Robust PCA for micro-doppler classification using SVM on embedded systems

Research output: Contribution to journalArticle

49 Citations (Scopus)

Abstract

In this paper a novel feature extraction technique for micro-Doppler classification and its real time implementation using SVM on an embedded low-cost DSP are presented. The effectiveness of the proposed technique is improved through the exploitation of the outlier rejection capabilities of the Robust PCA in place of the classic PCA.
LanguageEnglish
Pages2304-2310
Number of pages8
JournalIEEE Transactions on Aerospace and Electronic Systems
Volume50
Issue number3
Early online date21 Sep 2013
DOIs
Publication statusPublished - 31 Jul 2014

Fingerprint

Embedded systems
Feature extraction
Costs

Keywords

  • micro-Doppler classifications
  • real-time implementation
  • support vector machine classifier

Cite this

@article{c0ae21274bfe4a3d8f22274092e73a64,
title = "Robust PCA for micro-doppler classification using SVM on embedded systems",
abstract = "In this paper a novel feature extraction technique for micro-Doppler classification and its real time implementation using SVM on an embedded low-cost DSP are presented. The effectiveness of the proposed technique is improved through the exploitation of the outlier rejection capabilities of the Robust PCA in place of the classic PCA.",
keywords = "micro-Doppler classifications, real-time implementation, support vector machine classifier",
author = "Jaime Zabalza and Carmine Clemente and {Di Caterina}, Gaetano and Jinchang Ren and Soraghan, {John J.} and Stephen Marshall",
note = "(c) 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, 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 components of this work in other works.",
year = "2014",
month = "7",
day = "31",
doi = "10.1109/TAES.2014.130082",
language = "English",
volume = "50",
pages = "2304--2310",
journal = "IEEE Transactions on Aerospace and Electronic Systems",
issn = "0018-9251",
number = "3",

}

TY - JOUR

T1 - Robust PCA for micro-doppler classification using SVM on embedded systems

AU - Zabalza, Jaime

AU - Clemente, Carmine

AU - Di Caterina, Gaetano

AU - Ren, Jinchang

AU - Soraghan, John J.

AU - Marshall, Stephen

N1 - (c) 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, 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 components of this work in other works.

PY - 2014/7/31

Y1 - 2014/7/31

N2 - In this paper a novel feature extraction technique for micro-Doppler classification and its real time implementation using SVM on an embedded low-cost DSP are presented. The effectiveness of the proposed technique is improved through the exploitation of the outlier rejection capabilities of the Robust PCA in place of the classic PCA.

AB - In this paper a novel feature extraction technique for micro-Doppler classification and its real time implementation using SVM on an embedded low-cost DSP are presented. The effectiveness of the proposed technique is improved through the exploitation of the outlier rejection capabilities of the Robust PCA in place of the classic PCA.

KW - micro-Doppler classifications

KW - real-time implementation

KW - support vector machine classifier

UR - http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=7

U2 - 10.1109/TAES.2014.130082

DO - 10.1109/TAES.2014.130082

M3 - Article

VL - 50

SP - 2304

EP - 2310

JO - IEEE Transactions on Aerospace and Electronic Systems

T2 - IEEE Transactions on Aerospace and Electronic Systems

JF - IEEE Transactions on Aerospace and Electronic Systems

SN - 0018-9251

IS - 3

ER -