Hidden

Acoustic Emission Testing (AE) — Hidden Tier

(5 scenes)

Fully blind server-side evaluation — no data download.

What you get

No data downloadable. Algorithm runs server-side on hidden measurements.

How to use

Package algorithm as Docker container / Python script. Submit via link.

What to submit

Containerized algorithm accepting y + H, outputting x_hat + corrected spec.

Parameter Specifications

🔒

True spec hidden — blind evaluation, only ranges available.

Parameter Spec Range Unit
source_location_error -0.7 – 2.3 mm
wave_speed_error 5872.0 – 5992.0 m/s
sensor_coupling_gain 0.972 – 1.092 -
arrival_time_bias -0.07 – 0.23 us

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 DiffusionAE + gradient 0.618 23.87 0.764 0.87 ✓ Certified Song et al., ICLR 2021; SHM application 2024
2 SwinIR-AE + gradient 0.615 24.5 0.786 0.78 ✓ Certified Liang et al., ICCV 2021; AE-adapted 2024
3 Domain-Adapted ResNet + gradient 0.531 21.23 0.656 0.78 ✓ Certified Tabian et al., Sensors 2019
4 PINN-AE + gradient 0.522 21.15 0.652 0.75 ✓ Certified Raissi et al., J. Comput. Phys. 2019; AE extension 2024
5 PnP-ADMM + gradient 0.505 19.99 0.598 0.83 ✓ Certified Venkatakrishnan et al., IEEE GlobalSIP 2013
6 AE-CNN + gradient 0.489 19.72 0.585 0.79 ✓ Certified Ebrahimkhanlou & Salamone, Struct. Health Monit. 2019
7 TDOA-WLS + gradient 0.430 17.4 0.47 0.84 ✓ Certified Kundu, J. Acoust. Soc. Am. 2014
8 Sparse TR (L1) + gradient 0.398 16.4 0.421 0.83 ✓ Certified Gao et al., J. Sound Vib. 2016
9 Time-Reversal Imaging + gradient 0.393 16.42 0.422 0.8 ✓ Certified Fink, IEEE UFFC 1992; applied to AE: Grosse & Ohtsu 2008

Dataset

Scenes: 5

Scoring Formula

0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)

PSNR: 40% SSIM: 40% Consistency: 20%
Back to Acoustic Emission Testing (AE)