Differential entropy preserves variational information of near-infrared spectroscopy time series associated with working memory

Soheil Keshmiri, Hidenubo Sumioka, Ryuji Yamazaki Skov, Hiroshi Ishiguro

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Neuroscience research shows a growing interest in the application of Near-Infrared Spectroscopy (NIRS) in analysis and decoding of the brain activity of human subjects. Given the correlation that is observed between the Blood Oxygen Dependent Level (BOLD) responses that are exhibited by the time series data of functional Magnetic Resonance Imaging (fMRI) and the hemoglobin oxy/deoxy-genation that is captured by NIRS, linear models play a central role in these applications. This, in turn, results in adaptation of the feature extraction strategies that are well-suited for discretization of data that exhibit a high degree of linearity, namely, slope and the mean as well as their combination, to summarize the informational contents of the NIRS time series. In this article, we demonstrate that these features are inefficient in capturing the variational information of NIRS data, limiting the reliability and the adequacy of the conclusion on their results. Alternatively, we propose the linear estimate of differential entropy of these time series as a natural representation of such information. We provide evidence for our claim through comparative analysis of the application of these features on NIRS data pertinent to several working memory tasks as well as naturalistic conversational stimuli.

Original languageEnglish
Article number33
JournalFrontiers in Neuroinformatics
Volume12
DOIs
Publication statusPublished - 2018 Jun 5

Fingerprint

Near infrared spectroscopy
Near-Infrared Spectroscopy
Entropy
Short-Term Memory
Time series
Data storage equipment
Hemoglobin
Neurosciences
Human Activities
Decoding
Feature extraction
Linear Models
Brain
Hemoglobins
Blood
Magnetic Resonance Imaging
Oxygen
Research

Keywords

  • Brain activity decoding
  • Differential entropy
  • Near-infrared spectroscopy
  • NIRS time series feature extraction
  • Working memory

ASJC Scopus subject areas

  • Neuroscience (miscellaneous)
  • Biomedical Engineering
  • Computer Science Applications

Cite this

Differential entropy preserves variational information of near-infrared spectroscopy time series associated with working memory. / Keshmiri, Soheil; Sumioka, Hidenubo; Yamazaki Skov, Ryuji; Ishiguro, Hiroshi.

In: Frontiers in Neuroinformatics, Vol. 12, 33, 05.06.2018.

Research output: Contribution to journalArticle

Keshmiri, Soheil ; Sumioka, Hidenubo ; Yamazaki Skov, Ryuji ; Ishiguro, Hiroshi. / Differential entropy preserves variational information of near-infrared spectroscopy time series associated with working memory. In: Frontiers in Neuroinformatics. 2018 ; Vol. 12.
@article{d336c794415f4c5596159172767015da,
title = "Differential entropy preserves variational information of near-infrared spectroscopy time series associated with working memory",
abstract = "Neuroscience research shows a growing interest in the application of Near-Infrared Spectroscopy (NIRS) in analysis and decoding of the brain activity of human subjects. Given the correlation that is observed between the Blood Oxygen Dependent Level (BOLD) responses that are exhibited by the time series data of functional Magnetic Resonance Imaging (fMRI) and the hemoglobin oxy/deoxy-genation that is captured by NIRS, linear models play a central role in these applications. This, in turn, results in adaptation of the feature extraction strategies that are well-suited for discretization of data that exhibit a high degree of linearity, namely, slope and the mean as well as their combination, to summarize the informational contents of the NIRS time series. In this article, we demonstrate that these features are inefficient in capturing the variational information of NIRS data, limiting the reliability and the adequacy of the conclusion on their results. Alternatively, we propose the linear estimate of differential entropy of these time series as a natural representation of such information. We provide evidence for our claim through comparative analysis of the application of these features on NIRS data pertinent to several working memory tasks as well as naturalistic conversational stimuli.",
keywords = "Brain activity decoding, Differential entropy, Near-infrared spectroscopy, NIRS time series feature extraction, Working memory",
author = "Soheil Keshmiri and Hidenubo Sumioka and {Yamazaki Skov}, Ryuji and Hiroshi Ishiguro",
year = "2018",
month = "6",
day = "5",
doi = "10.3389/fninf.2018.00033",
language = "English",
volume = "12",
journal = "Frontiers in Neuroinformatics",
issn = "1662-5196",
publisher = "Frontiers Research Foundation",

}

TY - JOUR

T1 - Differential entropy preserves variational information of near-infrared spectroscopy time series associated with working memory

AU - Keshmiri, Soheil

AU - Sumioka, Hidenubo

AU - Yamazaki Skov, Ryuji

AU - Ishiguro, Hiroshi

PY - 2018/6/5

Y1 - 2018/6/5

N2 - Neuroscience research shows a growing interest in the application of Near-Infrared Spectroscopy (NIRS) in analysis and decoding of the brain activity of human subjects. Given the correlation that is observed between the Blood Oxygen Dependent Level (BOLD) responses that are exhibited by the time series data of functional Magnetic Resonance Imaging (fMRI) and the hemoglobin oxy/deoxy-genation that is captured by NIRS, linear models play a central role in these applications. This, in turn, results in adaptation of the feature extraction strategies that are well-suited for discretization of data that exhibit a high degree of linearity, namely, slope and the mean as well as their combination, to summarize the informational contents of the NIRS time series. In this article, we demonstrate that these features are inefficient in capturing the variational information of NIRS data, limiting the reliability and the adequacy of the conclusion on their results. Alternatively, we propose the linear estimate of differential entropy of these time series as a natural representation of such information. We provide evidence for our claim through comparative analysis of the application of these features on NIRS data pertinent to several working memory tasks as well as naturalistic conversational stimuli.

AB - Neuroscience research shows a growing interest in the application of Near-Infrared Spectroscopy (NIRS) in analysis and decoding of the brain activity of human subjects. Given the correlation that is observed between the Blood Oxygen Dependent Level (BOLD) responses that are exhibited by the time series data of functional Magnetic Resonance Imaging (fMRI) and the hemoglobin oxy/deoxy-genation that is captured by NIRS, linear models play a central role in these applications. This, in turn, results in adaptation of the feature extraction strategies that are well-suited for discretization of data that exhibit a high degree of linearity, namely, slope and the mean as well as their combination, to summarize the informational contents of the NIRS time series. In this article, we demonstrate that these features are inefficient in capturing the variational information of NIRS data, limiting the reliability and the adequacy of the conclusion on their results. Alternatively, we propose the linear estimate of differential entropy of these time series as a natural representation of such information. We provide evidence for our claim through comparative analysis of the application of these features on NIRS data pertinent to several working memory tasks as well as naturalistic conversational stimuli.

KW - Brain activity decoding

KW - Differential entropy

KW - Near-infrared spectroscopy

KW - NIRS time series feature extraction

KW - Working memory

UR - http://www.scopus.com/inward/record.url?scp=85049108005&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049108005&partnerID=8YFLogxK

U2 - 10.3389/fninf.2018.00033

DO - 10.3389/fninf.2018.00033

M3 - Article

AN - SCOPUS:85049108005

VL - 12

JO - Frontiers in Neuroinformatics

JF - Frontiers in Neuroinformatics

SN - 1662-5196

M1 - 33

ER -