RUI: Knowledge Processing with Interval Methods

点击翻译按钮获取中文摘要

Abstract - RUI: Knowledge processing with interval methodsThis research investigates knowledge processing with interval methods. Modern technologies have evolved collections of massive datasets from observations, experiments, and scientific simulation. However, it remains a significant challenge to effectively process these datasets to discover knowledge effectively and efficiently. Knowledge processing with interval methods has intrinsic merit. First, qualitative properties are often presented as ranges of data attributes rather than specific points. By grouping attribute values into meaningful intervals, insignificant quantitative differences can be ignored, allowing an increased focus on qualitative processing. More importantly, interval-valued attributes contain more information than points, representing variability and uncertainty. Finally, in practice, interval-valued computational results can be more meaningful and useful than point values. This study involves theories and algorithms for dataset interval representation, interval ordering relations, interval matrix decomposition and principal component analysis, inner approximation of interval solutions, interval-valued rule generation, and a portable computational environment for knowledge processing with interval methods. This research expands current knowledge on interval-valued data. The theoretical and algorithmic results of this research should have broad applicability to computing, especially for handling variability and uncertainty. In addition, this research project enhances the quality of education at a predominantly undergraduate institution and produce more high quality computer science graduates for Arkansas, a state which lags behind the nation in STEM workforce training.