Name
Title | ||
|---|---|---|
Meta-Lamarckian learning in multi-objective optimization for mobile social network search. |
Abstract | ||
|---|---|---|
•A Multi-Objective Mobile Social Network Search Optimization Problem is investigated.•A MOEA/D hybridized with Meta-Lamarckian Learning (MOEA/D-ML) is proposed.•MOEA/D-ML learns from the problem’s properties and objective functions.•It learns the behaviour of individual Local Searches (LSs) during the evolution.•It adaptively follows the best LSs at different areas of the objective space.•Its adaptiveness is also shown for different benchmark test instances and problems.•Evaluation on mobility & social behaviour patterns derived from real-world datasets.•MOEA/D-ML’s generalizability shown on the Permutation Flowshop Scheduling Problem. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1016/j.asoc.2018.02.026 | Applied Soft Computing |
Keywords | Field | DocType |
Multi-objective optimization,Evolutionary algorithms,Local search,Decomposition,Meta-Lamarckian learning,Smartphones,Social networks | Heuristic,Evolutionary algorithm,Mobile social network,Flow shop scheduling,Multi-objective optimization,Heuristics,Artificial intelligence,Search problem,Local search (optimization),Mathematics,Machine learning | Journal |
Volume | Issue | ISSN |
67 | C | 1568-4946 |
Citations | PageRank | References |
1 | 0.35 | 34 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Andreas Konstantinidis | 1 | 119 | 7.37 |
| Savvas Pericleous | 2 | 8 | 2.12 |
| Christoforos Charalambous | 3 | 50 | 4.35 |