Niki LaGrone, Author at Azavea

Image Classification Labeling: Single Class versus Multiple Class Projects

By Niki LaGrone on June 8th, 2020

When labeling for image classification is it faster to complete projects with single or multiple classes? We ran an experiment to find out.

Empty swingset overlaid with image of computer motherboard.

Software Engineering

Can AI Reduce Harm to Children?: Gabriel Fernandez and the Case for Machine Learning

By Niki LaGrone on April 9th, 2020

Could AI have saved Gabriel Fernandez’s life? Data and social scientists argue that machine learning might have kept him alive. What exactly is this potentially life-saving AI? Learn more about predictive risk modeling, how governments currently use similar AI, and the ethical questions such work raises.

Application screenshot of labeled satellite imagery.

Software Engineering

Labeling Satellite Imagery for Machine Learning

By Niki LaGrone on March 24th, 2020

Definitions and visuals of the most common ways to label satellite imagery for machine learning. Includes tips for managing annotations for each type.

Map showing the officials who left office in color-coded dots.

Spatial Analysis

U.S. Officials Who Left Office in 2019 and Why

By Niki LaGrone on February 20th, 2020

Who left office in 2019? Why? The Cicero Data team mapped the U.S. officials who left office before the end of their term in 2019.

Common vector of disease overlaid by maps.

Company

How Geospatial Technology and AI are Transforming Medicine

By Niki LaGrone on January 17th, 2020

From predicting outbreaks of infectious disease to predicting the likelihood of an asthma attack, Geospatial AI and medicine are transforming healthcare.

Azavea team team leading GIS training in Guyana.

Software Engineering

Ethical Machine Learning for Disaster Relief: Rage for Machine Learning

By Niki LaGrone on December 10th, 2019

ML's predictive powers are driving a rage for deep learning in the crisis management and disaster relief industries. How can these powers be harnessed for ethical machine learning?