Bin-Based Estimation of the Amount of Effort for Embedded Software Development Projects with Support Vector Machines

Iwata, Kazunori; Liebman, Elad; Stone, Peter; Nakashima, Toyoshiro; Anan, Yoshiyuki; Ishii, Naohiro

doi:10.1007/978-3-319-23467-0_11

Cited by 5 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The value of each element becomes the value of a coordinate, after that classification has been done in that differentiate two classes with the help of finding the hyper-plane. (Iwata et al, 2016).…”

Section: Support Vector Machinementioning

confidence: 99%

Risk Classification in Global Software Development Using a Machine Learning Approach

Iftikhar

Musa

Alam

et al. 2022

Journal of Information Technology Research

View full text Add to dashboard Cite

Software development through teams at different geographical locations is a trend of modern era, which is not only producing good results without costing lot of money but also productive in relation to its cost, low risk and high return. This shift of perception of working in a group rather than alone is getting stronger day by day and has become an important planning tool and part of their business strategy. In this research classification approaches like SVM and K-NN have been implemented to classify the true positive events of global software development project risk according to Time, Cost and Resource. Comparative analysis has also been performed between these two algorithms to determine the highest accuracy algorithms. Results proved that Support Vector Machine (SVM) performed very well in case of Cost Related Risk and Resource Related Risk. Whereas, KNN is found superior to SVM for Time Related Risk.

show abstract

Section: Support Vector Machinementioning

confidence: 99%

Risk Classification in Global Software Development Using a Machine Learning Approach

Iftikhar

Musa

Alam

et al. 2022

Journal of Information Technology Research

View full text Add to dashboard Cite

show abstract

“…The SVR technique has been used in many empirical software engineering studies especially in predicting several software characteristics such as bug and defect [23][24], reliability [25], quality [26] and enhancement effort [27]. Regarding application of an SVR for estimating software development effort, we identified 13 relevant studies in the literature [7,[27][28][29][30][31][32][33][34][35][36][37][38]. The first investigation of SVR in SDEE was originally carried out by Oliveira [7].…”

Section: Related Workmentioning

confidence: 99%

Improving Software Development effort estimating using Support Vector Regression and Feature Selection

Zakrani¹,

Hain²,

Idri

2019

IJ-AI

View full text Add to dashboard Cite

Accurate and reliable software development effort estimation (SDEE) is one of the main concerns for project managers. Planning and scheduling a software projects using and inaccurate estimate may cause severe risks to software project under development such as delayed delivery, poor quality software, missing features. Therefore, accurate prediction of software effort plays an important role in the minimization of these risks that can lead to projects failure. Nowadays, application of artificial intelligence techniques has grown dramatically for predicting software effort. The researchers found that these techniques are suitable tools for accurate prediction. In this study, an improved model is designed for estimating software effort using support vector regression (SVR) and two feature selection (FS) methods. Prior to building model step, a preprocessing stage is performed by random forest or Boruta feature selection methods to remove unimportant features. Next, the SVR model is tuned by a grid search approach. The performance of model is then evaluated over eight well-known datasets through 30%holdout validation method. To show the impact of feature selection on the accuracy of SVR model, the proposed model was compared with SVR model without feature selection. The results indicated that SVR with feature selection outperforms SVR without FS in terms of the three accuracy measures used in this empirical study.

show abstract

“…Weproposedathree-dimensionalgridsearchtofindthemostappropriatecombinationofthese parameters (Iwata, Liebman, Stone, Nakashima, Anan & Ishii, 2015). Our method improved the meanmagnitudeofrelativeerror(MMRE,seeEquation(3)inthesection"EvaluationCriteria")from 0.165 (Cortes&Vapnik,1995)to0.149usingleave-one-outcross-validation (Shin&Goel,2000).…”

Section: Support Vector Regressionmentioning

confidence: 99%

Machine Learning Classification to Effort Estimation for Embedded Software Development Projects

Iwata

Nakashima

Anan

et al. 2017

International Journal of Software Innovation

Self Cite

View full text Add to dashboard Cite

This paper discusses the effect of classification in estimating the amount of effort (in man-days) associated with code development. Estimating the effort requirements for new software projects is especially important. As outliers are harmful to the estimation, they are excluded from many estimation models. However, such outliers can be identified in practice once the projects are completed, and so they should not be excluded during the creation of models and when estimating the required effort. This paper presents classifications for embedded software development projects using an artificial neural network (ANN) and a support vector machine. After defining the classifications, effort estimation models are created for each class using linear regression, an ANN, and a form of support vector regression. Evaluation experiments are carried out to compare the estimation accuracy of the model both with and without the classifications using 10-fold cross-validation. In addition, the Games-Howell test with one-way analysis of variance is performed to consider statistically significant evidence.

show abstract

Bin-Based Estimation of the Amount of Effort for Embedded Software Development Projects with Support Vector Machines

Cited by 5 publications

References 13 publications

Risk Classification in Global Software Development Using a Machine Learning Approach

Risk Classification in Global Software Development Using a Machine Learning Approach

Improving Software Development effort estimating using Support Vector Regression and Feature Selection

Machine Learning Classification to Effort Estimation for Embedded Software Development Projects

Contact Info

Product

Resources

About