Objective profiling of varied human motion based on normative assessment of magnetometer time series data

• Published in: Physiological measurement 2018-04, Vol.39 (4), p.045007-045007
• Main Authors: Barnes, Claire M, Clark, Cain C T, Rees, Paul, Stratton, Gareth, Summers, Huw D
• Format: Article
• Language: English
• Subjects: dynamic time warping; magnetometer; movement skill; multi-dimensional scaling; physical activity; time series analysis
• ISSN: 0967-3334; 1361-6579; 1361-6579
• DOI: 10.1088/1361-6579/aab9de

Objective: To quantify varied human motion and obtain an objective assessment of relative performance across a cohort. Approach: A wrist-worn magnetometer was used to record and quantify the complex motion patterns of 55 children aged 10 to 12 years old, generated during a fundamental movement skills programme. Sensor-based quantification of the physical activity used dynamic time warping of the magnetometer time series data for pairs of children. Pairwise comparison across the whole cohort produced a similarity matrix of all child to child correlations. Normative assessment scores were based on the Euclidean distance between n participants within an n  −  1 multi-variate space, created from multi-dimensional scaling of the similarity matrix. The sensor-based scores were compared to the current standardised assessment which involves binary scoring of technique, outcome and time components by trained assessors. Main results: Visualisation of the relative performance using the first three axes of the multi-dimensional matrix, shows a 'performance sphere' in which children sit on concentric shells of increasing radius as performance deteriorates. Good agreement between standard and sensor scores is found, with Spearman rank correlation coefficients of the overall activity score in the range of 0.62-0.71 for different cohorts and a kappa statistic of 0.34 for categorisation of all 55 children into lower, middle, upper tertile and top 5% bands. Significance: By using multi-dimensional analysis of similarity measures between participants rather than direct parameterisation of the physiological data, complex and varied patterns of physical motion can be quantified, allowing objective and robust profiling of relative function across participant groups.