Towards realtime measurement of connectedness in human movement

Michael Krzyzaniak; Rushil Anirudh; Vinay Venkataraman; Pavan Turaga; Sha Xin Wei

doi:10.1145/2790994.2791012

Towards realtime measurement of connectedness in human movement

Michael Krzyzaniak, Rushil Anirudh, Vinay Venkataraman, Pavan Turaga, Sha Xin Wei

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

Abstract

With the proliferation of wearable sensors, we have access to rich information regarding human movement that gives us insights into our daily activities like never before. In a sensor rich environment, it is desirable to build systems that are aware of human interactions by studying contextual information. In this paper, we attempt to quantify one such contextual cue - the connectedness of physical movement. Inspired by the Semblance of Typology Entrainments, we estimate the connectedness of trained dancers as observed from inertial sensors, using a diverse set of techniques such as quaternion correlation, approximate entropy, Fourier temporal pyramids, and discrete cosine transform. Preliminary experiments show that it is possible to robustly estimate connectedness that is invariant to frequency, amplitude, noise or time lag.

Original language	English (US)
Title of host publication	ACM International Conference Proceeding Series
Publisher	Association for Computing Machinery
Pages	120-123
Number of pages	4
Volume	14-15-August-2015
ISBN (Print)	9781450334570
DOIs	https://doi.org/10.1145/2790994.2791012
State	Published - Aug 14 2015
Event	2nd International Workshop on Movement and Computing, MOCO 2015 - Vancouver, Canada Duration: Aug 14 2015 → Aug 15 2015

Other

Other	2nd International Workshop on Movement and Computing, MOCO 2015
Country	Canada
City	Vancouver
Period	8/14/15 → 8/15/15

Keywords

Automated society
Automation
CHI
Connectedness
Correlation
Cross approximate entropy
Discrete cosine transform
Fourier temporal pyramids
Group intention
Group movement
HCI
Human movement
Social signal processing
Time series analysis
Wearable sensing

ASJC Scopus subject areas

Human-Computer Interaction
Computer Networks and Communications
Computer Vision and Pattern Recognition
Software

Access to Document

10.1145/2790994.2791012

Fingerprint Dive into the research topics of 'Towards realtime measurement of connectedness in human movement'. Together they form a unique fingerprint.

Cite this

Krzyzaniak, M, Anirudh, R, Venkataraman, V, Turaga, P & Wei, SX 2015, Towards realtime measurement of connectedness in human movement. in ACM International Conference Proceeding Series. vol. 14-15-August-2015, Association for Computing Machinery, pp. 120-123, 2nd International Workshop on Movement and Computing, MOCO 2015, Vancouver, Canada, 8/14/15. https://doi.org/10.1145/2790994.2791012

@inproceedings{7fa96c4148504cb48e1b6c51602e0ba1,

title = "Towards realtime measurement of connectedness in human movement",

abstract = "With the proliferation of wearable sensors, we have access to rich information regarding human movement that gives us insights into our daily activities like never before. In a sensor rich environment, it is desirable to build systems that are aware of human interactions by studying contextual information. In this paper, we attempt to quantify one such contextual cue - the connectedness of physical movement. Inspired by the Semblance of Typology Entrainments, we estimate the connectedness of trained dancers as observed from inertial sensors, using a diverse set of techniques such as quaternion correlation, approximate entropy, Fourier temporal pyramids, and discrete cosine transform. Preliminary experiments show that it is possible to robustly estimate connectedness that is invariant to frequency, amplitude, noise or time lag.",

keywords = "Automated society, Automation, CHI, Connectedness, Correlation, Cross approximate entropy, Discrete cosine transform, Fourier temporal pyramids, Group intention, Group movement, HCI, Human movement, Social signal processing, Time series analysis, Wearable sensing",

author = "Michael Krzyzaniak and Rushil Anirudh and Vinay Venkataraman and Pavan Turaga and Wei, {Sha Xin}",

year = "2015",

month = aug,

day = "14",

doi = "10.1145/2790994.2791012",

language = "English (US)",

isbn = "9781450334570",

volume = "14-15-August-2015",

pages = "120--123",

booktitle = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

note = "2nd International Workshop on Movement and Computing, MOCO 2015 ; Conference date: 14-08-2015 Through 15-08-2015",

}

TY - GEN

T1 - Towards realtime measurement of connectedness in human movement

AU - Krzyzaniak, Michael

AU - Anirudh, Rushil

AU - Venkataraman, Vinay

AU - Turaga, Pavan

AU - Wei, Sha Xin

PY - 2015/8/14

Y1 - 2015/8/14

N2 - With the proliferation of wearable sensors, we have access to rich information regarding human movement that gives us insights into our daily activities like never before. In a sensor rich environment, it is desirable to build systems that are aware of human interactions by studying contextual information. In this paper, we attempt to quantify one such contextual cue - the connectedness of physical movement. Inspired by the Semblance of Typology Entrainments, we estimate the connectedness of trained dancers as observed from inertial sensors, using a diverse set of techniques such as quaternion correlation, approximate entropy, Fourier temporal pyramids, and discrete cosine transform. Preliminary experiments show that it is possible to robustly estimate connectedness that is invariant to frequency, amplitude, noise or time lag.

AB - With the proliferation of wearable sensors, we have access to rich information regarding human movement that gives us insights into our daily activities like never before. In a sensor rich environment, it is desirable to build systems that are aware of human interactions by studying contextual information. In this paper, we attempt to quantify one such contextual cue - the connectedness of physical movement. Inspired by the Semblance of Typology Entrainments, we estimate the connectedness of trained dancers as observed from inertial sensors, using a diverse set of techniques such as quaternion correlation, approximate entropy, Fourier temporal pyramids, and discrete cosine transform. Preliminary experiments show that it is possible to robustly estimate connectedness that is invariant to frequency, amplitude, noise or time lag.

KW - Automated society

KW - Automation

KW - CHI

KW - Connectedness

KW - Correlation

KW - Cross approximate entropy

KW - Discrete cosine transform

KW - Fourier temporal pyramids

KW - Group intention

KW - Group movement

KW - HCI

KW - Human movement

KW - Social signal processing

KW - Time series analysis

KW - Wearable sensing

UR - http://www.scopus.com/inward/record.url?scp=84958553875&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958553875&partnerID=8YFLogxK

U2 - 10.1145/2790994.2791012

DO - 10.1145/2790994.2791012

M3 - Conference contribution

AN - SCOPUS:84958553875

SN - 9781450334570

VL - 14-15-August-2015

SP - 120

EP - 123

BT - ACM International Conference Proceeding Series

PB - Association for Computing Machinery

T2 - 2nd International Workshop on Movement and Computing, MOCO 2015

Y2 - 14 August 2015 through 15 August 2015

ER -