ABC and PSO: A comparative analysis

Kulkarni, Vaishali R; Desai, Veena

doi:10.1109/iccic.2016.7919625

Cited by 20 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MOPSO algorithm is a multiple objective heuristic optimization method derived from the single-objective particle swarm optimization (PSO) algorithm. It has the advantages of simple calculation, less dependence on the set of initial points, fast convergence, easy implementation, and small influence of parameters on the solution [23].…”

Section: B Comprehensive Mopsomentioning

confidence: 99%

Kriging Aerodynamic Modeling and Multi-Objective Control Allocation for Flying Wing UAVs With Morphing Trailing-Edge

Zhao

Yang

2021

IEEE Access

View full text Add to dashboard Cite

Flexible skin and continuous deformable control surface are the basic of adaptive wing technology for future aircraft. This paper presents a continuous morphing trailing-edge and its control allocation method for the flying wing Unmanned Aerial Vehicle (UAV). Firstly, we apply the Kriging method to establish the aerodynamic model of the morphing trailing-edge, with the initial sample points generated by the non-uniform optimal Latin Hypercube Sampling (LHS). Then, based on the Kriging model, the multi-objective control allocation problem is converted into a standard optimization form. To solve such problem, we design a Comprehensive Multi-Objective Particle Swarm Optimization (C-MOPSO) algorithm and an improved Hierarchical MOPSO (H-MOPSO) algorithm, in which multiple optimization objectives are prioritized and hierarchically optimized using the PSO algorithm. As for performance analysis, an attitude angle tracking flight control system is established to validate the effectiveness of our proposed control allocation methods. Simulation results show that both the C-MOPSO and H-MOPSO methods have similar performance in attitude angle tracking, while H-MOPSO achieves better multi-objective allocation performance.INDEX TERMS Flying wing UAV, morphing trailing-edge, Kriging aerodynamic modeling, multiobjective control allocation, Particle Swarm Optimization.

show abstract

Section: B Comprehensive Mopsomentioning

confidence: 99%

Kriging Aerodynamic Modeling and Multi-Objective Control Allocation for Flying Wing UAVs With Morphing Trailing-Edge

Zhao

Yang

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…approach, usually take more time than ABC since it is challenging to parallelize. Also, although techniques such as PSO have a reasonable convergence rate, they have a higher chance of sticking into local optimums and proved to be less efficient in comparison to ABC regarding performance [31].…”

Section: A Hyper-parameter Tuningmentioning

confidence: 99%

HyP-ABC: A Novel Automated Hyper-Parameter Tuning Algorithm Using Evolutionary Optimization

Zahedi¹,

Mohammadi²,

Amini³

2021

Preprint

View full text Add to dashboard Cite

<p>Machine learning techniques lend themselves as promising decision-making and analytic tools in a wide range of applications. Different ML algorithms have various hyper-parameters. In order to tailor an ML model towards a specific application working at its best, its hyper-parameters should be tuned. Tuning the hyper-parameters directly affects the performance. However, for large-scale search spaces, efficiently exploring the ample number of combinations of hyper-parameters is computationally expensive. Many of the automated hyper-parameter tuning techniques suffer from low convergence rates and high experimental time complexities. In this paper, we propose HyP-ABC, an automatic innovative hybrid hyper-parameter optimization algorithm using the modified artificial bee colony approach, to measure the classification accuracy of three ML algorithms: random forest, extreme gradient boosting, and support vector machine. In order to ensure the robustness of the proposed method, the algorithm takes a wide range of feasible hyper-parameter values and is tested using a real-world educational dataset. Experimental results show that HyP-ABC is competitive with state-of-the-art techniques. Also, it has fewer hyper-parameters to be tuned than other population-based algorithms, making it worthwhile for real-world HPO problems.</p>

show abstract

“…On each iteration, particles moves using a combination of the best personal experience, denoted by subscript 'pbest', the best global experience, denoted by the subscript, 'gbest', and its actual velocity, W vel (k), as is explained in [46], [51]- [53]. Thus, next velocity component, W vel,i , of current particle, j,…”

Section: B Particles Motionmentioning

confidence: 99%

Predictive Incremental Vector Control for DFIG With Weighted-Dynamic Objective Constraint-Handling Method-PSO Weighting Matrices Design

et al. 2020

View full text Add to dashboard Cite

paper proposes a Particle Swarm Optimization (PSO) based method, the Weighted-Dynamic-Objective Constraint-Handling PSO Method (WDOCHM-PSO). This was used to design the weighting matrices of an incremental Model-Based Predictive Controller (MBPC) for a Doubly Fed Induction Generator (DFIG) applied in a small-scale wind energy system. In contrast to the original PSO, the proposed method has an inner mechanism for dealing with constraints and an adaptive search factor. Additionally, the proposed incremental MPBC implementation does not need the flux information, since the intrinsic integral action rejects the constant flux disturbance. Finally, experimental results show that the proposed controller with the new constraint handling design method is nearly two times faster (In terms of settling time) than other formulations reported in the literature.

show abstract

ABC and PSO: A comparative analysis

Cited by 20 publications

References 11 publications

Kriging Aerodynamic Modeling and Multi-Objective Control Allocation for Flying Wing UAVs With Morphing Trailing-Edge

Kriging Aerodynamic Modeling and Multi-Objective Control Allocation for Flying Wing UAVs With Morphing Trailing-Edge

HyP-ABC: A Novel Automated Hyper-Parameter Tuning Algorithm Using Evolutionary Optimization

Predictive Incremental Vector Control for DFIG With Weighted-Dynamic Objective Constraint-Handling Method-PSO Weighting Matrices Design

Contact Info

Product

Resources

About