An Improved Cost Estimation in Software Project Development Using Neural Networks and COCOMOII model

Abstract

An sympathetic of quality aspects is relevant for the software association to deliver high software dependability. An empirical consideration of metrics to prophesy the quality attributes is basic in order to acquire insight about the value of software in the primitive phases of software development and to certify corrective actions. Herein paper, we forecast a model to assess fault proneness via Object Oriented CK metrics and QMOOD metrics. We pertain one statistical method and six machine learning technique to predict the models. The proposed reproduction are validated using dataset unruffled from Open Source software. The consequences are analyzed using Area Under the Curve (AUC) achieve from Receiver Operating Characteristics (ROC) testing. The results show that the replica predicted using the random forest and bagging methods outperformed all the other mould. Hence, support on these results it is equitable to claim that quality models have a considerable relevance with Object Oriented metrics and that machine learning organizations have a equivalent performance with numerical methods. It is experimental that the CBR routine using the Mahalanobis detachment similarity occupation moreover the inverse distance weighted solution algorithm yielded the best fault prediction. In addition, the CBR models have superior performance than models basis on multiple linear regression.

Authors and Affiliations

Archana. R| Student of M.Tech (CSE) and Department of Computer Science Engineering, AITAM, Tekkali, Srikakulam, Ravikumar. T| Asst.Prof in Department of Computer Science Engineering, AITAM, Tekkali, Srikakulam

Keywords

Related Articles

Virus Attack Identification And Representation In Sensor Network

Clusters consist of circulated sensors and motor that interact with each other via wireless network. The use of open wireless intermediate and unattended deployment leaves these systems vulnerable to intelligent adve...

Detailed Analysis On Security And Performance Of Anonycontrol and Anonycontrol-F

Computing resources are make available enthusiastically via Internet and the data storage and computation are outsourced to somebody or some party in a ‘cloud. It very much pull towards you attention and interest f...

Conflict Resolution Ethos on Concessions Users for Privacy Preferences

The absence of multi-party protection administration bolster in current standard Social Media foundations makes clients not able to suitably control to whom these things are really shared or not. Computational compon...

A Study To Support First-N Queries And Incremental Updates To Answer Multi Keyword Queries

Most search engines and online search forms maintain auto completion which demonstrates suggested queries or even answers on the fly as a user types in a keyword query character by character. As many search systems a...

Grid Connected Single Phase Rooftop Pv System With Limited Reactive Power Supply

In this paper SRF theory based PV system with MPPT DC-DC controller for grid connected single phase rooftop system have been presented. Photovoltaic (PV) systems are the alternative source of generation because these...

Download PDF file
  • EP ID EP16489
  • DOI -
  • Views 320
  • Downloads 14

How To Cite

Archana. R, Ravikumar. T (2015). An Improved Cost Estimation in Software Project Development Using Neural Networks and COCOMOII model. International Journal of Science Engineering and Advance Technology, 3(4), 143-146. https://europub.co.uk/articles/-A-16489