English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The use of Deep Neural Network (DNN) models in risk-based decision-making hasattracted extensive attention with broad applications in medical, finance,manufacturing, and quality control. To mitigate prediction-related risks indecision making, prediction confidence or uncertainty should be assessedalongside the overall performance of algorithms. Recent studies on Bayesiandeep learning helps quantify prediction uncertainty arises from input noisesand model parameters. However, the normality assumption of input noise in thesemodels limits their applicability to problems involving categorical anddiscrete feature variables in tabular datasets. In this paper, we propose amathematical framework to quantify prediction uncertainty for DNN models. Theprediction uncertainty arises from errors in predictors that follow some knownfinite discrete distribution. We then conducted a case study using theframework to predict treatment outcome for tuberculosis patients during theircourse of treatment. The results demonstrate under a certain level of risk, wecan identify risk-sensitive cases, which are prone to be misclassified due toerror in predictors. Comparing to the Monte Carlo dropout method, our proposedframework is more aware of misclassification cases. Our proposed framework foruncertainty quantification in deep learning can support risk-based decisionmaking in applications when discrete errors in predictors are present.

Quantifying Uncertainty in Deep Learning Classification with Noise in Discrete Inputs for Risk-Based Decision Making