Dynamic Multi-Swarm Particle Swarm Optimization Based on Elite Learning

Xia, Xuewen; Tang, Yichao; Wei, Bo; Gui, Ling

doi:10.1109/access.2019.2960890

Cited by 17 publications

(6 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The personal and global best can be updated as follows [65] :

Where F is the fitness function. Despite its merit of a fast convergence speed [66] , [67] , the conventional PSO suffers the demerits of poor accuracy and being easily trapped in the local minima [66] , [67] , [68] . The authors in [66] introduced a mutation factor and a dynamic inertial factor.…”

Section: A Review Of Various Swarm-based Motmentioning

confidence: 99%

“…The third method is via the use of bubble net attacking. Bubble net attacking is a mathematical model used to imitate the spiral movement of the humpback whale [67] , [68] . In bubble net attacking, the whales update their positions as follows [99] , [102] , [103] :

1

Where b is a limited constant and l is a random number in the range [

11

].…”

Section: A Review Of Various Swarm-based Motmentioning

confidence: 99%

See 1 more Smart Citation

A review of swarm-based metaheuristic optimization techniques and their application to doubly fed induction generator

Reddy

Saha

2022

Heliyon

View full text Add to dashboard Cite

“…The personal and global best can be updated as follows [65] :

Section: A Review Of Various Swarm-based Motmentioning

confidence: 99%

1

Where b is a limited constant and l is a random number in the range [

11

].…”

Section: A Review Of Various Swarm-based Motmentioning

confidence: 99%

A review of swarm-based metaheuristic optimization techniques and their application to doubly fed induction generator

Reddy

Saha

2022

Heliyon

View full text Add to dashboard Cite

“…Reference [32] used the cooperative archive to exploit the valuable information of the current swarm and archive. Information about the elite particles from dynamic sub swarms was used in [33] to improve the following sub-swarm, while [32] introduced a new velocity updating technique that explores the external archive of non-dominated solutions in the current swarm. In this article, an elite archive learning is used to refine the solution in the final stages of the algorithm.…”

Section: Elite Archivementioning

confidence: 99%

Parameter Estimation for Industrial Robot Manipulators Using an Improved Particle Swarm Optimization Algorithm with Gaussian Mutation and Archived Elite Learning

Umar¹,

Shi²,

Zheng³

et al. 2020

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

“…For example, machine learning models can be trained to recognize the difference between a real face and a synthetic one [5]. Optimization algorithms such as particle swarm optimization (PSO) can be leveraged to refine the model's accuracy in detecting deepfake [6].…”

Section: Introductionmentioning

confidence: 99%

Detection of Deepfake Media Using a Hybrid CNN–RNN Model and Particle Swarm Optimization (PSO) Algorithm

Al-Adwan,

Alazzam,

Al-Anbaki

et al. 2024

Computers

View full text Add to dashboard Cite

Deepfakes are digital audio, video, or images manipulated using machine learning algorithms. These manipulated media files can convincingly depict individuals doing or saying things they never actually did. Deepfakes pose significant risks to our lives, including national security, financial markets, and personal privacy. The ability to create convincing deep fakes can also harm individuals’ reputations and can be used to spread disinformation and fake news. As such, there is a growing need for reliable and accurate methods to detect deep fakes and prevent their harmful effects. In this paper, a hybrid convolutional neural network (CNN) and recurrent neural network (RNN) with a particle swarm optimization (PSO) algorithm is utilized to demonstrate a deep learning strategy for detecting deepfake videos. High accuracy, sensitivity, specificity, and F1 score were attained by the proposed approach when tested on two publicly available datasets: Celeb-DF and the Deepfake Detection Challenge Dataset (DFDC). Specifically, the proposed method achieved an average accuracy of 97.26% on Celeb-DF and an average accuracy of 94.2% on DFDC. The results were compared to other state-of-the-art methods and showed that the proposed method outperformed many. The proposed method can effectively detect deepfake videos, which is essential for identifying and preventing the spread of manipulated content online.

show abstract

Dynamic Multi-Swarm Particle Swarm Optimization Based on Elite Learning

Cited by 17 publications

References 47 publications

A review of swarm-based metaheuristic optimization techniques and their application to doubly fed induction generator

A review of swarm-based metaheuristic optimization techniques and their application to doubly fed induction generator

Parameter Estimation for Industrial Robot Manipulators Using an Improved Particle Swarm Optimization Algorithm with Gaussian Mutation and Archived Elite Learning

Detection of Deepfake Media Using a Hybrid CNN–RNN Model and Particle Swarm Optimization (PSO) Algorithm

Contact Info

Product

Resources

About