Adaptive neuro - fuzzy model for assessing the reliability of component software systems
No Thumbnail Available
Date
Journal Title
Journal ISSN
Volume Title
Publisher
Research Parks Publishing LLC
Abstract
Description
Although many algorithms and methods have been developed for assessing the reliability of component software systems (CBSS), much more research is needed. An accurate assessment of the reliability of CBSS is difficult because it depends on two factors: the reliability of the components and the reliability of the glue code. Moreover, reliability is a real-world phenomenon associated with many real-time problems. Soft computing techniques can help solve problems for which solutions are uncertain or unpredictable. A number of soft computing approaches have been proposed to assess the reliability of CBSS. These methods learn from the past and capture existing patterns in the data. The two main elements of soft computing are neural networks and fuzzy logic. In this article, we propose a model for assessing the reliability of CBSS, known as Adaptive Neural Fuzzy Inference System (ANFIS), which builds on these two basic elements of soft computing, and compare its performance to that of a simple FIS (Fuzzy Inference System) for different datasets
Keywords
neuro-fuzziness, omponent Software Systems (CBSS), Fuzzy, Reliability, Reliability model