Machine Learning Classification to Effort Estimation for Embedded Software Development Projects

2022 ◽  
pp. 1652-1665
Author(s):  
Kazunori Iwata ◽  
Toyoshiro Nakashima ◽  
Yoshiyuki Anan ◽  
Naohiro Ishii
Keyword(s):  
Software Development ◽  
Embedded Software ◽  
Estimation Accuracy ◽  
Support Vector ◽  
Development Projects ◽  
Effort Estimation ◽  
Software Projects ◽  
Machine Learning Classification ◽  
Artificial Neural Network Ann ◽  
Estimation Models

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.

Machine Learning Classification to Effort Estimation for Embedded Software Development Projects

2017 ◽  
Vol 5 (4) ◽  
pp. 19-32 ◽  
Author(s):  
Kazunori Iwata ◽  
Toyoshiro Nakashima ◽  
Yoshiyuki Anan ◽  
Naohiro Ishii
Keyword(s):  
Software Development ◽  
Embedded Software ◽  
Estimation Accuracy ◽  
Support Vector ◽  
Development Projects ◽  
Effort Estimation ◽  
Software Projects ◽  
Machine Learning Classification ◽  
Artificial Neural Network Ann ◽  
Estimation Models

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.

Estimating Interval of the Number of Errors for Embedded Software Development Projects

2014 ◽  
Vol 2 (3) ◽  
pp. 40-50 ◽  
Author(s):  
Kazunori Iwata ◽  
Toyoshiro Nakasima ◽  
Yoshiyuki Anan ◽  
Naohiro Ishii
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Software Development ◽  
Previous Investigation ◽  
Interval Estimation ◽  
Embedded Software ◽  
Point Estimation ◽  
Support Vector ◽  
Development Projects ◽  
Artificial Neural Network Ann

Previous investigation focused on the prediction of total and errors for embedded software development projects using an artificial neural network (ANN). However, methods using ANNs have reached their improvement limits, since an appropriate value is estimated using what is known as point estimation in statistics. This paper proposes a method for predicting the number of errors for embedded software development projects using interval estimation provided by a support vector machine and ANN.

The Application of Meta-Heuristic Algorithms to Improve the Performance of Software Development Effort Estimation Models

2015 ◽  
Vol 6 (4) ◽  
pp. 39-68 ◽  
Author(s):  
Maryam Hassani Saadi ◽  
Vahid Khatibi Bardsiri ◽  
Fahimeh Ziaaddini
Keyword(s):  
Software Development ◽  
Optimization Algorithms ◽  
Heuristic Optimization ◽  
Development Effort ◽  
Special Role ◽  
Effort Estimation ◽  
Software Projects ◽  
Software Development Effort ◽  
Estimation Models ◽  
Software Development Effort Estimation

One of the major activities in effective and efficient production of software projects is the precise estimation of software development effort. Estimation of the effort in primary steps of software development is one of the most important challenges in managing software projects. Some reasons for these challenges such as: discordant software projects, the complexity of the manufacturing process, special role of human and high level of obscure and unusual features of software projects can be noted. Predicting the necessary efforts to develop software using meta-heuristic optimization algorithms has made significant progressions in this field. These algorithms have the potent to be used in estimation of the effort of the software. The necessity to increase estimation precision urged the authors to survey the efficiency of some meta-heuristic optimization algorithms and their effects on the software projects. To do so, in this paper, they investigated the effect of combining various optimization algorithms such as genetic algorithm, particle swarm optimization algorithm and ant colony algorithm on different models such as COCOMO, estimation based on analogy, machine learning methods and standard estimation models. These models have employed various data sets to evaluate the results such as COCOMO, Desharnais, NASA, Kemerer, CF, DPS, ISBSG and Koten & Gary. The results of this survey can be used by researchers as a primary reference.

scholarly journals Improving Effort Estimation by Voting Software Estimation Models

2009 ◽  
Vol 2009 ◽  
pp. 1-8 ◽  
Author(s):  
Luiz Fernando Capretz ◽  
Venus Marza
Keyword(s):  
Estimation Accuracy ◽  
Data Repository ◽  
Development Effort ◽  
Software Project ◽  
Effort Estimation ◽  
Software Projects ◽  
Software Estimation ◽  
Software Development Effort ◽  
Commercial Purpose ◽  
Estimation Models

Estimating software development effort is an important task in the management of large software projects. The task is challenging, and it has been receiving the attentions of researchers ever since software was developed for commercial purpose. A number of estimation models exist for effort prediction. However, there is a need for novel models to obtain more accurate estimations. The primary purpose of this study is to propose a precise method of estimation by selecting the most popular models in order to improve accuracy. Consequently, the final results are very precise and reliable when they are applied to a real dataset in a software project. Empirical validation of this approach uses the International Software Benchmarking Standards Group (ISBSG) Data Repository Version 10 to demonstrate the improvement in software estimation accuracy.

SOFTWARE DEVELOPMENT EFFORT ESTIMATION USING CLASSICAL AND FUZZY ANALOGY: A CROSS-VALIDATION COMPARATIVE STUDY

2014 ◽  
Vol 13 (03) ◽  
pp. 1450013 ◽  
Author(s):  
FATIMA AZZAHRA AMAZAL ◽  
ALI IDRI ◽  
ALAIN ABRAN
Keyword(s):  
Software Development ◽  
Case Based Reasoning ◽  
Development Effort ◽  
Software Project ◽  
Effort Estimation ◽  
Software Effort Estimation ◽  
Software Projects ◽  
Software Development Effort ◽  
Research Questions ◽  
Estimation Models

Software effort estimation is one of the most important tasks in software project management. Of several techniques suggested for estimating software development effort, the analogy-based reasoning, or Case-Based Reasoning (CBR), approaches stand out as promising techniques. In this paper, the benefits of using linguistic rather than numerical values in the analogy process for software effort estimation are investigated. The performance, in terms of accuracy and tolerance of imprecision, of two analogy-based software effort estimation models (Classical Analogy and Fuzzy Analogy, which use numerical and linguistic values respectively to describe software projects) is compared. Three research questions related to the performance of these two models are discussed and answered. This study uses the International Software Benchmarking Standards Group (ISBSG) dataset and confirms the usefulness of using linguistic instead of numerical values in analogy-based software effort estimation models.

Sign in / Sign up

Export Citation Format

Share Document