Neural Network Approaches for Software Development Time Estimation: A Review

Abstract

Software effort estimation calculates the effort necessary to complete the project, in term of scheduling, acquiring resources, and meeting costs. The aims of researchers have been: first is to determine which technique has the greatest effort prediction accuracy and secondly to propose new or combined techniques that could provide better estimates. Most of the research has focused on the construction of formal models and the early models were typically statistical regression-based. This paper presents an Adaptive Neuro-Fuzzy Approach for Software Development Time Estimation. This proposed technique is aimed at building and evaluating a Neuro - fuzzy model for software project development time. The forty one modules were used as a data set. Our proposed approach is software development time estimation method show the proposed ANFIS model gives new approach and ideas as compared to different types of neural network models. In the proposed method accurate estimation of software development time will be done and the results of Neuro Fuzzy approach will be compared with different types of neural network models based upon various parameters such as Root Mean Squared Error (RMSE), Relative Standard Deviation (RSD), Magnitude of Relative Error (MRE), Mean Magnitude of Relative Error (MMRE), Balanced Relative Error (BRE) and Prediction (Pred).

Authors and Affiliations

Vidisha Agrawal, Vishal Shrivastava

Keywords

Related Articles

Construction of control chart based on six sigma initiatives for Cumulative – Sum

A control chart is a statistical device used for the study and control of repetitive process. W.A. Shewhart [6] of Bell Telephone Laboratories suggested control charts based on the 3 sigma limits. Now the companies in d...

An Efficient System to Access Network Using Time Based Scheduling and Automatic Database Creation Using Data Perturbation

With the wide deployment of public cloud computing infrastructures the time constrain based system is required. Using clouds to host data query services has become an appealing solution for the advantages on scalability...

Aerodynamic Characteristic Analysis of UAV (Unmanned Aerial Vehicle) By Using CFD

the paper discusses the aerodynamics behavior of a baseline design and analysis of a UAV (Unmanned Aerial Vehicle). Analysis is presented, i.e. Steady-state, three- dimensional Computational Fluid Dynamics (CFD) at Mach...

Analysing the Effect of Unified Power Flow Controller on Power System Performance

The objective of the planning and operation of an electric power system is to satisfy the system load and energy requirement as economically as possible. Therefore, the system planner has to consider a variety of option...

Formability Analysis in Incremental Sheet Forming Of Aluminium Alloy

Non-corrosiveness and lightweight are the characteristics of aluminium due to which it is finding wider application in industries. However, forming aluminium sheet is difficult as compared to steel. Thus, emerging metho...

Download PDF file
  • EP ID EP19645
  • DOI -
  • Views 297
  • Downloads 4

How To Cite

Vidisha Agrawal, Vishal Shrivastava (2015). Neural Network Approaches for Software Development Time Estimation: A Review. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 3(3), -. https://europub.co.uk/articles/-A-19645