2018
DOI: 10.5815/ijitcs.2018.03.05
|View full text |Cite
|
Sign up to set email alerts
|

Machine Learning Application to Improve COCOMO Model using Neural Networks

Abstract: Abstract-Millions of companies expend billions of dollars on trillions of software for the development and maintenance. Still many projects result in failure causing heavy financial loss. Major reason is the inefficient effort estimation techniques which are not so suitable for the current development methods. The continuous change in the software development technology makes effort estimation more challenging. Till date, no estimation method has been found full-proof to accurately pre-compute the time, money,… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
17
0

Year Published

2019
2019
2021
2021

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 20 publications
(17 citation statements)
references
References 18 publications
0
17
0
Order By: Relevance
“…This experiment is performed on the Kemerer validation dataset divided in three clusters like as in step 1. In his papers [38], [22] he used data collected from 63 completed software projects to produce results. He also recognized the three main attributes which affect the results of the software productivity.…”
Section: B Orthogonal Array Tuning Methodsmentioning
confidence: 99%
See 2 more Smart Citations
“…This experiment is performed on the Kemerer validation dataset divided in three clusters like as in step 1. In his papers [38], [22] he used data collected from 63 completed software projects to produce results. He also recognized the three main attributes which affect the results of the software productivity.…”
Section: B Orthogonal Array Tuning Methodsmentioning
confidence: 99%
“…It was shown that the COCOMO the evaluated cost is closer to the actual cost. Goyal S. and experiments by other authors listed [22] proposed the ML approach to improve COCOMO Model using ANNs, but the results of MRE were large. An interesting study that was conducted [23] included the use of a Neural Network algorithm to evaluate the software cost with accuracy but neither of the methods mentioned is confidently better or worse than the other.…”
Section: Literature Reviewmentioning
confidence: 98%
See 1 more Smart Citation
“…GA is focused on a number of feasible alternatives to the issue, which are improving iteratively. The creation of forecast systems and wide-ranging data processing [18] is associated with the majority of GA apps. The objective of the present study is to tone COCOMO coefficients, especially COCOMO-II Coefficients of the post Architecture model using the online GA Data Series and some new data collected from the Project.…”
Section: Introductionmentioning
confidence: 99%
“…The process of estimating the amount of effort which is expressed in final cost or person-hours for developing a software project is termed as Software development effort estimation. The inputs which are taken for this prediction process are budgets, project plans, analysis of investment, bidding rounds and plans of iterations [1,2,3]. From the last few decades, the process for developing software for various software related project has advanced through heterogeneous stages.…”
Section: Introductionmentioning
confidence: 99%