Gait Event Detection Research Articles

Human gait-labeling uncertainty and a hybrid model for gait segmentation.

Evaluate manual labeling uncertainty and introduce a hybrid stride detection and gait-event estimation model for autonomous, long-term, and remote monitoring. Estimate inter-labeler inconsistencies by computing the limits-of-agreement. Develop a hybrid model based on dynamic time warping and convolutional neural network to identify valid strides and eliminate non-stride data in inertial (walking) data collected by a wearable device. Finally, detect gait events within a valid stride region. The limits of inter-labeler agreement for key gait events heel off, toe off, heel strike, and flat foot are 72, 16, 24, and 80 ms, respectively; The hybrid model's classification accuracy for stride and non-stride are 95.16 and 84.48%, respectively; The mean absolute error for detected heel off, toe off, heel strike, and flat foot are 24, 5, 9, and 13 ms, respectively, when compared to the average human labels. The results show the inherent labeling uncertainty and the limits of human gait labeling of motion capture data; The proposed hybrid-model's performance is comparable to that of human labelers, and it is a valid model to reliably detect strides and estimate the gait events in human gait data. This work establishes the foundation for fully automated human gait analysis systems with performances comparable to human-labelers.

Rules-Based Real-Time Gait Event Detection Algorithm for Lower-Limb Prosthesis Users during Level-Ground and Ramp Walking.

Real-time gait event detection (GED) using inertial sensors is important for applications such as remote gait assessments, intelligent assistive devices including microprocessor-based prostheses or exoskeletons, and gait training systems. GED algorithms using acceleration and/or angular velocity signals achieve reasonable performance; however, most are not suited for real-time applications involving clinical populations walking in free-living environments. The aim of this study was to develop and evaluate a real-time rules-based GED algorithm with low latency and high accuracy and sensitivity across different walking states and participant groups. The algorithm was evaluated using gait data collected from seven able-bodied (AB) and seven lower-limb prosthesis user (LLPU) participants for three walking states (level-ground walking (LGW), ramp ascent (RA), ramp descent (RD)). The performance (sensitivity and temporal error) was compared to a validated motion capture system. The overall sensitivity was 98.87% for AB and 97.05% and 93.51% for LLPU intact and prosthetic sides, respectively, across all walking states (LGW, RA, RD). The overall temporal error (in milliseconds) for both FS and FO was 10 (0, 20) for AB and 10 (0, 25) and 10 (0, 20) for the LLPU intact and prosthetic sides, respectively, across all walking states. Finally, the overall error (as a percentage of gait cycle) was 0.96 (0, 1.92) for AB and 0.83 (0, 2.08) and 0.83 (0, 1.66) for the LLPU intact and prosthetic sides, respectively, across all walking states. Compared to other studies and algorithms, the herein-developed algorithm concurrently achieves high sensitivity and low temporal error with near real-time detection of gait in both typical and clinical populations walking over a variety of terrains.

Gait Events Prediction Using Hybrid CNN-RNN-Based Deep Learning Models through a Single Waist-Worn Wearable Sensor.

Elderly gait is a source of rich information about their physical and mental health condition. As an alternative to the multiple sensors on the lower body parts, a single sensor on the pelvis has a positional advantage and an abundance of information acquirable. This study aimed to improve the accuracy of gait event detection in the elderly using a single sensor on the waist and deep learning models. Data were gathered from elderly subjects equipped with three IMU sensors while they walked. The input taken only from the waist sensor was used to train 16 deep-learning models including a CNN, RNN, and CNN-RNN hybrid with or without the Bidirectional and Attention mechanism. The groundtruth was extracted from foot IMU sensors. A fairly high accuracy of 99.73% and 93.89% was achieved by the CNN-BiGRU-Att model at the tolerance window of ±6 TS (±6 ms) and ±1 TS (±1 ms), respectively. Advancing from the previous studies exploring gait event detection, the model demonstrated a great improvement in terms of its prediction error having an MAE of 6.239 ms and 5.24 ms for HS and TO events, respectively, at the tolerance window of ±1 TS. The results demonstrated that the use of CNN-RNN hybrid models with Attention and Bidirectional mechanisms is promising for accurate gait event detection using a single waist sensor. The study can contribute to reducing the burden of gait detection and increase its applicability in future wearable devices that can be used for remote health monitoring (RHM) or diagnosis based thereon.

Predicting vertical ground reaction forces from 3D accelerometry using reservoir computers leads to accurate gait event detection.

Accelerometers are low-cost measurement devices that can readily be used outside the lab. However, determining isolated gait events from accelerometer signals, especially foot-off events during running, is an open problem. We outline a two-step approach where machine learning serves to predict vertical ground reaction forces from accelerometer signals, followed by force-based event detection. We collected shank accelerometer signals and ground reaction forces from 21 adults during comfortable walking and running on an instrumented treadmill. We trained one common reservoir computer using segmented data using both walking and running data. Despite being trained on just a small number of strides, this reservoir computer predicted vertical ground reaction forces in continuous gait with high quality. The subsequent foot contact and foot off event detection proved highly accurate when compared to the gold standard based on co-registered ground reaction forces. Our proof-of-concept illustrates the capacity of combining accelerometry with machine learning for detecting isolated gait events irrespective of mode of locomotion.

Smart Lacelock: A Novel Shoelace Tensioning Device for Human Motion Sensing

Shoe-mounted wearable sensors may serve a variety of important purposes (activity recognition, energy expenditure estimation, and so on) by providing rich information about human locomotion. However, reliably attaching such sensors to shoes still remains a challenge. Furthermore, pressure-sensing elements in such shoe sensor systems often suffer from poor durability due to the large dynamic load. This work presents a novel shoe-mounted sensor named Smart Lacelock, which takes the form of a common shoelace tensioning device (shoelace lock). With its unique form factor, the Smart Lacelock can be securely attached to the top of a shoe with minimal effort, enabling its embedded inertia measurement unit (IMU) to provide reliable 3-D motion measurement of the foot. Furthermore, the Smart Lacelock incorporates a load cell to measure the force applied by the shoelace, providing valuable information related to ankle movement, foot/shoe shape change, and ground force. Design details of the device are presented, including the mechanical structure and electronic circuitry. We also conducted a ten-participant human study, in which signals were recorded during free ankle swing, body weight (BW) shifting, sit-to-stand (STS), and overground walking. The results demonstrated the Smart Lacelock’s capability of providing consistent and observable responses to single contributing factors (ankle movement and foot loading) as well as complex movements with clearly defined events of interest (STS and walking). Such unique capability suggests that the Smart Lacelock may serve as an important source of human movement information to support related applications such as activity recognition and gait event detection.

E-Textile smart socks for gait analysis: a preliminary validation study

In the last years wearable technologies and smart fabrics are arousing a great deal of interest in the healthcare field. The possibility to directly interact with the body, along with the comfort of fabrics, represent great opportunities to develop interesting applications. Smart sensing socks, able to collect kinematic and/or foot pressure signals, are attractive solutions to perform gait analysis also outside clinical laboratories, e.g., in the home environment for remote continuous monitoring of patients. In this study we analyse the performance of Sensoria smart socks (Sensoria Health Inc. Seattle, WA, USA) in detecting the major spatio-temporal gait analysis metrics. We validate the results provided by the system in comparison with those of the IMU-based gait analysis system OPAL Mobility Lab by APDM (APDM Inc, Portland, OR, USA). Three textile pressure sensors are embedded in the Sensoria Sock to monitor plantar pressure, while the hardware unit is connected on the lateral part of the ankle to measure kinematic signals and transmit data to a smartphone. Twelve records were acquired on five healthy subjects (2 women). Each subject wore the sensing Sensoria smart socks and three OPAL Inertial Measurement Units (two on the feet and one in lumbar position), in order to perform simultaneous recording of the walking. The trial consisted of walking 10 metres, turning and returning to the starting point at preferred speed. The following resulting gait metrics were considered from the two systems and compared: Gait Cycle Time (GCT) [s], Stance Phase [%GCT], Cadence [steps/min]. Statistical comparison was performed by means of Bland-Altman test. Fig. 1 shows the results of the statistical analysis. Fig. 1 a presents the principal statistics of the considered metrics for the two systems. The table in Fig. 1 a also reports the numeric results of Bland- Altman test, expressed as the average bias (Sensoria minus OPAL) and its 95% Confidence Interval (CI) (Lower Bound LB – Upper Bound UB). Fig. 1 b, c and d respectively represent the Bland- Altman Plots for GCT, Stance Phase and Cadence. In this preliminary study we investigate the performances of the wearable Sensoria smart socks in evaluating the major temporal gait metrics. Results underline a general agreement in measuring GCT ( bias = − 0.00593 s ) and Cadence ( bias = − 0.0820 steps / min ). The confidence interval of bias includes the zero for both metrics, indicating that the differences randomly occur and are not systematic. The Bland-Altman plot for Stance Phase metric shows a significant difference between the measures provided by the two systems: Sensoria smart socks underestimate the foot stance phase duration with respect to the reference system OPAL Mobility Lab. In this case the average bias is − 7.75 % and its confidence interval does not include zero. The agreement in GCT values and the simultaneous disagreement of stance phase demonstrate discrepancies between the two systems in the detection of intermediate gait events (initial and terminal contact). In conclusion, smart socks performance in the detection of GCT and cadence are satisfactory, however improvements are needed in order to assess more specific gait metrics. In future studies, we aim to test the socks on a larger population and in the assessment of other temporal and spatial gait metrics.

Detecting Gait Events from Accelerations Using Reservoir Computing.

Segmenting the gait cycle into multiple phases using gait event detection (GED) is a well-researched subject with many accurate algorithms. However, the algorithms that are able to perform accurate and robust GED for real-life environments and physical diseases tend to be too complex for their implementation on simple hardware systems limited in computing power and memory, such as those used in wearable devices. This study focuses on a numerical implementation of a reservoir computing (RC) algorithm called the echo state network (ESN) that is based on simple computational steps that are easy to implement on portable hardware systems for real-time detection. RC is a neural network method that is widely used for signal processing applications and uses a fast-training method based on a ridge regression adapted to the large quantity and variety of IMU data needed to use RC in various real-life environment GED. In this study, an ESN was used to perform offline GED with gait data from IMU and ground force sensors retrieved from three databases for a total of 28 healthy adults and 15 walking conditions. Our main finding is that despite its low complexity, ESN is robust for GED, with performance comparable to other state-of-the-art algorithms. Our results show the ESN is robust enough to obtain good detection results in all conditions if the algorithm is trained with variable data that match those conditions. The distribution of the mean absolute errors (MAE) between the detection times from the ESN and the force sensors were between 40 and 120 ms for 6 defined gait events (95th percentile). We compared our ESN with four different state-of-the-art algorithms from the literature. The ESN obtained a MAE not more than 10 ms above three other reference algorithms for normal walking indoor and outdoor conditions and yielded the 2nd lowest MAE and the 2nd highest true positive rate and specificity when applied to outdoor walking and running conditions. Our work opens the door to using the ESN as a GED for applications in wearable sensors for long-term patient monitoring.

Gait Pattern Identification and Phase Estimation in Continuous Multilocomotion Mode Based on Inertial Measurement Units

In the field of lower limb exoskeletons, it is essential to accurately estimate the gait phase of humans. Many methods have been proposed to estimate the gait phase, but only a few studies have considered the multi-locomotion mode. This paper proposes a novel inertial measurement unit(IMU)-based method to estimate the gait phase of a pilot in continuous multi-locomotion mode. The method includes gait pattern recognition based on long short-term memory (LSTM), continuous phase estimation based on a dual adaptive frequency oscillator(DAFO), threshold-based toe-off event detection and a rule-based gait phase synchronization module. First, we used the LSTM-based network to identify four gait patterns including standing, level ground walking, upstairs and downstairs. Next, the DAFO was used to obtain the continuous gait phase of the pilot. Then, we detected the gait events in different gait modes. Finally, the continuous gait phase was synchronized according to the gait events. The experimental result shows that the gait pattern classification accuracy using 5 IMUs is 98.58% and the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathcal {F}_{\!{1}}$ </tex-math></inline-formula> score reaches 0.9875. The proposed DAFO model can maintain good stability when multiple gait modes are frequently switched, significantly improving the problem of slow convergence and the poor robustness of single adaptive frequency oscillator(SAFO) models. Toe-off gait events of 492 steps are all detected and the average error at the detected gait events in different gait modes is 15.34± 40.58 ms.

Gait Subphases Classification Based on Hidden Markov Models using in-shoes Capacitive Pressure Sensors: Preliminary Results.

Gait cycle analysis is widely practiced to determine alterations of normal walking. The challenge is to choose the ideal systems that suit the studies. One possibility is to measure the interaction of the sole and the support surface and detect gait events related to the positioning of the foot. This work proposes a gait subphase classification based on Hidden Markov Model that identifies gait stance subphases from a foot pressure measurement. A sensorized insole was used to record the pressure under the foot with eight custom-made capacitive sensors. Tests were performed on six volunteers with a 10-meter trial test. Mean cadence and stance/swing ratio were calculated. These parameters match the normal range for the age of the volunteers found in the literature. The results show that the proposed model can classify the gait in 5 subphases using the Center of Pressure (CoP) anteroposterior position and velocity as input. Changes in the slope of the CoP marks the step between subphases. Clinical Relevance- Most gait studies are performed in highly equipped gait laboratories. Due to technical requirements and the high cost of implementing a gait laboratory, access to these services is difficult for a large population. For this reason, it is necessary to develop equipment, devices, and algorithm to further study pathological and healthy gait.

Wearable Inertial Sensor-Based Limb Lameness Detection and Pose Estimation for Horses

Accurate objective, automated limb lameness detection and pose estimation play an important role for animal well-being and precision livestock farming. We present a wearable sensor-based limb lameness detection and pose estimation for horse walk and trot locomotion. The gait event and lameness detection are first built on a recurrent neural network (RNN) with long short-term memory (LSTM) cells. Its outcomes are used in the limb pose estimation. A learned low-dimensional motion manifold is parameterized by a phase variable with a Gaussian process dynamic model. We compare the RNN-LSTM-based lameness detection method with a feature-based multi-layer classifier (MLC) and a multi-class classifier (MCC) that are built on support vector machine/K-nearest-neighbors and deep convolutional neural network methods, respectively. Experimental results show that using only accelerometer measurements, the RNN-LSTM-based approach achieves 95% lameness detection accuracy and also outperforms the feature-based MLC or MCC in terms of several assessment criteria. The pose estimation scheme can predict the 24 limb joint angles in the sagittal plane with average errors less than 5 and 10 degs under normal and induced lameness conditions, respectively. The presented work demonstrate the successful use of machine learning techniques for high performance lameness detection and pose estimation in equine science. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Automation technologies are increasingly used for precision agriculture but few have focused on monitoring individual animals in open field for precision livestock farming. Limb lameness detection and pose estimation in open field is labor-intensive, unsafe for farmers, and inefficient. The presented machine learning-enabled, wearable inertial sensor-based design provides an effective and efficient approach for horse limb lameness detection and pose estimation applications. We present an RNN-LSTM for lameness detection and an integrated manifold learning model is used to predict the horse limb joint angles in walk and trot gaits under normal and induced lameness conditions. We also present a systematic analysis and experiments to demonstrate the impacts of the wearable sensor locations and signal information on lameness detection and pose estimation performance. Several other machine learning-based lameness detection methods are also presented and compared. The extensive multi-horse testing results are presented to demonstrate the superior accuracy and higher performance than other types of machine learning methods. One attractive feature of the proposed design lies in its high performance and fast computational capability for potential real-time applications in open field.

Adaptive Algorithm for Gait Segmentation Using a Single IMU in the Thigh Pocket

Gait segmentation may help monitoring the evolution of patients during rehabilitation treatment through the analysis of properly defined metrics. Many algorithms detect gait events using Inertial Measurement Units (IMUs). However, most of them require the IMUs to be attached to the body, or to assistive devices. Often individuals must go to a gait laboratory which owns specialized equipment so that gait analysis can be performed. IMUs are present in modern smartphones. An IMU<inline-formula> <tex-math notation="LaTeX">$/$ </tex-math></inline-formula>smartphone carried in the pocket during daily activities could allow the analysis of much more data in a more comfortable setting. We address the detection of four gait events: Heel-Strike (HS), Flat-Foot (FF), Heel-Off (HO) and Toe-Off (TO) using a single noisy IMU attached to a smartphone placed inside the thigh pocket. Gait was modelled as a four-state left-right Hidden Markov Model (HMM) whose observations follow multivariate Gaussian distributions. The decoding in post-processing was performed with a modified Viterbi decoder that accounts for a rule-based (RB) detection of TO. To validate the approach, experiments were performed in nine subjects with no gait abnormalities. Our algorithm obtained median F1-Scores <inline-formula> <tex-math notation="LaTeX">$\geq0.955$ </tex-math></inline-formula> for all events in intra-subject evaluation and median F1-Scores <inline-formula> <tex-math notation="LaTeX">$\geq0.757$ </tex-math></inline-formula> in inter-subject evaluations (with fast training and with a populational model). It demonstrated high generalization capability in our dataset and competitive performances when compared to other algorithms using high-quality IMUs attached to the body. This work is a step towards accurate and refined gait segmentation using a smartphone carried in the pocket.

Design of Gait Detection System Based on FCM Algorithm

Gait detection technology is widely used in medical and military fields. The key of gait detection technology is low cost, high accuracy and portable detection equipment and real-time detection algorithm. This paper introduces a real-time gait detection system, this kind of gait detection system using machine learning algorithm based on FCM clustering analysis and calibration of the sensor data filter algorithm based on rules, the kinematic data is divided into five different gait events, namely the heel strike , foot flat, heel off , toe off and initial swing phase . Compared with 3D posture capture experiment equipment, the accuracy of gait event detection of the proposed gait detection system is verified to be highly reliable.

Automatic gait event detection in pathologic gait using an auto-selection approach among concurrent methods

BackgroundAccurate gait event detection is crucial to analyze pathological gait data. Existing methods relying on marker trajectories were reported to be sensitive to different gait patterns, which is an inherent characteristic of pathologic gait. Research questionWe propose a new approach based on auto-selection among different methods, original and taken from the literature. MethodsThe auto-selection approach evaluates the accuracy of the implemented methods for both foot-strike and foot-off on all available events detected by the force platforms, independently, and automatically selects the most accurate one to be used on the whole gait session. Pathological gait data from 272 patients with cerebral palsy and idiopathic toe walking were used retrospectively to evaluate the accuracy of this approach. Three methods previously reported in literature together with original methods developed based on auto-correlation were implemented and constituted our auto-selection approach. The accuracy and precision were compared to a recently reported method based on deep events as it is the method that showed the best performance in literature. ResultsResults showed that the proposed approach outperformed all implemented methods used alone, with an accuracy of − 2.0 ms and − 0.9 ms for foot strike and foot-off, respectively. Additionally, more than 99% and 93% of events detected were detected within 20 ms and 10 ms of accuracy, respectively. SignificanceThe proposed methodology has demonstrated to improve the accuracy and precision of gait event detection in gait analysis.

An Algorithm for Accurate Marker-Based Gait Event Detection in Healthy and Pathological Populations During Complex Motor Tasks.

There is growing interest in the quantification of gait as part of complex motor tasks. This requires gait events (GEs) to be detected under conditions different from straight walking. This study aimed to propose and validate a new marker-based GE detection method, which is also suitable for curvilinear walking and step negotiation. The method was first tested against existing algorithms using data from healthy young adults (YA, n = 20) and then assessed in data from 10 individuals from the following five cohorts: older adults, chronic obstructive pulmonary disease, multiple sclerosis, Parkinson’s disease, and proximal femur fracture. The propagation of the errors associated with GE detection on the calculation of stride length, duration, speed, and stance/swing durations was investigated. All participants performed a variety of motor tasks including curvilinear walking and step negotiation, while reference GEs were identified using a validated methodology exploiting pressure insole signals. Sensitivity, positive predictive values (PPV), F1-score, bias, precision, and accuracy were calculated. Absolute agreement [intraclass correlation coefficient ()] between marker-based and pressure insole stride parameters was also tested. In the YA cohort, the proposed method outperformed the existing ones, with sensitivity, PPV, and F1 scores ≥ 99% for both GEs and conditions, with a virtually null bias (<10 ms). Overall, temporal inaccuracies minimally impacted stride duration, length, and speed (median absolute errors ≤1%). Similar algorithm performances were obtained for all the other five cohorts in GE detection and propagation to the stride parameters, where an excellent absolute agreement with the pressure insoles was also found (). In conclusion, the proposed method accurately detects GE from marker data under different walking conditions and for a variety of gait impairments.

A Deep Learning Approach for Gait Event Detection from a Single Shank-Worn IMU: Validation in Healthy and Neurological Cohorts.

Many algorithms use 3D accelerometer and/or gyroscope data from inertial measurement unit (IMU) sensors to detect gait events (i.e., initial and final foot contact). However, these algorithms often require knowledge about sensor orientation and use empirically derived thresholds. As alignment cannot always be controlled for in ambulatory assessments, methods are needed that require little knowledge on sensor location and orientation, e.g., a convolutional neural network-based deep learning model. Therefore, 157 participants from healthy and neurologically diseased cohorts walked 5 m distances at slow, preferred, and fast walking speed, while data were collected from IMUs on the left and right ankle and shank. Gait events were detected and stride parameters were extracted using a deep learning model and an optoelectronic motion capture (OMC) system for reference. The deep learning model consisted of convolutional layers using dilated convolutions, followed by two independent fully connected layers to predict whether a time step corresponded to the event of initial contact (IC) or final contact (FC), respectively. Results showed a high detection rate for both initial and final contacts across sensor locations (recall , precision ). Time agreement was excellent as witnessed from the median time error (0.005 s) and corresponding inter-quartile range (0.020 s). The extracted stride-specific parameters were in good agreement with parameters derived from the OMC system (maximum mean difference 0.003 s and corresponding maximum limits of agreement (−0.049 s, 0.051 s) for a confidence level). Thus, the deep learning approach was considered a valid approach for detecting gait events and extracting stride-specific parameters with little knowledge on exact IMU location and orientation in conditions with and without walking pathologies due to neurological diseases.

Validation of Running Gait Event Detection Algorithms in a Semi-Uncontrolled Environment.

The development of lightweight portable sensors and algorithms for the identification of gait events at steady-state running speeds can be translated into the real-world environment. However, the output of these algorithms needs to be validated. The purpose of this study was to validate the identification of running gait events using data from Inertial Measurement Units (IMUs) in a semi-uncontrolled environment. Fifteen healthy runners were recruited for this study, with varied running experience and age. Force-sensing insoles measured normal foot-shoe forces and provided a standard for identification of gait events. Three IMUs were mounted to the participant, two bilaterally on the dorsal aspect of the foot and one clipped to the back of each participant’s waistband, approximating their sacrum. The identification of gait events from the foot-mounted IMU was more accurate than from the sacral-mounted IMU. At running speeds <3.57 m s−1, the sacral-mounted IMU identified contact duration as well as the foot-mounted IMU. However, at speeds >3.57 m s−1, the sacral-mounted IMU overestimated foot contact duration. This study demonstrates that at controlled paces over level ground, we can identify gait events and measure contact time across a range of running skill levels.

Heading Direction Is Significantly Biased by Preceding Whole-Body Roll-Orientation While Lying

BackgroundAfter a prolonged static whole-body roll-tilt, a significant bias of the internal estimates of the direction of gravity has been observed when assessing the subjective visual vertical.ObjectiveWe hypothesized that this post-tilt bias represents a more general phenomenon, broadly affecting spatial orientation and navigation. Specifically, we predicted that after the prolonged roll-tilt to either side perceived straight-ahead would also be biased.MethodsTwenty-five healthy participants were asked to rest in three different lying positions (supine, right-ear-down, and left-ear-down) for 5 min (“adaptation period”) prior to walking straight-ahead blindfolded for 2 min. Walking was recorded with the inertial measurement unit sensors attached to different body locations and with sensor shoe insoles. The raw data was segmented with a gait–event detection method. The Heading direction was determined and linear mixed-effects models were used for statistical analyses.ResultsA significant bias in heading into the direction of the previous roll-tilt position was observed in the post-adaptation trials. This bias was identified in both measurement systems and decreased again over the 2-min walking period.ConclusionsThe bias observed further confirms the influence of prior knowledge on spatial orientation and navigation. Specifically, it underlines the broad impact of a shifting internal estimate of direction of gravity over a range of distinct paradigms, illustrating similar decay time constants. In the broader context, the observed bias in perceived straight-ahead emphasizes that getting up in the morning after a good night's sleep is a vulnerable period, with an increased risk of falls and fall-related injuries due to non-availability of optimally tuned internal estimates of the direction of gravity and the direction of straight-ahead.

Assessment of a novel deep learning-based marker-less motion capture system for gait study

BackgroundMarker-less systems based on digital video cameras and deep learning for gait analysis could have a deep impact in clinical routine. A recently developed system has shown promising results in terms of joint center position but has not been yet evaluated in terms of gait outcomes. Research questionHow does this novel marker-less system compare to a marker-based reference system in terms of clinically relevant gait parameters? MethodsThe deep learning method behind the developed marker-less system was trained on a dedicated dataset consisting of forty-one asymptomatic and pathological subjects each performing ten walking trials. The system could estimate the three-dimensional position of seventeen joint centers or keypoints (e.g., neck, shoulders, hip, knee, and ankles). We evaluated the marker-less system against a marker-based system in terms of differences in joint position (Euclidean distance), detection of gait events (e.g., heel strike and toe-off), spatiotemporal parameters (e.g., step length, time), kinematic parameters (e.g., hip and knee extension-flexion), and inter-trial reliability for kinematic parameters. ResultsThe marker-less system was able to estimate the three-dimensional position of joint centers with a mean difference of 13.1 mm (SD = 10.2 mm). 99% of the estimated gait events were estimated within 10 ms of the corresponding reference values. Estimated spatiotemporal parameters showed zero bias. The mean and standard deviation of the differences of the estimated kinematic parameters varied by parameter (for example, the mean and standard deviation for knee extension flexion angle were −3.0° and 2.7°). Inter-trial reliability of the measured parameters was similar to that of the marker-based references. SignificanceThe developed marker-less system can measure the spatiotemporal parameters within the range of the minimum detectable changes obtained using the marker-based reference system. Moreover, except for hip extension flexion, the system showed promising results in terms of several kinematic parameters.

Stance Phase Detection by Inertial Measurement Unit Placed on the Metacarpus of Horses Trotting on Hard and Soft Straight Lines and Circles.

The development of on-board technologies has enabled the development of quantification systems to monitor equine locomotion parameters. Their relevance among others relies on their ability to determine specific locomotor events such as foot-on and heel-off events. The objective of this study was to compare the accuracy of different methods for an automatic gait events detection from inertial measurement units (IMUs). IMUs were positioned on the cannon bone, hooves, and withers of seven horses trotting on hard and soft straight lines and circles. Longitudinal acceleration and angular velocity around the latero-medial axis of the cannon bone, and withers dorso-ventral displacement data were identified to tag the foot-on and a heel-off events. The results were compared with a reference method based on hoof-mounted-IMU data. The developed method showed bias less than 1.79%, 1.46%, 3.45% and −1.94% of stride duration, respectively, for forelimb foot-on and heel-off, and for hindlimb foot-on and heel-off detection, compared to our reference method. The results of this study showed that the developed gait-events detection method had a similar accuracy to other methods developed for straight line analysis and extended this validation to other types of exercise (circles) and ground surface (soft surface).

Method for Estimating Temporal Gait Parameters Concerning Bilateral Lower Limbs of Healthy Subjects Using a Single In-Shoe Motion Sensor through a Gait Event Detection Approach.

To expand the potential use of in-shoe motion sensors (IMSs) in daily healthcare or activity monitoring applications for healthy subjects, we propose a real-time temporal estimation method for gait parameters concerning bilateral lower limbs (GPBLLs) that uses a single IMS and is based on a gait event detection approach. To validate the established methods, data from 26 participants recorded by an IMS and a reference 3D motion analysis system were compared. The agreement between the proposed method and the reference system was evaluated by the intraclass correlation coefficient (ICC). The results showed that, by averaging over five continuous effective strides, all time parameters achieved precisions of no more than 30 ms and agreement at the “excellent” level, and the symmetry indexes of the stride time and stance phase time achieved precisions of 1.0% and 3.0%, respectively, and agreement at the “good” level. These results suggest our method is effective and shows promise for wide use in many daily healthcare or activity monitoring applications for healthy subjects.