LAST-PAIN: Learning Adaptive Spike Thresholds for Low Back Pain Biosignals Classification
Spiking neural networks (SNNs) present the potential for ultra-low-power computation, especially when implemented on dedicated neuromorphic hardware. However, a significant challenge is the efficient conversion of continuous real-world data into the discrete spike trains required by SNNs. In this pa...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10908225/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850138191917481984 |
|---|---|
| author | Freek Hens Mohammad Mahdi Dehshibi Leila Bagheriye Ana Tajadura-Jimenez Mahyar Shahsavari |
| author_facet | Freek Hens Mohammad Mahdi Dehshibi Leila Bagheriye Ana Tajadura-Jimenez Mahyar Shahsavari |
| author_sort | Freek Hens |
| collection | DOAJ |
| description | Spiking neural networks (SNNs) present the potential for ultra-low-power computation, especially when implemented on dedicated neuromorphic hardware. However, a significant challenge is the efficient conversion of continuous real-world data into the discrete spike trains required by SNNs. In this paper, we introduce Learning Adaptive Spike Thresholds (LAST), a novel, trainable encoding strategy designed to address this challenge. The LAST encoder learns adaptive thresholds to transform continuous signals of varying dimensionality-ranging from time series data to high dimensional tensors-into sparse spike trains. Our proposed encoder effectively preserves temporal dynamics and adapts to the characteristics of the input. We validate the LAST approach in a demanding healthcare application using the EmoPain dataset. This dataset contains multimodal biosignal analysis for assessing chronic lower back pain (CLBP). Despite the dataset’s small sample size and class imbalance, our LAST-driven SNN framework achieves a competitive Matthews Correlation Coefficient of 0.44 and an accuracy of 80.43% in CLBP classification. The experimental results also indicate that the same framework can achieve an F1-score of 0.65 in detecting protective behaviour. Furthermore, the LAST encoder outperforms conventional rate and latency-based encodings while maintaining sparse spike representations. This achievement shows promises for energy-efficient and real-time biosignal processing in resource-limited environments. |
| format | Article |
| id | doaj-art-ebc68cd7eacc4c9cab997cb760aa160b |
| institution | OA Journals |
| issn | 1534-4320 1558-0210 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj-art-ebc68cd7eacc4c9cab997cb760aa160b2025-08-20T02:30:38ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102025-01-01331038104710.1109/TNSRE.2025.354668210908225LAST-PAIN: Learning Adaptive Spike Thresholds for Low Back Pain Biosignals ClassificationFreek Hens0https://orcid.org/0009-0005-0405-0560Mohammad Mahdi Dehshibi1https://orcid.org/0000-0001-8112-5419Leila Bagheriye2https://orcid.org/0000-0003-1605-5850Ana Tajadura-Jimenez3https://orcid.org/0000-0003-3166-3512Mahyar Shahsavari4https://orcid.org/0000-0001-7703-6835Donders Institute for Brain, Cognition and Behavior, Radboud University Nijmegen, Nijmegen, The NetherlandsDepartment of Computer Science and Engineering, Universidad Carlos III de Madrid, Leganés, SpainDonders Institute for Brain, Cognition and Behavior, Radboud University Nijmegen, Nijmegen, The NetherlandsDepartment of Computer Science and Engineering, Universidad Carlos III de Madrid, Leganés, SpainDonders Institute for Brain, Cognition and Behavior, Radboud University Nijmegen, Nijmegen, The NetherlandsSpiking neural networks (SNNs) present the potential for ultra-low-power computation, especially when implemented on dedicated neuromorphic hardware. However, a significant challenge is the efficient conversion of continuous real-world data into the discrete spike trains required by SNNs. In this paper, we introduce Learning Adaptive Spike Thresholds (LAST), a novel, trainable encoding strategy designed to address this challenge. The LAST encoder learns adaptive thresholds to transform continuous signals of varying dimensionality-ranging from time series data to high dimensional tensors-into sparse spike trains. Our proposed encoder effectively preserves temporal dynamics and adapts to the characteristics of the input. We validate the LAST approach in a demanding healthcare application using the EmoPain dataset. This dataset contains multimodal biosignal analysis for assessing chronic lower back pain (CLBP). Despite the dataset’s small sample size and class imbalance, our LAST-driven SNN framework achieves a competitive Matthews Correlation Coefficient of 0.44 and an accuracy of 80.43% in CLBP classification. The experimental results also indicate that the same framework can achieve an F1-score of 0.65 in detecting protective behaviour. Furthermore, the LAST encoder outperforms conventional rate and latency-based encodings while maintaining sparse spike representations. This achievement shows promises for energy-efficient and real-time biosignal processing in resource-limited environments.https://ieeexplore.ieee.org/document/10908225/Spike train encoderspiking recurrent neural networkEmoPainchronic painbiosignal analysis |
| spellingShingle | Freek Hens Mohammad Mahdi Dehshibi Leila Bagheriye Ana Tajadura-Jimenez Mahyar Shahsavari LAST-PAIN: Learning Adaptive Spike Thresholds for Low Back Pain Biosignals Classification IEEE Transactions on Neural Systems and Rehabilitation Engineering Spike train encoder spiking recurrent neural network EmoPain chronic pain biosignal analysis |
| title | LAST-PAIN: Learning Adaptive Spike Thresholds for Low Back Pain Biosignals Classification |
| title_full | LAST-PAIN: Learning Adaptive Spike Thresholds for Low Back Pain Biosignals Classification |
| title_fullStr | LAST-PAIN: Learning Adaptive Spike Thresholds for Low Back Pain Biosignals Classification |
| title_full_unstemmed | LAST-PAIN: Learning Adaptive Spike Thresholds for Low Back Pain Biosignals Classification |
| title_short | LAST-PAIN: Learning Adaptive Spike Thresholds for Low Back Pain Biosignals Classification |
| title_sort | last pain learning adaptive spike thresholds for low back pain biosignals classification |
| topic | Spike train encoder spiking recurrent neural network EmoPain chronic pain biosignal analysis |
| url | https://ieeexplore.ieee.org/document/10908225/ |
| work_keys_str_mv | AT freekhens lastpainlearningadaptivespikethresholdsforlowbackpainbiosignalsclassification AT mohammadmahdidehshibi lastpainlearningadaptivespikethresholdsforlowbackpainbiosignalsclassification AT leilabagheriye lastpainlearningadaptivespikethresholdsforlowbackpainbiosignalsclassification AT anatajadurajimenez lastpainlearningadaptivespikethresholdsforlowbackpainbiosignalsclassification AT mahyarshahsavari lastpainlearningadaptivespikethresholdsforlowbackpainbiosignalsclassification |