We study the problem of identifying the best arm(s) in the stochastic multi-armed bandit setting. This problem has been studied in the literature from two different perspectives: fixed budget and fixed confidence. We propose a unifying approach that leads to a meta-algorithm called unified gap-based exploration (UGapE), with a common structure and similar theoretical analysis for these two sett...

Our original paper [1] included two Bayesian analyses [2] of the association between brain size and the probability of a passerine species of bird breeding in the city centre—at the level of families and at the level of individual species—with both analyses suggesting the same pattern. It has since been brought to our attention that in one of the analyses at the level of individual species, the...

In traditional applications of latent variable models, each exogenous latent variable must either have its variance parameter fixed or a loading path to a measured indicator variable fixed (either customarily to 1). Without doing so the measurement model will suffer from underidentification, thereby yielding no unique solution when estimating the parameters of interest. The choice of whether to...

This paper analyzes the problem of the spectral enhancement technique using global variance (GV) in HMM-based speech synthesis. In the conventional GV-based parameter generation, spectral enhancement with variance compensation is achieved by considering a GV pdf with fixed parameters for every output utterances through the generation process. Although the spectral peaks of the generated traject...

Magnetic resonance imaging (MRI) of the brain provides important outcome measures in the longitudinal evaluation of disease activity and progression in MS subjects. Two common measures derived from brain MRI scans are the brain parenchymal fraction (BPF) and T2 hyperintense lesion volume (T2LV), and these measures are routinely assessed longitudinally in clinical trials and observational studie...

Sequencing by synthesis is used in many next-generation DNA sequencing technologies. Some of the technologies, especially those exploring the principle of single-molecule sequencing, allow incomplete nucleotide incorporation in each cycle. We derive statistical distributions for sequencing by synthesis by taking into account the possibility that nucleotide incorporation may not be complete in e...

We study wave propagation in a one-dimensional disordered array of scattering potentials. We consider three different ensembles of scatterer configurations: an N-ensemble with a fixed number N of scatterers, an L-ensemble with a varying number of scatterers distributed over a fixed length L, and an NL-ensemble where both N and L are fixed. The latter ensemble allows a detailed study of the mean...

Generalized variance|S|quality control chart is very powerful way to detect small shifts in the mean vector. The main purpose of this paper, presents an improved the generalized variance |S|quality control chart for multivariate process. Generalized variance chart allow us to simultaneously monitor whether joint variability of two or more related variables is in control. In addition, a control ...

We present a new signal processing method that extracts the reference spectrum information from an acquired optical coherence tomography (OCT) image without a separate calibration step of reference spectrum measurement. The reference spectrum is used to remove the fixed-pattern noise that is a characteristic artifact of Fourier-domain OCT schemes. It was found that the conventional approach bas...

Increased reliance upon outsourcing has made the issue of vendor selection even more critical to the success of the modern manufacturing organization. The usual performance measure on which selection is based has been the distribution of the vendor’s delivery lead-time (LT), often as characterized by the mean and variance. In this paper, we show that the distribution of demand per unit time (DP...