Automation and segmentation of timed up and go test with single redundant IMU

ASchneider, Felipe B.; Vargas-Valencia, Laura; Bastos-Filho, Teodiano Freire; Marques-Ciarelli, Patrick; Frizera-Neto, Anselmo

doi:10.24243/jmeb/4.2.223

Cited by 1 publication

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They classified the subtask into static (sit, stand), dynamic (walk, turn), and transition (sit-to-stand, standto-sit) using BDT and classified subtask activities using MLP. For more details on contact methods, refer to [2][3][4]14,23,28,29]. Although these wearable devices generally show high resolution and accuracy, they require complex and inconvenient setup and calibration processes, increasing the physical burden on medical professionals and patients.…”

Section: Related Workmentioning

confidence: 99%

“…An observer records the total time taken for the whole TUG test using a stopwatch as a metric to explain the overall mobility [11][12][13]. As the TUG test contains various subtasks like sit-to-stand, walking, turning, and stand-to-sit, the robust and accurate elapsed time of each TUG subtask can provide important clinical information, such as elapsed time and speed of each TUG subtask, gait speed, cadence (number of steps per minute), and the stance (percentage of the gait cycle) of subjects [2,3,[11][12][13][14][15]. These can be used not only to assist clinicians in clinical interventions but also to distinguish patients' functional recovery [3,16].…”

Section: Introductionmentioning

confidence: 99%

“…This is a heavy burden for both patients and clinicians. Therefore, automatic TUG analysis methods, especially subtask segmentation methods [2,3,[10][11][12][13][14][15][16], have recently attracted considerable research attention [4,17,18].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning-Based Subtask Segmentation of Timed Up-and-Go Test Using RGB-D Cameras

Choi

Bae

Dong

et al. 2022

Sensors

View full text Add to dashboard Cite

The timed up-and-go (TUG) test is an efficient way to evaluate an individual’s basic functional mobility, such as standing up, walking, turning around, and sitting back. The total completion time of the TUG test is a metric indicating an individual’s overall mobility. Moreover, the fine-grained consumption time of the individual subtasks in the TUG test may provide important clinical information, such as elapsed time and speed of each TUG subtask, which may not only assist professionals in clinical interventions but also distinguish the functional recovery of patients. To perform more accurate, efficient, robust, and objective tests, this paper proposes a novel deep learning-based subtask segmentation of the TUG test using a dilated temporal convolutional network with a single RGB-D camera. Evaluation with three different subject groups (healthy young, healthy adult, stroke patients) showed that the proposed method demonstrated better generality and achieved a significantly higher and more robust performance (healthy young = 95.458%, healthy adult = 94.525%, stroke = 93.578%) than the existing rule-based and artificial neural network-based subtask segmentation methods. Additionally, the results indicated that the input from the pelvis alone achieved the best accuracy among many other single inputs or combinations of inputs, which allows a real-time inference (approximately 15 Hz) in edge devices, such as smartphones.

show abstract