Novel algorithms deriving clinical performance measures from smartphone sensor data collected under a walking test
Little, M. A.; Volotinen, S.; Sanderson, B.; Huopaniemi, U.; Mowlem, F.; Olt, J.; Byrom, B.
Show abstract
The modern ubiquity of smartphones which incorporate sensors such as inertial measurement units (IMU) and global positioning system (GPS) receivers, raises the possibility that they might be used as inexpensive devices for clinical performance testing. Here, we report on the development and testing of an app and associated statistical signal processing algorithms, to measure the basic gait properties of step rate, walking speed and distance under an outside short walk test experimental protocol, from digital accelerometry and GPS. We provide extensive details on the assumptions underlying the development of the algorithms. A small set of experiments across a range of conditions and individuals, demonstrate the reliability of the combined app, protocol and algorithms. With reasonable adherence to the test protocol, these experiments show 2% error across all metrics. The emphasis in this paper is on illustrating the design principles which all such systems, aiming to re-purpose consumer smartphones as clinical gait measurement devices, must address.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- The placement of foot-mounted IMU sensors does affect the accuracy of spatial parameters during regular walking 96%
- AddBiomechanics: Automating model scaling, inverse kinematics, and inverse dynamics from human motion data through sequential optimization 95%
- Determining jumping performance from a single body-worn accelerometer using machine learning 94%
Similar papers in this journal
- A model of task-level human stepping regulation yields semistable walking 92%
- Computationally efficient framework for diagnosing, understanding, and predicting biphasic population growth 92%
- A semi-parametric, state-space compartmental model with time-dependent parameters for forecasting COVID-19 cases, hospitalizations, and deaths 92%
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.