An Interpolation-Based Evolutionary Algorithm for Bi-Objective Feature Selection in Classification DOI Creative Commons
Hang Xu

Mathematics, Journal Year: 2024, Volume and Issue: 12(16), P. 2572 - 2572

Published: Aug. 20, 2024

When aimed at minimizing both the classification error and number of selected features, feature selection can be treated as a bi-objective optimization problem suitable for solving with multi-objective evolutionary algorithms (MOEAs). However, traditional MOEAs may encounter difficulties due to discrete environments curse dimensionality in space, especially high-dimensional datasets. Therefore, this paper an interpolation-based algorithm (termed IPEA) is proposed tackling classification, where interpolation based initialization method designed covering wide range search space exploring adaptively detected regions interest. In experiments, IPEA been compared four state-of-the-art terms two widely-used performance metrics on list 20 public real-world datasets ranging from low high. The overall empirical results suggest that generally performs best all tested algorithms, significantly better abilities much lower computational time cost.

Language: Английский

Data-driven hierarchical collaborative optimization method with multi-fidelity modeling for aerodynamic optimization DOI
Fan Cao, Zhili Tang, Caicheng Zhu

et al.

Aerospace Science and Technology, Journal Year: 2024, Volume and Issue: 150, P. 109206 - 109206

Published: May 9, 2024

Language: Английский

Citations

5
A Hybrid Initialization and Effective Reproduction-Based Evolutionary Algorithm for Tackling Bi-Objective Large-Scale Feature Selection in Classification DOI Creative Commons
Hang Xu,

Chaohui Huang,

Hui Wen

et al.

Mathematics, Journal Year: 2024, Volume and Issue: 12(4), P. 554 - 554

Published: Feb. 12, 2024

Evolutionary algorithms have been widely used for tackling multi-objective optimization problems, while feature selection in classification can also be seen as a discrete bi-objective problem that pursues minimizing both the error and number of selected features. However, traditional evolutionary (MOEAs) encounter setbacks when dimensionality features explodes to large scale, i.e., curse dimensionality. Thus, this paper, we focus on designing an adaptive MOEA framework solving selection, especially large-scale datasets, by adopting hybrid initialization effective reproduction (called HIER). The former attempts improve starting state evolution composing initial population, latter tries generate more offspring modifying whole process. Moreover, statistical experiment results suggest HIER generally performs best most 20 test compared with six state-of-the-art MOEAs, terms multiple metrics covering performances. Then, component contribution is studied, suggesting each its essential components has positive effect. Finally, computational time complexity analyzed, not time-consuming at all shows promising efficiency.

Language: Английский

Citations

3
Manifold-guided multi-objective gradient algorithm combined with adjoint method for supersonic aircraft shape design DOI
Fan Cao, Zhili Tang, Caicheng Zhu

et al.

Aerospace Science and Technology, Journal Year: 2024, Volume and Issue: 147, P. 109063 - 109063

Published: March 13, 2024

Language: Английский

Citations

1
A Multi-Task Decomposition-Based Evolutionary Algorithm for Tackling High-Dimensional Bi-Objective Feature Selection DOI Creative Commons
Hang Xu,

Chaohui Huang,

Jianbing Lin

et al.

Mathematics, Journal Year: 2024, Volume and Issue: 12(8), P. 1178 - 1178

Published: April 14, 2024

Evolutionary algorithms have been widely applied for solving multi-objective optimization problems, while the feature selection in classification can also be treated as a discrete bi-objective problem if attempting to minimize both error and ratio of selected features. However, traditional evolutionary (MOEAs) may drawbacks tackling large-scale selection, due curse dimensionality decision space. Therefore, this paper, we concentrated on designing an multi-task decomposition-based algorithm (abbreviated MTDEA), especially handling high-dimensional classification. To more specific, multiple subpopulations related different tasks are separately initialized then adaptively merged into single integrated population during evolution. Moreover, ideal points these dynamically adjusted every generation, order achieve search preferences directions. In experiments, proposed MTDEA was compared with seven state-of-the-art MOEAs 20 datasets terms three performance indicators, along using comprehensive Wilcoxon Friedman tests. It found that performed best most datasets, significantly better ability promising efficiency.

Language: Английский

Citations

1
Investigating the Effect of Organization Structure and Cognitive Profiles on Engineering Team Performance Using Agent-Based Models and Graph Theory DOI Creative Commons

Judson Estes,

Vijitashwa Pandey

Mathematics, Journal Year: 2023, Volume and Issue: 11(21), P. 4533 - 4533

Published: Nov. 3, 2023

In large engineering firms, most design projects are undertaken by teams of individuals. From the perspective senior management, overall project team must maintain scheduling, investment and return on discipline while solving technical problems. Various tools exist in systems (SE) that can reflect value provided resources invested; however, involvement human decision makers complicates types analyses. A critical ingredient this challenge is interplay cognitive attributes members relationships between them. This aspect has not been fully addressed literature, rendering many studies relatively oblivious to dynamics organization structures. To end, we propose a framework incorporate structure using graph representation. then used inform an agent-based model where simulated understand effects member relationships. work, aim context product development. The modeled Barabasi–Albert scale-free network. information regarding be acquired through metrics such as various centrality measures associated with distance when they work problem, conjunction their other attributes. We present some results discuss avenues for future work.

Language: Английский

Citations

1
An Interpolation-Based Evolutionary Algorithm for Bi-Objective Feature Selection in Classification DOI Creative Commons
Hang Xu

Mathematics, Journal Year: 2024, Volume and Issue: 12(16), P. 2572 - 2572

Published: Aug. 20, 2024

When aimed at minimizing both the classification error and number of selected features, feature selection can be treated as a bi-objective optimization problem suitable for solving with multi-objective evolutionary algorithms (MOEAs). However, traditional MOEAs may encounter difficulties due to discrete environments curse dimensionality in space, especially high-dimensional datasets. Therefore, this paper an interpolation-based algorithm (termed IPEA) is proposed tackling classification, where interpolation based initialization method designed covering wide range search space exploring adaptively detected regions interest. In experiments, IPEA been compared four state-of-the-art terms two widely-used performance metrics on list 20 public real-world datasets ranging from low high. The overall empirical results suggest that generally performs best all tested algorithms, significantly better abilities much lower computational time cost.

Language: Английский

Citations

0