The paper introduces a wavenumber-aware deep learning approach that represents each Raman spectral point as an intensity–wavenumber pair and uses Transformer positional encodings derived from the wavenumber. This method remains robust to noise, sparse sampling, and partial spectral coverage across various neural network architectures, outperforming index-based and learned encodings when only part of the spectrum is observed. The approach was validated on Raman spectra from three bacterial species, their synthetic mixtures, and a public 30-isolate bacterial benchmark, demonstrating consistent performance on unseen sampling grids.
arXiv:2606. 27096v1 Announce Type: new Abstract: Transformer-based models have recently attracted increasing attention for Raman spectral classification.
Sharpness-Aware Minimization (SAM) is applied to improve the generalization of machine learning models for classifying bacterial Raman spectra, a technique that could enable rapid, portable diagnostics for antimicrobial resistance. The study shows that SAM can increase classification accuracy by up to 10.5% on a single data split and by an average of 2.7% across multiple splits compared to the traditional Adam optimizer. These gains demonstrate SAM’s potential to enhance the clinical utility of AI-powered Raman spectroscopy tools.
arXiv:2608. 02157v1 Announce Type: new Abstract: Raman spectroscopy enables non-destructive, label-free molecular characterization across materials science, biomedicine and process monitoring.
Raman spectroscopy enables non-destructive, label-free molecular characterization across materials science, biomedicine and process monitoring. Predictive Raman datasets often contain few labelled spectra and thousands of ordered wavenumbers, with informative variation within bands and across distant spectral regions.
The paper presents a physics‑aware, multi‑domain self‑supervised learning framework for Raman spectroscopy that uses a masked autoencoder with a sparse Voigt‑profile decoder and a denoising objective. It learns transferable spectral representations from diverse biological, chemical, forensic, and materials datasets, and demonstrates improved performance on substance classification, component identification, concentration estimation, and spectral denoising. The study shows that self‑supervised pretraining is especially beneficial for tasks with limited labeled data, that attention‑based probing reveals richer information than linear probing, and that larger encoders benefit more from pretraining.
arXiv:2606. 14169v1 Announce Type: new Abstract: Raman spectroscopy provides label-free, chemically specific characterization of biological systems and has become an important tool for cancer diagnosis, molecular subtyping, microbiological identification, and intraoperative decision support.
arXiv:2610.02224v1 Announce Type: new Abstract: Rapid and reliable identification of pharmaceutical residues is important for safeguarding public health, ensuring food safety, and enabling practical...
arXiv:2610.32505v1 Announce Type: new Abstract: Spectroscopic instruments with limited wavenumber coverage require accurate scan positioning or multiple measurements to complete the material analysis...
arXiv:2605.02003v3 Announce Type: replace Abstract: Machine Learning (ML) has transformed many scientific fields, yet key applications still lack standardized benchmarks. Raman spectroscopy, a widely...
arXiv:2607. 10196v1 Announce Type: new Abstract: Access to sufficiently large biomedical datasets remains a major obstacle for machine learning in Raman spectroscopy-based diagnostics.
arXiv:2608. 12227v1 Announce Type: cross Abstract: Hyperspectral imaging (HSI) offers nondestructive assessment of fish freshness by detecting biochemical alterations across spectral bands.
Hyperspectral imaging (HSI) offers nondestructive assessment of fish freshness by detecting biochemical alterations across spectral bands. However, conventional deep learning approaches do not fully address the particular characteristics of HSI data, such as spectral dominance over spatial textures, ordinal label structure, and a small number of training samples.