Walking is a central activity of daily life, and there is an increasing demand for objective measurement-based gait assessment. In contrast to stationary systems, wearable inertial measurement units (IMUs) have the potential to enable non-restrictive and accurate gait assessment in daily life. We propose a set of algorithms that uses the measurements of two foot-worn IMUs to determine major spatiotemporal gait parameters that are essential for clinical gait assessment: durations of five gait phases for each side as well as stride length, walking speed, and cadence. Compared to many existing methods, the proposed algorithms neither require magnetometers nor a precise mounting of the sensor or dedicated calibration movements. They are therefore suitable for unsupervised use by non-experts in indoor as well as outdoor environments. While previously proposed methods are rarely validated in pathological gait, we evaluate the accuracy of the proposed algorithms on a very broad dataset consisting of 215 trials and three different subject groups walking on a treadmill: healthy subjects (n = 39), walking at three different speeds, as well as orthopedic (n = 62) and neurological (n = 36) patients, walking at a self-selected speed. The results show a very strong correlation of all gait parameters (Pearson's r between 0.83 and 0.99, p < 0.01) between the IMU system and the reference system. The mean absolute difference (MAD) is 1.4 % for the gait phase durations, 1.7 cm for the stride length, 0.04 km/h for the walking speed, and 0.7 steps/min for the cadence. We show that the proposed methods achieve high accuracy not only for a large range of walking speeds but also in pathological gait as it occurs in orthopedic and neurological diseases. In contrast to all previous research, we present calibration-free methods for the estimation of gait phases and spatiotemporal parameters and validate them in a large number of patients with different pathologies. The proposed methods lay the foundation for ubiquitous unsupervised gait assessment in daily-life environments.

Gait analysis using foot-mounted IMUs is a promising method to acquire gait parameters outside of laboratory settings and in everyday clinical practice. However, the need for precise sensor attachment or calibration, the requirement of environments with a homogeneous magnetic field, and the limited applicability to pathological gait patterns still pose challenges. Furthermore, in previously published work, the measurement accuracy of such systems is often only validated for specific points in time or in a single plane. This study investigates the measurement accuracy of a gait analysis method based on foot-mounted IMUs in the acquisition of the foot motion, i.e., position and angle trajectories of the foot in the sagittal, frontal, and transversal plane over the entire gait cycle. A comparison of the proposed method with an optical motion capture system showed an average RMSE of 0.67° for pitch, 0.63° for roll and 1.17° for yaw. For position trajectories, an average RMSE of 0.51 cm for vertical lift and 0.34 cm for lateral shift was found. The measurement error of the IMU-based method is found to be much smaller than the deviations caused by the shoes. The proposed method is found to be sufficiently accurate for clinical practice. It does not require precise mounting, special calibration movements, or magnetometer data, and shows no difference in measurement accuracy between normal and pathological gait. Therefore, it provides an easy-to-use alternative to optical motion capture and facilitates gait analysis independent of laboratory settings.

Demographic changes associated with an expanding and aging population will lead to an increasing number of orthopedic surgeries, such as joint replacements. To support patients’ home exercise programs after total hip replacement and completing subsequent inpatient rehabilitation, a low-cost, smartphone-based augmented reality training game (TG) was developed. To evaluate its motion detection accuracy, data from 30 healthy participants were recorded while using the TG. A 3D motion analysis system served as reference. The TG showed differences of 18.03 mm to 24.98 mm along the anatomical axes. Surveying the main movement direction of the implemented exercises (squats, step-ups, side-steps), differences between 10.13 mm to 24.59 mm were measured. In summary, the accuracy of the TG’s motion detection is sufficient for use in exergames and to quantify progress in patients’ performance. Considering the findings of this study, the presented exer-game approach has potential as a low-cost, easily accessible support for patients in their home exercise program.

Evaluating whether data streams are drawn from the same distribution is at the heart of various machine learning problems. This is particularly relevant for data generated by dynamical systems since such systems are essential for many real-world processes in biomedical, economic, or engineering systems. While kernel two-sample tests are powerful for comparing independent and identically distributed random variables, no established method exists for comparing dynamical systems. The main problem is the inherently violated independence assumption. We propose a two-sample test for dynamical systems by addressing three core challenges: we (i) introduce a novel notion of mixing that captures autocorrelations in a relevant metric, (ii) propose an efficient way to estimate the speed of mixing relying purely on data, and (iii) integrate these into established kernel two-sample tests. The result is a data-driven method that is straightforward to use in practice and comes with sound theoretical guarantees. In an example application to anomaly detection from human walking data, we show that the test is readily applicable without any human expert knowledge and feature engineering.