کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
389019 660956 2007 13 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
A PSO-aided neuro-fuzzy classifier employing linguistic hedge concepts
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر هوش مصنوعی
پیش نمایش صفحه اول مقاله
A PSO-aided neuro-fuzzy classifier employing linguistic hedge concepts
چکیده انگلیسی

The present paper proposes the development of an adaptive neuro-fuzzy classifier which employs two relatively less explored and comparatively new problem solving domains in fuzzy systems. The relatively less explored field is the domain of the fuzzy linguistic hedges which has been employed here to define the flexible shapes of the fuzzy membership functions (MFs). To achieve finer and finer adaptation, and hence control, over the fuzzy MFs, each MF is composed of several piecewise MF sections and the shape of each such MF section is varied by applying a fuzzy linguistic operator on it. The system employs a Takagi–Sugeno based neuro-fuzzy system where the rule consequences are described by zero order elements. This proposed linguistic hedge based neuro-fuzzy classifier (LHBNFC) employs a relatively new field in the area of combinatorial metaheuristics, called particle swarm optimization (PSO), for its efficient learning. PSO has been employed in this scheme to simultaneously tune the shape of the fuzzy MFs as well as the rule consequences for the entire fuzzy rule base. The performance of the proposed system is demonstrated by implementing it for two classical benchmark data sets: (i) the iris data and (ii) the thyroid data. Performance comparison vis-à-vis other available algorithms shows the effectiveness of our proposed algorithm.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Expert Systems with Applications - Volume 33, Issue 4, November 2007, Pages 1097–1109
نویسندگان
, ,