Performance analysis of self-organising neural networks tracking algorithms for intake monitoring using kinect

Samuele Gasparrini; Enea Cippitelli; Ennio Gambi; Susanna Spinsante; Francisco Florez Revuelta

doi:10.1049/ic.2015.0133

Performance analysis of self-organising neural networks tracking algorithms for intake monitoring using kinect

Samuele Gasparrini
, Enea Cippitelli
, Ennio Gambi
, Susanna Spinsante
, Francisco Florez Revuelta

Kingston University

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

Abstract

The analysis of intake behaviour is a key factor to understand the health condition of a subject, such as elderly or people affected by diet-related disorders. The technology can be exploited for this purpose to promptly identify anomalous situations. This paper presents a comparison between three unsupervised machine learning algorithms used to track the movements performed by a person during an intake action and provides experimental results showing the best performing algorithm among those compared.

Original language	English
Title of host publication	Proceedings of IET International Conference on Technologies for Active and Assisted Living (TechAAL)
Editors	Samuele Gasparrini, Enea Cippitelli, Ennio Gambi, Susanna Spinsante, Francisco Florez Revuelta
Publisher	Institution of Engineering and Technology
ISBN (Print)	9781785611599
DOIs	https://doi.org/10.1049/ic.2015.0133
Publication status	Published - 2015
Externally published	Yes
Event	IET International Conference on Technologies for Active and Assisted Living (TechAAL 2015) - Kingston upon Thames, U.K. Duration: 5 Nov 2015 → 5 Nov 2015

Conference

Conference	IET International Conference on Technologies for Active and Assisted Living (TechAAL 2015)
Period	5/11/15 → 5/11/15

Bibliographical note

Organising Body: Institution of Engineering and Technology (IET), Kingston University London.

Keywords

Computer science and informatics

Access to Document

10.1049/ic.2015.0133

Cite this

Gasparrini, S., Cippitelli, E., Gambi, E., Spinsante, S., & Florez Revuelta, F. (2015). Performance analysis of self-organising neural networks tracking algorithms for intake monitoring using kinect. In S. Gasparrini, E. Cippitelli, E. Gambi, S. Spinsante, & F. Florez Revuelta (Eds.), Proceedings of IET International Conference on Technologies for Active and Assisted Living (TechAAL) Institution of Engineering and Technology. https://doi.org/10.1049/ic.2015.0133

Gasparrini, Samuele ; Cippitelli, Enea ; Gambi, Ennio et al. / Performance analysis of self-organising neural networks tracking algorithms for intake monitoring using kinect. Proceedings of IET International Conference on Technologies for Active and Assisted Living (TechAAL). editor / Samuele Gasparrini ; Enea Cippitelli ; Ennio Gambi ; Susanna Spinsante ; Francisco Florez Revuelta. Institution of Engineering and Technology, 2015.

@inproceedings{a212401773b24e8dbc1fe253f6ad1aaa,

title = "Performance analysis of self-organising neural networks tracking algorithms for intake monitoring using kinect",

abstract = "The analysis of intake behaviour is a key factor to understand the health condition of a subject, such as elderly or people affected by diet-related disorders. The technology can be exploited for this purpose to promptly identify anomalous situations. This paper presents a comparison between three unsupervised machine learning algorithms used to track the movements performed by a person during an intake action and provides experimental results showing the best performing algorithm among those compared.",

keywords = "Computer science and informatics",

author = "Samuele Gasparrini and Enea Cippitelli and Ennio Gambi and Susanna Spinsante and \{Florez Revuelta\}, Francisco",

note = "Organising Body: Institution of Engineering and Technology (IET), Kingston University London.; IET International Conference on Technologies for Active and Assisted Living (TechAAL 2015) ; Conference date: 05-11-2015 Through 05-11-2015",

year = "2015",

doi = "10.1049/ic.2015.0133",

language = "English",

isbn = "9781785611599",

editor = "Samuele Gasparrini and Enea Cippitelli and Ennio Gambi and Susanna Spinsante and \{Florez Revuelta\}, Francisco",

booktitle = "Proceedings of IET International Conference on Technologies for Active and Assisted Living (TechAAL)",

publisher = "Institution of Engineering and Technology",

address = "United Kingdom",

}

Gasparrini, S, Cippitelli, E, Gambi, E, Spinsante, S & Florez Revuelta, F 2015, Performance analysis of self-organising neural networks tracking algorithms for intake monitoring using kinect. in S Gasparrini, E Cippitelli, E Gambi, S Spinsante & F Florez Revuelta (eds), Proceedings of IET International Conference on Technologies for Active and Assisted Living (TechAAL). Institution of Engineering and Technology, IET International Conference on Technologies for Active and Assisted Living (TechAAL 2015), 5/11/15. https://doi.org/10.1049/ic.2015.0133

Performance analysis of self-organising neural networks tracking algorithms for intake monitoring using kinect. / Gasparrini, Samuele; Cippitelli, Enea; Gambi, Ennio et al.
Proceedings of IET International Conference on Technologies for Active and Assisted Living (TechAAL). ed. / Samuele Gasparrini; Enea Cippitelli; Ennio Gambi; Susanna Spinsante; Francisco Florez Revuelta. Institution of Engineering and Technology, 2015.

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

TY - GEN

T1 - Performance analysis of self-organising neural networks tracking algorithms for intake monitoring using kinect

AU - Gasparrini, Samuele

AU - Cippitelli, Enea

AU - Gambi, Ennio

AU - Spinsante, Susanna

AU - Florez Revuelta, Francisco

N1 - Organising Body: Institution of Engineering and Technology (IET), Kingston University London.

PY - 2015

Y1 - 2015

N2 - The analysis of intake behaviour is a key factor to understand the health condition of a subject, such as elderly or people affected by diet-related disorders. The technology can be exploited for this purpose to promptly identify anomalous situations. This paper presents a comparison between three unsupervised machine learning algorithms used to track the movements performed by a person during an intake action and provides experimental results showing the best performing algorithm among those compared.

AB - The analysis of intake behaviour is a key factor to understand the health condition of a subject, such as elderly or people affected by diet-related disorders. The technology can be exploited for this purpose to promptly identify anomalous situations. This paper presents a comparison between three unsupervised machine learning algorithms used to track the movements performed by a person during an intake action and provides experimental results showing the best performing algorithm among those compared.

KW - Computer science and informatics

U2 - 10.1049/ic.2015.0133

DO - 10.1049/ic.2015.0133

M3 - Conference contribution

SN - 9781785611599

BT - Proceedings of IET International Conference on Technologies for Active and Assisted Living (TechAAL)

A2 - Gasparrini, Samuele

A2 - Cippitelli, Enea

A2 - Gambi, Ennio

A2 - Spinsante, Susanna

A2 - Florez Revuelta, Francisco

PB - Institution of Engineering and Technology

T2 - IET International Conference on Technologies for Active and Assisted Living (TechAAL 2015)

Y2 - 5 November 2015 through 5 November 2015

ER -

Gasparrini S, Cippitelli E, Gambi E, Spinsante S, Florez Revuelta F. Performance analysis of self-organising neural networks tracking algorithms for intake monitoring using kinect. In Gasparrini S, Cippitelli E, Gambi E, Spinsante S, Florez Revuelta F, editors, Proceedings of IET International Conference on Technologies for Active and Assisted Living (TechAAL). Institution of Engineering and Technology. 2015 doi: 10.1049/ic.2015.0133

Performance analysis of self-organising neural networks tracking algorithms for intake monitoring using kinect

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this