A Novel Adaptive Compression Technique for Dealing with Corrupt Bands and High Levels of Band Correlations in Hyperspectral Images Based on Binary Hybrid GA-PSO for Big Data Compression

Abstract

Hyperspectral sensors generate useful information about climate and the earth's surface in numerous contiguous narrow spectral bands, being widely used in resource management, agriculture, environmental monitoring, among others. The compression of hyperspectral data helps in long-term storage and transmission systems. This paper introduces a new adaptive compression method for hyperspectral data. The method is based on separating the bands with different specifications by the histogram analysis and Binary Hybrid Genetic Algorithm-Particle Swarm Optimization (BHGAPSO). The new proposed method improves the compression ratio of the bestknown JPEG standards, saves storage space, and speeds up the transmission system. The proposed method is applied on two different test cases, and the results are evaluated and compared with a few powerful compression techniques, such as lossless JPEG and JPEG2000. The results confirm that the proposed method is accurate, simple and fast, which can be useful for big data (i.e, a high volume of data) processing. General TermsAlgorithms.

Fractional Order Darwinian Particle Swarm Optimization

“…In addition, the concept of PSO and FODPSO has been used for other applications such as image clustering, classification, data compression, and feature selection in the remote-sensing community. For more information on other applications of the PSO family, we refer interested readers to (Ghamisi et al 2013(Ghamisi et al , 2015a(Ghamisi et al , 2015bKargozar Nahavandi et al 2015 andGhamisi andBenediktsson 2015) …”

A novel modified SFTA approach for feature extraction

“…Ghamisi et al proposed the HGAPSO method [3,4]; consisting of two main portions: one is for combining the standard velocity and another is for updating the rules of PSOs (Particle Swarm Optimization) with the ideas of collection, crossover and transfiguration from GA (Genetic Algorithm) [5]. We have used HGAPSO instead of Otsu because for an obvious reason.…”

“…In [3,4], Ghamisi et al proposed the HGAPSO method; which has two main parts. One is to the association of the standard velocity and with the planning of selection, crossover and mutation from GA [5]; another one is to update the procedure of Particle Swarm Optimization. Swarm or population is the set of solutions from PSO; in which each solution consists of a set of parameters and represents a point in the multidimensional space, denoted as a particle [21].…”

“…Where c1 and c2 are defined as acceleration constants and r1 and r2 have random values ranging from 0 to 1. Here W stands for inertia weight [5]; which displays the location of each particle in the d-dimensional search space by the parameter [5,23].The best previous position of each particle is represented by and considered as particle best position.…”

“…is the best position of all particles, being denoted as global best particle [5,23]. The i-th particle position is updated by: = (2) Then again, GA; based on the genetic process [5,20]; is able to find an ideal solution by not exploring the whole search space [5]. Chromosome or individual is the optimization technique of GA which has several solutions.…”