Unsupervised Learning In Body-Area Networks

Nicola Bicocchi; Matteo Lasagni; Marco Mamei; Andrea Prati; Rita Cucchiara; Franco Zambonelli

doi:10.1145/2221924.2221955

Unsupervised Learning In Body-Area Networks

Nicola Bicocchi, Matteo Lasagni, Marco Mamei, Andrea Prati, Rita Cucchiara, Franco Zambonelli

Institute of Computer Engineering

1 Citation (Scopus)

Abstract

Pattern recognition is becoming a key application in body-area networks. This paper presents a framework promoting unsupervised training for multi-modal, multi-sensor classification systems. Specifically, it enables sensors provided with pattern-recognition capabilities to autonomously supervise the learning process of other sensors. The approach is discussed using a case study combining a smart camera and a body-worn accelerometer. The body-worn accelerometer sensor is trained to recognize four user activities pairing accelerometer data with labels coming from the camera. Experimental results illustrate the applicability of the approach in different conditions. © 2010 ACM.

Original language	English
Title of host publication	BodyNets '10 Proceedings of the Fifth International Conference on Body Area Networks Pages 164-170
Number of pages	7
Publisher	ACM
Publication date	01.12.2011
Pages	164-170
ISBN (Print)	978-193696830-5
DOIs	https://doi.org/10.1145/2221924.2221955
Publication status	Published - 01.12.2011
Event	5th International ICST Conference on Body Area Networks - Corfu, Greece Duration: 10.09.2010 → 12.09.2010 Conference number: 90561

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Access to Document

10.1145/2221924.2221955

Cite this

@inproceedings{1f81f877bfb54252a1353c86ff9e5191,

title = "Unsupervised Learning In Body-Area Networks",

abstract = "Pattern recognition is becoming a key application in body-area networks. This paper presents a framework promoting unsupervised training for multi-modal, multi-sensor classification systems. Specifically, it enables sensors provided with pattern-recognition capabilities to autonomously supervise the learning process of other sensors. The approach is discussed using a case study combining a smart camera and a body-worn accelerometer. The body-worn accelerometer sensor is trained to recognize four user activities pairing accelerometer data with labels coming from the camera. Experimental results illustrate the applicability of the approach in different conditions. {\textcopyright} 2010 ACM. ",

author = "Nicola Bicocchi and Matteo Lasagni and Marco Mamei and Andrea Prati and Rita Cucchiara and Franco Zambonelli",

year = "2011",

month = dec,

day = "1",

doi = "10.1145/2221924.2221955",

language = "English",

isbn = "978-193696830-5",

series = "SIGCHI ACM Special Interest Group on Computer-Human Interaction",

publisher = "ACM",

pages = "164--170",

booktitle = "BodyNets '10 Proceedings of the Fifth International Conference on Body Area Networks Pages 164-170",

note = "5th International ICST Conference on Body Area Networks <br/>, BodyNets 2010 ; Conference date: 10-09-2010 Through 12-09-2010",

}

Bicocchi, N, Lasagni, M, Mamei, M, Prati, A, Cucchiara, R & Zambonelli, F 2011, Unsupervised Learning In Body-Area Networks. in BodyNets '10 Proceedings of the Fifth International Conference on Body Area Networks Pages 164-170. SIGCHI ACM Special Interest Group on Computer-Human Interaction, ACM, pp. 164-170, 5th International ICST Conference on Body Area Networks
, Corfu, Greece, 10.09.10. https://doi.org/10.1145/2221924.2221955

Unsupervised Learning In Body-Area Networks. / Bicocchi, Nicola; Lasagni, Matteo; Mamei, Marco et al.
BodyNets '10 Proceedings of the Fifth International Conference on Body Area Networks Pages 164-170. ACM, 2011. p. 164-170 (SIGCHI ACM Special Interest Group on Computer-Human Interaction).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Unsupervised Learning In Body-Area Networks

AU - Bicocchi, Nicola

AU - Lasagni, Matteo

AU - Mamei, Marco

AU - Prati, Andrea

AU - Cucchiara, Rita

AU - Zambonelli, Franco

N1 - Conference code: 90561

PY - 2011/12/1

Y1 - 2011/12/1

N2 - Pattern recognition is becoming a key application in body-area networks. This paper presents a framework promoting unsupervised training for multi-modal, multi-sensor classification systems. Specifically, it enables sensors provided with pattern-recognition capabilities to autonomously supervise the learning process of other sensors. The approach is discussed using a case study combining a smart camera and a body-worn accelerometer. The body-worn accelerometer sensor is trained to recognize four user activities pairing accelerometer data with labels coming from the camera. Experimental results illustrate the applicability of the approach in different conditions. © 2010 ACM.

AB - Pattern recognition is becoming a key application in body-area networks. This paper presents a framework promoting unsupervised training for multi-modal, multi-sensor classification systems. Specifically, it enables sensors provided with pattern-recognition capabilities to autonomously supervise the learning process of other sensors. The approach is discussed using a case study combining a smart camera and a body-worn accelerometer. The body-worn accelerometer sensor is trained to recognize four user activities pairing accelerometer data with labels coming from the camera. Experimental results illustrate the applicability of the approach in different conditions. © 2010 ACM.

UR - https://www.scopus.com/pages/publications/84862703470

U2 - 10.1145/2221924.2221955

DO - 10.1145/2221924.2221955

M3 - Conference contribution

SN - 978-193696830-5

T3 - SIGCHI ACM Special Interest Group on Computer-Human Interaction

SP - 164

EP - 170

BT - BodyNets '10 Proceedings of the Fifth International Conference on Body Area Networks Pages 164-170

PB - ACM

T2 - 5th International ICST Conference on Body Area Networks <br/>

Y2 - 10 September 2010 through 12 September 2010

ER -

Unsupervised Learning In Body-Area Networks

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this