The rapid development of new learning algorithms increases the need for improved accuracy estimation methods. Moreover, methods allowing the comparison of several different learning algorithms are important for the performance evaluation of new ones. In this paper we propose new accuracy estimation methods which are extensions of the k-fold cross-validation method. The methods proposed construct cross-validation folds deterministically instead of using the random sampling approach. The deterministic construction of folds is performed using unsupervised stratification by exploiting the distribution of instances in the instance space. Our methods are based either on the one-center approach or on clustering procedures. These methods attempt to construct more representative folds, therefore reducing the bias of the resulting estimator. At the same time, our methods allow direct comparisons between the performance of learning algorithms in different experiments, since no randomness is present. A simulation experiment examining the performance of the proposed methods is reported, depicting their behavior in a variety of situations. The new methods reduce mainly the bias of the estimator.
Various organisations have published proposals to prescribe the form and content of software requirements specification documents; the standards were designed to support the specific needs of these organisations and the intricacies of their development projects. To help third parties in taking advantage of this body of work, a set of criteria are proposed and discussed that can be used to evaluate such standards, according to the unique characteristics of specific combinations of organisations and software development projects, and then the question of how the criteria can be applied in an evaluation, selection and tailoring process, depending on the circumstances, is discussed. Finally, the criteria are demonstrated by applying them on some published standards, to help interested organisations to preselect those that seem most appropriate for their needs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.