Términos relacionados

6 resultados encontrados para: AUTOR: Arellano Verdejo, Javier
  • «
  • 1 de 1
  • »
1.
- Artículo con arbitraje
ERISNet: deep neural network for Sargassum detection along the coastline of the Mexican Caribbean
Arellano Verdejo, Javier (autor) ; Lazcano Hernández, Hugo Enrique (autor) ; Cabanillas Terán, Nancy (autora) ;
Disponible en línea
Contenido en: PeerJ Volumen 7, número e6842 (2019), p. 1-19 ISSN: 2167-8359
PDF
Resumen en: Inglés |
Resumen en inglés

Recently, Caribbean coasts have experienced atypical massive arrivals of pelagic Sargassum with negative consequences both ecologically and economically. Based on deep learning techniques, this study proposes a novel algorithm for floating and accumulated pelagic Sargassum detection along the coastline of Quintana Roo, Mexico. Using convolutional and recurrent neural networks architectures, a deep neural network (named ERISNet) was designed specifically to detect these macroalgae along the coastline through remote sensing support. A new dataset which includes pixel values with and without Sargassum was built to train and test ERISNet. Aqua-MODIS imagery was used to build the dataset. After the learning process, the designed algorithm achievesa 90% of probability in its classification skills. ERISNet provides a novel insight to detect accurately algal blooms arrivals.


2.
Capítulo de libro - Ponencia
Moderate resolution imaging spectroradiometer products classification using deep learning
Arellano Verdejo, Javier ;
Contenido en: Communications in computer and information science 1053 Mérida, Yucatán, México : Telematics and Computing, 2019 p. 61-70 ISBN:978-3-030-33228-0, 978-3-030-33229-7
PDF
Resumen en: Inglés |
Resumen en inglés

During the last years, the algorithms based on Artificial Intelligence have increased their popularity thanks to their application in multiple areas of knowledge. Nowadays with the increase of storage capacities and computing power, as well as the incorporation of new technologies for massively parallel processing (GPUs and TPUs) and Cloud Computing, it is increasingly common to incorporate this kind of algorithms and technology in tasks with a deep social and technological impact. In the present work a new Convolutional Neural Network specialized in the automatic classification of Moderate Resolution Imaging Spectroradiometer satellite products is proposed. The proposed architecture has shown a high-generalization by classifying more than 250,000 images with 99.99% accuracy. The methodology designed also can beextended, with other types of images, to make detection of Sargassum, oil spills, red tide, etc.


3.
Artículo
*Solicítelo con su bibliotecario/a
Optimal allocation of public parking spots in a smart city: problem characterisation and first algorithms
Arellano Verdejo, Javier ; Alonso Pecina, Federico (coaut.) ; Alba, Enrique (coaut.) ; Guzmán Arenas, Adolfo (coaut.) ;
Contenido en: Journal of Experimental and Theoretical Artificial Intelligence Vol. 31, no 4 (July 2019), p. 575-597 ISSN: 1362-3079
Nota: Solicítelo con su bibliotecario/a
Resumen en: Inglés |
Resumen en inglés

Having a mechanism to mathematically model the problem of the optimal allocation of parking spots within cities could bring great benefits to society. According to the International Parking Institute, about 38% of the cars circulating throughout a city are looking for available parking spots, leading to increased pollution and subsequent health problems, as well as economic losses due to wasted man-hours. In the work presented here, a new mathematical model describing the problem of the optimal allocation of parking spots is proposed, along with an evolutionary algorithm to demonstrate how this model can be used in practice. A simulated annealing algorithm was implemented to test the effectiveness of this approach. The proposed strategy will allow users to find parking more quickly and easily, as well as lead to new services for the hot-topic of smart mobility. For the definition of the problem, a real map of the city of Malaga, Spain, was used along with Sumo software to carry out the simulations. The results clearly demonstrated that the proposed mechanism is capable of minimising the global cost of parking, implying a direct benefit for users.


4.
- Artículo con arbitraje
Middle and late Holocene mangrove dynamics of the Yucatan Peninsula, Mexico
Aragón Moreno, Alejandro Antonio ; Islebe, Gerald A. (coaut.) ; Torrescano Valle, Nuria (coaut.) ; Arellano Verdejo, Javier (coaut.) ;
Contenido en: Journal of South American Earth Sciences Vol. 85 (August 2018), p. 307-311 ISSN: 0895-9811
PDF
Resumen en: Inglés |
Resumen en inglés

We present mangrove dynamics, related to precipitation changes derived from migration of the Intertropical Convergence Zone (ITCZ) and the El Niño Southern Oscillation (ENSO) during middle and late Holocene of the northern and southern Yucatan Peninsula. Sea level rise was the major determinant for mangrove establishment during middle Holocene. Following the sea level rate stabilization, changes in precipitation and increasing ENSO activity determined periods of expansion and reduction of mangrove cover. At the onset of late Holocene, mangroves fluctuated abruptly due the coupled effect of the ENSO and latitudinal movement of the ITCZ. Trend correlation analysis revealed significant relationship between the presence of Conocarpus erectus, ENSO and ITCZ. Rhizophora mangle showed a significant relationship with ITCZ based on trend correlation analysis. Expansion of mangrove populations in seasonally flooded wetlands is recorded during the late Holocene.


5.
Artículo
Off-line and on-line optical monitoring of microalgal growth
Lazcano Hernández, Hugo Enrique ; Aguilar, Gabriela (coaut.) ; Dzul Cetz, Gabriela Antonia (coaut.) ; Patiño, Rodrigo T. (coaut.) ; Arellano Verdejo, Javier (coaut.) ;
Contenido en: PeerJ Vol. 2019, no. 11, e7956 (2019), p. 1-17 ISSN: 2167-8359
PDF
Resumen en: Inglés |
Resumen en inglés

The growth of Chlamydomonas reinhardtii microalgae cultures was successfully monitored, using classic off-line optical techniques (optical density and fluorescence) and on-line analysis of digital images. In this study, we found that the chlorophyll fluorescence ratio F685/F740 has a linear correlation with the logarithmic concentration of microalgae. By using digital images, the biomass concentration correlated with the luminosity of the images through an exponential equation and the length of penetration of a super luminescent blue beam ( = 440 nm) through an inversely proportional function. The outcomes of this study are useful to monitor both research and industrial microalgae cultures.


6.
Artículo
Spatio-temporal assessment of chlorophyll a in Banco Chinchorro using remote sensing
Lazcano Hernández, Hugo Enrique (autor) ; Arellano Verdejo, Javier (autor) ; Hernández Arana, Héctor Abuid (autor) ; Alvarado Barrientos, María Susana (autora) ;
Contenido en: Research in Computing Science Vol. 147, no. 12 (December 2018), p. 213–223 ISSN: 1870-4069
PDF
Resumen en: Inglés |
Resumen en inglés

Quantitative assessments of the temporal variances of physical and biological phenomena are very useful for the understanding of ecosystem functioning. Marine ecosystems are very complex, and regarding biodiversity and fishing resources, Banco Chinchorro (BCh) is one of the most important in the south of the Yucatan Peninsula. Additionally, BCh is an important hotspot of assimilation and release of carbon, for which hurricanes play a supporting role by mixing deep and superficial water masses affecting nutrient mixing and distribution. Here, the concentration of chlorophyll a (Chl a) was quantitatively linked to the occurrence of the four most recent hurricanes that affected BCh utilizing time-series analysis of satellite-derived (AQUA-MODIS) data-sets. Interestingly, different Chl aconcentrations between the south and north of BCh were confirmed quantitatively, which points to differential conservation efforts. The aim of this study was also to provide a proof-of-concept for the development of long-term monitoring methodology using remotely sensed data so that it may be replicated in other regions and with other satellite databases.