Compression of spike data using the self-organizing map

António R C Paiva; José C. Príncipe; Justin C. Sanchez

doi:10.1109/CNE.2005.1419599

Compression of spike data using the self-organizing map

António R C Paiva, José C. Príncipe, Justin C. Sanchez

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Scopus citations

Abstract

Motivated by current attempts to use wireless in Brain-Machine Interfaces (BMIs), this paper presents a method for the compression of spike data. Supported by Vector Quantization (VQ) theory, we use a 1-dimensional Self-Organizing Map (SOM) to quantize vectors of input samples. The indices are entropy coded to further reduce the necessary bandwidth, taking advantage of the non-uniform frequency of firing of the SOM processing elements (PEs). The complexity of the use of the SOM is also considered and addressed. After training several SOMs, the method was simulated with real data achieving compression ratios as high as 185.7:1, i.e. a bitrate of 862 bits-per-second-per-channel, assuming sampling at 20 kHz with 8 bits-per-sample (bps).

Original language	English
Title of host publication	2nd International IEEE EMBS Conference on Neural Engineering
Pages	233-236
Number of pages	4
Volume	2005
DOIs	https://doi.org/10.1109/CNE.2005.1419599
State	Published - Dec 1 2005
Externally published	Yes
Event	2nd International IEEE EMBS Conference on Neural Engineering, 2005 - Arlington, VA, United States Duration: Mar 16 2005 → Mar 19 2005

Other

Other	2nd International IEEE EMBS Conference on Neural Engineering, 2005
Country	United States
City	Arlington, VA
Period	3/16/05 → 3/19/05

ASJC Scopus subject areas

Engineering(all)

Access to Document

10.1109/CNE.2005.1419599

Fingerprint Dive into the research topics of 'Compression of spike data using the self-organizing map'. Together they form a unique fingerprint.

Cite this

@inproceedings{3f12a7466b3540a98b5a70936ea6a659,

title = "Compression of spike data using the self-organizing map",

abstract = "Motivated by current attempts to use wireless in Brain-Machine Interfaces (BMIs), this paper presents a method for the compression of spike data. Supported by Vector Quantization (VQ) theory, we use a 1-dimensional Self-Organizing Map (SOM) to quantize vectors of input samples. The indices are entropy coded to further reduce the necessary bandwidth, taking advantage of the non-uniform frequency of firing of the SOM processing elements (PEs). The complexity of the use of the SOM is also considered and addressed. After training several SOMs, the method was simulated with real data achieving compression ratios as high as 185.7:1, i.e. a bitrate of 862 bits-per-second-per-channel, assuming sampling at 20 kHz with 8 bits-per-sample (bps).",

author = "Paiva, {Ant{\'o}nio R C} and Pr{\'i}ncipe, {Jos{\'e} C.} and Sanchez, {Justin C.}",

year = "2005",

month = dec,

day = "1",

doi = "10.1109/CNE.2005.1419599",

language = "English",

volume = "2005",

pages = "233--236",

booktitle = "2nd International IEEE EMBS Conference on Neural Engineering",

note = "null ; Conference date: 16-03-2005 Through 19-03-2005",

}

TY - GEN

T1 - Compression of spike data using the self-organizing map

AU - Paiva, António R C

AU - Príncipe, José C.

AU - Sanchez, Justin C.

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Motivated by current attempts to use wireless in Brain-Machine Interfaces (BMIs), this paper presents a method for the compression of spike data. Supported by Vector Quantization (VQ) theory, we use a 1-dimensional Self-Organizing Map (SOM) to quantize vectors of input samples. The indices are entropy coded to further reduce the necessary bandwidth, taking advantage of the non-uniform frequency of firing of the SOM processing elements (PEs). The complexity of the use of the SOM is also considered and addressed. After training several SOMs, the method was simulated with real data achieving compression ratios as high as 185.7:1, i.e. a bitrate of 862 bits-per-second-per-channel, assuming sampling at 20 kHz with 8 bits-per-sample (bps).

AB - Motivated by current attempts to use wireless in Brain-Machine Interfaces (BMIs), this paper presents a method for the compression of spike data. Supported by Vector Quantization (VQ) theory, we use a 1-dimensional Self-Organizing Map (SOM) to quantize vectors of input samples. The indices are entropy coded to further reduce the necessary bandwidth, taking advantage of the non-uniform frequency of firing of the SOM processing elements (PEs). The complexity of the use of the SOM is also considered and addressed. After training several SOMs, the method was simulated with real data achieving compression ratios as high as 185.7:1, i.e. a bitrate of 862 bits-per-second-per-channel, assuming sampling at 20 kHz with 8 bits-per-sample (bps).

UR - http://www.scopus.com/inward/record.url?scp=33744504181&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33744504181&partnerID=8YFLogxK

U2 - 10.1109/CNE.2005.1419599

DO - 10.1109/CNE.2005.1419599

M3 - Conference contribution

AN - SCOPUS:33744504181

VL - 2005

SP - 233

EP - 236

BT - 2nd International IEEE EMBS Conference on Neural Engineering

Y2 - 16 March 2005 through 19 March 2005

ER -