## Leandro Fabio Ariza Jiménez​​

### Áreas de interés e investigación:

• Análisis de redes, detección de comunidades en redes complejas, aprendizaje de máquina, análisis de clústeres, métodos de reducción de dimensionalidad, algoritmos de visualización de datos, y procesamiento digital de imágenes.

Director: Olga Lucía Quintero Montoya, Nicolás Pinel Peláez

### Publicaciones científicas más relevantes

Leandro Ariza-Jiménez, O. L. Quintero and Nicolás Pinel, "Unsupervised fuzzy binning of metagenomic sequence fragments on three-dimensional Barnes-Hut t-Stochastic Neighbor Embeddings". Proceedings of the 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Honolulu, HI, USA, 2018, pp. 1315-1318. ISSN:1557-170X.

Andrés Cardona, Leandro Ariza-Jiménez, Diego Uribe, Johanna C. Arroyave, and July Galeano, Fabian M. Cortés-Mancera. "Bio-EdIP: An automatic approach for in vitro cell confluence images quantification". Computer Methods and Programs in Biomedicine, Vol. 145, p. 23-33, 2017. ISSN 0169-2607.

L. Ariza-Jiménez, J.C. Gallego-Gómez, y J.C. Cardona. "Imagenología celular y máquina de aprendizaje para evaluar la distribución subcelular de mitocondrias en células infectadas con dengue". Biomédica: Revista del Instituto Nacional de Salud. Vol. 35(Sup.1), p. 28, 2015. ISSN: 0120-4157.

Juan Carlos Cardona-Gomez, Leandro Fabio Ariza-Jimenez and Juan Carlos Gallego-Gomez. "A Proposal for a Machine Learning Classifier for Viral Infection in Living Cells based on Mitochondrial Distribution". En Cell Biology. Editorial: InTech, 2015. ISBN: 978-953-51-4322-2.

A. Cardona, L. Ariza-Jiménez, D. Uribe, J. Arroyave, y F. Cortés-Mancera. "Automatic Image Segmentation Method for in vitro Wound Healing Assay Quantitative Analysis". En IFMBE Proceedings, Vol. 49, 2014. ISSN: 1680-0737.

• A network analysis approach for metagenomic binning.

Abstract: Metagenomics is the application of modern genomics techniques to the study of communities of microbial organisms directly in their natural environments. In metagenomics, the assignment of genomic fragments to the corresponding taxonomic group, e.g. species, genera or higher taxonomic groups, is commonly referred to as "binning", a procedure wherein each of the sequences is placed into an imaginary bin representing ideally only fragments belonging to this group. Since this is essentially a data clustering problem, here we attempt to develop and implement unsupervised strategies to address such problem. In particular, in this talk we will present the progress made by following a novel approach for the binning of genomic fragments based on similarity networks and community detection algorithms.

• Similarity-based clustering using a network analysis approach

Abstract: Networks represent relations between objects connected pairwise. Networks can have community structure, that is, objects interacting in a network can be organized into groups called communities. In addition, objects forming a community probably share some common properties as well as play similar roles within the interacting phenomenon that is being represented by the network. Thus, community detection can provide an insight into the structure of the networks.  Evident interactions between entities are often represented as networks, such as a social network of friendships between individuals or a network of citations between scientific papers. However, networks can be also used to represent similarity relationships between objects. Then, when it comes to cluster objects based on the above criteria, this problem could be solved by means of network community detection algorithms, rather than follow a cluster analysis approach.  In this talk we expose an alternative approach for data clustering based on network community detection algorithms. Details about the implementation and performance of this approach are given. In addition, this approach is exemplified by applying it in the identification and delimiting of microbial genomic populations.

• Transfer Learning on an Autoencoder- based Deep Network

Abstract: It is widely known that deep neural networks can be diﬃcult to train in practice, since in order to obtain state-of-the-art results we need a great amount of data and computing power. However, we can overcome this issue either using autoencoders as way to "pre-train" deep neural networks or following a "transfer learning" approach. In particular, here we carried out several experiments to study how both approaches can beneﬁt the training of deep networks.

• On the relation between Big Data and Machine Learning

Abstract: Recently the term "Big Data" was coined to capture the meaning of a data-explosion trend from diverse sources and domains, which society has been exposed due to technological advances since the second half of the 20th century. Machine Learning (ML) is a sophisticated analytical technology that can be used to provide us with intelligent analysis of Big Data. In this talk the relation between Big Data and ML is discussed, and two approaches of ML are presented: Clustering, and Deep Learning. The fundamental concepts of, and problems with Clustering will be discussed, followed by a description of some traditional algorithms and the presentation of experimental results in artificial datasets. With regard to Deep Learning, an introduction is given and future work in relation with big data is described.

### On the relation between big data and machine learning

Recently the term “Big Data” was coined to capture the meaning of a data-explosion trend from diverse sources and domains, which society has been exposed due to technological advances since the second half of the 20th century. Machine Learning (ML) is a sophisticated analytical technology that can be used to provide us with intelligent analysis of Big Data. In this talk the relation between Big Data and ML is discussed, and two approaches of ML are presented: Clustering, and Deep Learning. The fundamental concepts of, and problems with Clustering will be discussed, followed by a description of some traditional algorithms and the presentation of experimental results in artificial datasets. With regard to Deep Learning, an introduction is given and future work in relation with big data is described.

### Transfer learning on an Autoencoder-based Deep Network

It is widely known that deep neural networks can be diﬃcult to train in practice, since in order to obtain state-of-the-art results we need a great amount of data and computing power. However, we can overcome this issue either using autoencoders as way to “pre-train” deep neural networks or following a “transfer learning” approach. In particular, here we carried out several experiments to study how both approaches can beneﬁt the training of deep networks.

​​​

## Juan Guillermo Paniagua Castrillón

### ​Autor: ​Juan Guillermo Paniagua Castrillón.

Research project with Ecopetrol and Colciencias: develop algorithms of seismic migration using wave ﬁeld extrapolation in the direction of time (RTM, Reverse Time Migration), evaluating the preservation of amplitudes and frequencies as well as the conditions of stability, numerical dispersion and computational cost.

## An approach to the study of time, time-frequency and time-scale transformations for seismic migration problems

Autor: ​Juan Guillermo Paniagua Castrillón.
Research project with Ecopetrol and Colciencias: seismic pre-stack migration in depth by extrapolating wave ﬁelds using high performance computing for massive data in complex areas.

## Laguerre Gaussian filters in Reverse Time Migration image reconstruction ​

Autor: ​Juan Guillermo Paniagua Castrillón.

Reverse Time Migration (RTM) solves the acoustic or elastic wave equation by means of the extrapolation from source and receiver wavefield in time. A migrated image is obtained by applying some criteria known as imaging condition. The zero lag cross-correlation between source and receiver wavefields is the commonly used imaging condition. However, this imaging condition produces lowspatial-frequency noise or artifacts, due to the strong contrasts in velocity field (Pestana et al., 2014). Several imaging techniques have been proposed to reduce the artifacts occurrence. Derivative operators as Laplacian are the most frequently used. In this work, we propose the usage of a technique based on a spiral phase filter ranging from 0 to 2π​, and a toroidal amplitude bandpass filter, known as Laguerre-Gauss transform. Through numerical experiments we present the application of this particular filter on Seg Eage salt model and Sigsbee 2A model. We also present evidences that this method improves RTM images by reducing the artifacts and notably enhance the reflective events.

​​​​​​

## Riemannian wave-ﬁeld extrapolation: thesis proposal

• ### ​​​Autor: Hector Roman Quiceno E. ​

​​The earth is at least a visco elastic medium, in which absorption losses give rise to attenuation and dispersion effects. The elastic wave equation is framed in terms of tensor operators acting on vector quantities. It is also true that a proper treatment of anisotropy fundamentally demands an elastic viewpoint, even when only P-waves (quasi-P waves) are contemplated. Different representations for the same physical law can lead to diﬀerent computational techniques in solving the same problem, which can produce different and new numerical results, so this new but accurate representation should lead us to new results and descriptions of the phenomena.​

​​
​​​

​​​

## Juan David Palacio Dominguez

### Descripción personal breve

Soy Ingeniero Industrial de la Universidad de Antioquia, Medellín y magister en ingeniería industrial de la Universidad de los Andes, Bogotá. Actualmente,  soy estudiante de doctorado en ingeniería matemática en EAFIT. Mi experiencia docente incluye más de seis años en la Universidad de los Andes, la Universidad de Antioquia, el Instituto Tecnológico Metropolitano -ITM y EAFIT. He asistido a varias conferencias nacionales e internacionales en investigación operativa y optimización. He estado involucrado en proyectos de investigación relacionados con problemas de selección y programación de proyectos, modelos de planificación de personal y optimización de ruteo de vehículos. Parte de mi investigación apareció recientemente en International Transactions in Operational Research y en la serie Communication in Computer and Information Science. Mis intereses de investigación actuales incluyen programación matemática y diseño de heurísticas para problemas de ruteo de vehículos.

### Áreas de interés e investigación:

• Optimización combinatoria, programación matemática y heurística.
• Combinatorial optimization, mathematical programming and heuristics.

Director: Juan Carlos Rivera Agudelo

### Revistas a las que frecuentemente lee:

• Computers and operations research
• European Journal of Operational Research
• Expert Systems with Applications
• International Transactions in Operational Research
• Computers and Industrial Enginnering
• Annals of Operations Research

### Publicaciones científicas más relevantes

Cortés, S., Gutiérrez, E. V., Palacio, J. D., & Villegas, J. G. (2018, October). Districting Decisions in Home Health Care Services: Modeling and Case Study. In International Workshop on Experimental and Efficient Algorithms (pp. 73-84). Springer, Cham.

Posada, A., Rivera, J. C., & Palacio, J. D. (2018). A Mixed-Integer Linear Programming Model for a Selective Vehicle Routing Problem. In International Workshop on Experimental and Efficient Algorithms (pp. 108-119). Springer, Cham.

Palacio, J. D., Larrea, O. L. (2017), A lexicographic approach to the robust resource-constrained project scheduling problem. International Transactions in Operational Research, 24: 143–157. doi:10.1111/itor.12301.

Gutiérrez, V., Palacio, J.D., Villegas, J.G. (2007), Reseña del software disponible en Colombia para el diseño de rutas de distribución y servicios. Revista Universidad EAFIT. 43, No.145 (ene-feb-mar.2007); p. 60-80. ISSN: 0120-341x.

​​​

​​​

## Andres Yarce Botero

### Descripción personal breve

Soy estudiante del segundo año del Doctorado en Ingenieria Matematica de la Universidad EAFIT y de la Universidad TUDelft en los Paises Bajos. Estoy interesado en utilizar técnicas matemáticas junto a modelos de química y transporte atmosférico para simular, de la manera más apropiada, fenómenos con consecuencias perjudiciales para el medio ambiente, como la deposición de contaminantes que son emitidos por nosotros, humanos, desde centros urbanos y agrícolas. El deporte que más me gusta es el boxeo, la comida que más me gusta es la hamburguesa.

### Áreas de interés e investigación:

•  Asimilación de datos.
• Reducción de orden de modelos dinámicos.
• Satelites de pequeño formato

Directores:  Arnold Heemink (TUDELFT) Nicolas Pinel (EAFIT) Olga Lucia Quintero (EAFIT)

Grupo de investigación:  Modelado Matematico GRIMMAT, Biología Evolucion y Conservacion BEC, Mecanica Aplicada

### Publicaciones científicas más relevantes

MARCO ALUNNO, ANDRES YARCE BOTERO, "Directional Landscapes: Using Parametric Loudspeakers for Sound Reproduction in Art" . En: Inglaterra
Journal Of New Music Research  ISSN: 0929-8215  ed:
v.fasc.N/A p.1 - 11 ,2016,  DOI: http://dx.doi.org/10.1080/09298215.2016.1227340

ANDRES YARCE BOTERO, JUAN SEBASTIAN RODRIGUEZ, JULIAN GALVEZ, ALEJANDRO GOMEZ "Simple-1: Development stage of the data transmission system for a solid propellant midpower rocket model" . En: Estados Unidos
Journal Of Physics: Conference Series  ISSN: 1742-6596  ed: IOP Publishing Ltd
v.850 fasc.N/A p.12 - 19 ,2017,  DOI: doi :10.1088/1742-6596/850/1/012019

ANDRES YARCE BOTERO, JUAN SEBASTIAN RODRIGUEZ, JULIAN GALVEZ, ALEJANDRO GOMEZ "Design, construction and testing of a data transmission system for a mid-power rocket model" . En: Estados Unidos
Ieee Aerospace Conference Proceedings  ISSN: 1095-323X  ed:
v.2017 fasc.N/A p.1 - 14 ,2017,  DOI: 10.1109/AERO.2017.7943739

​​​

## Jhon Willington Bernal Vera

### Descripción personal breve

Futuro Doctor en Ingeniería Matemática. Docente de matemáticas EAFIT. Youtuber en proceso.

### Áreas de interés e investigación:

• Geometría y topología.

Grupo de investigación:  Matemáticas y Aplicaciones

​​​

## Juan Carlos Arango Parra

### Descripción personal breve

Me considero una persona respetuosa, me gusta la puntualidad, los viajes. Me gusta compartir con mi familia (hija y esposa). Aprovecho al tiempo al máximo en las diferentes actividades laborales y académicas, pero también disfruto ver anime, series y películas.

### Áreas de interés e investigación:

Geometría Diferencial, Análisis matemático, Ecuación del Calor, Machine Learning.

Codirector: Gabriel Ignacio Loaiza Ossa.

Grupo de investigación:  Análisis funcional y aplicaciones.

### Revistas a las que frecuentemente lee:

• Journal of Mathematics Analysis and Applications.
• Entropy.
• Differential Geometry and its Applications.
• Journal of Machine Learning.
• Applied Mathematics.

### Publicaciones científicas más relevantes

Quiceno, Héctor, Loaiza, Gabriel and Arango, Juan. A Riemannian Geometry in the $q$-Exponential Banach Manifold Induced by $q$-Divergences. Capítulo 5 del libro Geometric Theory of Information. Springer, Signals and Communications Technology, 2014. DOI 10.1007/978-3-319-05317-2

Quiceno, Héctor y Arango, Juan. A statistical manifold modeled on Orlicz spaces using Kaniadakis $\kappa$-exponential models. Journal of Mathematics Analysis and Applications, volumen 432, 2015, páginas 1080-1098.  DOI: http://dx.doi.org/10.1016/j.jmaa.2015.05.065

Arango, Juan; Quiceno, Héctor y Plata, Osiris. Secciones cónicas $\kappa$-deformadas. Ingeniería y Ciencia, volumen 12, número 24, páginas 9-29, julio-diciembre de 2016. DOI: doi:10.17230/ingciencia.12.24.1.

​​​

## Jhon Edilson Hinestroza

### Descripción personal breve

Me encanta la academia y saber que desde ella se pueden generar las transformaciones que el país requiere. La educación es el camino para que Colombia pueda dar a sus ciudadanos lo que tanto requieren. Pertenezco a ese grupo de colombianos que tuvieron la fortuna de nacer en el Chocó, con lo que trae eso, la oportunidad de despertar y ver la majestuosidad de su hermosa selva y la dulzura de sus ríos.

Soy un enamorado de mi familia, de mi esposa que me sostiene, mis hijas que me inspiran y mis padres que fueron el combustible para intentarlo cada vez, una vez y otra vez.

### Áreas de interés e investigación:

• Reducción de incertidumbre.

Director: Olga Lucía Quintero Montoya.

Codirector: Ángela María Rendón Pérez

Grupo de investigación:  Grupo de Investigación en Modelado Matemático, GRIMMAT.

​​​

## Jorge Eliecer Agudelo Quiceno

​​​

​​​

Última modificación: 27/05/2019 11:09