An Optimized Neuro-Fuzzy Network for Software Project Effort Estimation

Abstract

Estimating software effort is an essential project management practice. The software effort estimation is the process of predicting the time and efforts required in the development of software projects. Estimating software cost is a critical challenge during the planning stage. Due to the lack of availability of quality data and the dynamic nature of software development, accurate estimation is difficult. This paper proposes an efficient software cost estimation method for the Genetic Elephant Herding Optimization-based Neuro-Fuzzy Network (GEHO-based NFN). In this method, a neuro-fuzzy network (NFN) is used to predict the software efforts in terms of cost. The training of this NFN is optimized using the genetic elephant herding optimization (GEHO) method, which combines the features of the genetic algorithm (GA) and the elephant herding optimization (EHO) techniques. The performance of the developed method was evaluated using five historical & benchmark datasets from the industrial projects. These are based on the four widely used performance evaluation metrics, such as Mean magnitude of relative Error (MMRE), Median magnitude of relative error (MdMRE), Root Mean Square Error (RMSE), and Prediction Accuracy (PRED). The Comparative analysis and experimental results of the proposed method conclude that the performance of the GEHO-based NFN method is better than other popular soft computing methods like Linear regression, Support Vector Regression (SVR), Wavelet ANN (WNN), and Decision Tree (DT) based Software project effort estimation (SPEE) methods.