Investigation on Hyperspectral Augmentation to Construction Materials Classification

• Abstract:

  The recycling of construction waste faces challenges in material identification due to class imbalance in hyperspectral datasets. To address this, we propose integrating a data augmentation module into the classification workflow for construction materials using short-wavelength infrared (SWIR) reflectance spectra. Experiments were conducted with Random Forest (RF) and 1D-CNN classifiers across multi-class and binary classification tasks, where the latter targeted classes commonly confused with minority categories. Various augmentation methods were tested, with the self-attention-based WGAN (SA-WGAN) showing the most notable improvement. It increased the recall of the minority class by up to 60 and 48 percentage points in the multi-class and binary classification tasks, respectively, while maintaining stable performance on the majority classes.
• Download:

  IMEKO-TC2-2025-008.pdf
• DOI:

  tc2-2025.008

Event details:

• IMEKO TC:

  TC2
• Event name:

  IMEKO TC2 PhotoMet 2025
• Title:

  2025 IMEKO TC2 International Symposium on Modern Photonic Metrology

  PhotoMet 2025 - Shaping the Future of Photonic Metrology

• Place:

  Modena, ITALY
• Time:

  1 September 2025 - 3 September 2025