GymSkill: A personal trainer for physical exercises

Andreas Moller; Luis Roalter; Stefan Diewald; Johannes Scherr; Matthias Kranz; Nils Hammerla; Patrick Olivier; Thomas Plotz

doi:10.1109/PerCom.2012.6199869

GymSkill: A personal trainer for physical exercises

Andreas Moller, Luis Roalter, Stefan Diewald, Johannes Scherr, Matthias Kranz, Nils Hammerla, Patrick Olivier, Thomas Plotz

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

44 Citations (Scopus)

Abstract

We present GymSkill, a personal trainer for ubiquitous monitoring and assessment of physical activity using standard fitness equipment. The system records and analyzes exercises using the sensors of a personal smartphone attached to the gym equipment. Novel fine-grained activity recognition techniques based on pyramidal Principal Component Breakdown Analysis (PCBA) provide a quantitative analysis of the quality of human movements. In addition to overall quality judgments, GymSkill identifies interesting portions of the recorded sensor data and provides suggestions for improving the individual performance, thereby extending existing work. The system was evaluated in a case study where 6 participants performed a variety of exercises on balance boards. GymSkill successfully assessed the quality of the exercises, in agreement with the professional judgment provided by a physician. User feedback suggests that GymSkill has the potential to serve as an effective tool for motivating and supporting lay people to overcome sedentary, unhealthy lifestyles. GymSkill is available in the Android Market as VMI Fit.

Original language	English
Title of host publication	2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012
Pages	213-220
Number of pages	8
DOIs	https://doi.org/10.1109/PerCom.2012.6199869
Publication status	Published - 4 Jun 2012
Event	IEEE International Conference on Pervasive Computing and Communications 2012 - Lugano, Switzerland Duration: 19 Mar 2012 → 23 Mar 2012 Conference number: 10th http://www.percom.org/Previous/ST2012/ https://ieeexplore.ieee.org/xpl/conhome/6192377/proceeding (Proceedings)

Conference

Conference	IEEE International Conference on Pervasive Computing and Communications 2012
Abbreviated title	PerCom 2012
Country/Territory	Switzerland
City	Lugano
Period	19/03/12 → 23/03/12
Internet address	http://www.percom.org/Previous/ST2012/ https://ieeexplore.ieee.org/xpl/conhome/6192377/proceeding (Proceedings)

Keywords

Activity recognition
Health
Mobile
Quantitative time-series analysis
Skill assessment

Access to Document

10.1109/PerCom.2012.6199869

Cite this

@inproceedings{748004e97b864feea1ee0b5386b575df,

title = "GymSkill: A personal trainer for physical exercises",

abstract = "We present GymSkill, a personal trainer for ubiquitous monitoring and assessment of physical activity using standard fitness equipment. The system records and analyzes exercises using the sensors of a personal smartphone attached to the gym equipment. Novel fine-grained activity recognition techniques based on pyramidal Principal Component Breakdown Analysis (PCBA) provide a quantitative analysis of the quality of human movements. In addition to overall quality judgments, GymSkill identifies interesting portions of the recorded sensor data and provides suggestions for improving the individual performance, thereby extending existing work. The system was evaluated in a case study where 6 participants performed a variety of exercises on balance boards. GymSkill successfully assessed the quality of the exercises, in agreement with the professional judgment provided by a physician. User feedback suggests that GymSkill has the potential to serve as an effective tool for motivating and supporting lay people to overcome sedentary, unhealthy lifestyles. GymSkill is available in the Android Market as VMI Fit.",

keywords = "Activity recognition, Health, Mobile, Quantitative time-series analysis, Skill assessment",

author = "Andreas Moller and Luis Roalter and Stefan Diewald and Johannes Scherr and Matthias Kranz and Nils Hammerla and Patrick Olivier and Thomas Plotz",

year = "2012",

month = jun,

day = "4",

doi = "10.1109/PerCom.2012.6199869",

language = "English",

isbn = "9781467302586",

pages = "213--220",

booktitle = "2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012",

note = "IEEE International Conference on Pervasive Computing and Communications 2012, PerCom 2012 ; Conference date: 19-03-2012 Through 23-03-2012",

url = "http://www.percom.org/Previous/ST2012/, https://ieeexplore.ieee.org/xpl/conhome/6192377/proceeding",

}

Moller, A, Roalter, L, Diewald, S, Scherr, J, Kranz, M, Hammerla, N, Olivier, P & Plotz, T 2012, GymSkill: A personal trainer for physical exercises. in 2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012., 6199869, pp. 213-220, IEEE International Conference on Pervasive Computing and Communications 2012, Lugano, Switzerland, 19/03/12. https://doi.org/10.1109/PerCom.2012.6199869

TY - GEN

T1 - GymSkill

T2 - IEEE International Conference on Pervasive Computing and Communications 2012

AU - Moller, Andreas

AU - Roalter, Luis

AU - Diewald, Stefan

AU - Scherr, Johannes

AU - Kranz, Matthias

AU - Hammerla, Nils

AU - Olivier, Patrick

AU - Plotz, Thomas

N1 - Conference code: 10th

PY - 2012/6/4

Y1 - 2012/6/4

N2 - We present GymSkill, a personal trainer for ubiquitous monitoring and assessment of physical activity using standard fitness equipment. The system records and analyzes exercises using the sensors of a personal smartphone attached to the gym equipment. Novel fine-grained activity recognition techniques based on pyramidal Principal Component Breakdown Analysis (PCBA) provide a quantitative analysis of the quality of human movements. In addition to overall quality judgments, GymSkill identifies interesting portions of the recorded sensor data and provides suggestions for improving the individual performance, thereby extending existing work. The system was evaluated in a case study where 6 participants performed a variety of exercises on balance boards. GymSkill successfully assessed the quality of the exercises, in agreement with the professional judgment provided by a physician. User feedback suggests that GymSkill has the potential to serve as an effective tool for motivating and supporting lay people to overcome sedentary, unhealthy lifestyles. GymSkill is available in the Android Market as VMI Fit.

AB - We present GymSkill, a personal trainer for ubiquitous monitoring and assessment of physical activity using standard fitness equipment. The system records and analyzes exercises using the sensors of a personal smartphone attached to the gym equipment. Novel fine-grained activity recognition techniques based on pyramidal Principal Component Breakdown Analysis (PCBA) provide a quantitative analysis of the quality of human movements. In addition to overall quality judgments, GymSkill identifies interesting portions of the recorded sensor data and provides suggestions for improving the individual performance, thereby extending existing work. The system was evaluated in a case study where 6 participants performed a variety of exercises on balance boards. GymSkill successfully assessed the quality of the exercises, in agreement with the professional judgment provided by a physician. User feedback suggests that GymSkill has the potential to serve as an effective tool for motivating and supporting lay people to overcome sedentary, unhealthy lifestyles. GymSkill is available in the Android Market as VMI Fit.

KW - Activity recognition

KW - Health

KW - Mobile

KW - Quantitative time-series analysis

KW - Skill assessment

UR - http://www.scopus.com/inward/record.url?scp=84861635367&partnerID=8YFLogxK

U2 - 10.1109/PerCom.2012.6199869

DO - 10.1109/PerCom.2012.6199869

M3 - Conference Paper

AN - SCOPUS:84861635367

SN - 9781467302586

SP - 213

EP - 220

BT - 2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012

Y2 - 19 March 2012 through 23 March 2012

ER -

GymSkill: A personal trainer for physical exercises

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this