Improved quantum evolutionary particle swarm optimization for band selection of hyperspectral image

Yu, Lei; Han, Yifei; Mu, Lin-lin

doi:10.1080/2150704x.2020.1782501

Cited by 20 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The concept of quantum computing was proposed by Beninff and Feynman [ 28 ]. In the late 1990s, Narayanan and Kuk-Hyun Han began to combine quantum theory with genetic algorithms, and successfully used them for multimodal function optimization and a class of combinatorial optimization problems and solution of the knapsack problem [ 29 , 30 ]. Thus, QGA not only improves the capability of global search, but also avoids the problem of premature convergence.…”

Section: Itcs Depth-controller Optimization Methods Designmentioning

confidence: 99%

Depth-Keeping Control for a Deep-Sea Self-Holding Intelligent Buoy System Based on Inversion Time Constraint Stability Strategy Optimization

Wang

Qiu

et al. 2022

Sensors

View full text Add to dashboard Cite

Based on the nonlinear disturbance observer (NDO), the inversion time-constraint stability strategy (ITCS) is designed to make the deep-sea self-holding intelligent buoy (DSIB) system hovered at an appointed depth within a specified time limit. However, it is very challenging to determine the optimal parameters of an ITCS depth controller. Firstly, a genetic algorithm based on quantum theory (QGA) is proposed to obtain the optimal parameter combination by using the individual expression form of quantum bit and the adjustment strategy of quantum rotary gate. To improve the speed and accuracy of global search in the QGA optimization process, taking the number of odd and even evolutions as the best combination point of the genetic and chaos particle swarm algorithm (GACPSO), an ITCS depth controller based on GACPSO strategy is proposed. Besides, the simulations and hardware-in-the-loop system experiments are conducted to examine the effectiveness and feasibility of the proposed QGA–ITCS and GACPSO–ITCS depth controller. The results show that the proposed GACPSO–ITCS depth controller provides higher stability with smaller steady-state error and less settling time in the depth-control process. The research of the proposed method can provide a stable operation condition for the marine sensors carried by the DSIB.

show abstract

Section: Itcs Depth-controller Optimization Methods Designmentioning

confidence: 99%

Depth-Keeping Control for a Deep-Sea Self-Holding Intelligent Buoy System Based on Inversion Time Constraint Stability Strategy Optimization

Wang

Qiu

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…In order to verify the performance of our proposed inertia weight, five test functions are used to test it. Meanwhile, our simulation results are also compared with standard particle swarm optimization [18] (PSO), a particle swarm optimization algorithm based on compression factor [4] (FPSO), a hybrid particle swarm optimization algorithm combined with adaptive inertia weight [25](P-PSO-SA) and a hybrid particle swarm optimization algorithm that dynamically adjusts inertia weight [22] (IDWPSO). The optimal value of each test function was solved 50 times by using these five algorithms respectively.…”

Section: Test Functionmentioning

confidence: 99%

“…Paper [16] proposed an intelligent fuzzy level set method and an improved quantum particle swarm optimization algorithm with global search capability are proposed. Paper [25] developed a new algorithm-Improved quantum evolutionary PSO (IQEPSO) while the learning factor and inertia factor varied with the number of iterations.…”

Section: Introductionmentioning

confidence: 99%

A new particle swarm optimization algorithm for identifying the hydraulic conductivity and diffusivity parameters in the unsaturated soil water

Wanga¹,

Panga²,

Suna³

et al. 2022

IJMSOR

View full text Add to dashboard Cite

In this paper, we present the new particle swarm optimization algorithm by defining the inertia weight which depends on linearly the iteration step for solving the unsaturated soil water problem. By comparing with the exist particle swarm optimizations such as such as PSO algorithm, FPSO algorithm, P-PSO-SA algorithm and IDWPSO algorithm, numerical experiments verify that our proposed algorithm is more efficient and accurate to reach the optimal solution in the multimodal function extremum problem. Combining the characteristic difference method, our algorithm is applied to solve the unsaturated soil water problem. Numerical experiments show that our algorithm is quicker and more precision to approximate the exact solution. Keywords: Particle swarm optimization; Unsaturated soil water; Inertia weight; Characteristic difference; Parameter identification

show abstract

“…Sawant et al [22,23] proposed a modified wind-driven optimization algorithm and cuckoo search algorithm to find the best band, avoiding premature convergence. Similarly, Yu et al [24] proposed a quantum evolutionary algorithm for band selection. In addition to considering the search algorithm for band selection, the band evaluation criteria are equally important.…”

Section: Introductionmentioning

confidence: 99%

Three-Stages Hyperspectral Image Compression Sensing with Band Selection

Zhang¹,

Zhang²,

Cai³

et al. 2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

Compressed sensing (CS), as an efficient data transmission method, has achieved great success in the field of data transmission such as image, video and text. It can robustly recover signals from fewer Measurements, effectively alleviating the bandwidth pressure during data transmission. However, CS has many shortcomings in the transmission of hyperspectral image (HSI) data. This work aims to consider the application of CS in the transmission of hyperspectral image (HSI) data, and provides a feasible research scheme for CS of HSI data. HSI has rich spectral information and spatial information in bands, which can reflect the physical properties of the target. Most of the hyperspectral image compressed sensing (HSICS) algorithms cannot effectively use the inter-band information of HSI, resulting in poor reconstruction effects. In this paper, A three-stage hyperspectral image compression sensing algorithm (Three-stages HSICS) is proposed to obtain intra-band and inter-band characteristics of HSI, which can improve the reconstruction accuracy of HSI. Here, we establish a multi-objective band selection (Mop-BS) model, a multi-hypothesis prediction (MHP) model and a residual sparse (ReWSR) model for HSI, and use a staged reconstruction method to restore the compressed HSI. The simulation results show that the three-stage HSICS successfully improves the reconstruction accuracy of HSICS, and it performs best among all comparison algorithms.

show abstract

Improved quantum evolutionary particle swarm optimization for band selection of hyperspectral image

Cited by 20 publications

References 14 publications

Depth-Keeping Control for a Deep-Sea Self-Holding Intelligent Buoy System Based on Inversion Time Constraint Stability Strategy Optimization

Depth-Keeping Control for a Deep-Sea Self-Holding Intelligent Buoy System Based on Inversion Time Constraint Stability Strategy Optimization

A new particle swarm optimization algorithm for identifying the hydraulic conductivity and diffusivity parameters in the unsaturated soil water

Three-Stages Hyperspectral Image Compression Sensing with Band Selection

Contact Info

Product

Resources

About