Learn More
Introduction An important need, especially for space-borne applications, is the early identification and rejection of laser diode arrays which may fail prematurely. The search for reliable failure predictors is ongoing and has led to the development of two techniques, infrared imagery and monitoring the Temporally-resolved and Spectrally-Resolved (TSR)(More)
Lack of classifier robustness is a barrier to widespread adoption of computer-aided diagnosis systems for computed tomography (CT). We propose a novel Robustness-Driven Feature Selection (RDFS) algorithm that preferentially selects features robust to variations in CT technical factors. We evaluated RDFS in CT classification of fibrotic interstitial lung(More)
  • 1