Low-Complexity CNN-Based Classification of Electroneurographic Signals
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915279939829760 |
|---|---|
| author | Gokdag, Arek Berc Mura, Silvia Coviello, Antonio Zhu, Michele Magarini, Maurizio Spagnolini, Umberto |
| author_facet | Gokdag, Arek Berc Mura, Silvia Coviello, Antonio Zhu, Michele Magarini, Maurizio Spagnolini, Umberto |
| contents | Peripheral nerve interfaces (PNIs) facilitate neural recording and stimulation for treating nerve injuries, but real-time classification of electroneurographic (ENG) signals remains challenging due to constraints on complexity and latency, particularly in implantable devices. This study introduces MobilESCAPE-Net, a lightweight architecture that reduces computational cost while maintaining and slightly improving classification performance. Compared to the state-of-the-art ESCAPE-Net, MobilESCAPE-Net achieves comparable accuracy and F1-score with significantly lower complexity, reducing trainable parameters by 99.9\% and floating point operations per second by 92.47\%, enabling faster inference and real-time processing. Its efficiency makes it well-suited for low-complexity ENG signal classification in resource-constrained environments such as implantable devices. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_06241 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Low-Complexity CNN-Based Classification of Electroneurographic Signals Gokdag, Arek Berc Mura, Silvia Coviello, Antonio Zhu, Michele Magarini, Maurizio Spagnolini, Umberto Signal Processing Artificial Intelligence Machine Learning Peripheral nerve interfaces (PNIs) facilitate neural recording and stimulation for treating nerve injuries, but real-time classification of electroneurographic (ENG) signals remains challenging due to constraints on complexity and latency, particularly in implantable devices. This study introduces MobilESCAPE-Net, a lightweight architecture that reduces computational cost while maintaining and slightly improving classification performance. Compared to the state-of-the-art ESCAPE-Net, MobilESCAPE-Net achieves comparable accuracy and F1-score with significantly lower complexity, reducing trainable parameters by 99.9\% and floating point operations per second by 92.47\%, enabling faster inference and real-time processing. Its efficiency makes it well-suited for low-complexity ENG signal classification in resource-constrained environments such as implantable devices. |
| title | Low-Complexity CNN-Based Classification of Electroneurographic Signals |
| topic | Signal Processing Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2505.06241 |