Hardware support vector machine (SVM) for satellite on-board applications

Abdul Halim M. Jallad; Lubna B. Mohammed

doi:10.1109/AHS.2014.6880185

Hardware support vector machine (SVM) for satellite on-board applications

Abdul Halim M. Jallad, Lubna B. Mohammed

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

14 Citations (Scopus)

Abstract

Since their introduction in 1995, Support Vector Machines (SVM) have shown that classification by this relatively recent machine learning tool can be more accurate than popular contemporary techniques such as neural networks and decision trees, hence causing it to find its way quickly to various applications in engineering, economy and statistics. Despite their possible advantages, SVM use in space applications is still very limited for several reasons including low technology maturity and high computational demand. This paper proposes overcoming the computational demand hurdle through a hardware friendly implementation of SVM for satellite onboard applications using FPGAs. The evaluation of the proposed system shows excellent classification accuracy, low device utilization and acceptable speed for satellite onboard applications. The results shown in this paper opens the door for further exploration of various possible onboard applications including on-board image analysis, compression and autonomy.

Original language	English
Title of host publication	Proceedings of the 2014 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2014
Publisher	IEEE Computer Society
Pages	256-261
Number of pages	6
ISBN (Print)	9781479953561
DOIs	https://doi.org/10.1109/AHS.2014.6880185
Publication status	Published - 2014
Externally published	Yes
Event	2014 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2014 - Leicester, United Kingdom Duration: Jul 14 2014 → Jul 18 2014

Publication series

Name	Proceedings of the 2014 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2014

Conference

Conference	2014 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2014
Country/Territory	United Kingdom
City	Leicester
Period	7/14/14 → 7/18/14

Keywords

Embedded Systems
FPGAs
Satellites
Support Vector Machines

ASJC Scopus subject areas

Hardware and Architecture
Control and Systems Engineering

Access to Document

10.1109/AHS.2014.6880185

Cite this

Jallad, A. H. M., & Mohammed, L. B. (2014). Hardware support vector machine (SVM) for satellite on-board applications. In Proceedings of the 2014 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2014 (pp. 256-261). Article 6880185 (Proceedings of the 2014 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2014). IEEE Computer Society. https://doi.org/10.1109/AHS.2014.6880185

Hardware support vector machine (SVM) for satellite on-board applications. / Jallad, Abdul Halim M.; Mohammed, Lubna B.
Proceedings of the 2014 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2014. IEEE Computer Society, 2014. p. 256-261 6880185 (Proceedings of the 2014 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2014).

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

Jallad, AHM & Mohammed, LB 2014, Hardware support vector machine (SVM) for satellite on-board applications. in Proceedings of the 2014 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2014., 6880185, Proceedings of the 2014 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2014, IEEE Computer Society, pp. 256-261, 2014 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2014, Leicester, United Kingdom, 7/14/14. https://doi.org/10.1109/AHS.2014.6880185

@inproceedings{c23d6e13181241f79872ffff9beb0634,

title = "Hardware support vector machine (SVM) for satellite on-board applications",

abstract = "Since their introduction in 1995, Support Vector Machines (SVM) have shown that classification by this relatively recent machine learning tool can be more accurate than popular contemporary techniques such as neural networks and decision trees, hence causing it to find its way quickly to various applications in engineering, economy and statistics. Despite their possible advantages, SVM use in space applications is still very limited for several reasons including low technology maturity and high computational demand. This paper proposes overcoming the computational demand hurdle through a hardware friendly implementation of SVM for satellite onboard applications using FPGAs. The evaluation of the proposed system shows excellent classification accuracy, low device utilization and acceptable speed for satellite onboard applications. The results shown in this paper opens the door for further exploration of various possible onboard applications including on-board image analysis, compression and autonomy.",

keywords = "Embedded Systems, FPGAs, Satellites, Support Vector Machines",

author = "Jallad, {Abdul Halim M.} and Mohammed, {Lubna B.}",

year = "2014",

doi = "10.1109/AHS.2014.6880185",

language = "English",

isbn = "9781479953561",

series = "Proceedings of the 2014 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2014",

publisher = "IEEE Computer Society",

pages = "256--261",

booktitle = "Proceedings of the 2014 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2014",

note = "2014 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2014 ; Conference date: 14-07-2014 Through 18-07-2014",

}

TY - GEN

T1 - Hardware support vector machine (SVM) for satellite on-board applications

AU - Jallad, Abdul Halim M.

AU - Mohammed, Lubna B.

PY - 2014

Y1 - 2014

N2 - Since their introduction in 1995, Support Vector Machines (SVM) have shown that classification by this relatively recent machine learning tool can be more accurate than popular contemporary techniques such as neural networks and decision trees, hence causing it to find its way quickly to various applications in engineering, economy and statistics. Despite their possible advantages, SVM use in space applications is still very limited for several reasons including low technology maturity and high computational demand. This paper proposes overcoming the computational demand hurdle through a hardware friendly implementation of SVM for satellite onboard applications using FPGAs. The evaluation of the proposed system shows excellent classification accuracy, low device utilization and acceptable speed for satellite onboard applications. The results shown in this paper opens the door for further exploration of various possible onboard applications including on-board image analysis, compression and autonomy.

AB - Since their introduction in 1995, Support Vector Machines (SVM) have shown that classification by this relatively recent machine learning tool can be more accurate than popular contemporary techniques such as neural networks and decision trees, hence causing it to find its way quickly to various applications in engineering, economy and statistics. Despite their possible advantages, SVM use in space applications is still very limited for several reasons including low technology maturity and high computational demand. This paper proposes overcoming the computational demand hurdle through a hardware friendly implementation of SVM for satellite onboard applications using FPGAs. The evaluation of the proposed system shows excellent classification accuracy, low device utilization and acceptable speed for satellite onboard applications. The results shown in this paper opens the door for further exploration of various possible onboard applications including on-board image analysis, compression and autonomy.

KW - Embedded Systems

KW - FPGAs

KW - Satellites

KW - Support Vector Machines

UR - http://www.scopus.com/inward/record.url?scp=84906674168&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906674168&partnerID=8YFLogxK

U2 - 10.1109/AHS.2014.6880185

DO - 10.1109/AHS.2014.6880185

M3 - Conference contribution

AN - SCOPUS:84906674168

SN - 9781479953561

T3 - Proceedings of the 2014 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2014

SP - 256

EP - 261

BT - Proceedings of the 2014 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2014

PB - IEEE Computer Society

T2 - 2014 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2014

Y2 - 14 July 2014 through 18 July 2014

ER -

Hardware support vector machine (SVM) for satellite on-board applications

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this