Pulse-Width Modulation based Algorithm for Spike Phase Encoding and Decoding of Time Dependent Analog Data

Ander Arriandiaga , Eva Portillo, Josafath Espinosa-Ramos , Nikola Kasabov

Research output: Contribution to journalArticle

Abstract

This article proposes a new spike encoding and decoding algorithm for analogue data. The algorithm uses the pulse-width modulation principles to achieve a high reconstruction accuracy of the signal, along with a high level of data compression. Two benchmark data sets are used to illustrate the method: stock index time series and human voice data. Applications of the method for spiking neural network (SNN) modelling and neuromorphic implementations are discussed. The proposed method would allow the development of new applications of SNNs as regression techniques for predictive time-series modelling.
Original languageEnglish
Pages (from-to)1-12
Number of pages12
JournalIEEE Transactions on Neural Networks and Learning Systems
Early online date14 Nov 2019
DOIs
Publication statusE-pub ahead of print - 14 Nov 2019

Keywords

  • Analog data
  • Data compression
  • Spike encoding
  • spike series decoding
  • spiking neural netwoks
  • streaming data

Fingerprint Dive into the research topics of 'Pulse-Width Modulation based Algorithm for Spike Phase Encoding and Decoding of Time Dependent Analog Data'. Together they form a unique fingerprint.

  • Cite this