Move well, move often: Understanding motor competence in children and young people: New horizons in movement skill assessment: sensors

Cain Clark, Gareth Stratton, Claire M. Barnes, Huw D. Summers, Paul Rees

Research output: Contribution to journalMeeting Abstract

Abstract

Introduction: Accelerometers are widely used to study physical activity and have been shown to be informative of motion mechanics. Whilst Process-oriented assessment is an important tool in the development of children’s fundamental movement skills, current methods of assessment are cumbersome and subjective. We present a novel analysis framework for activity assessment that uses accelerometry to create sophisticated motion maps and demonstrate their utility in profiling and categorising movement mechanics, objectively, in a diverse range of fundamental movements. Methods: Acceleration data were collected from ankle and wrist mounted sensors. Children aged 9 - 12 years were assessed in a multi-stage fitness test and a fundamental movement skill (FMS) challenge. Acceleration and magnetometer data were used to construct spectrograms, phase maps of motion and a performance sphere. Specific activity components were analysed through pattern recognition using machine learning, and dynamic time-warping. Results: Novel analyses of FMS displayed patterns clearly linked to specific activities such as throwing, jumping and body roll. These were sufficient to classify performance into activity categories using pattern recognition and a training set from expert observer scores. Discussion: Novel analyses of children’s mechanical motion patterns can be achieved for FMS using lightweight, low cost wearable sensors. These motion maps can be predictive of performance based on limited sampling allowing population profiling of FMS. Further, the use of computerised pattern recognition and classification gives an objective scoring of complex motion, normally requiring subjective assessment by expert human observers
Original languageEnglish
JournalJournal of Physical Activity & Health
Volume15
Issue number(S1-S249)
DOIs
Publication statusPublished - Oct 2018
Event7th International Society for Physical Activity and Health Congress (ISPAH) - Queen Elizabeth II Conference Centre, London, United Kingdom
Duration: 15 Oct 201817 Oct 2018

Fingerprint

Mental Competency
Mechanics
Accelerometry
Process Assessment (Health Care)
Wrist
Ankle
Exercise
Costs and Cost Analysis
Population

Cite this

Move well, move often: Understanding motor competence in children and young people: New horizons in movement skill assessment: sensors. / Clark, Cain; Stratton, Gareth; Barnes, Claire M.; Summers, Huw D.; Rees, Paul.

In: Journal of Physical Activity & Health, Vol. 15, No. (S1-S249), 10.2018.

Research output: Contribution to journalMeeting Abstract

@article{389c66134fc9452ea063b609487c457a,
title = "Move well, move often: Understanding motor competence in children and young people: New horizons in movement skill assessment: sensors",
abstract = "Introduction: Accelerometers are widely used to study physical activity and have been shown to be informative of motion mechanics. Whilst Process-oriented assessment is an important tool in the development of children’s fundamental movement skills, current methods of assessment are cumbersome and subjective. We present a novel analysis framework for activity assessment that uses accelerometry to create sophisticated motion maps and demonstrate their utility in profiling and categorising movement mechanics, objectively, in a diverse range of fundamental movements. Methods: Acceleration data were collected from ankle and wrist mounted sensors. Children aged 9 - 12 years were assessed in a multi-stage fitness test and a fundamental movement skill (FMS) challenge. Acceleration and magnetometer data were used to construct spectrograms, phase maps of motion and a performance sphere. Specific activity components were analysed through pattern recognition using machine learning, and dynamic time-warping. Results: Novel analyses of FMS displayed patterns clearly linked to specific activities such as throwing, jumping and body roll. These were sufficient to classify performance into activity categories using pattern recognition and a training set from expert observer scores. Discussion: Novel analyses of children’s mechanical motion patterns can be achieved for FMS using lightweight, low cost wearable sensors. These motion maps can be predictive of performance based on limited sampling allowing population profiling of FMS. Further, the use of computerised pattern recognition and classification gives an objective scoring of complex motion, normally requiring subjective assessment by expert human observers",
author = "Cain Clark and Gareth Stratton and Barnes, {Claire M.} and Summers, {Huw D.} and Paul Rees",
year = "2018",
month = "10",
doi = "10.1123/jpah.2018-0535",
language = "English",
volume = "15",
journal = "Journal of Physical Activity & Health",
number = "(S1-S249)",

}

TY - JOUR

T1 - Move well, move often: Understanding motor competence in children and young people: New horizons in movement skill assessment: sensors

AU - Clark, Cain

AU - Stratton, Gareth

AU - Barnes, Claire M.

AU - Summers, Huw D.

AU - Rees, Paul

PY - 2018/10

Y1 - 2018/10

N2 - Introduction: Accelerometers are widely used to study physical activity and have been shown to be informative of motion mechanics. Whilst Process-oriented assessment is an important tool in the development of children’s fundamental movement skills, current methods of assessment are cumbersome and subjective. We present a novel analysis framework for activity assessment that uses accelerometry to create sophisticated motion maps and demonstrate their utility in profiling and categorising movement mechanics, objectively, in a diverse range of fundamental movements. Methods: Acceleration data were collected from ankle and wrist mounted sensors. Children aged 9 - 12 years were assessed in a multi-stage fitness test and a fundamental movement skill (FMS) challenge. Acceleration and magnetometer data were used to construct spectrograms, phase maps of motion and a performance sphere. Specific activity components were analysed through pattern recognition using machine learning, and dynamic time-warping. Results: Novel analyses of FMS displayed patterns clearly linked to specific activities such as throwing, jumping and body roll. These were sufficient to classify performance into activity categories using pattern recognition and a training set from expert observer scores. Discussion: Novel analyses of children’s mechanical motion patterns can be achieved for FMS using lightweight, low cost wearable sensors. These motion maps can be predictive of performance based on limited sampling allowing population profiling of FMS. Further, the use of computerised pattern recognition and classification gives an objective scoring of complex motion, normally requiring subjective assessment by expert human observers

AB - Introduction: Accelerometers are widely used to study physical activity and have been shown to be informative of motion mechanics. Whilst Process-oriented assessment is an important tool in the development of children’s fundamental movement skills, current methods of assessment are cumbersome and subjective. We present a novel analysis framework for activity assessment that uses accelerometry to create sophisticated motion maps and demonstrate their utility in profiling and categorising movement mechanics, objectively, in a diverse range of fundamental movements. Methods: Acceleration data were collected from ankle and wrist mounted sensors. Children aged 9 - 12 years were assessed in a multi-stage fitness test and a fundamental movement skill (FMS) challenge. Acceleration and magnetometer data were used to construct spectrograms, phase maps of motion and a performance sphere. Specific activity components were analysed through pattern recognition using machine learning, and dynamic time-warping. Results: Novel analyses of FMS displayed patterns clearly linked to specific activities such as throwing, jumping and body roll. These were sufficient to classify performance into activity categories using pattern recognition and a training set from expert observer scores. Discussion: Novel analyses of children’s mechanical motion patterns can be achieved for FMS using lightweight, low cost wearable sensors. These motion maps can be predictive of performance based on limited sampling allowing population profiling of FMS. Further, the use of computerised pattern recognition and classification gives an objective scoring of complex motion, normally requiring subjective assessment by expert human observers

U2 - 10.1123/jpah.2018-0535

DO - 10.1123/jpah.2018-0535

M3 - Meeting Abstract

VL - 15

JO - Journal of Physical Activity & Health

JF - Journal of Physical Activity & Health

IS - (S1-S249)

ER -