SSGIE-KFCM: Source Code for Hyperspectral Band Selection Algorithm

An algorithm's source code for selecting optimal bands from hyperspectral remote sensing images. The code implements a two-stage optimization framework using kernel fuzzy C-means clustering and an improved firefly algorithm. Author Dandan He published the code on figshare in April 2026.

Use Cases

• Benchmarking band selection algorithms based on the described classification accuracy and computational efficiency.
• Implementing a lightweight solution for real-time hyperspectral image processing as mentioned in the description.
• Applying the method to agricultural monitoring or urban feature classification tasks referenced in the study.

Strengths

• Reported average classification accuracy exceeding 90% on the Indian Pines and Pavia University datasets.
• Reported area under the curve value of 0.958.
• Reported computational time reduced to 40% of traditional methods, with spectral feature computation times of 0.058s and 0.172s.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset is very small at 17.5 KB, indicating it is likely source code rather than a substantial data corpus.

Provenance

Source

figshare

Collection Method

Algorithm source code published as part of a research study.

Time Range

null

Freshness

Last updated 2026-04-17 17:37:42; freshness should be verified.

Geography

null