Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2509.25964 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911185775886336 |
|---|---|
| author | Soysal, Deniz García-Andrade, Xabier Rodriguez, Laura E. Sobron, Pablo Barge, Laura M. Detry, Renaud |
| author_facet | Soysal, Deniz García-Andrade, Xabier Rodriguez, Laura E. Sobron, Pablo Barge, Laura M. Detry, Renaud |
| contents | Autonomous Raman instruments on Mars rovers, deep-sea landers, and field robots must interpret raw spectra distorted by fluorescence baselines, peak shifts, and limited ground-truth labels. Using curated subsets of the RRUFF database, we evaluate one-dimensional convolutional neural networks (CNNs) and report four advances: (i) Baseline-independent classification: compact CNNs surpass $k$-nearest-neighbors and support-vector machines on handcrafted features, removing background-correction and peak-picking stages while ensuring reproducibility through released data splits and scripts. (ii) Pooling-controlled robustness: tuning a single pooling parameter accommodates Raman shifts up to $30 \,\mathrm{cm}^{-1}$, balancing translational invariance with spectral resolution. (iii) Label-efficient learning: semi-supervised generative adversarial networks and contrastive pretraining raise accuracy by up to $11\%$ with only $10\%$ labels, valuable for autonomous deployments with scarce annotation. (iv) Constant-time adaptation: freezing the CNN backbone and retraining only the softmax layer transfers models to unseen minerals at $\mathcal{O}(1)$ cost, outperforming Siamese networks on resource-limited processors. This workflow, which involves training on raw spectra, tuning pooling, adding semi-supervision when labels are scarce, and fine-tuning lightly for new targets, provides a practical path toward robust, low-footprint Raman classification in autonomous exploration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_25964 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reevaluating Convolutional Neural Networks for Spectral Analysis: A Focus on Raman Spectroscopy Soysal, Deniz García-Andrade, Xabier Rodriguez, Laura E. Sobron, Pablo Barge, Laura M. Detry, Renaud Machine Learning Autonomous Raman instruments on Mars rovers, deep-sea landers, and field robots must interpret raw spectra distorted by fluorescence baselines, peak shifts, and limited ground-truth labels. Using curated subsets of the RRUFF database, we evaluate one-dimensional convolutional neural networks (CNNs) and report four advances: (i) Baseline-independent classification: compact CNNs surpass $k$-nearest-neighbors and support-vector machines on handcrafted features, removing background-correction and peak-picking stages while ensuring reproducibility through released data splits and scripts. (ii) Pooling-controlled robustness: tuning a single pooling parameter accommodates Raman shifts up to $30 \,\mathrm{cm}^{-1}$, balancing translational invariance with spectral resolution. (iii) Label-efficient learning: semi-supervised generative adversarial networks and contrastive pretraining raise accuracy by up to $11\%$ with only $10\%$ labels, valuable for autonomous deployments with scarce annotation. (iv) Constant-time adaptation: freezing the CNN backbone and retraining only the softmax layer transfers models to unseen minerals at $\mathcal{O}(1)$ cost, outperforming Siamese networks on resource-limited processors. This workflow, which involves training on raw spectra, tuning pooling, adding semi-supervision when labels are scarce, and fine-tuning lightly for new targets, provides a practical path toward robust, low-footprint Raman classification in autonomous exploration. |
| title | Reevaluating Convolutional Neural Networks for Spectral Analysis: A Focus on Raman Spectroscopy |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.25964 |