People stink!: Towards identification of people from breath samples

Katri Salminen; Jussi Rantala; Philipp Müller

doi:10.1109/ISOEN54820.2022.9789603

People stink! Towards identification of people from breath samples

Katri Salminen, Jussi Rantala, Philipp Müller

Tietotekniikka

Tutkimustuotos: Konferenssiartikkeli › Scientific › vertaisarvioitu

2 Lataukset (Pure)

Abstrakti

The paper addresses the potential to use breath samples for identifying people. Participants were asked to exhale ten times for a length of five seconds to a tube attached to a commercial ion-mobility spectrometry device on three separate sessions. The data of each participant was divided into training (50% of the samples) and test data sets (50% of the samples) in random order. Classification decision tree (CDT), K nearest neighbor (KNN), naïve Bayes (NB), linear discriminant analysis (LDA), and quadratic discriminant analysis (QDA) were used to analyze if the data could be classified correctly. Within a session, KNN (75.2%), NB (78.3%), and LDA (85.8%) were able to identify participants. Between sessions, the performance decreased.

Alkuperäiskieli	Englanti
Otsikko	2022 International Symposium on Olfaction and Electronic Nose (ISOEN)
Kustantaja	IEEE
Sivut	1-3
ISBN (elektroninen)	978-1-6654-5860-3
DOI - pysyväislinkit	https://doi.org/10.1109/ISOEN54820.2022.9789603
Tila	Julkaistu - kesäk. 2022
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisussa
Tapahtuma	IEEE International Symposium on Olfaction and Electronic Nose (ISOEN) - Aveiro, Portugali Kesto: 29 toukok. 2022 → 1 kesäk. 2022

Conference

Conference	IEEE International Symposium on Olfaction and Electronic Nose (ISOEN)
Maa/Alue	Portugali
Kaupunki	Aveiro
Ajanjakso	29/05/22 → 1/06/22

Julkaisufoorumi-taso

Jufo-taso 1

Pääsy asiakirjaan

10.1109/ISOEN54820.2022.9789603

People stink final_author_version
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited
Accepted author manuscript, 409 KBLisenssi: Unspecified

https://urn.fi/URN:NBN:fi:tuni-202302132302Lisenssi: Unspecified

Siteeraa tätä

@inproceedings{d9620a851e624efda08868e551be37c9,

title = "People stink!: Towards identification of people from breath samples",

abstract = "The paper addresses the potential to use breath samples for identifying people. Participants were asked to exhale ten times for a length of five seconds to a tube attached to a commercial ion-mobility spectrometry device on three separate sessions. The data of each participant was divided into training (50% of the samples) and test data sets (50% of the samples) in random order. Classification decision tree (CDT), K nearest neighbor (KNN), na{\"i}ve Bayes (NB), linear discriminant analysis (LDA), and quadratic discriminant analysis (QDA) were used to analyze if the data could be classified correctly. Within a session, KNN (75.2%), NB (78.3%), and LDA (85.8%) were able to identify participants. Between sessions, the performance decreased.",

author = "Katri Salminen and Jussi Rantala and Philipp M{\"u}ller",

year = "2022",

month = jun,

doi = "10.1109/ISOEN54820.2022.9789603",

language = "English",

pages = "1--3",

booktitle = "2022 International Symposium on Olfaction and Electronic Nose (ISOEN)",

publisher = "IEEE",

note = "IEEE International Symposium on Olfaction and Electronic Nose (ISOEN) ; Conference date: 29-05-2022 Through 01-06-2022",

}

TY - GEN

T1 - People stink!

T2 - IEEE International Symposium on Olfaction and Electronic Nose (ISOEN)

AU - Salminen, Katri

AU - Rantala, Jussi

AU - Müller, Philipp

PY - 2022/6

Y1 - 2022/6

N2 - The paper addresses the potential to use breath samples for identifying people. Participants were asked to exhale ten times for a length of five seconds to a tube attached to a commercial ion-mobility spectrometry device on three separate sessions. The data of each participant was divided into training (50% of the samples) and test data sets (50% of the samples) in random order. Classification decision tree (CDT), K nearest neighbor (KNN), naïve Bayes (NB), linear discriminant analysis (LDA), and quadratic discriminant analysis (QDA) were used to analyze if the data could be classified correctly. Within a session, KNN (75.2%), NB (78.3%), and LDA (85.8%) were able to identify participants. Between sessions, the performance decreased.

AB - The paper addresses the potential to use breath samples for identifying people. Participants were asked to exhale ten times for a length of five seconds to a tube attached to a commercial ion-mobility spectrometry device on three separate sessions. The data of each participant was divided into training (50% of the samples) and test data sets (50% of the samples) in random order. Classification decision tree (CDT), K nearest neighbor (KNN), naïve Bayes (NB), linear discriminant analysis (LDA), and quadratic discriminant analysis (QDA) were used to analyze if the data could be classified correctly. Within a session, KNN (75.2%), NB (78.3%), and LDA (85.8%) were able to identify participants. Between sessions, the performance decreased.

U2 - 10.1109/ISOEN54820.2022.9789603

DO - 10.1109/ISOEN54820.2022.9789603

M3 - Conference contribution

SP - 1

EP - 3

BT - 2022 International Symposium on Olfaction and Electronic Nose (ISOEN)

PB - IEEE

Y2 - 29 May 2022 through 1 June 2022

ER -