Improved Effort and Cost Estimation Model Using Artificial Neural Networks and Taguchi Method with Different Activation Functions

Abstract

Software estimation involves meeting a huge number of different requirements, such as resource allocation, cost estimation, effort estimation, time estimation, and the changing demands of software product customers. Numerous estimation models try to solve these problems. In our experiment, a clustering method of input values to mitigate the heterogeneous nature of selected projects was used. Additionally, homogeneity of the data was achieved with the fuzzification method, and we proposed two different activation functions inside a hidden layer, during the construction of artificial neural networks (ANNs). In this research, we present an experiment that uses two different architectures of ANNs, based on Taguchi’s orthogonal vector plans, to satisfy the set conditions, with additional methods and criteria for validation of the proposed model, in this approach. The aim of this paper is the comparative analysis of the obtained results of mean magnitude relative error (MMRE) values. At the same time, our goal is also to find a relatively simple architecture that minimizes the error value while covering a wide range of different software projects. For this purpose, six different datasets are divided into four chosen clusters. The obtained results show that the estimation of diverse projects by dividing them into clusters can contribute to an efficient, reliable, and accurate software product assessment. The contribution of this paper is in the discovered solution that enables the execution of a small number of iterations, which reduces the execution time and achieves the minimum error.

Influence of input values on the prediction model error using artificial neural network based on Taguchi's orthogonal array

“…The number of iterations required for a complete factorial analysis is N = L P (e.g., when three levels with The main advantages of this model are the relatively straightforward architecture of the presented construction of the artificial neural network ANN-L36, wide coverage of different projects, the minimal number of iterations, reduced execution time of iterations, and reliability of the obtained results. 40,41 Additional extensions to this model could be validation on different datasets and by the introduction of other criteria. There are no limitations in applying this model.…”

Evaluating Kernel Functions in Software Effort Estimation: A Comparative Study of Moving Window and Spectral Clustering Models Across Diverse Datasets

“…Azzeh et al addressed the issue of determining the number of projects nearby using a method known as bisecting k-medoids [14]. It is shown in [15] that grouping of varied projects into clusters can aid in accurate evaluation. In this paper, it is confirmed that clustering improves estimate accuracy.…”

Spectral Clustering Effect in Software Development Effort Estimation

“…Azzeh et al, addressed the issue of determining the number of nearby projects by using a method known as bisecting k-medoids [10]. It is demonstrated in [11] that grouping varied projects into clusters can aid to accurate assessment. In this paper is confirmed that clustering improves estimate accuracy.…”

“…All experiments were evaluated using the following criteria [37][38][39]: mean absolute residual (MAR), calculated by using (7), mean magnitude of the relative error (MMRE), as in (8), percentage relative error deviation (PRED), as in (9), and mean absolute percentage error (MAPE), as in (10). Finally, the sum of squared errors (11) and mean squared error (MSE), as in (12), were included in the evaluation.…”