- Full text PDF available (2)
- This year (1)
- Last five years (4)
In this paper, we describe our experiments using Latent Dirichlet Allocation (LDA) to model images containing both perceptual features and words. To build a large-scale image tagging system, we distribute the computation of LDA parameters using MapReduce. Empirical study shows that our scalable LDA supports image annotation both effectively and efficiently.
BACKGROUND Recently, the total prostate-specific antigen (PSA) assay used in a laboratory had a positive bias of 0.03 μg/L, which went undetected. Consequently, a number of post-prostatectomy patients with previously undetectable PSA concentrations (defined as <0.03 μg/L in that laboratory) were being reported as having detectable PSA, which suggested… (More)
BACKGROUND Between-reagent lot verification is a routine laboratory exercise in which a set of samples is tested in parallel with an existing reagent lot and a candidate reagent lot (before the candidate lot is committed to test patient samples). The exercise aims to verify and maintain consistency in the analytical performance of a test. We examined the… (More)
OBJECTIVES "Average of normal" (AoN) or "moving average" is increasingly used as an adjunct quality control tool in laboratory practice. Little guidance exists on how to verify if an out-of-control situation in the AoN chart is due to a shift in analytical performance, or underlying patient characteristics. DESIGN AND METHODS Through simulation based on… (More)