BlobSnake: gamification of feature extraction for 'plug and play' human activity recognition

Reuben Kirkham; Carlton Shepherd; Thomas Plötz

doi:10.1145/2783446.2783579

BlobSnake: gamification of feature extraction for 'plug and play' human activity recognition

Reuben Kirkham, Carlton Shepherd, Thomas Plötz

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

Abstract

We present BlobSnake, a casual game designed to help generate new feature representations in the context of Human Activity Recognition. Feature selection is an essential task to be completed in the context of developing any non-trivial activity recognition system for a new set of activities. Presently, using anything other than a set of standard features requires a considerable amount of effort to be expended upon expert driven algorithm development. BlobSnake is an alternative approach which uses direct interaction with real sensor data by non-experts in order to develop additional features, thus lowering the cost and expertise otherwise required to produce more effective recognition performance. Our experiments demonstrate that our method improves upon the state of the art performance of standard features in a challenging recognition scenario.

Original language	English
Title of host publication	Proceedings of the British HCI Conference 2015
Editors	Patrick Olivier, Derek Foster
Place of Publication	New York NY USA
Publisher	Association for Computing Machinery (ACM)
Pages	74-81
Number of pages	8
ISBN (Electronic)	9781450336437
DOIs	https://doi.org/10.1145/2783446.2783579
Publication status	Published - 2015
Externally published	Yes
Event	British Computer Society Conference on Human-Computer Interaction 2015 - Lincoln, United Kingdom Duration: 13 Jul 2015 → 17 Jul 2015 https://british-hci2015.org/

Conference

Conference	British Computer Society Conference on Human-Computer Interaction 2015
Abbreviated title	HCI 2015
Country	United Kingdom
City	Lincoln
Period	13/07/15 → 17/07/15
Internet address	https://british-hci2015.org/

Keywords

Crowdsourcing
Gameification
Human Activity Recognition
Machine Learning

Access to Document

10.1145/2783446.2783579

Link to publication in Scopus

Cite this

@inproceedings{47320ce7fc584aa08446d62b864eca91,

title = "BlobSnake: gamification of feature extraction for 'plug and play' human activity recognition",

abstract = "We present BlobSnake, a casual game designed to help generate new feature representations in the context of Human Activity Recognition. Feature selection is an essential task to be completed in the context of developing any non-trivial activity recognition system for a new set of activities. Presently, using anything other than a set of standard features requires a considerable amount of effort to be expended upon expert driven algorithm development. BlobSnake is an alternative approach which uses direct interaction with real sensor data by non-experts in order to develop additional features, thus lowering the cost and expertise otherwise required to produce more effective recognition performance. Our experiments demonstrate that our method improves upon the state of the art performance of standard features in a challenging recognition scenario.",

keywords = "Crowdsourcing, Gameification, Human Activity Recognition, Machine Learning",

author = "Reuben Kirkham and Carlton Shepherd and Thomas Pl{\"o}tz",

year = "2015",

doi = "10.1145/2783446.2783579",

language = "English",

pages = "74--81",

editor = "Olivier, {Patrick } and Foster, {Derek }",

booktitle = "Proceedings of the British HCI Conference 2015",

publisher = "Association for Computing Machinery (ACM)",

address = "United States of America",

note = "British Computer Society Conference on Human-Computer Interaction 2015, HCI 2015 ; Conference date: 13-07-2015 Through 17-07-2015",

url = "https://british-hci2015.org/",

}

Kirkham, R, Shepherd, C & Plötz, T 2015, BlobSnake: gamification of feature extraction for 'plug and play' human activity recognition. in P Olivier & D Foster (eds), Proceedings of the British HCI Conference 2015. Association for Computing Machinery (ACM), New York NY USA, pp. 74-81, British Computer Society Conference on Human-Computer Interaction 2015, Lincoln, United Kingdom, 13/07/15. https://doi.org/10.1145/2783446.2783579

BlobSnake : gamification of feature extraction for 'plug and play' human activity recognition. / Kirkham, Reuben; Shepherd, Carlton; Plötz, Thomas.

Proceedings of the British HCI Conference 2015. ed. / Patrick Olivier; Derek Foster. New York NY USA : Association for Computing Machinery (ACM), 2015. p. 74-81.

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

TY - GEN

T1 - BlobSnake

T2 - British Computer Society Conference on Human-Computer Interaction 2015

AU - Kirkham, Reuben

AU - Shepherd, Carlton

AU - Plötz, Thomas

PY - 2015

Y1 - 2015

N2 - We present BlobSnake, a casual game designed to help generate new feature representations in the context of Human Activity Recognition. Feature selection is an essential task to be completed in the context of developing any non-trivial activity recognition system for a new set of activities. Presently, using anything other than a set of standard features requires a considerable amount of effort to be expended upon expert driven algorithm development. BlobSnake is an alternative approach which uses direct interaction with real sensor data by non-experts in order to develop additional features, thus lowering the cost and expertise otherwise required to produce more effective recognition performance. Our experiments demonstrate that our method improves upon the state of the art performance of standard features in a challenging recognition scenario.

AB - We present BlobSnake, a casual game designed to help generate new feature representations in the context of Human Activity Recognition. Feature selection is an essential task to be completed in the context of developing any non-trivial activity recognition system for a new set of activities. Presently, using anything other than a set of standard features requires a considerable amount of effort to be expended upon expert driven algorithm development. BlobSnake is an alternative approach which uses direct interaction with real sensor data by non-experts in order to develop additional features, thus lowering the cost and expertise otherwise required to produce more effective recognition performance. Our experiments demonstrate that our method improves upon the state of the art performance of standard features in a challenging recognition scenario.

KW - Crowdsourcing

KW - Gameification

KW - Human Activity Recognition

KW - Machine Learning

UR - http://www.scopus.com/inward/record.url?scp=85015425314&partnerID=8YFLogxK

U2 - 10.1145/2783446.2783579

DO - 10.1145/2783446.2783579

M3 - Conference Paper

AN - SCOPUS:85015425314

SP - 74

EP - 81

BT - Proceedings of the British HCI Conference 2015

A2 - Olivier, Patrick

A2 - Foster, Derek

PB - Association for Computing Machinery (ACM)

CY - New York NY USA

Y2 - 13 July 2015 through 17 July 2015

ER -