Automatic Hyperspectral Image Clustering Using Qutrit Differential Evolution

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F24%3A10256315" target="_blank" >RIV/61989100:27240/24:10256315 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-981-97-7184-4_24" target="_blank" >https://link.springer.com/chapter/10.1007/978-981-97-7184-4_24</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-981-97-7184-4_24" target="_blank" >10.1007/978-981-97-7184-4_24</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Automatic Hyperspectral Image Clustering Using Qutrit Differential Evolution

Popis výsledku v původním jazyce

A hyperspectral image serves as a valuable data source for ground cover analysis. However, determining the optimum number of clusters in hyperspectral images faces challenges due to the &quot;curse of dimensionality&quot; and the unavailability of ground truth images. Therefore, employing unsupervised cluster detection methods proves more advantageous in practical scenarios. This paper introduces a qutrit differential evolution algorithm for automatic clustering of hyperspectral images. The proposed algorithm incorporates qutrit Hadamard gates for population initialization and qutrit NOT gates for mutation. A qutrit-based crossover operation is also implemented following the normalization principle. The results of the proposed qutrit differential evolution are compared with the classical and qubit differential evolution algorithms utilizing different statistical tests and the F score. The Adjusted Rand Index serves as the fitness function and is used to validate the clusters. In most cases, the proposed algorithm outperforms the competing algorithms and the K-means algorithm with predefined cluster numbers.

Název v anglickém jazyce

Automatic Hyperspectral Image Clustering Using Qutrit Differential Evolution

Popis výsledku anglicky

A hyperspectral image serves as a valuable data source for ground cover analysis. However, determining the optimum number of clusters in hyperspectral images faces challenges due to the &quot;curse of dimensionality&quot; and the unavailability of ground truth images. Therefore, employing unsupervised cluster detection methods proves more advantageous in practical scenarios. This paper introduces a qutrit differential evolution algorithm for automatic clustering of hyperspectral images. The proposed algorithm incorporates qutrit Hadamard gates for population initialization and qutrit NOT gates for mutation. A qutrit-based crossover operation is also implemented following the normalization principle. The results of the proposed qutrit differential evolution are compared with the classical and qubit differential evolution algorithms utilizing different statistical tests and the F score. The Adjusted Rand Index serves as the fitness function and is used to validate the clusters. In most cases, the proposed algorithm outperforms the competing algorithms and the K-means algorithm with predefined cluster numbers.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

ADVANCES IN SWARM INTELLIGENCE, PT II, ICSI 2024

ISBN

978-981-9771-83-7

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

15

Strana od-do

280-294

Název nakladatele

SPRINGER-VERLAG SINGAPORE PTE LTD

Místo vydání

SINGAPORE

Místo konání akce

Xining

Datum konání akce

23. 8. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001308319900024