One-against-all and one-against-one based neuro-fuzzy classifiers

摘要: This paper introduces a neuro-fuzzy framework for handling multi-class classification problems. Instead of decomposing such problems into simple sub-problems and solving each part using different classifier, the proposed system decomposes implements entire problem automatically in same framework. The decomposition is performed most commonly used methods dividing problems: OAA (one-against-all) OAO (one-against-one). Consequently, two models are introduced: based classifiers. design on implementation sub-problem set weights. learning by adjusting every independently, without parameters membership functions. considerably simplifies tasks. After stage, systems act as single-module classifier recognizing new examples.