Signals to Spikes for Neuromorphic Regulated Reservoir Computing and EMG Hand Gesture Recognition

Surface electromyogram (sEMG) signals result from muscle movement and hence they are an ideal candidate for benchmarking event-driven sensing and computing. We propose a simple yet novel approach for optimizing the spike encoding algorithm’s hyper-parameters inspired by the readout layer concept in reservoir computing. Using a simple machine learning algorithm after spike encoding, we report performance higher than the state-of-the-art spiking neural networks on two open-source datasets for hand gesture recognition. The spike encoded data is processed through a spiking reservoir with a biologically inspired topology and neuron model. When trained with the unsupervised activity regulation CRITICAL algorithm to operate at the edge of chaos, the reservoir yields better performance than state-of-the-art convolutional neural networks. The reservoir performance with regulated activity was found to be 89.72% for the Roshambo EMG dataset and 70.6% for the EMG subset of sensor fusion dataset. Therefore, the biologically-inspired computing paradigm, which is known for being power efficient, also proves to have a great potential when compared with conventional AI algorithms.

[1]  Parami Wijesinghe,et al.  Analysis of Liquid Ensembles for Enhancing the Performance and Accuracy of Liquid State Machines , 2019, Front. Neurosci..

[2]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[3]  Thomas L. Carroll.  Mutual Information and the Edge of Chaos in Reservoir Computers , 2019, ArXiv.

[4]  K. Salama,et al.  Neural Coding in Spiking Neural Networks: A Comparative Study for Robust Neuromorphic Systems , 2021, Frontiers in Neuroscience.

[5]  Carver Mead,et al.  How we created neuromorphic engineering , 2020, Nature Electronics.

[6]  Romain Brette,et al.  Brian 2: an intuitive and efficient neural simulator , 2019, bioRxiv.

[7]  Neil Davey,et al.  High capacity, small world associative memory models , 2006, Connect. Sci..

[8]  Nikola Kasabov,et al.  Feasibility of NeuCube spiking neural network architecture for EMG pattern recognition , 2015, 2015 International Conference on Advanced Mechatronic Systems (ICAMechS).

[9]  Active Upper-Limb Prostheses: The International Perspective , 2017 .

[10]  Elisa Donati,et al.  Hand-Gesture Recognition Based on EMG and Event-Based Camera Sensor Fusion: A Benchmark in Neuromorphic Computing , 2020, Frontiers in Neuroscience.

[11]  Robert A. Legenstein,et al.  2007 Special Issue: Edge of chaos and prediction of computational performance for neural circuit models , 2007 .

[12]  Giacomo Indiveri,et al.  Discrimination of EMG Signals Using a Neuromorphic Implementation of a Spiking Neural Network , 2019, IEEE Transactions on Biomedical Circuits and Systems.

[13]  Kim Joris Boström,et al.  Model for a flexible motor memory based on a self-active recurrent neural network. , 2013, Human movement science.

[14]  Jean Rouat,et al.  P-CRITICAL: a reservoir autoregulation plasticity rule for neuromorphic hardware , 2020, Neuromorph. Comput. Eng..

[15]  Nikola Kasabov,et al.  Selection and Optimization of Temporal Spike Encoding Methods for Spiking Neural Networks , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[16]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[17]  Giacomo Indiveri,et al.  EMG-Based Gestures Classification Using a Mixed-Signal Neuromorphic Processing System , 2020, IEEE Journal on Emerging and Selected Topics in Circuits and Systems.

[18]  John M Beggs,et al.  Critical branching captures activity in living neural networks and maximizes the number of metastable States. , 2005, Physical review letters.

[19]  Jacob K. Rosenstein,et al.  A microwatt front end and asynchronous ADC for sparse biopotential acquisition , 2017, 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS).

[20]  Simon Brodeur,et al.  Classification of auditory stimuli from EEG signals with a regulated recurrent neural network reservoir , 2018, ArXiv.

[21]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .

[22]  Yongqiang Ma,et al.  Neuromorphic Implementation of a Recurrent Neural Network for EMG Classification , 2020, 2020 2nd IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS).

[23]  Erik Scheme,et al.  EMG Pattern Recognition in the Era of Big Data and Deep Learning , 2018, Big Data Cogn. Comput..

[24]  Erik Scheme,et al.  Electromyogram pattern recognition for control of powered upper-limb prostheses: state of the art and challenges for clinical use. , 2011, Journal of rehabilitation research and development.

[25]  Pornchai Phukpattaranont,et al.  A Review of Control Methods for Electric Power Wheelchairs Based on Electromyography Signals with Special Emphasis on Pattern Recognition , 2011 .

[26]  Giacomo Indiveri,et al.  A Neuromorphic Event-Based Neural Recording System for Smart Brain-Machine-Interfaces , 2015, IEEE Transactions on Biomedical Circuits and Systems.

[27]  J. Rouat,et al.  Regulation toward Self-organized Criticality in a Recurrent Spiking Neural Reservoir , 2012, ICANN.

[28]  Bo Wen,et al.  A Silicon Cochlea With Active Coupling , 2009, IEEE Transactions on Biomedical Circuits and Systems.

[29]  Yuan Li,et al.  Asynchronous biphasic pulse signal coding and its CMOS realization , 2006, 2006 IEEE International Symposium on Circuits and Systems.

[30]  S Christopher,et al.  A Comprehensive Study on EMG Feature Extraction and Classifiers , 2018 .

[31]  Tobi Delbruck,et al.  Feature Representations for Neuromorphic Audio Spike Streams , 2018, Front. Neurosci..

[32]  Loredana Zollo,et al.  Literature Review on Needs of Upper Limb Prosthesis Users , 2016, Front. Neurosci..

[33]  L. F Abbott,et al.  Lapicque’s introduction of the integrate-and-fire model neuron (1907) , 1999, Brain Research Bulletin.

[34]  T. Delbruck,et al.  A 128 128 120 dB 15 s Latency Asynchronous Temporal Contrast Vision Sensor , 2006 .