A New Learning Mechanism for Resolving Inconsistencies in Using Cooperative Co-evolution Model

Y.R. Xu; P. Liang

doi:10.1007/978-3-319-09940-8_15

A New Learning Mechanism for Resolving Inconsistencies in Using Cooperative Co-evolution Model

Y.R. Xu, P. Liang

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

Abstract

The selection of the requirements to be included in the next release of a software is a complex task. Each customer has their needs, but it is usually impossible to fulfill all of them due to constraints such as budget availability. The Next Release Problem (NRP) aims to select the requirements that maximize customer's benefit, while minimizing development effort. Visualizing the problem search space from a customer concentration perspective, we observed a recurring behavior in all instances analyzed. This work presents these findings and shows some initial results of a Hill Climbing algorithm modified to take advantage of this pattern. The modified algorithm was able to generate solutions that are statistically better than those generated by the original Hill Climbing. © 2014 Springer International Publishing Switzerland.

Original language	English
Title of host publication	Proceedings of the 6th International Symposium on Search-Based Software Engineering (SSBSE)
Pages	215-221
DOIs	https://doi.org/10.1007/978-3-319-09940-8_15
Publication status	Published - 2014
Event	The 6th International Symposium on Search-Based Software Engineering (SSBSE) - Duration: 1 Jan 2014 → 1 Jan 2014

Conference

Conference	The 6th International Symposium on Search-Based Software Engineering (SSBSE)
Period	1/01/14 → 1/01/14

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-319-09940-8_15

Handle.net

Persistent link

Cite this

@inproceedings{e700b948acac45acb5cb4bf0421474e0,

title = "A New Learning Mechanism for Resolving Inconsistencies in Using Cooperative Co-evolution Model",

abstract = "The selection of the requirements to be included in the next release of a software is a complex task. Each customer has their needs, but it is usually impossible to fulfill all of them due to constraints such as budget availability. The Next Release Problem (NRP) aims to select the requirements that maximize customer's benefit, while minimizing development effort. Visualizing the problem search space from a customer concentration perspective, we observed a recurring behavior in all instances analyzed. This work presents these findings and shows some initial results of a Hill Climbing algorithm modified to take advantage of this pattern. The modified algorithm was able to generate solutions that are statistically better than those generated by the original Hill Climbing. {\textcopyright} 2014 Springer International Publishing Switzerland.",

author = "Y.R. Xu and P. Liang",

year = "2014",

doi = "10.1007/978-3-319-09940-8_15",

language = "English",

pages = "215--221",

booktitle = "Proceedings of the 6th International Symposium on Search-Based Software Engineering (SSBSE)",

note = "The 6th International Symposium on Search-Based Software Engineering (SSBSE) ; Conference date: 01-01-2014 Through 01-01-2014",

}

TY - GEN

T1 - A New Learning Mechanism for Resolving Inconsistencies in Using Cooperative Co-evolution Model

AU - Xu, Y.R.

AU - Liang, P.

PY - 2014

Y1 - 2014

N2 - The selection of the requirements to be included in the next release of a software is a complex task. Each customer has their needs, but it is usually impossible to fulfill all of them due to constraints such as budget availability. The Next Release Problem (NRP) aims to select the requirements that maximize customer's benefit, while minimizing development effort. Visualizing the problem search space from a customer concentration perspective, we observed a recurring behavior in all instances analyzed. This work presents these findings and shows some initial results of a Hill Climbing algorithm modified to take advantage of this pattern. The modified algorithm was able to generate solutions that are statistically better than those generated by the original Hill Climbing. © 2014 Springer International Publishing Switzerland.

AB - The selection of the requirements to be included in the next release of a software is a complex task. Each customer has their needs, but it is usually impossible to fulfill all of them due to constraints such as budget availability. The Next Release Problem (NRP) aims to select the requirements that maximize customer's benefit, while minimizing development effort. Visualizing the problem search space from a customer concentration perspective, we observed a recurring behavior in all instances analyzed. This work presents these findings and shows some initial results of a Hill Climbing algorithm modified to take advantage of this pattern. The modified algorithm was able to generate solutions that are statistically better than those generated by the original Hill Climbing. © 2014 Springer International Publishing Switzerland.

U2 - 10.1007/978-3-319-09940-8_15

DO - 10.1007/978-3-319-09940-8_15

M3 - Conference contribution

SP - 215

EP - 221

BT - Proceedings of the 6th International Symposium on Search-Based Software Engineering (SSBSE)

T2 - The 6th International Symposium on Search-Based Software Engineering (SSBSE)

Y2 - 1 January 2014 through 1 January 2014

ER -

A New Learning Mechanism for Resolving Inconsistencies in Using Cooperative Co-evolution Model

Abstract

Conference

UN SDGs

Access to Document

Handle.net

Fingerprint

Cite this