Automated Segmentation of a Timed Up and Go Test Using an Instrumented Cane

The Timed Up and Go (TUG) test is used to test a person’s mobility, static and dynamic balance. It measures the time a person takes to stand up from a chair, walk three meters, turn around, walk back to the chair, and sit down. Typically, a TUG test is observed by a physiotherapist with a stopwatch, thus, making the test results prone to error, limited, and difficult to analyse. Consequently, automated approaches capable of assessing the various segments of the TUG test have been widely explored. This study extends upon this body of work by evaluating the feasibility of segmenting the TUG test using an instrumented walking cane. More general contributions are made by introducing the use of error in transition time as opposed to accuracy, and a time-series inspired binary segmentation approach that allows for comparison of only two segments at a time. Data were collected using an instrumented cane from 16 participants with musculoskeletal injuries, with TUG times ranging from 11.12s to 28.57s, and a mean of 17.8s. Results of segmenting the TUG into six segments - Sitting to standing, Walking, Turning, Walking back, Turning back, Standing to sitting - were validated using a leave one trial out approach. SVM and LDA classifiers yielded average total subject dependent errors of 1.915s and 1.898s (the sum of all segment errors), and subject-independent errors of 3.425s and 3.417s, respectively. The performance of measuring the total test time (without sub-segments, as per current clinical practice), an average error of only 0.201s was recorded.