Gustavo A Valencia-ZapataAdvanced Agrilytics · Office of Science
Gustavo A Valencia-Zapata
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
Data Scientist with strong Statistics and Computer Engineering background. Involved in R open-source community and passionate about classifiers and synthetic data generation. Main Research Topics: 1) Precision agriculture 2) Synthetic data generation 3) Performance Metrics for supervised learning
December 2019 - present
- Develop and help support new analytical techniques to address quantitative problems in digital agriculture using large datasets.
August 2014 - December 2019
- Research Assistant
- Develop and apply data analytics models to identify behavior patterns based on the user actions on "nanoHUB", the largest online nanotechnology user facility in the world.
February 2014 - August 2014
- Design data models to mine enterprise systems and applications for knowledge and information that enhances business processes.
Several studies point out different causes of performance degradation in supervised machine learning. Problems such as class imbalance, overlapping, small-disjuncts, noisy labels, and sparseness limit accuracy in classification algorithms. Even though a number of approaches either in the form of a methodology or an algorithm try to minimize perform...
nanoHUB annually serves 17,000+ registered users with over 1 million simulations. In the past, we have used data analytics to demonstrate that nanoHUB can be a powerful scientific knowledge sharing platform. We used retrospective data analytics to show how simulation tools were used in structured education and how simulation tools were used in nove...
Tunnel Field Effect Transistors (FETs) have the potential to achieve steep Subthreshold Swing (S.S.) below 60 mV/dec, but their S.S. could be limited by trap-assisted tunneling (TAT) due to interface traps. In this paper, the effect of trap energy and location on OFF-current (IOFF) of tunnel FETs is evaluated systematically using an atomistic trap...
Probabilistic mixture models have been widely used for different machine learning and pattern recognition tasks such as clustering, dimensionality reduction, and classification. In this paper, we focus on trying to solve the most common challenges related to supervised learning algorithms by using mixture probability distribution functions. With th...
Orientation effects on the resistivity of copper grain boundaries are studied systematically with two different atomistic tight binding methods. A methodology is developed to model the resistivity of grain boundaries using the Embedded Atom Model, tight binding methods and non-equilibrum Green's functions (NEGF). The methodology is validated agains...
As logic devices continue to downscale, interconnections are reaching the nanoscale where quantum effects are important. In this work we introduce a semi-empirical method to describe the resistance of copper interconnections of the sizes predicted by ITRS roadmap. The resistance calculated by our method was benchmarked against DFT for single grain...