Sep 2026· Italian National Conference on Sensors· Vol 26· 0 citations· 35 references
Medicine
Abstract
High-value recycling of waste textiles requires accurate fiber-composition identification, yet similar blends often exhibit overlapping near-infrared absorption bands and substantial within-class variation. Using 291 waste-textile swatches, this study develops ConvPatchTST, a convolution-enhanced Patch Transformer that integrates Raw and SNV (SG) spectra as complementary input channels. Overlapping convolutional patch embedding captures local continuous absorption features, while a Transformer encoder models cross-band dependencies. Spectral bands spanning 958.5–1646.6 nm were selected for model training and analysis. Under a single fabric-swatch-grouped internal train-validation split with pixel-level evaluation, ConvPatchTST achieves an accuracy of 0.966 and a macro F1 of 0.970, outperforming several baseline models. The Raw + SNV (SG) representation also surpasses single-channel, three-channel, and alternative dual-channel inputs. Pairwise analysis identifies statistically discriminative and highly attributed intervals for four similar material pairs. For polyester/polysp, the intervals near 1369.0–1379.6 nm show clear statistical-model agreement. These results indicate that complementary spectral representations and convolution-enhanced Patch modeling support accurate classification and provide band-level clues for interpreting model decisions. Generalization to external samples, batches, and instruments requires further validation.
The results suggest that decoupled spatial–spectral representation and adaptive multi-scale fusion can improve hyperspectral image classification under the evaluated benchmark settings.
Findings indicate that preserving wavelength-wise co-location among multi-order spectral attributes and jointly learning regional importance and global dependencies can improve qualitative adulteration recognition.
Xiao-Zheng Liu, Ying-Xue Ma, Hao-Xia Huang et al.· Frontiers in Sustainable Foo...· 0 citations
This work proposes a four–stage hybrid framework for hyperspectral image classification that integrates spectral modeling and spatial feature extraction within a unified pipeline and compares the model with recent baselines, including DaViT.
Hyperspectral image classification is an important research topic in the field of remote sensing. Its core objective is to accurately identify different land-cover categories by jointly exploiting the spatial information and spectral characteristics of pixels. However, the complex and diverse spatial structures of grou...
Li-Guo Wang, Teng Wen, Dan-Feng Liu· Remote Sensing· 0 citations
Direct adoption of generic vision-transformer tokenization is often inefficient for hyperspectral image (HSI) classification because the data are high-dimensional, spectrally redundant, spatially structured, and label-scarce. This paper presents a multi-benchmark empirical study built on two ideas: linear spectral embe...
Ilkim Aydar, Paul Cotae, Nian Zhang· International Conference on...· 0 citations
Geographical authentication of Meconopsis integrifolia is important for the quality control and sustainable utilization of plateau medicinal plant resources, but adjacent origins often exhibit highly similar spectral and chemical profiles. In this study, a shared-private multimodal fusion (SPMF) framework was developed...
Xian-Dong Sun, Dong Li, Xiao-Ming Song et al.· Talanta: The International J...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.