A Novel Neural Network Approach For Software Cost Estimation Using Functional Link Artificial Neural Network (FLANN)
B. Tirimula Rao, B. Sameet, Kavya Gupta · 2009
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