitud.

Se hace uso de una base de datos con licencia libre conteniendo una gran di- versidad de géneros musicales así como un etiquetado completo de cada una de las pistas que contiene. La descripción de la implementación junto con la metodología de pruebas y resultados obtenidos busca ayudar a obtener un panorama distinto al de artículos ya publicados, ya que muchas veces ciertos detalles son omitidos por tratarse de aplicaciones comerciales.

La exactitud obtenida en las pruebas realizadas se asemeja bastante a la descrita en el estado del arte, sin embargo los tiempos de respuesta obtenidos no son tan buenos como los reportados, resultando en un área de oportunidad para intentar nuevos métodos a partir de este trabajo.

Tesis de maestría en Computación, Identificación de secuencias auditrivas con big data, 2021

M. Sc. Thesis. 2008

En este trabajo se presenta un estudio cienciométrico, donde se utilizan indicadores de publicaci... more En este trabajo se presenta un estudio cienciométrico, donde se utilizan indicadores de publicación, indicadores de análisis de citas y el método de las palabras asociadas (análisis cowords), todo esto en una muestra de documentos de tesis de maestría en ciencias de la computación concluidas en un Centro de Investigación en Computación, desde 1996 hasta 2007. Se ha organizado la información requerida para este análisis cienciométrico de 202 tesis en una base de datos; los datos se han recuperado acudiendo a diferentes fuentes de información, como lo son: Biblioteca, Área de Control Escolar y Apoyo de Investigadores.

En la parte de indicadores de publicación ayudó a describir como se lleva a cabo la producción científica con documentos de tesis concluidas, en la parte de indicadores de análisis de cita ayudo a describir como es la fuente de conocimiento en cuanto a citas bibliográficas y por ultimo con el método de las palabras asociadas ayudo a generar diagramas estratégicos y grafos (representación visual de la información) con los tópicos de las ciencias de la computación para analizar las relaciones entre ellos, los tópicos son de acuerdo al grupo de IEEE Computing Society and ACM.

Los indicadores de producción científica se pudo observar la productividad de los directores en diversos tópicos de las Ciencias de la Computación, lo que permitió analizar si se tiene la preferencia o la tendencia en determinados tópicos.

Con los diagramas estratégicos y los grafos de los tópicos o temas en diferentes periodos de tiempo, permitió seguir la evolución en el tiempo (patrones y tendencias) en los tópicos estudiados en las tesis.

This these presents a study scientometric, where indicators of publication are used, citation analysis of indicators and the method of associated words (analysis cowords), all in a sample of master's thesis in computer science finished Computer Research Center from 1996 to 2007. It has organized the information required for this analysis scientometric of 202 theses in a database; the data have been recovered by resorting to different sources of information such as: Library, School Control Area and Researchers Support, creating a database.

The citation analysis works helped to described the what conduct is of scientific production of thesis documents concluded, as the source of knowledge in terms of references to books and finally using the words associated method generate strategic diagrams and graphs about topics of computer science (visual information) to discuss relations in the topics or research o in the discipline or field of Computer Science.

With the strategic diagrams and graphs of the topics or themes in different periods of time, allowed to follow the evolution over time (patterns and trends) of the areas in the field of computer science, areas according to Computer Society of the Institute for Electrical and Electronic Engineers and Asociation Computing Machine (IEEE Computing Society and ACM).

Based on indicators of scientific production was observed productivity of managers in various topics of Computer Science, which will allow to analyze whether there is a tendency or preference to a particular area according to the group of IEEE Computing Society and ACM.

Prólogo del libro "Computación y Programación Moderna". , 2001

La misma juventud de la Ciencia de la Computación (nació cerca de 1950) provoca su muy rápida evo... more La misma juventud de la Ciencia de la Computación (nació cerca de 1950) provoca su muy rápida evolución: con acelerado ritmo surgen nuevas teorías, conceptos, métodos, circuitos, tipos de computadoras, lenguajes, programas, aplicaciones, etc. Este compás frenético hace pronto obsoleto a su estudioso si no tiene buena formación teórica. Él o ella debe tener una buena base sobre la cual construir su futuro intelectual. Esa base le permitirá reaprender a lo largo de su vida profesional, adquiriendo nuevos conocimientos que no se encuentran en este libro, ni en ningún otro, porque la humanidad aún no los inventa o descubre. La forma-ción básica y teórica del estudiante lo hace resistente a la obsolescencia. Es el temple de un machete, que le permite adquirir nuevas afiladas: conocimientos informáticos que aparece-rán en el futuro. De hecho, es un error relativamente común de varios currícula de enseñan-za de computación el sólo incluir los conocimientos útiles hoy-formación práctica-sin darle al estudiante una buena base para que él mismo adquiera los conocimientos prácticos y teóricos que existirán mañana. Machete filoso, pero sin temple. ¿Y qué tanto y cuán a menudo debe el egresado de informática reaprender? ¿Con qué frecuencia? ¿Cuántos conocimientos por unidad de tiempo se tornan anticuados? Estimo que en Computación, el tiempo de vida medio' de un concepto es de cinco años: cada ' El tiempo de vida medio de una substancia radiactiva es aquel en el cual su masa decae a la mitad de la masa original.