001033656 001__ 1033656
001033656 005__ 20250203103355.0
001033656 037__ $$aFZJ-2024-06528
001033656 041__ $$aEnglish
001033656 1001_ $$0P:(DE-Juel1)188273$$aNeftci, Emre$$b0$$ufzj
001033656 1112_ $$aArtificial Intelligence BioMedical Circuits And Systems For Health$$cToronto$$d2023-10-19 - 2023-10-21$$gBiocas IEEE$$wCanada
001033656 245__ $$aOnline Transformers with Spiking Neurons for Fast Prosthetic Hand Control
001033656 260__ $$c2023
001033656 3367_ $$033$$2EndNote$$aConference Paper
001033656 3367_ $$2BibTeX$$aINPROCEEDINGS
001033656 3367_ $$2DRIVER$$aconferenceObject
001033656 3367_ $$2ORCID$$aCONFERENCE_POSTER
001033656 3367_ $$2DataCite$$aOutput Types/Conference Poster
001033656 3367_ $$0PUB:(DE-HGF)24$$2PUB:(DE-HGF)$$aPoster$$bposter$$mposter$$s1732779931_10399$$xAfter Call
001033656 500__ $$aAlso published in 2023 IEEE Biomedical Circuits and Systems Conference (BioCAS), Electronic ISBN:979-8-3503-0026-0Print on Demand(PoD) ISBN:979-8-3503-0027-7
001033656 520__ $$aFast and accurate online processing is essential for smooth prosthetic hand control with Surface Electromyography signals (sEMG). Although transformers are state-of-the-art deep learning models in signal processing, the self-attention mechanism at the core of their operations requires accumulating data for large time-windows. They are therefore not suited for online signal processing. In this paper, we use an attention mechanism with sliding windows that allows a transformer to process sequences element-by-element. Moreover, we increase the sparsity of the network using spiking neurons. We test the model on the NinaproDB8 finger position regression dataset. Our model sets its new state-of-the-art in terms of accuracy on NinaproDB8, while requiring only very short time windows of 3.5 ms at each inference step, and reducing the number of synaptic operations up to a factor of ×5.3 thanks to the spiking neurons. Our results hold great promises for wearable online sEMG processing systems for prosthetic hand control.
001033656 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x0
001033656 7001_ $$0P:(DE-Juel1)190112$$aFinkbeiner, Jan Robert$$b1$$ufzj
001033656 7001_ $$0P:(DE-Juel1)194421$$aLeroux, Nathan$$b2$$ufzj
001033656 8564_ $$uhttps://ieeexplore.ieee.org/document/10388996
001033656 8564_ $$uhttps://juser.fz-juelich.de/record/1033656/files/Online_Transformers_with_Spiking_Neurons_for_Fast_Prosthetic_Hand_Control.pdf$$yRestricted
001033656 909CO $$ooai:juser.fz-juelich.de:1033656$$pVDB
001033656 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)188273$$aForschungszentrum Jülich$$b0$$kFZJ
001033656 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)190112$$aForschungszentrum Jülich$$b1$$kFZJ
001033656 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)194421$$aForschungszentrum Jülich$$b2$$kFZJ
001033656 9131_ $$0G:(DE-HGF)POF4-523$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5234$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vNeuromorphic Computing and Network Dynamics$$x0
001033656 9141_ $$y2024
001033656 9201_ $$0I:(DE-Juel1)PGI-15-20210701$$kPGI-15$$lNeuromorphic Software Eco System$$x0
001033656 980__ $$aposter
001033656 980__ $$aVDB
001033656 980__ $$aI:(DE-Juel1)PGI-15-20210701
001033656 980__ $$aUNRESTRICTED