Abstract
Abstract. A particle swarm optimization (PSO) algorithm has been widely used in the field of remote sensing image classification. We proposed the IPSO-FKM algorithm, which use the improved PSO (IPSO) algorithm to optimize the initial parameters of the Fuzzy K-Means (FKM) clustering algorithm. We combine the crossover operator of genetic algorithms with PSO, and introduce the fuzzy membership degree of fuzzy mathematics into K-means clustering algorithm. Then we use the IPSO-FKM algorithm to optimize the classification results of the Hyperion remotely sensed images, and use FKM, IPSO, and IPSO-FKM to extract the land cover information on the wetlands in Dongting Lakes, China. The experimental results have been validated by the classification results of MLC and the field investigation data. The validation results have been evaluated from three perspectives: the overall classification accuracy and the Kappa coefficient from the pixel perspective, the intra-cluster distance and the inter-cluster distance from the feature perspective, and the partition coefficient and partition entropy from the information perspective. According to the comparison of IPSO and FKM algorithms，the IPSO-FKM algorithm has a better performance than the others in all three respects. Additionally, in terms of the fitness convergence, the IPSO-FKM algorithm has a better searching velocity and better convergence to lower the quantization errors compared with the other two algorithms.
Highlights
Data clustering is a process of grouping together similar multidimensional data vectors into a number of clusters
By comparing the classification results of Fuzzy K-means and improved PSO (IPSO) with that of IPSO-Fuzzy K-Means (FKM) based on the truth data, we analyzed the classification precision in terms of the three aspects and the convergence speed of the new hybrid clustering algorithm
After the image classification with the three algorithms, six objects in the image were extracted, and these six objects were classified into six surface feature types based on the field investigation data
Summary
Data clustering is a process of grouping together similar multidimensional data vectors into a number of clusters. FKM is an iteration optimal algorithm; its objective function is built based on the weighted distance between each pixel in the image and each of the cluster centers. Eberhart and Kennedy(Kennedy and Eberhart, 1995) proposed the Particle Swarm Optimization (PSO) algorithm first in 1995; this approach is a simple and effective new-style evolutionary computation technique and is similar to a genetic algorithm or an ant colony algorithm. PSO is a population-based optimization algorithm and a type of evolutionary computation that is based on the swarm intelligence algorithm(Civicioglu and Besdok, 2013). The algorithm has typical characteristics of swarm intelligence. It uses an information-sharing mechanism, which allows individuals to learn from each other to promote the development of the entire swarm(Jain, Nangia et al, 2018)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
