A Technique for Evaluation of Interactive Evolutionary Systems

Shackelford, M.; Corne, David

doi:10.1007/978-0-85729-338-1_17

Cited by 2 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When testing the effects of user error (reported in [11]) it was shown that overall the levels of error do not have much effect until the error level reaches 7% (about 1 in 14). At this level, for a population of 16 individuals, we get over 1 error in each generation, and these errors can therefore be expected to affect the best individual once every 16 iterations.…”

Section: Handling Errorsmentioning

confidence: 96%

Implementation issues for an interactive evolutionary computation system

Shackelford

2007

Proceedings of the 9th Annual Conference Companion on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

The design and development of an Interactive Evolutionary Computation (IEC) system needs to take into account the implementation issues found when delivering the system to "Real World" users. This paper reports and reflects on the implementation issues found when rolling-out an IEC-based Programme Management system [1]. Although the system under discussion was for a specific application, it is felt that the issues and their resolution are generally applicable to a wide range of IEC systems.

show abstract

Section: Handling Errorsmentioning

confidence: 96%

Implementation issues for an interactive evolutionary computation system

Shackelford

2007

Proceedings of the 9th Annual Conference Companion on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

show abstract

“…Similar to the used idea in Shackelford and Corne (2004) and Tonella et al (2013), the human tacit assessment is simulated by creating a "target solution" which represents a solution that the DM would consider "ideal" or "gold standard". Such solution has the same structure of an individual and, consequently, comprises of a subset of the selected requirements to be implemented, respecting the budget and the interdependency constraints.…”

Section: Artificial Experimentsmentioning

confidence: 99%

An Architecture based on interactive optimization and machine learning applied to the next release problem

et al. 2016

View full text Add to dashboard Cite

The next release problem (NRP) consists of selecting which requirements will be implemented in the next release of a software system. For many search based software engineering approaches to the NRP, there is still a lack of capability to efficiently incorporate human experience and preferences in the search process. Therefore, this paper proposes an architecture to deal with this issue, where the decision maker (DM) and his/her tacit assessments are taken into account during the solutions evaluations alongside the interactive genetic algorithm. Furthermore, a learning model is employed to avoid an overwhelming number of interactions. An empirical study involving software engineer practitioners, different instances, and different machine learning techniques was performed to assess the feasibility of the architecture to incorporate human knowledge in the overall optimization process. Obtained results indicate the architecture can assist the DM in selecting a set of requirements that properly incor-B Allysson Allex Araújo allysson.araujo@uece.br 123 Autom Softw Eng porate his/her expertise, while optimizing other explicit measurable aspects equally important to the next release planning. On a scale of 0 (very ineffective) to 5 (very effective), all participants found the experience of interactively selecting the requirements using the approach as a 4 (effective).

show abstract

A Technique for Evaluation of Interactive Evolutionary Systems

Cited by 2 publications

References 9 publications

Implementation issues for an interactive evolutionary computation system

Implementation issues for an interactive evolutionary computation system

An Architecture based on interactive optimization and machine learning applied to the next release problem

Contact Info

Product

Resources

About