Antonio Coviello
ABSTRACT
The paper evaluates two different neural network strategies for the classification of electroneurographic (ENG) recordings obtained in response to mechanical stimulations of a rat paw available from an open-access dataset. The first strategy is based on spiking neural networks (SNNs), a new class of artificial neural networks inspired by the information processing solutions of biological neurons. SNNs are considered to be promising for the classification of complex space-time models. The second strategy relies on convolutional neural networks (CNNs), a well-established tool for processing structured arrays of data such as images or space-time data. The existing effects of power line noise and other distortions generated by the non-idealities of the acquisition system (e.g., timing jitter) are removed by a suitable pre-processing. The accuracy and F1-score achieved by the SNN and the CNN are reported for a multi-class problem aiming to separate different types of somatosensory stimuli (i.e., nociception, plantar flexion, dorsiflexion, and touch, which are the mechanical stimulations of the dataset) and their different intensities.
- Sanjeev Agarwal, Ronald J Triolo, Rudi Kobetic, Michael Miller, Carol Bieri, Sahana Kukke, Lori Rohde, and John A Davis. 2003. Long-term user perceptions of an implanted neuroprosthesis for exercise, standing, and transfers after spinal cord injury. Journal of rehabilitation research and development 40, 3 (2003), 241--252.Google Scholar
- Emma Brunton, Christoph W Blau, and Kianoush Nazarpour. 2017. ENG recordings in response to mechanical stimulation. Retrieved August 29, 2022 from https://data.ncl.ac.uk/articles/dataset/ENG_recordings_in_response_to_mechanical_stimulation/10280846Google Scholar
- Emma Brunton, Christoph W Blau, and Kianoush Nazarpour. 2017. Separability of neural responses to standardised mechanical stimulation of limbs. Scientific reports 7, 1 (2017), 1--14.Google Scholar
- Yongqiang Cao, Yang Chen, and Deepak Khosla. 2015. Spiking deep convolutional neural networks for energy-efficient object recognition. International Journal of Computer Vision 113, 1 (2015), 54--66.Google ScholarDigital Library
- Haowen Fang, Amar Shrestha, and Qinru Qiu. 2020. Multivariate time series classification using spiking neural networks. In 2020 International Joint Conference on Neural Networks (IJCNN). IEEE, 1--7.Google ScholarCross Ref
- Wei Fang, Zhaofei Yu, Yanqi Chen, Timothée Masquelier, Tiejun Huang, and Yonghong Tian. 2021. Incorporating learnable membrane time constant to enhance learning of spiking neural networks. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 2661--2671.Google ScholarCross Ref
- David Guiraud, Thomas Stieglitz, Klaus Peter Koch, Jean-Louis Divoux, and Pierre Rabischong. 2006. An implantable neuroprosthesis for standing and walking in paraplegia: 5-year patient follow-up. Journal of neural engineering 3, 4 (2006), 268.Google ScholarCross Ref
- Robert Gütig. 2016. Spiking neurons can discover predictive features by aggregate-label learning. Science 351, 6277 (2016), aab4113.Google Scholar
- Sašo Jezernik and Thomas Sinkjaer. 1999. On statistical properties of whole nerve cuff recordings. IEEE transactions on biomedical engineering 46, 10 (1999), 1240--1245.Google ScholarCross Ref
- Ryan GL Koh, Michael Balas, Adrian I Nachman, and José Zariffa. 2020. Selective peripheral nerve recordings from nerve cuff electrodes using convolutional neural networks. Journal of Neural Engineering 17, 1 (2020), 016042.Google ScholarCross Ref
- Christopher E Larson and Ellis Meng. 2020. A review for the peripheral nerve interface designer. Journal of neuroscience methods 332 (2020), 108523.Google ScholarCross Ref
- Wolfgang Maass. 1997. Networks of spiking neurons: the third generation of neural network models. Neural networks 10, 9 (1997), 1659--1671.Google Scholar
- Benjamin W Metcalfe, Daniel J Chew, Christopher T Clarke, Nick De Neufvillle Donaldson, and John T Taylor. 2015. A new method for spike extraction using velocity selective recording demonstrated with physiological ENG in Rat. Journal of neuroscience methods 251 (2015), 47--55.Google ScholarCross Ref
- Benjamin W Metcalfe, Alan J Hunter, Jonathan E Graham-Harper-Cater, and John T Taylor. 2021. Array processing of neural signals recorded from the peripheral nervous system for the classification of action potentials. Journal of Neuroscience Methods 347 (2021), 108967.Google ScholarCross Ref
- Xavier Navarro, Thilo B Krueger, Natalia Lago, Silvestro Micera, Thomas Stieglitz, and Paolo Dario. 2005. A critical review of interfaces with the peripheral nervous system for the control of neuroprostheses and hybrid bionic systems. Journal of the Peripheral Nervous System 10, 3 (2005), 229--258.Google ScholarCross Ref
- DB Rao and Sun-Yuan Kung. 1984. Adaptive notch filtering for the retrieval of sinusoids in noise. IEEE Transactions on Acoustics, speech, and signal processing 32, 4 (1984), 791--802.Google ScholarCross Ref
- Stanisa Raspopovic, Jacopo Carpaneto, Esther Udina, Xavier Navarro, and Silvestro Micera. 2010. On the identification of sensory information from mixed nerves by using single-channel cuff electrodes. Journal of neuroengineering and rehabilitation 7, 1 (2010), 1--15.Google ScholarCross Ref
- Aleid CJ Ruijs, Jean-Bart Jaquet, Sandra Kalmijn, Henk Giele, and Steven ER Hovius. 2005. Median and ulnar nerve injuries: a meta-analysis of predictors of motor and sensory recovery after modern microsurgical nerve repair. Plastic and reconstructive surgery 116, 2 (2005), 484--494.Google Scholar
- Christopher Russell, Aidan D Roche, and Samit Chakrabarty. 2019. Peripheral nerve bionic interface: a review of electrodes. International Journal of Intelligent Robotics and Applications 3, 1 (2019), 11--18.Google ScholarCross Ref
- Wim LC Rutten. 2002. Selective electrical interfaces with the nervous system. Annual review of biomedical engineering 4, 1 (2002), 407--452.Google Scholar
- Martin Schuettler, Nick Donaldson, Vipin Seetohul, and John Taylor. 2013. Fibre-selective recording from the peripheral nerves of frogs using a multi-electrode cuff. Journal of neural engineering 10, 3 (2013), 036016.Google ScholarCross Ref
- Maria Siemionow and Grzegorz Brzezicki. 2009. Current techniques and concepts in peripheral nerve repair. International review of neurobiology 87 (2009), 141--172.Google ScholarCross Ref
- Yuang Tang, Brian Wodlinger, and DM Durand. 2014. Bayesian spatial filters for source signal extraction: A study in the peripheral nerve. IEEE Transactions on Neural Systems and Rehabilitation Engineering 22, 2 (2014), 302--311.Google ScholarCross Ref
- John Taylor, Benjamin Metcalfe, Chris Clarke, Daniel Chew, Thomas Nielsen, and Nick Donaldson. 2015. A summary of current and new methods in velocity selective recording (VSR) of electroneurogram (ENG). In 2015 IEEE Computer Society Annual Symposium on VLSI. IEEE, 221--226.Google ScholarCross Ref
- Yujie Wu, Lei Deng, Guoqi Li, Jun Zhu, Yuan Xie, and Luping Shi. 2019. Direct training for spiking neural networks: Faster, larger, better. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 1311--1318.Google ScholarDigital Library
- Jose Zariffa and Milos R Popovic. 2008. Application of EEG source localization algorithms to the monitoring of active pathways in peripheral nerves. In 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, 4216--4219.Google ScholarCross Ref
Index Terms
- Neural network-based classification of ENG recordings in response to naturally evoked stimulation
Recommendations
Spike history neural response model
There is a potential for improved efficacy of neural stimulation if stimulation levels can be modified dynamically based on the responses of neural tissue in real time. A neural model is developed that describes the response of neurons to electrical ...
A Deep-Learning-Based Method For Spike Sorting With Spiking Neural Network
ICBSP '22: Proceedings of the 2022 7th International Conference on Biomedical Imaging, Signal ProcessingSpike sorting is a technique of detecting and assigning signals generated by the neurons of the brain and classifying which spike belongs to which neurons. Spike sorting is usually done by a clustering algorithm that groups the spikes coming from the ...
Analysis of entrainment of respiratory rhythm by somatic afferent stimulation in cats using phase response curves
To elucidate how peripheral somatic afferents synchronize the respiratory rhythm to the exercise rhythm, the phrenic nerve activity in the vagotomized, paralyzed, and artificially ventilated cats anesthetized with chloralose-urethane was recorded during ...
Comments