ROLE OF ANN AND FUZZY IN SOFTWARE COST ESTIMATION
MAHSA HASSANKASHI
Department of Computer Science and Engineering, Ovidius GmbH, Berlin, Germany.
DINESH BHAGWAN HANCHATE *
Department of Computer Engineering, VP’s KBIET, Baramati, Pune, India
*Author to whom correspondence should be addressed.
Abstract
This paper aims to provide a novel methodology for cost estimated; it is a hybrid of artificial neural network back propagation which is a computational approach and fuzzy logic, which is a propositional calculus based on functional point of the training data set. These kind of solutions are regardless of mathematical views of the problem and it is useful for such case which does not have precise inputs, for instance in software cost estimation. There are different methods in four major categories such as algorithmic COCOMO-II (Constructive Cost Model) model, functional point, analogy, expert judgment, top down and bottom down method which have their own cons and pros.Their merits will be discussed in comparison with the methodology of the hybrid off ANN BP (Artificial Neural Network Back Propogation) and fuzzy and functional point; in order to achieve their advantages and disadvantages. It will lead us to know that which method should be used with specific conditions.
Keywords: Software cost estimation, machine learning, artificial neural network, ANN, back propagation, fuzzy logic