Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

Mixed-signal neuromorphic platform design for streaming biomedical signal processing

Mixed-signal neuromorphic platform design for streaming biomedical signal processing

For access to this article, please select a purchase option:

Buy chapter PDF
$16.00
(plus tax if applicable)
Buy Knowledge Pack
10 chapters for $120.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
Hardware Architectures for Deep Learning — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

This chapter presents the mixed -signal design approach for the design of neuromorphic platforms for the biomedical signal processing. The proposed approach combines algorithmic, architectural and circuit design concepts to offer a low -power neuromorphic platform for streaming biomedical signal processing. The platform employs liquid state machines using spiking neurons (implemented on analog neuron circuits) and support vector machine (SVM) (implemented as software running on advanced RISC machine (ARM) processor). A dynamic global synaptic communication network realized using the ultralow leakage IGZO thin film transistor (TFT) technology circuit switch is also presented. The proposed architectural technique offers a scalable low -power neuromorphic platform design approach suitable for processing real-time biomedical signals.

Chapter Contents:

  • 10.1 Introduction
  • 10.2 Related work
  • 10.2.1 Mixed-signal neuromorphic architectures - brief review
  • 10.2.2 Biomedical signal processing challenges for ECG application
  • 10.3 NeuRAM3 mixed-signal neuromorphic platform
  • 10.3.1 Analog neural components including local synapse array
  • 10.3.2 Global synapse communication network realized with TFT-based switches
  • 10.3.3 NeuRAM3 mixed-signal neuromorphic platform FPGA architecture
  • 10.4 ECG application mapping on non-scaled neuromorphic platform instance
  • 10.4.1 ECG classification and overall setup
  • 10.4.2 ECG signal compression and encoding in spikes
  • 10.4.3 Recurrent spiking neural network
  • 10.4.4 Recurrent neural network implemented in VLSI spiking neurons
  • 10.4.5 Training LIF classifiers
  • 10.4.6 VLSI implementation of the recurrent spiking neural network
  • 10.5 Results and discussion
  • 10.5.1 Classification accuracy
  • 10.5.2 Discussion on results for ECG application
  • 10.5.3 NeuRAM3 hardware platform results
  • 10.6 Summary and conclusions
  • Acknowledgments
  • References

Inspec keywords: neuromorphic engineering; medical signal processing; support vector machines; thin film transistors

Other keywords: low-power neuromorphic platform; analog neuron circuits; liquid state machines; dynamic global synaptic communication network; circuit design concepts; ultralow leakage IGZO thin film transistor technology; biomedical signal processing; mixed-signal neuromorphic platform design; spiking neurons; advanced RISC machine; support vector machine

Subjects: Neural nets (circuit implementations); Knowledge engineering techniques; Biomedical measurement and imaging; Other field effect devices; Signal processing and detection; Neural net devices; Digital signal processing; Biology and medical computing; Biomedical engineering

Preview this chapter:
Zoom in
Zoomout

Mixed-signal neuromorphic platform design for streaming biomedical signal processing, Page 1 of 2

| /docserver/preview/fulltext/books/cs/pbcs055e/PBCS055E_ch10-1.gif /docserver/preview/fulltext/books/cs/pbcs055e/PBCS055E_ch10-2.gif

Related content

content/books/10.1049/pbcs055e_ch10
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address