Comparing the quality of neural network uncertainty estimates for classification problems

no code implementations • 11 Aug 2023 • Daniel Ries, Joshua Michalenko, Tyler Ganter, Rashad Imad-Fayez Baiyasi, Jason Adams

We apply these different UQ for DL methods to a hyperspectral image target detection problem and show the inconsistency of the different methods' results and the necessity of a UQ quality metric.

Decision Making Uncertainty Quantification +1

Target Detection on Hyperspectral Images Using MCMC and VI Trained Bayesian Neural Networks

no code implementations • 11 Aug 2023 • Daniel Ries, Jason Adams, Joshua Zollweg

Both MCMC- and VI-trained BNN perform well overall at target detection on a simulated HSI scene.

Image Classification Uncertainty Quantification +1

Deep Learning-Based Detection of the Acute Respiratory Distress Syndrome: What Are the Models Learning?

no code implementations • 25 Sep 2021 • Gregory B. Rehm, Chao Wang, Irene Cortes-Puch, Chen-Nee Chuah, Jason Adams

The acute respiratory distress syndrome (ARDS) is a severe form of hypoxemic respiratory failure with in-hospital mortality of 35-46%.

Feature Engineering Respiratory Failure +1

Clinical Validation of Single-Chamber Model-Based Algorithms Used to Estimate Respiratory Compliance

no code implementations • 19 Sep 2021 • Gregory Rehm, Jimmy Nguyen, Chelsea Gilbeau, Marc T Bomactao, Chen-Nee Chuah, Jason Adams

Non-invasive estimation of respiratory physiology using computational algorithms promises to be a valuable technique for future clinicians to detect detrimental changes in patient pathophysiology.