Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Making Likelihood Ratios Digestible for Cross-Application Performance Assessment

Abstract: 

Performance estimation is crucial to the assessment of novel algorithms and systems. In detection error trade-off (DET) diagrams, discrimination performance is solely assessed targeting one application, where cross-application performance considers risks resulting from decisions, depending on application constraints. For the purpose of interchangeability of research results across different application constraints, we propose to augment DET curves by depicting systems regarding their support of security and convenience levels. Therefore, application policies are aggregated into levels based on verbal likelihood ratio scales, providing an easy to use concept for business-to-business (B2B) communication to denote operative thresholds. We supply a reference implementation in Python, an exemplary performance assessment on synthetic score distributions, and a fine-tuning scheme for Bayes decision thresholds, when decision policies are bounded rather than fix.

up
0 users have voted:

Paper Details

Authors:
Andreas Nautsch, Didier Meuwly, Daniel Ramos, Jonas Lindh, Christoph Busch
Submitted On:
12 April 2018 - 1:11pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Andreas Nautsch
Paper Code:
4717
Document Year:
2018
Cite

Document Files

poster.pdf

(71 downloads)

Subscribe

[1] Andreas Nautsch, Didier Meuwly, Daniel Ramos, Jonas Lindh, Christoph Busch, "Making Likelihood Ratios Digestible for Cross-Application Performance Assessment", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2447. Accessed: Sep. 24, 2018.
@article{2447-18,
url = {http://sigport.org/2447},
author = {Andreas Nautsch; Didier Meuwly; Daniel Ramos; Jonas Lindh; Christoph Busch },
publisher = {IEEE SigPort},
title = {Making Likelihood Ratios Digestible for Cross-Application Performance Assessment},
year = {2018} }
TY - EJOUR
T1 - Making Likelihood Ratios Digestible for Cross-Application Performance Assessment
AU - Andreas Nautsch; Didier Meuwly; Daniel Ramos; Jonas Lindh; Christoph Busch
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2447
ER -
Andreas Nautsch, Didier Meuwly, Daniel Ramos, Jonas Lindh, Christoph Busch. (2018). Making Likelihood Ratios Digestible for Cross-Application Performance Assessment. IEEE SigPort. http://sigport.org/2447
Andreas Nautsch, Didier Meuwly, Daniel Ramos, Jonas Lindh, Christoph Busch, 2018. Making Likelihood Ratios Digestible for Cross-Application Performance Assessment. Available at: http://sigport.org/2447.
Andreas Nautsch, Didier Meuwly, Daniel Ramos, Jonas Lindh, Christoph Busch. (2018). "Making Likelihood Ratios Digestible for Cross-Application Performance Assessment." Web.
1. Andreas Nautsch, Didier Meuwly, Daniel Ramos, Jonas Lindh, Christoph Busch. Making Likelihood Ratios Digestible for Cross-Application Performance Assessment [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2447