Pulse-based feature extraction for hardware-efficient neural recording systems

Current brain-machine interfaces have two machine learners-one for spike sorting and the second for intention decoding that acts on the sorted spatio-temporal spike train. In this paper, we propose a pulse-based feature extractor that can enable these two machine learners to be combined into one. We show from simulations and measurements that the information about the spike shape is still retained in the pulse counts-hence, the circuit can also be used as a traditional feature extractor. The proposed circuit also has the advantage of sharing several blocks with spike detector designs reducing system level cost. Fabricated in 65nm CMOS and operating from Vdd = 1V, the feature extractor dissipates roughly 2μW of power for an input spike rate of 100Hz.

[1]  Arindam Basu,et al.  A 128 channel 290 GMACs/W machine learning based co-processor for intention decoding in brain machine interfaces , 2015, 2015 IEEE International Symposium on Circuits and Systems (ISCAS).

[2]  Krishna V. Shenoy,et al.  Information Systems Opportunities in Brain–Machine Interface Decoders , 2014, Proceedings of the IEEE.

[3]  Giacomo Indiveri,et al.  Toward neuromorphic intelligent brain-machine interfaces: An event-based neural recording and processing system , 2014, 2014 IEEE Biomedical Circuits and Systems Conference (BioCAS) Proceedings.

[4]  M S Lewicki,et al.  A review of methods for spike sorting: the detection and classification of neural action potentials. , 1998, Network.

[5]  Vaibhav Karkare,et al.  A 130-$\mu$ W, 64-Channel Neural Spike-Sorting DSP Chip , 2011, IEEE Journal of Solid-State Circuits.

[6]  J. Letelier,et al.  Spike sorting based on discrete wavelet transform coefficients , 2000, Journal of Neuroscience Methods.

[7]  J. Mason Andrew,et al.  On-chip feature extraction for spike sorting in high density implantable neural recording systems , 2010, 2010 Biomedical Circuits and Systems Conference (BioCAS).

[8]  M. Abeles,et al.  Multispike train analysis , 1977, Proceedings of the IEEE.

[9]  Arindam Basu,et al.  A 0.7 V, 40 nW Compact, Current-Mode Neural Spike Detector in 65 nm CMOS , 2016, IEEE Transactions on Biomedical Circuits and Systems.

[10]  Timothy G. Constandinou,et al.  A 1.5 μW NEO-based spike detector with adaptive-threshold for calibration-free multichannel neural interfaces , 2013, 2013 IEEE International Symposium on Circuits and Systems (ISCAS2013).

[11]  Timothy G. Constandinou,et al.  Feature extraction using first and second derivative extrema (FSDE) for real-time and hardware-efficient spike sorting , 2013, Journal of Neuroscience Methods.

[12]  R. Quian Quiroga,et al.  Unsupervised Spike Detection and Sorting with Wavelets and Superparamagnetic Clustering , 2004, Neural Computation.

[13]  Dejan Markovic,et al.  Comparison of spike-sorting algorithms for future hardware implementation , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.