Feature-based diagnostic distortion measure for unsupervised self-guided biomedical signal compressors

Jose Santos, Dongming Peng, Michael Hempel, Hamid Sharif

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this work, the advantages of coupling biomedical signal compressors with clinical feature-based distortion measures are demonstrated. Such a coupling allow biomedical signal compressors to self-establish hard limits with regards to choices surrounding compression ratios, or 'quality settings', a compressor can safely choose from to guarantee that features of clinical significance are protected so that their reconstruction remains clinically relevant. This coupling allows biomedical signal compressors to operate in an unsupervised manner, since it is demonstrated that establishing hard limits that are applied equally to all signals does not allow one to maximize and/or strike a balance between compression ratio and signal fidelity. Such mechanisms can be employed in communication architectures in wearable body area sensor networks (BASNs) for emerging Internet of Things (IoT) applications for autonomous tasks. While feature-based distortion measures such as the Clinical Distortion Index (CDI), and the Weighted Distortion Measure (WDD) already exist, we demonstrate the viability of our work by proposing a generalizable feature-based distortion measure we call the Diagnostic Distortion Measure (DDM), which offers several benefits that address a few shortcomings present in the CDI and WDD in real-time applications for unsupervised self-guided compressors. Experimental results show successful application of our DDM with ECG signals from the PhysioNet database.

Original languageEnglish (US)
Title of host publication2017 IEEE 13th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2017
PublisherIEEE Computer Society
ISBN (Electronic)9781538638392
DOIs
StatePublished - Nov 20 2017
Event13th IEEE International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2017 - Rome, Italy
Duration: Oct 9 2017Oct 11 2017

Publication series

NameInternational Conference on Wireless and Mobile Computing, Networking and Communications
Volume2017-October
ISSN (Print)2161-9646
ISSN (Electronic)2161-9654

Other

Other13th IEEE International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2017
CountryItaly
CityRome
Period10/9/1710/11/17

Fingerprint

Compressors
Compression ratio (machinery)
Electrocardiography
Sensor networks
Communication

Keywords

  • Biomedical
  • Blind Compressors
  • CDI
  • Communication Architectures
  • DDM
  • Diagnostic Distortion Measure
  • ECG
  • Feature-Based Distortion Measures
  • PRD
  • Sample-Based Distortion Measures
  • Self-Guided Compressors
  • WDD
  • WWPRD

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Software

Cite this

Santos, J., Peng, D., Hempel, M., & Sharif, H. (2017). Feature-based diagnostic distortion measure for unsupervised self-guided biomedical signal compressors. In 2017 IEEE 13th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2017 [8115801] (International Conference on Wireless and Mobile Computing, Networking and Communications; Vol. 2017-October). IEEE Computer Society. https://doi.org/10.1109/WiMOB.2017.8115801

Feature-based diagnostic distortion measure for unsupervised self-guided biomedical signal compressors. / Santos, Jose; Peng, Dongming; Hempel, Michael; Sharif, Hamid.

2017 IEEE 13th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2017. IEEE Computer Society, 2017. 8115801 (International Conference on Wireless and Mobile Computing, Networking and Communications; Vol. 2017-October).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Santos, J, Peng, D, Hempel, M & Sharif, H 2017, Feature-based diagnostic distortion measure for unsupervised self-guided biomedical signal compressors. in 2017 IEEE 13th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2017., 8115801, International Conference on Wireless and Mobile Computing, Networking and Communications, vol. 2017-October, IEEE Computer Society, 13th IEEE International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2017, Rome, Italy, 10/9/17. https://doi.org/10.1109/WiMOB.2017.8115801
Santos J, Peng D, Hempel M, Sharif H. Feature-based diagnostic distortion measure for unsupervised self-guided biomedical signal compressors. In 2017 IEEE 13th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2017. IEEE Computer Society. 2017. 8115801. (International Conference on Wireless and Mobile Computing, Networking and Communications). https://doi.org/10.1109/WiMOB.2017.8115801
Santos, Jose ; Peng, Dongming ; Hempel, Michael ; Sharif, Hamid. / Feature-based diagnostic distortion measure for unsupervised self-guided biomedical signal compressors. 2017 IEEE 13th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2017. IEEE Computer Society, 2017. (International Conference on Wireless and Mobile Computing, Networking and Communications).
@inproceedings{f2402c0696a0464ab1f42a3db2eb992a,
title = "Feature-based diagnostic distortion measure for unsupervised self-guided biomedical signal compressors",
abstract = "In this work, the advantages of coupling biomedical signal compressors with clinical feature-based distortion measures are demonstrated. Such a coupling allow biomedical signal compressors to self-establish hard limits with regards to choices surrounding compression ratios, or 'quality settings', a compressor can safely choose from to guarantee that features of clinical significance are protected so that their reconstruction remains clinically relevant. This coupling allows biomedical signal compressors to operate in an unsupervised manner, since it is demonstrated that establishing hard limits that are applied equally to all signals does not allow one to maximize and/or strike a balance between compression ratio and signal fidelity. Such mechanisms can be employed in communication architectures in wearable body area sensor networks (BASNs) for emerging Internet of Things (IoT) applications for autonomous tasks. While feature-based distortion measures such as the Clinical Distortion Index (CDI), and the Weighted Distortion Measure (WDD) already exist, we demonstrate the viability of our work by proposing a generalizable feature-based distortion measure we call the Diagnostic Distortion Measure (DDM), which offers several benefits that address a few shortcomings present in the CDI and WDD in real-time applications for unsupervised self-guided compressors. Experimental results show successful application of our DDM with ECG signals from the PhysioNet database.",
keywords = "Biomedical, Blind Compressors, CDI, Communication Architectures, DDM, Diagnostic Distortion Measure, ECG, Feature-Based Distortion Measures, PRD, Sample-Based Distortion Measures, Self-Guided Compressors, WDD, WWPRD",
author = "Jose Santos and Dongming Peng and Michael Hempel and Hamid Sharif",
year = "2017",
month = "11",
day = "20",
doi = "10.1109/WiMOB.2017.8115801",
language = "English (US)",
series = "International Conference on Wireless and Mobile Computing, Networking and Communications",
publisher = "IEEE Computer Society",
booktitle = "2017 IEEE 13th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2017",

}

TY - GEN

T1 - Feature-based diagnostic distortion measure for unsupervised self-guided biomedical signal compressors

AU - Santos, Jose

AU - Peng, Dongming

AU - Hempel, Michael

AU - Sharif, Hamid

PY - 2017/11/20

Y1 - 2017/11/20

N2 - In this work, the advantages of coupling biomedical signal compressors with clinical feature-based distortion measures are demonstrated. Such a coupling allow biomedical signal compressors to self-establish hard limits with regards to choices surrounding compression ratios, or 'quality settings', a compressor can safely choose from to guarantee that features of clinical significance are protected so that their reconstruction remains clinically relevant. This coupling allows biomedical signal compressors to operate in an unsupervised manner, since it is demonstrated that establishing hard limits that are applied equally to all signals does not allow one to maximize and/or strike a balance between compression ratio and signal fidelity. Such mechanisms can be employed in communication architectures in wearable body area sensor networks (BASNs) for emerging Internet of Things (IoT) applications for autonomous tasks. While feature-based distortion measures such as the Clinical Distortion Index (CDI), and the Weighted Distortion Measure (WDD) already exist, we demonstrate the viability of our work by proposing a generalizable feature-based distortion measure we call the Diagnostic Distortion Measure (DDM), which offers several benefits that address a few shortcomings present in the CDI and WDD in real-time applications for unsupervised self-guided compressors. Experimental results show successful application of our DDM with ECG signals from the PhysioNet database.

AB - In this work, the advantages of coupling biomedical signal compressors with clinical feature-based distortion measures are demonstrated. Such a coupling allow biomedical signal compressors to self-establish hard limits with regards to choices surrounding compression ratios, or 'quality settings', a compressor can safely choose from to guarantee that features of clinical significance are protected so that their reconstruction remains clinically relevant. This coupling allows biomedical signal compressors to operate in an unsupervised manner, since it is demonstrated that establishing hard limits that are applied equally to all signals does not allow one to maximize and/or strike a balance between compression ratio and signal fidelity. Such mechanisms can be employed in communication architectures in wearable body area sensor networks (BASNs) for emerging Internet of Things (IoT) applications for autonomous tasks. While feature-based distortion measures such as the Clinical Distortion Index (CDI), and the Weighted Distortion Measure (WDD) already exist, we demonstrate the viability of our work by proposing a generalizable feature-based distortion measure we call the Diagnostic Distortion Measure (DDM), which offers several benefits that address a few shortcomings present in the CDI and WDD in real-time applications for unsupervised self-guided compressors. Experimental results show successful application of our DDM with ECG signals from the PhysioNet database.

KW - Biomedical

KW - Blind Compressors

KW - CDI

KW - Communication Architectures

KW - DDM

KW - Diagnostic Distortion Measure

KW - ECG

KW - Feature-Based Distortion Measures

KW - PRD

KW - Sample-Based Distortion Measures

KW - Self-Guided Compressors

KW - WDD

KW - WWPRD

UR - http://www.scopus.com/inward/record.url?scp=85041396923&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041396923&partnerID=8YFLogxK

U2 - 10.1109/WiMOB.2017.8115801

DO - 10.1109/WiMOB.2017.8115801

M3 - Conference contribution

AN - SCOPUS:85041396923

T3 - International Conference on Wireless and Mobile Computing, Networking and Communications

BT - 2017 IEEE 13th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2017

PB - IEEE Computer Society

ER -