Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2606.00081 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916067953082368 |
|---|---|
| author | Dione, Michel Lonlac, Jerry Louis, Hélène Fleury, Anthony Lecoeuche, Stephane |
| author_facet | Dione, Michel Lonlac, Jerry Louis, Hélène Fleury, Anthony Lecoeuche, Stephane |
| contents | Distributed Acoustic Sensing (DAS) enables large-scale monitoring through optical fibers, but its high dimensionality and complex spatio-temporal patterns make event classification demanding. Existing deep learning approaches-CNNs, recurrent models, and Transformer variants-either fail to capture long-range dependencies or require processing raw DAS matrices at prohibitive cost. We propose DAStatFormer, a hybrid multibranch Transformer that combines compact multidomain statistical features with Gated Transformer Networks. Instead of raw signals, we extract 24 ANOVA-selected attributes per channel from the temporal, waveform, and spectral domains, reducing data size by orders of magnitude while preserving discriminative information. Each domain is processed via dedicated step-wise and channel-wise attention branches, fused by an adaptive gating mechanism. Experiments on the open $Φ$-OTDR benchmark and a real-scenario DAS dataset show that DAS-tatFormer achieves up to 99.4% accuracy and near-perfect real-world performance, while using significantly fewer parameters and lower inference cost than models such as DASFormer and DeepViT. These results demonstrate its suitability for scalable, real-time DAS-based monitoring. We release our code at https://github.com/MichelD-git/DAStatFormer |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_00081 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DAStatFormer: A Hybrid Multibranch Transformer with Statistical Feature Integration for DAS-Based Pattern Recognitions Dione, Michel Lonlac, Jerry Louis, Hélène Fleury, Anthony Lecoeuche, Stephane Machine Learning Artificial Intelligence Sound Distributed Acoustic Sensing (DAS) enables large-scale monitoring through optical fibers, but its high dimensionality and complex spatio-temporal patterns make event classification demanding. Existing deep learning approaches-CNNs, recurrent models, and Transformer variants-either fail to capture long-range dependencies or require processing raw DAS matrices at prohibitive cost. We propose DAStatFormer, a hybrid multibranch Transformer that combines compact multidomain statistical features with Gated Transformer Networks. Instead of raw signals, we extract 24 ANOVA-selected attributes per channel from the temporal, waveform, and spectral domains, reducing data size by orders of magnitude while preserving discriminative information. Each domain is processed via dedicated step-wise and channel-wise attention branches, fused by an adaptive gating mechanism. Experiments on the open $Φ$-OTDR benchmark and a real-scenario DAS dataset show that DAS-tatFormer achieves up to 99.4% accuracy and near-perfect real-world performance, while using significantly fewer parameters and lower inference cost than models such as DASFormer and DeepViT. These results demonstrate its suitability for scalable, real-time DAS-based monitoring. We release our code at https://github.com/MichelD-git/DAStatFormer |
| title | DAStatFormer: A Hybrid Multibranch Transformer with Statistical Feature Integration for DAS-Based Pattern Recognitions |
| topic | Machine Learning Artificial Intelligence Sound |
| url | https://arxiv.org/abs/2606.00081 |