Self-Organizing Map (SOM) of Space Acceleration Measurement System (SAMS) data

Alok Sinha, A. D. Smith

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, space acceleration measurement system (SAMS) data have been classified using self-organizing map (SOM) networks without any supervision; i.e., no a priori knowledge is assumed regarding input patterns belonging to a certain class. Input patterns are created an the basis of power spectral densities of SAMS data. Results for SAMS data from STS-50 and STS-57 missions are presented. Following issues are discussed in details: impact of number of neurons, global ordering of SOM weight vectors, effectiveness of a SOM in data classification, and effects of shifting time windows in the generation of input patterns. The concept of 'cascade of SOM networks' is also developed and tested. It has been found that a SOM network can successfully classify SAMS data obtained during STS-50 and STS-57 missions.

Original languageEnglish (US)
Pages (from-to)78-87
Number of pages10
JournalMicrogravity Science and Technology
Volume12
Issue number2
StatePublished - Jan 1 1999

Fingerprint

acceleration measurement
Acceleration measurement
data systems
organizing
Self organizing maps
Self-organizing Map
Measurement System
space transportation system
Data Classification
Power Spectral Density
Power spectral density
Time Windows
neurons
Neurons
Cascade
Neuron
cascades
Classify

All Science Journal Classification (ASJC) codes

  • Modeling and Simulation
  • Engineering(all)
  • Physics and Astronomy(all)
  • Applied Mathematics

Cite this

@article{7c39e70a2fcc4a9a861250eeffdc82c3,
title = "Self-Organizing Map (SOM) of Space Acceleration Measurement System (SAMS) data",
abstract = "In this paper, space acceleration measurement system (SAMS) data have been classified using self-organizing map (SOM) networks without any supervision; i.e., no a priori knowledge is assumed regarding input patterns belonging to a certain class. Input patterns are created an the basis of power spectral densities of SAMS data. Results for SAMS data from STS-50 and STS-57 missions are presented. Following issues are discussed in details: impact of number of neurons, global ordering of SOM weight vectors, effectiveness of a SOM in data classification, and effects of shifting time windows in the generation of input patterns. The concept of 'cascade of SOM networks' is also developed and tested. It has been found that a SOM network can successfully classify SAMS data obtained during STS-50 and STS-57 missions.",
author = "Alok Sinha and Smith, {A. D.}",
year = "1999",
month = "1",
day = "1",
language = "English (US)",
volume = "12",
pages = "78--87",
journal = "Microgravity Science and Technology",
issn = "0938-0108",
publisher = "Springer Netherlands",
number = "2",

}

Self-Organizing Map (SOM) of Space Acceleration Measurement System (SAMS) data. / Sinha, Alok; Smith, A. D.

In: Microgravity Science and Technology, Vol. 12, No. 2, 01.01.1999, p. 78-87.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Self-Organizing Map (SOM) of Space Acceleration Measurement System (SAMS) data

AU - Sinha, Alok

AU - Smith, A. D.

PY - 1999/1/1

Y1 - 1999/1/1

N2 - In this paper, space acceleration measurement system (SAMS) data have been classified using self-organizing map (SOM) networks without any supervision; i.e., no a priori knowledge is assumed regarding input patterns belonging to a certain class. Input patterns are created an the basis of power spectral densities of SAMS data. Results for SAMS data from STS-50 and STS-57 missions are presented. Following issues are discussed in details: impact of number of neurons, global ordering of SOM weight vectors, effectiveness of a SOM in data classification, and effects of shifting time windows in the generation of input patterns. The concept of 'cascade of SOM networks' is also developed and tested. It has been found that a SOM network can successfully classify SAMS data obtained during STS-50 and STS-57 missions.

AB - In this paper, space acceleration measurement system (SAMS) data have been classified using self-organizing map (SOM) networks without any supervision; i.e., no a priori knowledge is assumed regarding input patterns belonging to a certain class. Input patterns are created an the basis of power spectral densities of SAMS data. Results for SAMS data from STS-50 and STS-57 missions are presented. Following issues are discussed in details: impact of number of neurons, global ordering of SOM weight vectors, effectiveness of a SOM in data classification, and effects of shifting time windows in the generation of input patterns. The concept of 'cascade of SOM networks' is also developed and tested. It has been found that a SOM network can successfully classify SAMS data obtained during STS-50 and STS-57 missions.

UR - http://www.scopus.com/inward/record.url?scp=0032586337&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032586337&partnerID=8YFLogxK

M3 - Article

C2 - 11543426

AN - SCOPUS:0032586337

VL - 12

SP - 78

EP - 87

JO - Microgravity Science and Technology

JF - Microgravity Science and Technology

SN - 0938-0108

IS - 2

ER -