Using meta-cognitive sequential learning Neuro-fuzzy inference system to estimate software development effort
- PDF / 1,353,015 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 83 Downloads / 189 Views
ORIGINAL RESEARCH
Using meta‑cognitive sequential learning Neuro‑fuzzy inference system to estimate software development effort E. Praynlin1 Received: 20 March 2020 / Accepted: 27 October 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Software development effort estimation plays a crucial role in the successful completion of any software development project. Estimating the software development effort accurately is one of the challenges in the software industry. In this paper a soft computing technique named Meta Cognitive sequential learning is used to improve the software development effort estimate of a software project. Different datasets namely, Deshernais, NASA, Kitchenham, Maxwell, Telecom, IBM, Kemerer, Hallmark and ISBSG are used in the training and testing of the estimation process. The performance comparison of the former method is compared with other methods such as Particle swarm optimization, Genetic Algorithm and Back propagation network using Mean magnitude of relative error (MMRE) parameter. It is found that the MMRE of Meta cognitive neuro fuzzy method is less than the MMRE of other methods taken for comparison. Thus the Meta cognitive neuro fuzzy method can produce a better estimate of the software development effort and hence can produce an estimate with much precision to the actual effort. Keywords Software development · Effort estimation · Meta cognitive neuro fuzzy inference system (McNFIS)
1 Introduction When computer era began, there were very few computers and their application was mostly small. In recent years, software has become more important in many domains. Quality of the developed software also plays an important role. The poor quality software may even lead to business failure. Software project managers usually estimate the software development effort, cost and duration in the early stage of the software development. Software cost estimation at the early stage of software development holds great significance to the industry to meet the competitive demand of today’s world (Sharma and Verma 2010). All Industries are in a situation to develop a software of high quality with less cost and less time. Two types of estimation, namely, over estimation and under estimation occur while estimating effort. In the case of overestimation, the calculated cost exceeds the actual cost. * E. Praynlin [email protected]; [email protected] 1
Department of Electronics and Communication Engineering, V V College of Engineering, Tisaiyanvillai, Triunelveli, Tamil Nadu, India
Where as in the case of under estimation, the calculated cost falls below the actual cost. Overestimation leads to loss of project during bidding, too much allocation of resource to a project etc. Under estimation leads to financial loss, insufficient resource to the project and hence leads to low quality of software (Praynlin and Latha 2018). Software effort estimation mainly involves the estimation of cost, effort and schedule. All the three parameters effort cost and schedule are interrelated
Data Loading...
