schliessen

Filtern

 

Bibliotheken

A novel feature ranking algorithm for biometric recognition with PPG signals

Abstract This study is intended for describing the application of the Photoplethysmography (PPG) signal and the time domain features acquired from its first and second derivatives for biometric identification. For this purpose, a sum of 40 features has been extracted and a feature-ranking algorithm... Full description

Journal Title: Computers in biology and medicine 2014, Vol.49, p.1-14
Main Author: Reşit Kavsaoğlu, A
Other Authors: Polat, Kemal , Recep Bozkurt, M
Format: Electronic Article Electronic Article
Language: English
Subjects:
Age
Quelle: Alma/SFX Local Collection
Publisher: United States: Elsevier Ltd
ID: ISSN: 0010-4825
Link: https://www.ncbi.nlm.nih.gov/pubmed/24705467
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: cdi_proquest_miscellaneous_1529955733
title: A novel feature ranking algorithm for biometric recognition with PPG signals
format: Article
creator:
  • Reşit Kavsaoğlu, A
  • Polat, Kemal
  • Recep Bozkurt, M
subjects:
  • Adolescent
  • Adult
  • Age
  • Algorithms
  • Biometric identification
  • Biometric Identification - instrumentation
  • Biometric Identification - methods
  • Biometrics
  • Biometry
  • Cardiovascular disease
  • Classification
  • Derivatives
  • Electrocardiography
  • Feature Extraction
  • Female
  • Fingers - physiology
  • Heart
  • Humans
  • Identification
  • Internal Medicine
  • Light
  • Male
  • Methods
  • Middle Aged
  • Other
  • Photoplethysmography (PPG)
  • Photoplethysmography - instrumentation
  • Photoplethysmography - methods
  • Ratings & rankings
  • Signal Processing, Computer-Assisted - instrumentation
  • Skin
  • Studies
  • Veins & arteries
  • Wavelet transforms
  • Young Adult
ispartof: Computers in biology and medicine, 2014, Vol.49, p.1-14
description: Abstract This study is intended for describing the application of the Photoplethysmography (PPG) signal and the time domain features acquired from its first and second derivatives for biometric identification. For this purpose, a sum of 40 features has been extracted and a feature-ranking algorithm is proposed. This proposed algorithm calculates the contribution of each feature to biometric recognition and collocates the features, the contribution of which is from great to small. While identifying the contribution of the features, the Euclidean distance and absolute distance formulas are used. The efficiency of the proposed algorithms is demonstrated by the results of the k-NN (k-nearest neighbor) classifier applications of the features. During application, each 15-period-PPG signal belonging to two different durations from each of the thirty healthy subjects were used with a PPG data acquisition card. The first PPG signals recorded from the subjects were evaluated as the 1st configuration; the PPG signals recorded later at a different time as the 2nd configuration and the combination of both were evaluated as the 3rd configuration. When the results were evaluated for the k-NN classifier model created along with the proposed algorithm, an identification of 90.44% for the 1st configuration, 94.44% for the 2nd configuration, and 87.22% for the 3rd configuration has successfully been attained. The obtained results showed that both the proposed algorithm and the biometric identification model based on this developed PPG signal are very promising for contactless recognizing the people with the proposed method.
language: eng
source: Alma/SFX Local Collection
identifier: ISSN: 0010-4825
fulltext: fulltext
issn:
  • 0010-4825
  • 1879-0534
url: Link


@attributes
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
RANK2.6104488
LOCALfalse
PrimoNMBib
record
control
sourceidgale_opena
recordidTN_cdi_proquest_miscellaneous_1529955733
sourceformatXML
sourcesystemPC
galeidA368093264
sourcerecordidA368093264
originalsourceidFETCH-LOGICAL-c586t-62d2781d878ff3d857337e563630670f1acc11eab98e0748ce7a36c2dc3188053
addsrcrecordideNqNUsFu1DAQjRCILoVfQJG4cNkwjh3buVRaKiiVVqIScLYce7x4m9iLky3q3-N0WyrtaeXDSJ43b2bevKIoCVQECP-0rUwcdp2PA9qqBsIqoBVA86JYECnaJTSUvSwWAASWTNbNWfFmHLcAwIDC6-KsZgIaxsWiWK_KEO-wLx3qaZ-wTDrc-rApdb-JyU-_h9LFVD60mpI3ZUITN8FPPobyb86XNzdX5eg3Qffj2-KVywHfPcbz4tfXLz8vvy3X36-uL1frpWkkn5a8trWQxEohnaNWNoJSgQ2nnAIX4Ig2hhDUXSsRBJMGhabc1NZQImXe7by4PvDGHQbtE6pd8oNO9ypqr2zASUWr2iyCspaioE3LbCdr0zXYGZDAO-KcNm3rMtfHA9cuxT97HCc1-NFg3-uAcT8q0tRt28wjngJlRDBGRYZ-OIJu4z7NGs2ous3LkhlVHVAb3aPywcUpaZOfxcGbGND5_L-iXEJLa85ygTwUmBTHMaH7vzgBNTtDbdWzM9TsDAVUwYNm7x8n2ndz7qnwyQoZcHHEbfyk5zvnoXx_SofPBwLMp7_zmNRoPAaDNl_ITMpGfwrJxRGJ6X3wRve3eI_js4pqrBWoH7PFZ4cTlt3NpaD_AAHA9dg
sourcetypeOpen Access Repository
isCDItrue
recordtypearticle
pqid1522956317
display
typearticle
titleA novel feature ranking algorithm for biometric recognition with PPG signals
sourceAlma/SFX Local Collection
creatorReşit Kavsaoğlu, A ; Polat, Kemal ; Recep Bozkurt, M
creatorcontribReşit Kavsaoğlu, A ; Polat, Kemal ; Recep Bozkurt, M
descriptionAbstract This study is intended for describing the application of the Photoplethysmography (PPG) signal and the time domain features acquired from its first and second derivatives for biometric identification. For this purpose, a sum of 40 features has been extracted and a feature-ranking algorithm is proposed. This proposed algorithm calculates the contribution of each feature to biometric recognition and collocates the features, the contribution of which is from great to small. While identifying the contribution of the features, the Euclidean distance and absolute distance formulas are used. The efficiency of the proposed algorithms is demonstrated by the results of the k-NN (k-nearest neighbor) classifier applications of the features. During application, each 15-period-PPG signal belonging to two different durations from each of the thirty healthy subjects were used with a PPG data acquisition card. The first PPG signals recorded from the subjects were evaluated as the 1st configuration; the PPG signals recorded later at a different time as the 2nd configuration and the combination of both were evaluated as the 3rd configuration. When the results were evaluated for the k-NN classifier model created along with the proposed algorithm, an identification of 90.44% for the 1st configuration, 94.44% for the 2nd configuration, and 87.22% for the 3rd configuration has successfully been attained. The obtained results showed that both the proposed algorithm and the biometric identification model based on this developed PPG signal are very promising for contactless recognizing the people with the proposed method.
identifier
0ISSN: 0010-4825
1EISSN: 1879-0534
2DOI: 10.1016/j.compbiomed.2014.03.005
3PMID: 24705467
4CODEN: CBMDAW
languageeng
publisherUnited States: Elsevier Ltd
subjectAdolescent ; Adult ; Age ; Algorithms ; Biometric identification ; Biometric Identification - instrumentation ; Biometric Identification - methods ; Biometrics ; Biometry ; Cardiovascular disease ; Classification ; Derivatives ; Electrocardiography ; Feature Extraction ; Female ; Fingers - physiology ; Heart ; Humans ; Identification ; Internal Medicine ; Light ; Male ; Methods ; Middle Aged ; Other ; Photoplethysmography (PPG) ; Photoplethysmography - instrumentation ; Photoplethysmography - methods ; Ratings & rankings ; Signal Processing, Computer-Assisted - instrumentation ; Skin ; Studies ; Veins & arteries ; Wavelet transforms ; Young Adult
ispartofComputers in biology and medicine, 2014, Vol.49, p.1-14
rights
0Elsevier Ltd
12014 Elsevier Ltd
2Copyright © 2014 Elsevier Ltd. All rights reserved.
3COPYRIGHT 2014 Elsevier B.V.
4Copyright Elsevier Limited Jun 2014
lds50peer_reviewed
oafree_for_read
citedbyFETCH-LOGICAL-c586t-62d2781d878ff3d857337e563630670f1acc11eab98e0748ce7a36c2dc3188053
links
openurl$$Topenurl_article
openurlfulltext$$Topenurlfull_article
thumbnail$$Usyndetics_thumb_exl
backlink$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/24705467$$D View this record in MEDLINE/PubMed
search
creatorcontrib
0Reşit Kavsaoğlu, A
1Polat, Kemal
2Recep Bozkurt, M
title
0A novel feature ranking algorithm for biometric recognition with PPG signals
1Computers in biology and medicine
addtitleComput Biol Med
descriptionAbstract This study is intended for describing the application of the Photoplethysmography (PPG) signal and the time domain features acquired from its first and second derivatives for biometric identification. For this purpose, a sum of 40 features has been extracted and a feature-ranking algorithm is proposed. This proposed algorithm calculates the contribution of each feature to biometric recognition and collocates the features, the contribution of which is from great to small. While identifying the contribution of the features, the Euclidean distance and absolute distance formulas are used. The efficiency of the proposed algorithms is demonstrated by the results of the k-NN (k-nearest neighbor) classifier applications of the features. During application, each 15-period-PPG signal belonging to two different durations from each of the thirty healthy subjects were used with a PPG data acquisition card. The first PPG signals recorded from the subjects were evaluated as the 1st configuration; the PPG signals recorded later at a different time as the 2nd configuration and the combination of both were evaluated as the 3rd configuration. When the results were evaluated for the k-NN classifier model created along with the proposed algorithm, an identification of 90.44% for the 1st configuration, 94.44% for the 2nd configuration, and 87.22% for the 3rd configuration has successfully been attained. The obtained results showed that both the proposed algorithm and the biometric identification model based on this developed PPG signal are very promising for contactless recognizing the people with the proposed method.
subject
0Adolescent
1Adult
2Age
3Algorithms
4Biometric identification
5Biometric Identification - instrumentation
6Biometric Identification - methods
7Biometrics
8Biometry
9Cardiovascular disease
10Classification
11Derivatives
12Electrocardiography
13Feature Extraction
14Female
15Fingers - physiology
16Heart
17Humans
18Identification
19Internal Medicine
20Light
21Male
22Methods
23Middle Aged
24Other
25Photoplethysmography (PPG)
26Photoplethysmography - instrumentation
27Photoplethysmography - methods
28Ratings & rankings
29Signal Processing, Computer-Assisted - instrumentation
30Skin
31Studies
32Veins & arteries
33Wavelet transforms
34Young Adult
issn
00010-4825
11879-0534
fulltexttrue
rsrctypearticle
creationdate2014
recordtypearticle
recordideNqNUsFu1DAQjRCILoVfQJG4cNkwjh3buVRaKiiVVqIScLYce7x4m9iLky3q3-N0WyrtaeXDSJ43b2bevKIoCVQECP-0rUwcdp2PA9qqBsIqoBVA86JYECnaJTSUvSwWAASWTNbNWfFmHLcAwIDC6-KsZgIaxsWiWK_KEO-wLx3qaZ-wTDrc-rApdb-JyU-_h9LFVD60mpI3ZUITN8FPPobyb86XNzdX5eg3Qffj2-KVywHfPcbz4tfXLz8vvy3X36-uL1frpWkkn5a8trWQxEohnaNWNoJSgQ2nnAIX4Ig2hhDUXSsRBJMGhabc1NZQImXe7by4PvDGHQbtE6pd8oNO9ypqr2zASUWr2iyCspaioE3LbCdr0zXYGZDAO-KcNm3rMtfHA9cuxT97HCc1-NFg3-uAcT8q0tRt28wjngJlRDBGRYZ-OIJu4z7NGs2ous3LkhlVHVAb3aPywcUpaZOfxcGbGND5_L-iXEJLa85ygTwUmBTHMaH7vzgBNTtDbdWzM9TsDAVUwYNm7x8n2ndz7qnwyQoZcHHEbfyk5zvnoXx_SofPBwLMp7_zmNRoPAaDNl_ITMpGfwrJxRGJ6X3wRve3eI_js4pqrBWoH7PFZ4cTlt3NpaD_AAHA9dg
startdate2014
enddate2014
creator
0Reşit Kavsaoğlu, A
1Polat, Kemal
2Recep Bozkurt, M
general
0Elsevier Ltd
1Elsevier B.V
2Elsevier Limited
3PERGAMON-ELSEVIER SCIENCE LTD
scope
0CGR
1CUY
2CVF
3ECM
4EIF
5NPM
6AAYXX
7CITATION
8BSHEE
93V.
107QO
117RV
127X7
137XB
1488E
158AL
168AO
178FD
188FE
198FG
208FH
218FI
228FJ
238FK
248G5
25ABUWG
26ARAPS
27AZQEC
28BBNVY
29BENPR
30BGLVJ
31BHPHI
32DWQXO
33FR3
34FYUFA
35GHDGH
36GNUQQ
37GUQSH
38HCIFZ
39JQ2
40K7-
41K9.
42KB0
43LK8
44M0N
45M0S
46M1P
47M2O
48M7P
49MBDVC
50NAPCQ
51P5Z
52P62
53P64
54PADUT
55PQEST
56PQQKQ
57PQUKI
58PRINS
59Q9U
607X8
61BOBZL
62CLFQK
sort
creationdate2014
titleA novel feature ranking algorithm for biometric recognition with PPG signals
authorReşit Kavsaoğlu, A ; Polat, Kemal ; Recep Bozkurt, M
facets
frbrtype5
frbrgroupidcdi_FETCH-LOGICAL-c586t-62d2781d878ff3d857337e563630670f1acc11eab98e0748ce7a36c2dc3188053
rsrctypearticles
prefilterarticles
languageeng
creationdate2014
topic
0Adolescent
1Adult
2Age
3Algorithms
4Biometric identification
5Biometric Identification - instrumentation
6Biometric Identification - methods
7Biometrics
8Biometry
9Cardiovascular disease
10Classification
11Derivatives
12Electrocardiography
13Feature Extraction
14Female
15Fingers - physiology
16Heart
17Humans
18Identification
19Internal Medicine
20Light
21Male
22Methods
23Middle Aged
24Other
25Photoplethysmography (PPG)
26Photoplethysmography - instrumentation
27Photoplethysmography - methods
28Ratings & rankings
29Signal Processing, Computer-Assisted - instrumentation
30Skin
31Studies
32Veins & arteries
33Wavelet transforms
34Young Adult
toplevel
0peer_reviewed
1online_resources
creatorcontrib
0Reşit Kavsaoğlu, A
1Polat, Kemal
2Recep Bozkurt, M
collection
0Medline
1MEDLINE
2MEDLINE (Ovid)
3MEDLINE
4MEDLINE
5PubMed
6CrossRef
7Academic OneFile (A&I only)
8ProQuest Central (Corporate)
9Biotechnology Research Abstracts
10Nursing & Allied Health Database
11Health & Medical Collection
12ProQuest Central (purchase pre-March 2016)
13Medical Database (Alumni Edition)
14Computing Database (Alumni Edition)
15ProQuest Pharma Collection
16Technology Research Database
17ProQuest SciTech Collection
18ProQuest Technology Collection
19ProQuest Natural Science Collection
20Hospital Premium Collection
21Hospital Premium Collection (Alumni Edition)
22ProQuest Central (Alumni) (purchase pre-March 2016)
23Research Library (Alumni Edition)
24ProQuest Central (Alumni Edition)
25Advanced Technologies & Aerospace Collection
26ProQuest Central Essentials
27Biological Science Collection
28ProQuest Central
29Technology Collection
30Natural Science Collection
31ProQuest Central Korea
32Engineering Research Database
33Health Research Premium Collection
34Health Research Premium Collection (Alumni)
35ProQuest Central Student
36Research Library Prep
37SciTech Premium Collection
38ProQuest Computer Science Collection
39Computer Science Database
40ProQuest Health & Medical Complete (Alumni)
41Nursing & Allied Health Database (Alumni Edition)
42ProQuest Biological Science Collection
43Computing Database
44Health & Medical Collection (Alumni Edition)
45Medical Database
46Research Library
47Biological Science Database
48Research Library (Corporate)
49Nursing & Allied Health Premium
50Advanced Technologies & Aerospace Database
51ProQuest Advanced Technologies & Aerospace Collection
52Biotechnology and BioEngineering Abstracts
53Research Library China
54ProQuest One Academic Eastern Edition
55ProQuest One Academic
56ProQuest One Academic UKI Edition
57ProQuest Central China
58ProQuest Central Basic
59MEDLINE - Academic
60OpenAIRE (Open Access)
61OpenAIRE
jtitleComputers in biology and medicine
delivery
delcategoryRemote Search Resource
fulltextfulltext
addata
au
0Reşit Kavsaoğlu, A
1Polat, Kemal
2Recep Bozkurt, M
formatjournal
genrearticle
ristypeJOUR
atitleA novel feature ranking algorithm for biometric recognition with PPG signals
jtitleComputers in biology and medicine
addtitleComput Biol Med
date2014
risdate2014
volume49
spage1
epage14
pages1-14
issn0010-4825
eissn1879-0534
codenCBMDAW
abstractAbstract This study is intended for describing the application of the Photoplethysmography (PPG) signal and the time domain features acquired from its first and second derivatives for biometric identification. For this purpose, a sum of 40 features has been extracted and a feature-ranking algorithm is proposed. This proposed algorithm calculates the contribution of each feature to biometric recognition and collocates the features, the contribution of which is from great to small. While identifying the contribution of the features, the Euclidean distance and absolute distance formulas are used. The efficiency of the proposed algorithms is demonstrated by the results of the k-NN (k-nearest neighbor) classifier applications of the features. During application, each 15-period-PPG signal belonging to two different durations from each of the thirty healthy subjects were used with a PPG data acquisition card. The first PPG signals recorded from the subjects were evaluated as the 1st configuration; the PPG signals recorded later at a different time as the 2nd configuration and the combination of both were evaluated as the 3rd configuration. When the results were evaluated for the k-NN classifier model created along with the proposed algorithm, an identification of 90.44% for the 1st configuration, 94.44% for the 2nd configuration, and 87.22% for the 3rd configuration has successfully been attained. The obtained results showed that both the proposed algorithm and the biometric identification model based on this developed PPG signal are very promising for contactless recognizing the people with the proposed method.
copUnited States
pubElsevier Ltd
pmid24705467
doi10.1016/j.compbiomed.2014.03.005
oafree_for_read