Gabriela Marín Raventós

Gabriela Marín Raventós

Es estudiante: 
No

Formación académica

  • "Doctor of Philosophy" en Administración de Negocios, con énfasis en Sistemas de Información Gerencial, Graduate School of Business Administration, Texas A&M University, College Station, Texas, U.S.A., agosto 1993.
  • "Master of Science" en Ciencias de la Computación, Department of Computer Engineering and Science, Graduate School of Engineering, Case Western Reserve University, Cleveland, Ohio, U.S.A., agosto 1985.
  • Estudios de Maestría en Administración Pública, Programa Instituto Centroamericano de Administración Pública (ICAP) - Universidad de Costa Rica, San José, Costa Rica, de junio 1981 a abril 1982 (29 créditos).
  • Licenciatura en Ciencias de la Computación, Escuela de Matemáticas, Universidad de Costa Rica, San Pedro, Costa Rica, febrero 1981.
  • Bachillerato en Ciencias de la Computación, Escuela de Matemáticas, Universidad de Costa Rica, San Pedro, Costa Rica, agosto 1980.

Experiencia laboral

  • Directora, Centro de Investigación en Tecnologías de Información y Comunicación (CITIC), Universidad de Costa Rica,  21 de junio 2012 al 31 de julio 2017.
  • Decana del Sistema de Estudios de Posgrado, Universidad de Costa Rica, 30 junio 2008 al 29 junio 2012.
  • Vice-Decana del Sistema de Estudios de Posgrado, Universidad de Costa Rica, 14 de noviembre del 2007 al 29 de junio del 2008. 
  • Directora, Programa de Posgrado en Computación e Informática, Universidad de Costa Rica, 15 de mayo de 1998 al 30 de julio del 2009.
  • Representante, Area de Ingeniería ante el Cosejo del Sistema de Estudios de Posgradp, Universidad de Costa Rica, 2002-2004, 2004-2006, 2006-2008.
  • Profesora Catedrática, Escuela de Ciencia de la Computación e Informática, Universidad de Costa Rica, julio 1981- al presente.
  • Miembro, Comisión de Maestría, Telemática, 1998 hasta 2001.
  • Profesora y coordinadora, Programa de Diplomado en Computación Administrativa, Universidad de Costa Rica, desde 1987 hasta julio 1989.
  • Investigador I, Consejo Nacional de Rectores (CONARE), dese agosto 1980 a junio 1981.

Proyectos

Publicaciones

Typifying Data Required for the Development of Smart Agriculture Systems

Descripción:

Smart agriculture is an active research field. Currently, many researchers are working on the construction of platforms directed to improve efficiency, crop processes, and data awareness. However, it is common that developers focus on data monitoring instead of the data relevance for decision making or the costs associated with the creation of monitoring platforms. In this paper, we present a classification of the data required by researchers on the construction of decision-support systems applied to smart agriculture processes. By using this classification, the user can define which data are relevant according to the characteristics of the problem that needs to be solved.We have applied the classification to data recollected in a study case conducted by the end of last year. Besides, we identify a list of agronomic and climatic variables commonly used in the construction of decision support systems. We apply the classification to this list of variables as an example for researchers. As a conclusion, this typification permits the researcher to identify data that has to be monitored and controlled, and data that does not have to be measured, the later based on the data characteristics and utility for the farmer.

Tipo de publicación: Conference Paper

Publicado en: 2019 IV Jornadas Costarricenses de Investigación en Computación e Informática (JoCICI)

Alzheimer’s Disease Early Detection Using a Low Cost Three-Dimensional Densenet-121 Architecture

Descripción:

The objective of this work is to detect Alzheimer’s disease using Magnetic Resonance Imaging. For this, we use a three-dimensional densenet-121 architecture. With the use of only freely available tools, we obtain good results: a deep neural network showing metrics of 87% accuracy, 87% sensitivity (micro-average), 88% specificity (micro-average), and 92% AUROC (micro-average) for the task of classifying five different classes (disease stages). The use of tools available for free means that this work can be replicated in developing countries.

Tipo de publicación: Conference Paper

Publicado en: Lecture Notes in Computer Science

Effects of oral metaphors and allegories on programming problem solving

Descripción:

Metaphors of ordinary concepts are intensively used in computer science for naming abstract concepts and for designing users interfaces. Metaphors are mappings from a source domain (e.g., a stream) to a target domain (e.g., a sequence of bytes). Typically computing phenomena are explained using incoherent discourses at the source domain, formed by metaphors taken from a diversity of origins. Nonetheless, versatility of metaphors allows for the creation of coherent discourses in the origin domain that map the target computing discourse, and we call them allegories. The limited number of existing studies about this topic has compared only textual allegories, visual allegories, and the traditional unconnected metaphors. Although their findings are heterogeneous, equal effectiveness is the most frequent empirical result between these three types of metaphors. Furthermore, we have not found any study about oral allegories, in spite of oral being the most used modality for metaphors in computer science education. This article experimentally compares the effects of oral allegories and oral metaphors on a complex problem‐solving task. As in previous studies, our results did not find any significant differences on support or detriment of oral allegories. Our results support new metaphor theories posing that the context significantly influences the metaphors’ efficacy, and encourages future research about the interaction between context and allegories.

Tipo de publicación: Journal Article

Publicado en: Computer Applications in Engineering Education

A Precise Layout Manager for Vector Graphics

Descripción:

Automated layout is the use of software to determine the positions and sizes of visual elements that are part of an information presentation. As the amount of data that computers are able to process increases, automatic layout becomes more necessary. During the process of creating a program visualization, the authors needed a precise layout manager for scalable vector graphics that supported layers and animations. A literature review revealed the lack of a layout manager that satisfies these requirements. This paper reports the creation of a layout manager that uses floating-point arithmetic for precise and imperative arrangement of visual elements, that may be useful for other visual applications facing similar requirements.

Tipo de publicación: Conference Paper

Publicado en: 2019 IV Jornadas Costarricenses de Investigación en Computación e Informática (JoCICI)

Early Detection of Diseases in Precision Agriculture Processes Supported by Technology

Descripción:

One of the biggest challenges for farmers is the prevention of disease appearance on crops. Governments around the world control border product entry to reduce the number of foreign diseases affecting local producers. Evenmore, it is also important to reduce the spread of crop diseases as quickly as possible and in early stages of propagation, to enable farmers to attack them on time, or to remove the affected plants. In this research, we propose the use of convolutional neural networks to detect diseases in horticultural crops. We compare the results of disease classification in images of plant leaves, in terms of performance, time execution, and classifier size. In the analysis, we implement two distinct classifiers, a densenet-161 pre-trained model and a custom created model. We concluded that for disease detection in tomato crops, our custom model has better execution time and size, and the classification performance is acceptable. Therefore, the custom model could be useful to use to create a solution that helps small farmers in rural areas in resource-limited mobile devices.

Tipo de publicación: Book Chapter

Publicado en: Advances in Sustainability Science and Technology

Online Judge Support for Programming Teaching

Descripción:

Online programming judges are considered useful and sometimes indispensable tools to support competitive programming, professionals' recruiting, and programming education. In this last field, the scientific literature on these tools focuses on the learners' needs, but neglects the requirements of the professors, even though they are who mainly decide whether or not an educational tool is adopted in the courses they teach. This article collected 132 functional requirements for educative online judges, from the scientific literature and programming teachers with experience in the use of this type of tool. To know the degree of support, the requirements were grouped into 27 categories, and a requirements verification was performed with four available educative online judges reported in a recent systematic literature review. A low degree of satisfaction of requirements was found. This result encourages future research to create tools that better support teaching-learning processes and the requirements collected are a useful contribution as a starting point for such research.

Tipo de publicación: Conference Paper

Publicado en: 2020 XLVI Latin American Computing Conference (CLEI)