Neural Network model for software size estimation using Use Case Point approach

Ajitha, S.; Kumar, T. V. Suresh; Geetha, D. Evangelin; Kanth, K. Rajani

doi:10.1109/iciinfs.2010.5578675

Cited by 19 publications

(15 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A Treeboost model [7] was used to estimate effort based on UCP and team productivity. Neural network based models [5][6] [31] have also been used to predict the software effort. The inputs of these neural network models include software size in UCP and other quality attributes such as complexity.…”

Section: Related Workmentioning

confidence: 99%

A hybrid model for estimating software project effort from Use Case Points

Azzeh

Nassif

2016

Applied Soft Computing

View full text Add to dashboard Cite

Early software effort estimation is a hallmark of successful software project management. Building a reliable effort estimation model usually requires historical data. Unfortunately, since the information available at early stages of software development is scarce, it is recommended to use software size metrics as key cost factor of effort estimation. Use Case Points (UCP) is a prominent size measure designed mainly for object-oriented projects. Nevertheless, there are no established models that can translate UCP into its corresponding effort; therefore, most models use productivity as a second cost driver. The productivity in those models is usually guessed by experts and does not depend on historical data, which makes it subject to uncertainty. Thus, these models were not well examined using a large number of historical data. In this paper, we designed a hybrid model that consists of classification and prediction stages using a support vector machine and radial basis neural networks. The proposed model was constructed over a large number of observations collected from industrial and student projects. The proposed model was compared against previous UCP prediction models. The validation and empirical results demonstrated that the proposed model significantly surpasses these models on all datasets. The main conclusion is that the environmental factors of UCP can be used to classify and estimate productivity.

show abstract

Section: Related Workmentioning

confidence: 99%

A hybrid model for estimating software project effort from Use Case Points

Azzeh

Nassif

2016

Applied Soft Computing

View full text Add to dashboard Cite

show abstract

“…The use of machine learning to improve the accuracy of estimations using UCP has been done by some researchers, for instance with artificial neural network, which can improve the accuracy of prediction. [16][17][18] The use of the fuzzy logic method to improve accuracy has also been made. 19,20 Comparison of six machine learning methods in which four variants of artificial neural network techniques, namely, multilayer perceptron neural network (MLP), radial base function neural network (RBFNN), general regression neural network (GRNN), and cascade correlation neural network (CCNN).…”

Section: Related Workmentioning

confidence: 99%

A model of owner estimate cost for software development project in Indonesia

Sholiq

Subriadi

Muqtadiroh

et al. 2019

J Software Evolu Process

View full text Add to dashboard Cite

The purpose of this study is to develop a model of owner estimate cost of software development projects. The model consists of three main components, namely, personnel direct costs, nonpersonnel direct costs, and taxes. Personnel direct costs are obtained by using the use case points (UCP) method that has been advanced. Initially, UCP was utilized to calculate the effort required to complete the software project. In this study, UCP was institutionalized to obtain personnel direct costs by distributing the acquired effort into each activity in a project. Further, the effort per activity is multiplied by the pay rate for each activity. Personnel direct costs are resulted by adding up the cost of all activities. The experiment has been conducted on nine software development projects in which the model is applied to get the estimated cost calculation. KEYWORDSowner estimate cost, personnel direct cost, software project, use case points | INTRODUCTIONIn Indonesia, the process of procurement of goods or services for government agencies is carried out by the committed officer (CO) established under Presidential Regulation number 54 of 2010 and reinforced 1 Presidential Regulation number 70 of 2012. Procurement activities of goods and services by CO begin by making the planning of procurement of goods/services, which includes the following: (a) technical specifications of goods/services, (b) owner estimate cost (OEC), and (c) draft contracts. For the procurement of custom software (software that is not mass sold on the market), then the determination of OEC is a difficult activity.The task of setting OEC by CO is very important. The OEC should not be made too low because supplier candidates may not dare to follow the auction, so the auction process must be repeated even can fail. On the other hand, OEC should not be too high because CO should apply the efficiency principle in every process of goods/services to prevent financial wastage. One of the OEC functions is as a tool to assess the fairness of the offer including its details. Therefore, CO must compile OECs based on valid data sources resulting in a value that can be accounted for. On the other hand, procurement of goods/services for government agencies is often influenced by corruption, collusion, and nepotism behavior. 2 One of the ways is by inflating the budget at the planning stage or OEC markup. 3The preparation of the OEC is based on local market price data, obtained based on survey results prior to the procurement of goods/services. 4Unfortunately, for the preparation of OEC custom software projects, there is no market price or standard methods that can be used as a reference.To overcome this problem, the standardized price is needed as a reference and model to get a reliable OEC. The software project is categorized as a consulting services project 5 ; therefore, the OEC software project consists of three components, including personnel direct costs (PDC), nonpersonnel direct costs (NPDC), and taxes. To help simplify the CO task of creating OEC, it is impor...

show abstract

“…Iraji and Motameni presented an adaptive fuzzy neural network model that uses case size point approach to predict the effort of object‐oriented software to improve the accuracy of estimation. Some authors constructed various neural networks models to construct a reliable early effort estimation based on UCP size metrics . However, few authors used regression models where nonlinear regression was the most frequently used.…”

Section: Related Workmentioning

confidence: 99%

“…Some authors constructed various neural networks models to construct a reliable early effort estimation based on UCP size metrics. [22][23][24][25] However, few authors 11,20,26 used regression models where nonlinear regression was the most frequently used.…”

Section: Related Workmentioning

confidence: 99%

Project productivity evaluation in early software effort estimation

Azzeh

Nassif

2018

J Software Evolu Process

View full text Add to dashboard Cite

The productivity factor has long been a key driver to estimate effort from Use Case Points (UCP) size measure, especially when historical dataset is absent. But, no one questions: Does productivity still matter when historical data are also available? To facilitate answering this question, the present paper studies the role of productivity from 2 perspectives. First, does learning productivity from historical data lead to better accuracy than using fixed productivity ratios? Second, what is the impact of ignoring productivity when estimating the effort from UCP? Five different models that use productivity factor have been used under different experimental settings and compared with some regression models that use only UCP size metrics. We found that dynamically learning and adjusting productivity from historical data are more efficient than using fixed productivity values. Moreover, using UCP size variables to estimate effort tends to be more accurate than using productivity and UCP variables. We also did not find any significant improvement when using UCP adjustment factors for measuring productivity. Finally, we conclude that the productivity factor is a good driver to generate effort estimate from UCP in the presence and absence of historical datasets. But using UCP size variables alone for predicting effort is more accurate than using productivity.

show abstract

Neural Network model for software size estimation using Use Case Point approach

Cited by 19 publications

References 12 publications

A hybrid model for estimating software project effort from Use Case Points

A hybrid model for estimating software project effort from Use Case Points

A model of owner estimate cost for software development project in Indonesia

Project productivity evaluation in early software effort estimation

Contact Info

Product

Resources

About