Is this project an undergraduate, graduate, or faculty project?

Undergraduate

Project Type

group

Campus

Daytona Beach

Authors' Class Standing

Daniel Wilczak, Senior Jack Nguyen, Senior

Lead Presenter's Name

Daniel Wilczak

Lead Presenter's College

DB College of Arts and Sciences

Faculty Mentor Name

Dr Berezovski, Mihhail

Abstract

Optical absorption spectroscopy is an important characterization of materials for applications such as solar energy generation. The purpose of the study is to build an ensemble neural network for predicting metal oxide spectrograms from images of metal oxide that have been scanned. With an ensemble network, several models are trained to produce a variety of predictions. By averaging these predictions, an even more accurate prediction can be made. Furthermore, uncertainty quantification will be applied by measuring the variance between the predictions, allowing more useful statistical analysis to be done such as producing confidence intervals to determine how accurate the results are. The study is done through a quantitative empirical research method. The research is a collaboration with Nevada National Security Site.

Did this research project receive funding support (Spark, SURF, Research Abroad, Student Internal Grants, Collaborative, Climbing, or Ignite Grants) from the Office of Undergraduate Research?

No

Share

COinS
 

Building an ensemble neural network optimized using uncertainty quantification for predicting metal oxide spectrograms from scanned metal oxide images.

Optical absorption spectroscopy is an important characterization of materials for applications such as solar energy generation. The purpose of the study is to build an ensemble neural network for predicting metal oxide spectrograms from images of metal oxide that have been scanned. With an ensemble network, several models are trained to produce a variety of predictions. By averaging these predictions, an even more accurate prediction can be made. Furthermore, uncertainty quantification will be applied by measuring the variance between the predictions, allowing more useful statistical analysis to be done such as producing confidence intervals to determine how accurate the results are. The study is done through a quantitative empirical research method. The research is a collaboration with Nevada National Security Site.

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.