Authors: S. Levashkin, V. Alexandrov, and A. Guzmán. This article appears in IEEE LATIN AMERICA TRANSACTIONS, VOL. 14, NO. 3, MARCH 2016. Full text: click here.
Abstract— In the present work, we follow in chronological order the ideas, contributions and discoveries of the greatest Russian mathematician Andrei Kolmogorov in Computer Science. We interpret such Kolmogorov's concepts as algorithm, complexity, komputer mathematics, machine, in the context of the state-of-the art information theories and technologies. We conclude that in broad sense these theories and technologies follow the ways sketched and predicted by Kolmogorov about half century ago.
El presente trabajo integra las contribuciones del científico soviético Andrei Kolmogorov en el contexto de las tecnologías de la información moderna y sus aplicaciones. Contribuciones tales como la teoría algorítmica de la informática [en el artículo se usa la notación “informática” y “ciencia de la computación” dependiendo del contexto actual. Sin embargo se entienden ambos en un sentido común como son definidos en las enciclopedias de la ciencia de la computación]. Por ejemplo, uno puede pensar en informática y/o en la ciencia de la computación. También se usa la notación “matemáticas Komputacionales” o matemáticas K, en vez de matemáticas Computacionales, para distinguir el enfoque de Kolmogorov hacia los problemas de la ciencia de la computación... para seguir leyendo, pulse aquí.
Climate patterns of political division units obtained using automatic classification trees
Article published in ATMÓSFERA. Authors: Sergio R. Coria, Carlos Gay-García, Lourdes Villers-Ruiz, Adolfo
Guzmán-Arenas, Óscar Sánchez-Meneses, Oswaldo R. Ávila-Barrón, Mónica
Pérez-Meza, Xóchitl Cruz-Núñez, Gilberto Lorenzo Martínez-Luna. Full text: click here.
|Abstract. 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 minimum temperature, 12 to a maximum temperature, and 12 to cumulative rainfall. The altitude feature is also used as one of the predictors, in addition to the other 36; however, it is used only to quantify its additional contribution to the modelling. The results show that classification trees are effective models for describing and representing non-trivial patterns to characterize the political division units based on their monthly temperatures and rainfalls. One of the remarkable findings is that the cumulative rainfall of May is the feature with highest discrimination capability to the characterization task, which is consistent with the theoretical background on Mexican climatology. In addition, classification trees offer higher expressivity to non-experts in machine learning.
Atmósfera, vol. 29, issue 4, October-December 2016, is a quarterly journal published by the Universidad Nacional Autónoma de México.
|Abstract. 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 minimum temperature, 12 to a maximum temperature, and 12 to cumulative rainfall. The altitude feature is also used as one of the predictors, in addition to the other 36; however, it is used only to quantify its additional contribution to the modelling. The results show that classification trees are effective models for describing and representing non-trivial patterns to characterize the political division units based on their monthly temperatures and rainfalls. One of the remarkable findings is that the cumulative rainfall of May is the feature with highest discrimination capability to the characterization task, which is consistent with the theoretical background on Mexican climatology. In addition, classification trees offer higher expressivity to non-experts in machine learning.
Atmósfera, vol. 29, issue 4, October-December 2016, is a quarterly journal published by the Universidad Nacional Autónoma de México.
Los Premios Nacionales de Ciencia nos reunimos en Guanajuato
Fue el Primer Congreso del Consejo Consultivo de Ciencias (CCC) - Encuentro de ideas y propuestas. De los aproximadamente 125 Premios Nacionales de Ciencias que son miembros del CCC, asistimos 25 a esa reunión. Se discutieron ideas y propuestas para mejorar la ciencia en México.
 |
| En primera fila, de izq. a der., Lorena Macías (Secr. Ejecutiva del CCC), Elías Micha Zaga (Coordinador de Ciencia, Tecnología e Innovación de la Presidencia de la República), Sen. Juan Carlos Romero Ricks (Secretario de la Comisión de Ciencia y Tecnología del Senado),, Arturo Menchaca (Presidente del CCC), Enrique Cabrero (Director del Consejo Nacional de Ciencia y Tecnología, traje beige). Yo estoy en la última fila, penúltima posición de izq. a der., parcialmente visible. |
 |
| En la primera fila hasta la izquierda aparezco sentado. Desafortunadamente, la imagen es de resolución baja. |