Search results

The functionality, compatibility, and longevity planned for future digital talking books require clear, exact definitions of component format and content. NLS will achieve this by working with a diverse team of experts to establish an applicable standard. This article outlines the plan, describes progress, and indicates what further work is necessary to complete the standard.

The National Library Service (NLS) produces about 2,000 talking books and 50 magazines per year on specially formatted cassette tape for free distribution to a readership of about 764,000. Cassettes and special players are delivered by US Postal Service from a network of 138 participating libraries. To control the cost of technical obsolescence and to meet patron and sponsor expectations, NLS will replace this analog system with a digital system over the next ten years.

Advocates the use of CD‐ROM technology to enable blind or visually impaired library users to access information, which can be downloaded on to a disk and then treated in one of three ways: it can be translated into and printed in Braille; it can have the text enlarged sufficiently for a visually impaired person to read it; or it can be read aloud by screen‐reading software. Evaluates some of the reference CD‐ROMs available and lists the equipment that will be needed in order to provide access for the users.

Statistical methods of spatial analysis are often successful at either prediction or explanation, but not necessarily both. In a recent paper, Dearmon and Smith (2016) showed that by combining Gaussian Process Regression (GPR) with Bayesian Model Averaging (BMA), a modeling framework could be developed in which both needs are addressed. In particular, the smoothness properties of GPR together with the robustness of BMA allow local spatial analyses of individual variable effects that yield remarkably stable results. However, this GPR-BMA approach is not without its limitations. In particular, the standard (isotropic) covariance kernel of GPR treats all explanatory variables in a symmetric way that limits the analysis of their individual effects. Here we extend this approach by introducing a mixture of kernels (both isotropic and anisotropic) which allow different length scales for each variable. To do so in a computationally efficient manner, we also explore a number of Bayes-factor approximations that avoid the need for costly reversible-jump Monte Carlo methods.

To demonstrate the effectiveness of this Variable Length Scale (VLS) model in terms of both predictions and local marginal analyses, we employ selected simulations to compare VLS with Geographically Weighted Regression (GWR), which is currently the most popular method for such spatial modeling. In addition, we employ the classical Boston Housing data to compare VLS not only with GWR but also with other well-known spatial regression models that have been applied to this same data. Our main results are to show that VLS not only compares favorably with spatial regression at the aggregate level but is also far more accurate than GWR at the local level.