Tampere University of Technology

TUTCRIS Research Portal

Online Scent Classification by Ion-Mobility Spectrometry Sequences

Research output: Contribution to journalArticleScientificpeer-review

Standard

Online Scent Classification by Ion-Mobility Spectrometry Sequences. / Müller, Philipp; Salminen, Katri; Kontunen, Anton; Karjalainen, Markus; Isokoski, Poika; Rantala, Jussi; Leivo, Joni; Väliaho, Jari; Kallio, Pasi; Lekkala, Jukka; Surakkka, Veikko.

In: Frontiers in Applied Mathematics and Statistics, Vol. 5, 39, 30.07.2019.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Müller, P, Salminen, K, Kontunen, A, Karjalainen, M, Isokoski, P, Rantala, J, Leivo, J, Väliaho, J, Kallio, P, Lekkala, J & Surakkka, V 2019, 'Online Scent Classification by Ion-Mobility Spectrometry Sequences', Frontiers in Applied Mathematics and Statistics, vol. 5, 39. https://doi.org/10.3389/fams.2019.00039

APA

Müller, P., Salminen, K., Kontunen, A., Karjalainen, M., Isokoski, P., Rantala, J., ... Surakkka, V. (2019). Online Scent Classification by Ion-Mobility Spectrometry Sequences. Frontiers in Applied Mathematics and Statistics, 5, [39]. https://doi.org/10.3389/fams.2019.00039

Vancouver

Müller P, Salminen K, Kontunen A, Karjalainen M, Isokoski P, Rantala J et al. Online Scent Classification by Ion-Mobility Spectrometry Sequences. Frontiers in Applied Mathematics and Statistics. 2019 Jul 30;5. 39. https://doi.org/10.3389/fams.2019.00039

Author

Müller, Philipp ; Salminen, Katri ; Kontunen, Anton ; Karjalainen, Markus ; Isokoski, Poika ; Rantala, Jussi ; Leivo, Joni ; Väliaho, Jari ; Kallio, Pasi ; Lekkala, Jukka ; Surakkka, Veikko. / Online Scent Classification by Ion-Mobility Spectrometry Sequences. In: Frontiers in Applied Mathematics and Statistics. 2019 ; Vol. 5.

Bibtex - Download

@article{0de5c34da8eb45deabc3e52ac04691c2,
title = "Online Scent Classification by Ion-Mobility Spectrometry Sequences",
abstract = "For ion-mobility spectrometry (IMS)-based electronic noses (eNose) samples of scents are markedly time-dependent, with a transient phase and a highly volatile stable phase in certain conditions. At the same time, the samples depend on various environmental factors, such as temperature and humidity. This makes fast classification of scents challenging. The present aim was to develop and test an algorithm for online scent classification that mitigates these dependencies by using both baseline measurements and sequences of samples for classification. A classifier based on the K nearest neighbors approach was derived. The classifier is able to use measurements from both transient and stable phase, yields a label for the analyzed scent, and information on the trustworthiness of the returned label. In order to avoid the classifier being fooled by irrelevant features and to reduce the dimensionality of the feature space, principal component analysis was applied to the data. The classifier was tested with four food scents, each presented in two different ways to the IMS. By using baseline measurements, the misclassification rate was reduced from 20.0 to 13.3{\%}. A second experiment showed that the used IMS type experiences device heterogeneity.",
author = "Philipp M{\"u}ller and Katri Salminen and Anton Kontunen and Markus Karjalainen and Poika Isokoski and Jussi Rantala and Joni Leivo and Jari V{\"a}liaho and Pasi Kallio and Jukka Lekkala and Veikko Surakkka",
note = "INT=comp,{"}Isokoski, Poika{"} INT=comp,{"}Rantala, Jussi{"} INT=comp,{"}Surakka, Veikko{"} dupl=51441409",
year = "2019",
month = "7",
day = "30",
doi = "10.3389/fams.2019.00039",
language = "English",
volume = "5",
journal = "Frontiers in Applied Mathematics and Statistics",
issn = "2297-4687",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Online Scent Classification by Ion-Mobility Spectrometry Sequences

AU - Müller, Philipp

AU - Salminen, Katri

AU - Kontunen, Anton

AU - Karjalainen, Markus

AU - Isokoski, Poika

AU - Rantala, Jussi

AU - Leivo, Joni

AU - Väliaho, Jari

AU - Kallio, Pasi

AU - Lekkala, Jukka

AU - Surakkka, Veikko

N1 - INT=comp,"Isokoski, Poika" INT=comp,"Rantala, Jussi" INT=comp,"Surakka, Veikko" dupl=51441409

PY - 2019/7/30

Y1 - 2019/7/30

N2 - For ion-mobility spectrometry (IMS)-based electronic noses (eNose) samples of scents are markedly time-dependent, with a transient phase and a highly volatile stable phase in certain conditions. At the same time, the samples depend on various environmental factors, such as temperature and humidity. This makes fast classification of scents challenging. The present aim was to develop and test an algorithm for online scent classification that mitigates these dependencies by using both baseline measurements and sequences of samples for classification. A classifier based on the K nearest neighbors approach was derived. The classifier is able to use measurements from both transient and stable phase, yields a label for the analyzed scent, and information on the trustworthiness of the returned label. In order to avoid the classifier being fooled by irrelevant features and to reduce the dimensionality of the feature space, principal component analysis was applied to the data. The classifier was tested with four food scents, each presented in two different ways to the IMS. By using baseline measurements, the misclassification rate was reduced from 20.0 to 13.3%. A second experiment showed that the used IMS type experiences device heterogeneity.

AB - For ion-mobility spectrometry (IMS)-based electronic noses (eNose) samples of scents are markedly time-dependent, with a transient phase and a highly volatile stable phase in certain conditions. At the same time, the samples depend on various environmental factors, such as temperature and humidity. This makes fast classification of scents challenging. The present aim was to develop and test an algorithm for online scent classification that mitigates these dependencies by using both baseline measurements and sequences of samples for classification. A classifier based on the K nearest neighbors approach was derived. The classifier is able to use measurements from both transient and stable phase, yields a label for the analyzed scent, and information on the trustworthiness of the returned label. In order to avoid the classifier being fooled by irrelevant features and to reduce the dimensionality of the feature space, principal component analysis was applied to the data. The classifier was tested with four food scents, each presented in two different ways to the IMS. By using baseline measurements, the misclassification rate was reduced from 20.0 to 13.3%. A second experiment showed that the used IMS type experiences device heterogeneity.

U2 - 10.3389/fams.2019.00039

DO - 10.3389/fams.2019.00039

M3 - Article

VL - 5

JO - Frontiers in Applied Mathematics and Statistics

JF - Frontiers in Applied Mathematics and Statistics

SN - 2297-4687

M1 - 39

ER -