Open Access. Powered by Scholars. Published by Universities.®

Physical Sciences and Mathematics Commons

Open Access. Powered by Scholars. Published by Universities.®

Computer Sciences

The University of San Francisco

Conference

2020

Articles 1 - 3 of 3

Full-Text Articles in Physical Sciences and Mathematics

Fire Progression, Ashwini Badgujar, L. Zheng, S. Hu, Aj Purdy May 2020

Fire Progression, Ashwini Badgujar, L. Zheng, S. Hu, Aj Purdy

Creative Activity and Research Day - CARD

Fires have grown up to 70% in recent years. Fire Progression is a Machine Learning research project wherein we are trying to predict the direction in which the fire might grow in future. We are using Machine Learning technique and features like surface temperature, air temperature, moisture, precipitation and other additional parameters to predict the progression.


Active/Transfer Learning With Medical Imaging, Nicholas Kebbas, Maggie Lu May 2020

Active/Transfer Learning With Medical Imaging, Nicholas Kebbas, Maggie Lu

Creative Activity and Research Day - CARD

We've developed a robust web application to assist researchers in improving the accuracy of their Machine Learning Models. The system provides an image labeling web interface so that researchers can label and classify the models, and multiple data visualizations that help researchers identify and resolve inconsistencies between the classifications determined by their models and user feedback.


Evaluation Of Visualization Techniques For Communicating Off-Screen Data, Tony Jimenez May 2020

Evaluation Of Visualization Techniques For Communicating Off-Screen Data, Tony Jimenez

Creative Activity and Research Day - CARD

Worldwide, the use of mobile devices like tablets has begun to integrate themselves in people’s daily lives. People have thus begun to bring over desktop applications, more specifically visualization applications, into the mobile atmosphere. However, this brings forth some challenges, like how to manage screen space and how the visualizations should present the relevant information. Our take on this was to use various aggregations that would allow users to see data elements that would otherwise be off-screen. We thought it was best to create a variety of different aggregations, allowing us to figure out the best method of the group. …