Methods for detection and classification of normal swallowing from muscle activation and sound

O.D. Amft; G. Tröster

doi:10.1109/PCTHEALTH.2006.361624

Methods for detection and classification of normal swallowing from muscle activation and sound

O.D. Amft, G. Tröster

Signal Processing Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

78 Citations (Scopus)

328 Downloads (Pure)

Abstract

Swallowing is an important part of the dietary process. This paper presents an investigation to detect and classify normal swallowing during eating and drinking from electromyography and microphone sensors. The non-invasive sensors are selected in order to integrate them into a collarlike fabric for continuous monitoring of swallowing activity over a day. We compare methods for the detection of individual swallowing events from continuous sensor data. Furthermore we present a classifier comparison for the swallowing event properties volume and viscosity. The methods are evaluated on experimental data and a performance analysis is shown. Moreover we present a class skew analysis based on the metrics precision and recall.

Original language	English
Title of host publication	Proceedings 2006 Pervasive Health Conference and Workshops, PervasiveHealth, 29 November 2006 through 1 December 2006, Innsbruck
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	4205194-
ISBN (Print)	1-4244-1085-1
DOIs	https://doi.org/10.1109/PCTHEALTH.2006.361624
Publication status	Published - 2007

Access to Document

10.1109/PCTHEALTH.2006.361624

Metis248464Final published version, 10.6 MB

Cite this

Amft, O. D., & Tröster, G. (2007). Methods for detection and classification of normal swallowing from muscle activation and sound. In Proceedings 2006 Pervasive Health Conference and Workshops, PervasiveHealth, 29 November 2006 through 1 December 2006, Innsbruck (pp. 4205194-). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/PCTHEALTH.2006.361624

@inproceedings{c0b00640e35946cdbc0dceeb81046bbc,

title = "Methods for detection and classification of normal swallowing from muscle activation and sound",

abstract = "Swallowing is an important part of the dietary process. This paper presents an investigation to detect and classify normal swallowing during eating and drinking from electromyography and microphone sensors. The non-invasive sensors are selected in order to integrate them into a collarlike fabric for continuous monitoring of swallowing activity over a day. We compare methods for the detection of individual swallowing events from continuous sensor data. Furthermore we present a classifier comparison for the swallowing event properties volume and viscosity. The methods are evaluated on experimental data and a performance analysis is shown. Moreover we present a class skew analysis based on the metrics precision and recall.",

author = "O.D. Amft and G. Tr{\"o}ster",

year = "2007",

doi = "10.1109/PCTHEALTH.2006.361624",

language = "English",

isbn = "1-4244-1085-1",

pages = "4205194--",

booktitle = "Proceedings 2006 Pervasive Health Conference and Workshops, PervasiveHealth, 29 November 2006 through 1 December 2006, Innsbruck",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

}

Amft, OD & Tröster, G 2007, Methods for detection and classification of normal swallowing from muscle activation and sound. in Proceedings 2006 Pervasive Health Conference and Workshops, PervasiveHealth, 29 November 2006 through 1 December 2006, Innsbruck. Institute of Electrical and Electronics Engineers, Piscataway, pp. 4205194-. https://doi.org/10.1109/PCTHEALTH.2006.361624

Methods for detection and classification of normal swallowing from muscle activation and sound. / Amft, O.D.; Tröster, G.
Proceedings 2006 Pervasive Health Conference and Workshops, PervasiveHealth, 29 November 2006 through 1 December 2006, Innsbruck. Piscataway: Institute of Electrical and Electronics Engineers, 2007. p. 4205194-.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Methods for detection and classification of normal swallowing from muscle activation and sound

AU - Amft, O.D.

AU - Tröster, G.

PY - 2007

Y1 - 2007

N2 - Swallowing is an important part of the dietary process. This paper presents an investigation to detect and classify normal swallowing during eating and drinking from electromyography and microphone sensors. The non-invasive sensors are selected in order to integrate them into a collarlike fabric for continuous monitoring of swallowing activity over a day. We compare methods for the detection of individual swallowing events from continuous sensor data. Furthermore we present a classifier comparison for the swallowing event properties volume and viscosity. The methods are evaluated on experimental data and a performance analysis is shown. Moreover we present a class skew analysis based on the metrics precision and recall.

AB - Swallowing is an important part of the dietary process. This paper presents an investigation to detect and classify normal swallowing during eating and drinking from electromyography and microphone sensors. The non-invasive sensors are selected in order to integrate them into a collarlike fabric for continuous monitoring of swallowing activity over a day. We compare methods for the detection of individual swallowing events from continuous sensor data. Furthermore we present a classifier comparison for the swallowing event properties volume and viscosity. The methods are evaluated on experimental data and a performance analysis is shown. Moreover we present a class skew analysis based on the metrics precision and recall.

U2 - 10.1109/PCTHEALTH.2006.361624

DO - 10.1109/PCTHEALTH.2006.361624

M3 - Conference contribution

SN - 1-4244-1085-1

SP - 4205194-

BT - Proceedings 2006 Pervasive Health Conference and Workshops, PervasiveHealth, 29 November 2006 through 1 December 2006, Innsbruck

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

ER -

Methods for detection and classification of normal swallowing from muscle activation and sound

Abstract

Access to Document

Fingerprint

Cite this