Home > Research > Publications & Outputs > Beyond activity recognition

Research

Links

Text available via DOI:

Keywords

View graph of relations

Beyond activity recognition: skill assessment from accelerometer data

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Beyond activity recognition: skill assessment from accelerometer data. / Khan, Aftab; Mellor, Sebastian; Berlin, Eugen et al.
UbiComp 2015 - Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing. New York: Association for Computing Machinery, Inc, 2015. p. 1155-1166.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Khan, A, Mellor, S, Berlin, E, Thompson, R, McNaney, R, Olivier, P & Plötz, T 2015, Beyond activity recognition: skill assessment from accelerometer data. in UbiComp 2015 - Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Association for Computing Machinery, Inc, New York, pp. 1155-1166, 3rd ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2015, Osaka, Japan, 7/09/15. https://doi.org/10.1145/2750858.2807534

APA

Khan, A., Mellor, S., Berlin, E., Thompson, R., McNaney, R., Olivier, P., & Plötz, T. (2015). Beyond activity recognition: skill assessment from accelerometer data. In UbiComp 2015 - Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing (pp. 1155-1166). Association for Computing Machinery, Inc. https://doi.org/10.1145/2750858.2807534

Vancouver

Khan A, Mellor S, Berlin E, Thompson R, McNaney R, Olivier P et al. Beyond activity recognition: skill assessment from accelerometer data. In UbiComp 2015 - Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing. New York: Association for Computing Machinery, Inc. 2015. p. 1155-1166 doi: 10.1145/2750858.2807534

Author

Khan, Aftab ; Mellor, Sebastian ; Berlin, Eugen et al. / Beyond activity recognition : skill assessment from accelerometer data. UbiComp 2015 - Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing. New York : Association for Computing Machinery, Inc, 2015. pp. 1155-1166

Bibtex

@inproceedings{ae61d3cb0dde4b36ae796d9053b6e649,
title = "Beyond activity recognition: skill assessment from accelerometer data",
abstract = "The next generation of human activity recognition applications in ubiquitous computing scenarios focuses on assessing the quality of activities, which goes beyond mere identification of activities of interest. Objective quality assessments are often difficult to achieve, hard to quantify, and typically require domain specific background information that bias the overall judgement and limit generalisation. In this paper we propose a framework for skill assessment in activity recognition that enables automatic quality analysis of human activities. Our approach is based on a hierarchical rule induction technique that effectively abstracts from noise-prone activity data and assesses activity data at different temporal contexts. Our approach requires minimal domain specific knowledge about the activities of interest, which makes it largely generalisable. By means of an extensive case study we demonstrate the effectiveness of the proposed framework in the context of dexterity training of 15 medical students engaging in 50 attempts of surgical activities.",
keywords = "Accelerometer, Activity Recognition, Classification, Rule induction, Skill Assessment",
author = "Aftab Khan and Sebastian Mellor and Eugen Berlin and Robin Thompson and Roisin McNaney and Patrick Olivier and Thomas Pl{\"o}tz",
year = "2015",
month = sep,
day = "7",
doi = "10.1145/2750858.2807534",
language = "English",
pages = "1155--1166",
booktitle = "UbiComp 2015 - Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing",
publisher = "Association for Computing Machinery, Inc",
note = "3rd ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2015 ; Conference date: 07-09-2015 Through 11-09-2015",

}

RIS

TY - GEN

T1 - Beyond activity recognition

T2 - 3rd ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2015

AU - Khan, Aftab

AU - Mellor, Sebastian

AU - Berlin, Eugen

AU - Thompson, Robin

AU - McNaney, Roisin

AU - Olivier, Patrick

AU - Plötz, Thomas

PY - 2015/9/7

Y1 - 2015/9/7

N2 - The next generation of human activity recognition applications in ubiquitous computing scenarios focuses on assessing the quality of activities, which goes beyond mere identification of activities of interest. Objective quality assessments are often difficult to achieve, hard to quantify, and typically require domain specific background information that bias the overall judgement and limit generalisation. In this paper we propose a framework for skill assessment in activity recognition that enables automatic quality analysis of human activities. Our approach is based on a hierarchical rule induction technique that effectively abstracts from noise-prone activity data and assesses activity data at different temporal contexts. Our approach requires minimal domain specific knowledge about the activities of interest, which makes it largely generalisable. By means of an extensive case study we demonstrate the effectiveness of the proposed framework in the context of dexterity training of 15 medical students engaging in 50 attempts of surgical activities.

AB - The next generation of human activity recognition applications in ubiquitous computing scenarios focuses on assessing the quality of activities, which goes beyond mere identification of activities of interest. Objective quality assessments are often difficult to achieve, hard to quantify, and typically require domain specific background information that bias the overall judgement and limit generalisation. In this paper we propose a framework for skill assessment in activity recognition that enables automatic quality analysis of human activities. Our approach is based on a hierarchical rule induction technique that effectively abstracts from noise-prone activity data and assesses activity data at different temporal contexts. Our approach requires minimal domain specific knowledge about the activities of interest, which makes it largely generalisable. By means of an extensive case study we demonstrate the effectiveness of the proposed framework in the context of dexterity training of 15 medical students engaging in 50 attempts of surgical activities.

KW - Accelerometer

KW - Activity Recognition

KW - Classification

KW - Rule induction

KW - Skill Assessment

U2 - 10.1145/2750858.2807534

DO - 10.1145/2750858.2807534

M3 - Conference contribution/Paper

AN - SCOPUS:84960857809

SP - 1155

EP - 1166

BT - UbiComp 2015 - Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing

PB - Association for Computing Machinery, Inc

CY - New York

Y2 - 7 September 2015 through 11 September 2015

ER -