Application of Optimized Partitioning Around Medoid Algorithm in Image Retrieval

2021 ◽  
Vol 12 (1) ◽  
pp. 77-94
Author(s):  
Yanxia Jin ◽  
Xin Zhang ◽  
Yao Jia
Keyword(s):  
Image Retrieval ◽  
Clustering Algorithm ◽  
Particle Swarm ◽  
Image Data ◽  
Experimental Comparison ◽  
Cluster Center ◽  
Particle Swarm Algorithm ◽  
Query Image ◽  
Retrieval Accuracy ◽  
Swarm Algorithm

In image retrieval, the major challenge is that the number of images in the gallery is large and irregular, which results in low retrieval accuracy. This paper analyzes the disadvantages of the PAM (partitioning around medoid) clustering algorithm in image data classification and the excessive consumption of time in the computation process of searching clustering representative objects using the PAM clustering algorithm. Fireworks particle swarm algorithm is utilized in the optimization process. PF-PAM algorithm, which is an improved PAM algorithm, is proposed and applied in image retrieval. First, extract the feature vector of the image in the gallery for the first clustering. Next, according to the clustering results, the most optimal cluster center is searched through the firework particle swarm algorithm to obtain the final clustering result. Finally, according to the incoming query image, determine the related image category and get similar images. The experimental comparison with other approaches shows that this method can effectively improve retrieval accuracy.

Clustering Algorithm Based on Improved Particle Swarm Algorithm

2013 ◽  
Vol 798-799 ◽  
pp. 689-692 ◽  
Author(s):  
Jin Hui Yang ◽  
Xi Cao
Keyword(s):  
Cluster Analysis ◽  
Particle Swarm Optimization ◽  
Local Search ◽  
Clustering Algorithm ◽  
Particle Swarm ◽  
Particle Swarm Algorithm ◽  
Swarm Optimization ◽  
Initial Cluster ◽  
Cluster Analysis Method ◽  
Swarm Algorithm

K-means algorithm is a traditional cluster analysis method, has the characteristics of simple ideas and algorithms, and thus become one of the commonly used methods of cluster analysis. However, the K-means algorithm classification results are too dependent on the choice of the initial cluster centers for some initial value, the algorithm may converge in general suboptimal solutions. Analysis of the K-means algorithm and particle swarm optimization based on a clustering algorithm based on improved particle swarm algorithm. The algorithm local search ability of the K-means algorithm and the global search ability of particle swarm optimization, local search ability to improve the K-means algorithm to accelerate the convergence speed effectively prevent the occurrence of the phenomenon of precocious puberty. The experiments show that the clustering algorithm has better convergence effect.

A K-Medoids Clustering Algorithm Based on Particle Swarm Algorithm with Simulated Annealing

2013 ◽  
Vol 325-326 ◽  
pp. 1628-1631 ◽  
Author(s):  
Hong Zhou ◽  
Ke Luo
Keyword(s):  
Particle Swarm Optimization ◽  
Simulated Annealing ◽  
Optimization Algorithm ◽  
Clustering Algorithm ◽  
Particle Swarm Optimization Algorithm ◽  
Particle Swarm ◽  
Particle Swarm Algorithm ◽  
Swarm Optimization ◽  
Optimal Value ◽  
Swarm Algorithm

Be aimed at the problems that K-medoids algorithm is easy to fall into the local optimal value and basic particle swarm algorithm is easy to fall into the premature convergence, this paper joins the Simulated Annealing (SA) thought and proposes a novel K-medoids clustering algorithm based on Particle swarm optimization algorithm with simulated annealing. The new algorithm combines the quick optimization ability of particle swarm optimization algorithm and the probability of jumping property with SA, and maintains the characteristics that particle swarm algorithm is easy to realize, and improves the ability of the algorithm from local extreme value point. The experimental results show that the algorithm enhances the convergence speed and accuracy of the algorithm, and the clustering effect is better than the original k-medoids algorithm.

Dynamic simulation of wind field in three-dimensional display space considering particle swarm algorithm fuzzy logic

2021 ◽  
pp. 1-6
Author(s):  
Honglei Xu ◽  
Linhuan Wang
Keyword(s):  
Fuzzy Logic ◽  
Dynamic Simulation ◽  
Wind Field ◽  
Three Dimensional ◽  
Measurement Data ◽  
Particle Swarm ◽  
Particle Swarm Algorithm ◽  
Three Dimensional Display ◽  
Swarm Algorithm ◽  
Synchronous Measurement

In order to improve the accuracy of dynamic detection of wind field in the three-dimensional display space, system software is carried out on the actual scene and corresponding airborne radar observation information data, and the particle swarm algorithm fuzzy logic algorithm is introduced into the wind field dynamic simulation process in three-dimensional display space, to analyze the error of the filtering result in detail, to process the hurricane Lily Doppler radar measurement data with the optimal adaptive filtering according to the error data. The three-dimensional wind field synchronous measurement data obtained by filtering was compared with three-dimensional wind field synchronous measurement data of the GPS dropsonde in this experiment, the sea surface wind field measurement data of the multi-band microwave radiometer, and the wind field data at aircraft altitude.

Sign in / Sign up

Export Citation Format

Share Document