TY - JOUR
T1 - Making Likelihood Ratios Digestible for Cross-Application Performance Assessment
AU - Nautsch, Andreas
AU - Meuwly, Didier
AU - Ramos, Daniel
AU - Lindh, Jonas
AU - Busch, Christoph
PY - 2017/9/4
Y1 - 2017/9/4
N2 - Performance estimation is crucial to the assessment of novel algorithms and systems. In detection error tradeoff (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 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
AB - Performance estimation is crucial to the assessment of novel algorithms and systems. In detection error tradeoff (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 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
KW - Bayes decision framework
KW - biometric verification
KW - binary decisions
KW - detection error tradeoff (DET)
KW - verbal scales
U2 - 10.1109/LSP.2017.2748899
DO - 10.1109/LSP.2017.2748899
M3 - Article
SN - 1070-9908
VL - 24
SP - 1552
EP - 1556
JO - IEEE signal processing letters
JF - IEEE signal processing letters
IS - 10
M1 - 17176768
ER -