General Framing of Low-, Mid-, and High-Level Data Fusion With Examples in the Life Sciences

Agnieszka Smolinska*, Jasper Engel, Ewa Szymanska, Lutgarde Buydens, Lionel Blanchet

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

The constant development of analytical techniques leads to an increase in the amount of information available to describe phenomena in life science. In parallel, the inherent complexity of life science makes it almost impossible to obtain a comprehensive description using only one technical modality. Therefore, it became very popular to combine several biological or technical platforms/modalities to obtain a better understanding of the underlying problems. Merging different types of measurements/platforms into a single analysis is, however, a complex topic. Combining various platforms into single analysis is defined as data fusion. We describe here different types of data fusion strategies: the well-established low-, mid-, and high-level data fusion and the more recently introduced sustainable mid-level data fusion and kernel-based data fusion. For each type, we provide a detailed description. To illustrate these various data fusion approaches, we rely on four real data sets, namely, exhaled breath data of patients with Crohn disease (CD) obtained by gas chromatography–mass spectrometry (GC-MS), 454 pyrosequencing microbiome data of patients with CD, and metabolic profiling of beer brands by GC-MS and positive and negative ion modes of liquid chromatography.

Original languageEnglish
Title of host publicationData Fusion Methodology and Applications
PublisherElsevier Ltd, Academic Press
Pages51-79
Number of pages29
ISBN (Print)9780444639844
DOIs
Publication statusPublished - 2019

Publication series

NameData Handling in Science and Technology
Volume31
ISSN (Print)0922-3487

Fingerprint

Life sciences
Data Fusion
Data fusion
Modality
Spectrometry
Gases
Beer
Liquid chromatography
Profiling
Chromatography
Merging
Negative ions
Positive ions
Liquid
kernel

Keywords

  • Analytical technique
  • Data fusion
  • Gas chromatography–mass spectrometry
  • Kernel-based data fusion
  • Liquid chromatography
  • Microbiome data

Cite this

Smolinska, A., Engel, J., Szymanska, E., Buydens, L., & Blanchet, L. (2019). General Framing of Low-, Mid-, and High-Level Data Fusion With Examples in the Life Sciences. In Data Fusion Methodology and Applications (pp. 51-79). (Data Handling in Science and Technology; Vol. 31). Elsevier Ltd, Academic Press. https://doi.org/10.1016/B978-0-444-63984-4.00003-X
Smolinska, Agnieszka ; Engel, Jasper ; Szymanska, Ewa ; Buydens, Lutgarde ; Blanchet, Lionel. / General Framing of Low-, Mid-, and High-Level Data Fusion With Examples in the Life Sciences. Data Fusion Methodology and Applications. Elsevier Ltd, Academic Press, 2019. pp. 51-79 (Data Handling in Science and Technology).
@inbook{fb7eddbc704544afbdf68bfe22572ebb,
title = "General Framing of Low-, Mid-, and High-Level Data Fusion With Examples in the Life Sciences",
abstract = "The constant development of analytical techniques leads to an increase in the amount of information available to describe phenomena in life science. In parallel, the inherent complexity of life science makes it almost impossible to obtain a comprehensive description using only one technical modality. Therefore, it became very popular to combine several biological or technical platforms/modalities to obtain a better understanding of the underlying problems. Merging different types of measurements/platforms into a single analysis is, however, a complex topic. Combining various platforms into single analysis is defined as data fusion. We describe here different types of data fusion strategies: the well-established low-, mid-, and high-level data fusion and the more recently introduced sustainable mid-level data fusion and kernel-based data fusion. For each type, we provide a detailed description. To illustrate these various data fusion approaches, we rely on four real data sets, namely, exhaled breath data of patients with Crohn disease (CD) obtained by gas chromatography–mass spectrometry (GC-MS), 454 pyrosequencing microbiome data of patients with CD, and metabolic profiling of beer brands by GC-MS and positive and negative ion modes of liquid chromatography.",
keywords = "Analytical technique, Data fusion, Gas chromatography–mass spectrometry, Kernel-based data fusion, Liquid chromatography, Microbiome data",
author = "Agnieszka Smolinska and Jasper Engel and Ewa Szymanska and Lutgarde Buydens and Lionel Blanchet",
year = "2019",
doi = "10.1016/B978-0-444-63984-4.00003-X",
language = "English",
isbn = "9780444639844",
series = "Data Handling in Science and Technology",
publisher = "Elsevier Ltd, Academic Press",
pages = "51--79",
booktitle = "Data Fusion Methodology and Applications",

}

Smolinska, A, Engel, J, Szymanska, E, Buydens, L & Blanchet, L 2019, General Framing of Low-, Mid-, and High-Level Data Fusion With Examples in the Life Sciences. in Data Fusion Methodology and Applications. Data Handling in Science and Technology, vol. 31, Elsevier Ltd, Academic Press, pp. 51-79. https://doi.org/10.1016/B978-0-444-63984-4.00003-X

General Framing of Low-, Mid-, and High-Level Data Fusion With Examples in the Life Sciences. / Smolinska, Agnieszka; Engel, Jasper; Szymanska, Ewa; Buydens, Lutgarde; Blanchet, Lionel.

Data Fusion Methodology and Applications. Elsevier Ltd, Academic Press, 2019. p. 51-79 (Data Handling in Science and Technology; Vol. 31).

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - General Framing of Low-, Mid-, and High-Level Data Fusion With Examples in the Life Sciences

AU - Smolinska, Agnieszka

AU - Engel, Jasper

AU - Szymanska, Ewa

AU - Buydens, Lutgarde

AU - Blanchet, Lionel

PY - 2019

Y1 - 2019

N2 - The constant development of analytical techniques leads to an increase in the amount of information available to describe phenomena in life science. In parallel, the inherent complexity of life science makes it almost impossible to obtain a comprehensive description using only one technical modality. Therefore, it became very popular to combine several biological or technical platforms/modalities to obtain a better understanding of the underlying problems. Merging different types of measurements/platforms into a single analysis is, however, a complex topic. Combining various platforms into single analysis is defined as data fusion. We describe here different types of data fusion strategies: the well-established low-, mid-, and high-level data fusion and the more recently introduced sustainable mid-level data fusion and kernel-based data fusion. For each type, we provide a detailed description. To illustrate these various data fusion approaches, we rely on four real data sets, namely, exhaled breath data of patients with Crohn disease (CD) obtained by gas chromatography–mass spectrometry (GC-MS), 454 pyrosequencing microbiome data of patients with CD, and metabolic profiling of beer brands by GC-MS and positive and negative ion modes of liquid chromatography.

AB - The constant development of analytical techniques leads to an increase in the amount of information available to describe phenomena in life science. In parallel, the inherent complexity of life science makes it almost impossible to obtain a comprehensive description using only one technical modality. Therefore, it became very popular to combine several biological or technical platforms/modalities to obtain a better understanding of the underlying problems. Merging different types of measurements/platforms into a single analysis is, however, a complex topic. Combining various platforms into single analysis is defined as data fusion. We describe here different types of data fusion strategies: the well-established low-, mid-, and high-level data fusion and the more recently introduced sustainable mid-level data fusion and kernel-based data fusion. For each type, we provide a detailed description. To illustrate these various data fusion approaches, we rely on four real data sets, namely, exhaled breath data of patients with Crohn disease (CD) obtained by gas chromatography–mass spectrometry (GC-MS), 454 pyrosequencing microbiome data of patients with CD, and metabolic profiling of beer brands by GC-MS and positive and negative ion modes of liquid chromatography.

KW - Analytical technique

KW - Data fusion

KW - Gas chromatography–mass spectrometry

KW - Kernel-based data fusion

KW - Liquid chromatography

KW - Microbiome data

U2 - 10.1016/B978-0-444-63984-4.00003-X

DO - 10.1016/B978-0-444-63984-4.00003-X

M3 - Chapter

SN - 9780444639844

T3 - Data Handling in Science and Technology

SP - 51

EP - 79

BT - Data Fusion Methodology and Applications

PB - Elsevier Ltd, Academic Press

ER -

Smolinska A, Engel J, Szymanska E, Buydens L, Blanchet L. General Framing of Low-, Mid-, and High-Level Data Fusion With Examples in the Life Sciences. In Data Fusion Methodology and Applications. Elsevier Ltd, Academic Press. 2019. p. 51-79. (Data Handling in Science and Technology). https://doi.org/10.1016/B978-0-444-63984-4.00003-X