Physical Sciences and Mathematics Commons^™

Implementing Facial Recognition Technology In A Municipal Archives Digitization Project, Rebecca Bakker

Works of the FIU Libraries

This poster at the 2019 annual meeting of the South Florida Archivists highlights a project where the facial recognition technology of Adobe Lightroom CC is used to identify individuals in photographs held by a local municipal archive. The photographs contain hundreds of images showing unnamed commissioners and city workers from the 1970s to the 1990s, with most of the images lacking metadata or information. Various strategies are employed to identify key city officials in the photographs, allowing their names to be added to the metadata of the records hosted in a digital repository. The poster demonstrates the potential and limitations …

Generating Alternatives: The Possible Energy Transitions For France And Germany After The Paris Accord, Anna Fache

FIU Electronic Theses and Dissertations

Following the Paris Accord of 2015, multiple countries, including France and Germany, promised to reduce their greenhouse gas emissions in order to slow down climate change. Current energy production and consumption patterns do not allow for such targets. Meeting these emission reduction goals requires a transition in energy production. Energy transitions can be inefficient and costly if not planned properly, and multiple constraints need to be taken into account when putting such a process in place. The model proposed in the present study aims to find the most cost-effective energy portfolios for France and Germany, two highly industrialized nations in …

Essays On Economic Valuation Of Water Resources, Christina Estela Brown

FIU Electronic Theses and Dissertations

Increased potential of flooding caused by heavy precipitation events and sea level rise, as well as growing risk of drought that are likely changes in the frequency and spatial distribution of climatic conditions, pose particular challenges to water management in coastal areas. Extreme events are expected to increase the complexity of managing scarce water resources for competing water users. South Florida, which is characterized by a mosaic of urban settlements, agricultural areas and natural areas, is served by a highly human-engineered water management system grappling to meet multiple objectives, including urban and agricultural water supply, flood control, and environmental restoration. …

Analysis Of Flickr, Snapchat, And Twitter Use For The Modeling Of Visitor Activity In Florida State Parks, Hartwig H. Hochmair, Levente Juhasz

GIS Center

Spatio-temporal information attached to social media posts allows analysts to study human activity and travel behavior. This study analyzes contribution patterns to the Flickr, Snapchat, and Twitter platforms in over 100 state parks in Central and Northern Florida. The first part of the study correlates monthly visitor count data with the number of Flickr images, snaps, or tweets, contributed within the park areas. It provides insight into the suitability of these different social media platforms to be used as a proxy for the prediction of visitor numbers in state parks. The second part of the study analyzes the spatial distribution …

Automated, Efficient, And Accelerated Knowledge Modeling Of The Cognitive Neuroimaging Literature Using The Athena Toolkit, Michael C. Riedel, Taylor P. Salo, Jason Hays, Matthew D. Turner, Matthew T. Sutherland, Jessica A. Turner, Angela Laird

Department of Physics

Neuroimaging research is growing rapidly, providing expansive resources for synthesizing data. However, navigating these dense resources is complicated by the volume of research articles and variety of experimental designs implemented across studies. The advent of machine learning algorithms and text-mining techniques has advanced automated labeling of published articles in biomedical research to alleviate such obstacles. As of yet, a comprehensive examination of document features and classifier techniques for annotating neuroimaging articles has yet to be undertaken. Here, we evaluated which combination of corpus (abstract-only or full-article text), features (bag-of-words or Cognitive Atlas terms), and classifier (Bernoulli naïve Bayes, k-nearest …

Best Probable Subset: A New Method For Reducing Data Dimensionality In Linear Regression, Elieser Nodarse

FIU Electronic Theses and Dissertations

Regression is a statistical technique for modeling the relationship between a dependent variable Y and two or more predictor variables, also known as regressors. In the broad field of regression, there exists a special case in which the relationship between the dependent variable and the regressor(s) is linear. This is known as linear regression.

The purpose of this paper is to create a useful method that effectively selects a subset of regressors when dealing with high dimensional data and/or collinearity in linear regression. As the name depicts it, high dimensional data occurs when the number of predictor variables is far …