.png){kind=icon}
.png){kind=icon}
Return
Hyperspectral Endmember Extraction by (μ plus λ) Multiobjective Differential Evolution Algorithm Based on Ranking Multiple Mutations
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2020.3004307.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Endmember extraction (EE) plays a crucial part in the hyperspectral unmixing (HU) process. To obtain satisfactory EE results, the EE can be considered as the multiobjective optimization problem to optimize the volume maximization (VM) and root-mean-square error (RMSE) simultaneously. However, it is often quite challenging to balance the conflict of these objectives. In order to tackle the challenges of multiobjective EE, we present a (mu + lambda) multiobjective differential evolution algorithm (( mu + lambda)-MODE) based on ranking multiple mutations. In the (mu + lambda)-MODE algorithm, ranking multiple mutations are adopted to create the mutant vectors via the scaling factor pool to enhance the population diversity. Moreover, mutant vectors employ the binary crossover operator to generate the trial vectors through a crossover control parameter pool in (mu + lambda)-MODE to take advantage of the good information of the population. In addition, (mu + lambda)-MODE utilizes the fast nondominated sorting approach to sort the parent and trial vectors, and then selects the elitism offspring as the next population via the (mu + lambda) selection strategy. Eventually, experimental comparative results in three real HSIs reveal that our proposed (mu + lambda)-MODE is superior to other EE methods.
Keywords:
Endmember extraction (EE)
multiobjective differential evolution (DE)
ranking multiple mutations
(mu plus lambda) selection strategy
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
8.6
Papers:
2.1W
Citations:
10.7W
View more organizations