A 41 μW real-time adaptive neural spike classifier

A 41 μW real-time adaptive neural spike classifier

Zjajo, Amir (TU Delft Signal Processing Systems)
van Leuken, T.G.R.M. (TU Delft Signal Processing Systems)

2016-04-21

Robust, power- and area-efficient spike classifier, capable of accurate identification of the neural spikes even for low SNR, is a prerequisite for the real-time, implantable, closed-loop brain-machine interface. In this paper, we propose an easily-scalable, 128-channel, programmable, neural spike classifier based on nonlinear energy operator spike detection, and a boosted cascade, multiclass kernel support vector machine classification. The power-efficient classification is obtained with a combination of the algorithm and circuit techniques. The classifier implemented in a 65 nm CMOS technology consumes less than 41 μW of power, and occupy an area of 2.64 mm2.

Kernel
Feature extraction
Registers
Support vector machine classification
Sorting
Training

http://resolver.tudelft.nl/uuid:3a6b78eb-1acd-42e7-94bf-ef076b20c910

https://doi.org/10.1109/bhi.2016.7455941

IEEE, Piscataway, NJ

978-1-5090-2455-1

2016 IEEE-EMBS International Conference on Biomedical and Health Informatics, BHI 2016

2016 IEEE-EMBS International Conference on Biomedical and Health Informatics, BHI 2016, 2016-02-24 → 2016-02-27, Las Vegas, United States

Institutional Repository

conference paper

© 2016 Amir Zjajo, T.G.R.M. van Leuken