期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2009
卷号：9
期号：6
页码：126-131
出版社：International Journal of Computer Science and Network Security
摘要：Software engineering measurement and analysis specifically, cost estimation initiatives have been in the center of attention for many firms. The use of the expert judgment and machine learning techniques using neural network as well as referencing COCOMO approach to predict the cost of software have shown their strength in solving complex problems of tolerating extreme inputs but as the number of inputs increases the complexity of the neural network is maximized. A novel computationally efficient Functional Link Artificial Neural Network (FLANN) is proposed for this purpose and to reduce the computational complexity so that the neural net becomes suitable for on-line applications. FLANN do not have any hidden layer; the architecture becomes simple and training does not involve full back propagation. In the course of adversity in neural networks, this dynamic neural network excellently works which will initially use COCOMO approach to predict the cost of software and uses FLANN technology with backward propagation. The proposed network processes each and every neuron crystal clear so that the entire network is completely ��white box��. This method gives much more accurate value when compared with others because our method involves proper training of data using back propagation algorithm which is used to train the network, becomes very simple because of absence of any hidden layer. As this method uses COCOMO as a base model, this model gives best estimate for the projects applied in Software Development Approach.
关键词：Functional Link Artificial Neural Networks (FLANN); Chebyshev Functional Link Artificial Neural Networks (C-FLANN); Legendre Functional Link Artificial Neural Networks (L-FLANN); Power Functional Link Artificial Neural Networks (P-FLANN);Constructive Cost
Loading...
