A GA-based feature selection and parameters optimization for support vector regression applied to software effort estimation

Braga, Petrônio L.; Oliveira, Adriano L. I.; Meira, Sílvio R. L.

doi:10.1145/1363686.1364116

Cited by 47 publications

(29 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Search-based methods have also been used in combination with other estimation techniques (see e.g., (Braga et al 2008) (Faheem et al 2008)), such as some Machine Learning (ML) techniques, aiming to obtain better estimates. Indeed, as 15 reported in several studies, ML approaches have the potential as techniques for software development effort estimation; nevertheless, their accuracy strongly depends on an accurate setting of these methods (see e.g., (Song et al 2013)).…”

Section: Using Sb Approaches For Software Development Effort Estimationmentioning

confidence: 99%

Search-Based Software Project Management

Ferrucci

Harman

Sarro

2014

Software Project Management in a Changing World

View full text Add to dashboard Cite

Abstract. Project management presents the manager with a complex set of related optimisation problems. Decisions made can more profoundly affect the outcome of a project than any other activity. In the chapter, we provide an overview of Search-Based Software Project Management, in which Search-Based Software Engineering (SBSE) is applied to problems in software project management. We show how SBSE has been used to attack the problems of staffing, scheduling, risk, and effort estimation. SBSE can help to solve the optimisation problems the manager faces, but it can also yield insight. SBSE therefore provides both decision making and decision support. We provide a comprehensive survey of Search-Based Software Project Management, and give directions for the development of this subfield of SBSE. IntroductionSoftware Project Management includes several activities critical for the success of a project (e.g., cost estimation, project planning, quality management). These activities often involve finding a suitable balance between competing and potentially conflicting goals. For example, planning a project schedule requires to minimise the project duration and the project cost, and to maximise the product quality. Many of these problems are essentially optimization questions characterised by competing goals/constraints and with a bewilderingly large set of possible choices. So finding good solutions can be hard.Search-Based Software Engineering seeks to reformulate software engineering problems as search-based optimisation problems and applies a variety of metaheuristics based on local and global search to solve them (such as Hill Climbing, Tabu Search, and Genetic Algorithms). These meta-heuristics search for a suitable solution in a typically large input space guided by a fitness function that expresses the goals and leads the exploration into potentially promising areas of the search space.Though the term Search-Based Software Engineering (SBSE) was coined by Harman and Jones in 2001 to cover the application of computational search and optimisation across the wide spectrum of software engineering activities (Harman and Jones 2001), there were already pockets of activity on several specific software engineering problems prior to the introduction of the term SBSE. One such topic was Search-Based Software Project Management, the topic of this chapter. In particular, there was work on search-based project scheduling and staffing by

show abstract

Section: Using Sb Approaches For Software Development Effort Estimationmentioning

confidence: 99%

Search-Based Software Project Management

Ferrucci

Harman

Sarro

2014

Software Project Management in a Changing World

View full text Add to dashboard Cite

show abstract

“…Many of the above limitations can be found also in the studies that assessed the use of SB approaches to improve existing effort estimation techniques [4] [7] [21] [27] [29] [36]. As an example, as we can observe from Table 2, all the studies exploited Genetic Algorithms.…”

Section: Brief Literature Reviewmentioning

confidence: 99%

Search-based approaches for software development effort estimation

Sarro

2011

Proceedings of the 12th International Conference on Product Focused Software Development and Process Improvement

View full text Add to dashboard Cite

In the last years the use of Search-Based techniques has been suggested to estimate software development effort. These techniques are meta-heuristics able to find optimal or near optimal solutions to problems characterized by large space. In the context of effort estimation Search-Based approaches can be exploited to build estimation models or to enhance the effectiveness of other methods. The preliminary investigations carried out so far have provided promising results. Nevertheless, the capabilities of these approaches have not been fully explored and the empirical analyses carried out so far have not considered the more recent recommendations on how to perform this kind of empirical assessment in the effort estimation context and in Search-Based Software Engineering. The main aim of the PhD dissertation is to provide an insight on the use of Search-Based techniques for effort estimation trying to highlight strengths and weaknesses.

show abstract

“…In recent years, evolutionary computing algorithms have been used in software effort estimation by various researchers [5,8,17,22,29,30]. Although numerous models have been proposed still no model has been found to be highly accurate or efficient approach in all the environments.…”

Section: Introductionmentioning

confidence: 99%