Sw-SSFCM_Dataset: benchmark scenes, label-budget splits and guidance-scale parameters for spatial-weighted semi-supervised fuzzy c-means on hyperspectral imagery

Domain:

geospatial

Record type:

dataset

Creator:

NguMaiNgu

Publisher:

Host:

Reproducibility kit for the manuscript A novel approach to spatial-weighted semi-supervised fuzzy c-means clustering for hyperspectral image analysis (Computers & Geosciences). Contains the retrieval scripts for the six public hyperspectral benchmarks (Botswana, Kennedy Space Center, Indian Pines, Pavia University, Houston 2013, WHU-Hi-LongKou), a self-contained Python loader reproducing the exact preprocessing and label encoding of the paper, the 300 canonical semi-supervised splits (6 scenes x 5 label budgets x 10 draws) and the guidance-scale parameters of the theta-rule. The hyperspectral cubes themselves remain with their original providers and are not redistributed here.

Visit

doi.org

Licenses

MIT License https://opensource.org/licenses/MIT

Fuzzy Unsupervised Artificial Learning Based on Credibilistic Fuzzy C-Means

This study proposes an unsupervised artificial learning approach based on the Credibilistic Fuzzy C-

Defining Brightness-Shape-Moisture Soil Parameters for Southern Africa From Hyperion Hyperspectral Imagery

CLUSTERING CREDIBILISTE FLOU DES DONNEES PETROLIERES VIA FUZZY C-MEANS.

Our paper deals with the application of the Fuzzy C-Means credibilistic method by adding a one-sided

Modifikasi Metode Fuzzy C-Means untuk Klasifikasi Citra Daun Padi

Metode Fuzzy C-means merupakan algoritma pembelajaran tidak terawasi yang menggunakan derajat keangg

COMPARATIVE ANALYSIS OF THYROID DISEASE USING FUZZY C AND K MEANS ALGORITHMS

Data mining is a process which involves sorting large data sets and spots patterns and relationships

Morphological Band Selection for Hyperspectral Imagery

International audience In this letter, a novel morphological band selection method is