An efficient, approximate path-following algorithm for elastic net based nonlinear spike enhancement

Max A. Little

An efficient, approximate path-following algorithm for elastic net based nonlinear spike enhancement

Max A. Little^*

^*Corresponding author for this work

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

Unwanted spike noise in a digital signal is a common problem in digital filtering. However, sometimes the spikes are wanted and other, superimposed, signals are unwanted, and linear, time invariant (LTI) filtering is ineffective because the spikes are wideband - overlapping with independent noise in the frequency domain. So, no LTI filter can separate them, necessitating nonlinear filtering. However, there are applications in which the noise includes drift or smooth signals for which LTI filters are ideal. We describe a nonlinear filter formulated as the solution to an elastic net regularization problem, which attenuates band-limited signals and independent noise, while enhancing superimposed spikes. Making use of known analytic solutions a novel, approximate path-following algorithm is given that provides a good, filtered output with reduced computational effort by comparison to standard convex optimization methods. Accurate performance is shown on real, noisy electrophysiological recordings of neural spikes.

Original language	English
Title of host publication	2014 Proceedings of the 22nd European Signal Processing Conference (EUSIPCO)
Publisher	IEEE
Pages	1442-1446
Number of pages	5
ISBN (Print)	978-0-9928626-1-9
Publication status	Published - 2014
Event	22nd European Signal Processing Conference - Lisbon, Portugal Duration: 1 Sept 2014 → 5 Sept 2014

Conference

Conference	22nd European Signal Processing Conference
Abbreviated title	EUSIPCO 2014
Country/Territory	Portugal
City	Lisbon
Period	1/09/14 → 5/09/14

Bibliographical note

© 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Funding: Wellcome Trust (Grant WT090651MF)

Keywords

filter
noise
nonlinear
regularization
spike

Access to Document

Path-following algorithm for elastic net based nonlinear spike enhancement
© 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 736 KB

http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6952508

Cite this

@inproceedings{0534d28f3eb64bd5827e5910a3453260,

title = "An efficient, approximate path-following algorithm for elastic net based nonlinear spike enhancement",

abstract = "Unwanted spike noise in a digital signal is a common problem in digital filtering. However, sometimes the spikes are wanted and other, superimposed, signals are unwanted, and linear, time invariant (LTI) filtering is ineffective because the spikes are wideband - overlapping with independent noise in the frequency domain. So, no LTI filter can separate them, necessitating nonlinear filtering. However, there are applications in which the noise includes drift or smooth signals for which LTI filters are ideal. We describe a nonlinear filter formulated as the solution to an elastic net regularization problem, which attenuates band-limited signals and independent noise, while enhancing superimposed spikes. Making use of known analytic solutions a novel, approximate path-following algorithm is given that provides a good, filtered output with reduced computational effort by comparison to standard convex optimization methods. Accurate performance is shown on real, noisy electrophysiological recordings of neural spikes.",

keywords = "filter, noise, nonlinear, regularization, spike",

author = "Little, {Max A.}",

note = "{\textcopyright} 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Funding: Wellcome Trust (Grant WT090651MF); 22nd European Signal Processing Conference, EUSIPCO 2014 ; Conference date: 01-09-2014 Through 05-09-2014",

year = "2014",

language = "English",

isbn = "978-0-9928626-1-9",

pages = "1442--1446",

booktitle = "2014 Proceedings of the 22nd European Signal Processing Conference (EUSIPCO)",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - An efficient, approximate path-following algorithm for elastic net based nonlinear spike enhancement

AU - Little, Max A.

N1 - © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Funding: Wellcome Trust (Grant WT090651MF)

PY - 2014

Y1 - 2014

N2 - Unwanted spike noise in a digital signal is a common problem in digital filtering. However, sometimes the spikes are wanted and other, superimposed, signals are unwanted, and linear, time invariant (LTI) filtering is ineffective because the spikes are wideband - overlapping with independent noise in the frequency domain. So, no LTI filter can separate them, necessitating nonlinear filtering. However, there are applications in which the noise includes drift or smooth signals for which LTI filters are ideal. We describe a nonlinear filter formulated as the solution to an elastic net regularization problem, which attenuates band-limited signals and independent noise, while enhancing superimposed spikes. Making use of known analytic solutions a novel, approximate path-following algorithm is given that provides a good, filtered output with reduced computational effort by comparison to standard convex optimization methods. Accurate performance is shown on real, noisy electrophysiological recordings of neural spikes.

AB - Unwanted spike noise in a digital signal is a common problem in digital filtering. However, sometimes the spikes are wanted and other, superimposed, signals are unwanted, and linear, time invariant (LTI) filtering is ineffective because the spikes are wideband - overlapping with independent noise in the frequency domain. So, no LTI filter can separate them, necessitating nonlinear filtering. However, there are applications in which the noise includes drift or smooth signals for which LTI filters are ideal. We describe a nonlinear filter formulated as the solution to an elastic net regularization problem, which attenuates band-limited signals and independent noise, while enhancing superimposed spikes. Making use of known analytic solutions a novel, approximate path-following algorithm is given that provides a good, filtered output with reduced computational effort by comparison to standard convex optimization methods. Accurate performance is shown on real, noisy electrophysiological recordings of neural spikes.

KW - filter

KW - noise

KW - nonlinear

KW - regularization

KW - spike

UR - http://www.scopus.com/inward/record.url?scp=84911881154&partnerID=8YFLogxK

M3 - Conference publication

AN - SCOPUS:84911881154

SN - 978-0-9928626-1-9

SP - 1442

EP - 1446

BT - 2014 Proceedings of the 22nd European Signal Processing Conference (EUSIPCO)

PB - IEEE

T2 - 22nd European Signal Processing Conference

Y2 - 1 September 2014 through 5 September 2014

ER -

An efficient, approximate path-following algorithm for elastic net based nonlinear spike enhancement

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this