Automatic recognition of human movement is an effective strategy to assess abnormal gait patterns. Machine learning approaches are mainly applied due to their ability to work with multidimensional nonlinear features. to compare several machine learning algorithms employed for gait pattern recognition in motor disorders using discriminant features extracted from gait dynamics. Additionally, this work highlights procedures that improve gait recognition performance. we conducted an electronic literature search on Web of Science, IEEE, and Scopus, using "human recognition", "gait patterns'', and "feature selection methods" as relevant keywords. analysis of the literature showed that kernel principal component analysis and genetic algorithms are efficient at reducing dimensional features due to their ability to process nonlinear data and converge to global optimum. Comparative analysis of machine learning performance showed that support vector machines (SVMs) exhibited higher accuracy and proper generalization for new instances. automatic recognition by combining dimensional data reduction, cross-validation and normalization techniques with SVMs may offer an objective and rapid tool for investigating the subject's clinical status. Future directions comprise the real-time application of these tools to drive powered assistive devices in free-living conditions.

Understanding the lower limb kinematic, kinetic, and electromyography (EMG) data interrelation in controlled speeds is challenging for fully assessing human locomotion conditions. This paper provides a complete dataset with the above-mentioned raw and processed data simultaneously recorded for sixteen healthy participants walking on a 10 meter-flat surface at seven controlled speeds (1.0, 1.5, 2.0, 2.5, 3.0, 3.5, and 4.0 km/h). The raw data include 3D joint trajectories of 24 retro-reflective markers, ground reaction forces (GRF), force plate moments, center of pressures, and EMG signals from Tibialis Anterior, Gastrocnemius Lateralis, Biceps Femoris, and Vastus Lateralis. The processed data present gait cycle-normalized data including filtered EMG signals and their envelope, 3D GRF, joint angles, and torques. This study details the experimental setup and presents a brief validation of the data quality. The presented dataset may contribute to (i) validate and enhance human biomechanical gait models, and (ii) serve as a reference trajectory for personalized control of robotic assistive devices, aiming an adequate assistance level adjusted to the gait speed and user’s anthropometry.

A benchmark and time-effective computational method is needed to assess human gait events in real-life walking situations using few sensors to be easily reproducible. This paper fosters a reliable gait event detection system that can operate at diverse gait speeds and on diverse real-life terrains by detecting several gait events in real time. This detection only relies on the foot angular velocity measured by a wearable gyroscope mounted in the foot to facilitate its integration for daily and repeated use. To operate as a benchmark tool, the proposed detection system endows an adaptive computational method by applying a finite-state machine based on heuristic decision rules dependent on adaptive thresholds. Repeated measurements from 11 healthy subjects (28.27 ± 4.17 years) were acquired in controlled situations through a treadmill at different speeds (from 1.5 to 4.5 km/h) and slopes (from 0% to 10%). This validation also includes heterogeneous gait patterns from nine healthy subjects (27 ± 7.35 years) monitored at three self-selected paces (from 1 ± 0.2 to 2 ± 0.18 m/s) during forward walking on flat, rough, and inclined surfaces and climbing staircases. The proposed method was significantly more accurate ( ${p}>\textsf {0.9925}$ ) and time effective (< 30.53 ± 9.88 ms, ${p}>\textsf {0.9314}$ ) in a benchmarking analysis with a state-of-the-art method during 5657 steps. Heel strike was the gait event most accurately detected under controlled (accuracy of 100%) and real-life situations (accuracy > 96.98%). Misdetection was more pronounced in middle mid swing (accuracy > 90.12%). The lower computational load, together with an improved performance, makes this detection system suitable for quantitative benchmarking in the locomotor rehabilitation field.

More versatile, user-independent tools for recognizing and predicting locomotion modes (LMs) and LM transitions (LMTs) in natural gaits are still needed. This study tackles these challenges by proposing an automatic, user-independent recognition and prediction tool using easily wearable kinematic motion sensors for innovatively classifying several LMs (walking direction, level-ground walking, ascend and descend stairs, and ascend and descend ramps) and respective LMTs. We compared diverse state-of-the-art feature processing and dimensionality reduction methods and machine-learning classifiers to find an effective tool for recognition and prediction of LMs and LMTs. The comparison included kinematic patterns from 10 able-bodied subjects. The more accurate tools were achieved using min-max scaling [-1;1]interval and “mRMR plus forward selection” algorithm for feature normalization and dimensionality reduction, respectively, and Gaussian support vector machine classifier. The developed tool was accurate in the recognition (accuracy > 99% and > 96%) and prediction (accuracy > 99% and > 93%) of daily LMs and LMTs, respectively, using exclusively kinematic data. The use of kinematic data yielded an effective recognition and prediction tool, predicting the LMs and LMTs one-step-ahead. This timely prediction is relevant for assistive devices providing personalized assistance in daily scenarios. The kinematic data-based machine learning tool innovatively addresses several LMs and LMTs while allowing the user to self-select the leading limb to perform LMTs, ensuring a natural gait.

Powered Assistive Devices (PADs) have been proposed to enable repetitive, user-oriented gait rehabilitation. They may include torque controllers that typically require reference joint torque trajectories to determine the most suitable level of assistance. However, a robust approach able to automatically estimate user-oriented reference joint torque trajectories, namely ankle torque, while considering the effects of varying walking speed, body mass, and height on the gait dynamics, is needed. This study evaluates the accuracy and generalization ability of two Deep Learning (DL) regressors (Long-Short Term Memory and Convolutional Neural Network (CNN)) to generate user-oriented reference ankle torque trajectories by innovatively customizing them according to the walking speed (ranging from 1.0 to 4.0 km/h) and users’ body height and mass (ranging from 1.51 to 1.83 m and 52.0 to 83.7 kg, respectively). Furthermore, this study hypothesizes that DL regressors can estimate joint torque without resourcing electromyography signals. CNN was the most robust algorithm (Normalized Root Mean Square Error: 0.70 ± 0.06; Spearman Correlation: 0.89 ± 0.03; Coefficient of Determination: 0.91 ± 0.03). No statistically significant differences were found in CNN accuracy (p-value > 0.05) whether electromyography signals are included as inputs or not, enabling a less obtrusive and accurate setup for torque estimation.

This paper presents a cost- and time-effective wearable inertial sensor system, the InertialLAB. It includes gyroscopes and accelerometers for the real-time monitoring of 3D-angular velocity and 3D-acceleration of up to six lower limbs and trunk segment and sagittal joint angle up to six joints. InertialLAB followed an open architecture with a low computational load to be executed by wearable processing units up to 200 Hz for fostering kinematic gait data to third-party systems, advancing similar commercial systems. For joint angle estimation, we developed a trigonometric method based on the segments’ orientation previously computed by fusion-based methods. The validation covered healthy gait patterns in varying speed and terrain (flat, ramp, and stairs) and including turns, extending the experiments approached in the literature. The benchmarking analysis to MVN BIOMECH reported that InertialLAB provides more reliable measures in stairs than in flat terrain and ramp. The joint angle time-series of InertialLAB showed good waveform similarity (>0.898) with MVN BIOMECH, resulting in high reliability and excellent validity. User-independent neural network regression models successfully minimized the drift errors observed in InertialLAB’s joint angles (NRMSE < 0.092). Further, users ranked InertialLAB as good in terms of usability. InertialLAB shows promise for daily kinematic gait analysis and real-time kinematic feedback for wearable third-party systems.