Gait Event Detection From Accelerometry Using the Teager-Kaiser Energy Operator

Automatic gait events detection with inertial measurement units: healthy subjects and moderate to severe impaired patients

BACKGROUND

Recently, the use of inertial measurement units (IMUs) in quantitative gait analysis has been widely developed in clinical practice. Numerous methods have been developed for the automatic detection of gait events (GEs). While many of them have achieved high levels of efficiency in healthy subjects, detecting GEs in highly degraded gait from moderate to severely impaired patients remains a challenge. In this paper, we aim to present a method for improving GE detection from IMU recordings in such cases.

METHODS

We recorded 10-meter gait IMU signals from 13 healthy subjects, 29 patients with multiple sclerosis, and 21 patients with post-stroke equino varus foot. An instrumented mat was used as the gold standard. Our method detects GEs from filtered acceleration free from gravity and gyration signals. Firstly, we use autocorrelation and pattern detection techniques to identify a reference stride pattern. Next, we apply multiparametric Dynamic Time Warping to annotate this pattern from a model stride, in order to detect all GEs in the signal.

RESULTS

We analyzed 16,819 GEs recorded from healthy subjects and achieved an F1-score of 100%, with a median absolute error of 8 ms (IQR [3-13] ms). In multiple sclerosis and equino varus foot cohorts, we analyzed 6067 and 8951 GEs, respectively, with F1-scores of 99.4% and 96.3%, and median absolute errors of 18 ms (IQR [8-39] ms) and 26 ms (IQR [12-50] ms).

CONCLUSIONS

Our results are consistent with the state of the art for healthy subjects and demonstrate a good accuracy in GEs detection for pathological patients. Therefore, our proposed method provides an efficient way to detect GEs from IMU signals, even in degraded gaits. However, it should be evaluated in each cohort before being used to ensure its reliability.

Waist-What? Can a single sensor positioned at the waist detect parameters of gait at a speed and distance reflective of older adults' activity?

One of the problems facing an ageing population is functional decline associated with reduced levels of physical activity (PA). Traditionally researcher or clinician input is necessary to capture parameters of gait or PA. Enabling older adults to monitor their activity independently could raise their awareness of their activitiy levels, promote self-care and potentially mitigate the risks associated with ageing. The ankle is accepted as the optimum position for sensor placement to capture parameters of gait however, the waist is proposed as a more accessible body-location for older adults. This study aimed to compare step-count measurements obtained from a single inertial sensor positioned at the ankle and at the waist to that of a criterion measure of step-count, and to compare gait parameters obtained from the sensors positioned at the two different body-locations. Step-count from the waist-mounted inertial sensor was compared with that from the ankle-mounted sensor, and with a criterion measure of direct observation in healthy young and healthy older adults during a three-minute treadmill walk test. Parameters of gait obtained from the sensors at both body-locations were also compared. Results indicated there was a strong positive correlation between step-count measured by both the ankle and waist sensors and the criterion measure, and between ankle and waist sensor step-count, mean step time and mean stride time (r = .802-1.0). There was a moderate correlation between the step time variability measures at the waist and ankle (r = .405). This study demonstrates that a single sensor positioned at the waist is an appropriate method for the capture of important measures of gait and physical activity among older adults.

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

Motion capture systems are widely accepted as ground-truth for gait analysis and are used for the validation of other gait analysis systems. To date, their reliability and limitations in manual labeling of gait events have not been studied.

Objectives

Evaluate manual labeling uncertainty and introduce a hybrid stride detection and gait-event estimation model for autonomous, long-term, and remote monitoring.

Methods

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.

Results

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.

Conclusions

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.

Significance

This work establishes the foundation for fully automated human gait analysis systems with performances comparable to human-labelers.

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.

The Effect of Number of Gait Cycles on Principal Activation Extraction

To cope with the high intra-subject variability of muscle activation intervals, a large amount of gait cycles is necessary to clearly document physiological or pathological muscle activity patterns during human locomotion. The Clustering for Identification of Muscle Activation Pattern (CIMAP) algorithm has been proposed to help clinicians obtaining a synthetic and clear description of normal and pathological muscle functions in human walking. Moreover, this algorithm allows the extraction of Principal Activations (PAs), defined as those muscle activations that are strictly necessary to perform a specific task and occur in every gait cycle. This contribution aims at assessing the impact of the number of gait cycles on the extraction of the PAs. Results demonstrated no statistically significant differences between PAs extracted considering different numbers of gait cycles, revealing, on average, similarity values higher than 0.88.Clinical Relevance-This contribution demonstrates the potential applicability of the CIMAP algorithm to the analysis of subjects affected by neurological disorders, for whom the assessment of motor functions may be of the uttermost importance and only a reduced number of gait cycles can be acquired.

Machine-Learning-Based Prediction of Gait Events From EMG in Cerebral Palsy Children

Machine-learning techniques are suitably employed for gait-event prediction from only surface electromyographic (sEMG) signals in control subjects during walking. Nevertheless, a reference approach is not available in cerebral-palsy hemiplegic children, likely due to the large variability of foot-floor contacts. This study is designed to investigate a machine-learning-based approach, specifically developed to binary classify gait events and to predict heel-strike (HS) and toe-off (TO) timing from sEMG signals in hemiplegic-child walking. To this objective, sEMG signals are acquired from five hemiplegic-leg muscles in nearly 2500 strides from 20 hemiplegic children, acknowledged as Winters' group 1 and 2. sEMG signals, segmented in overlapping windows of 600 samples (pace = 5 samples), are used to train a multi-layer perceptron model. Intra-subject and inter-subject experimental settings are tested. The best-performing intra-subject approach is able to provide in the hemiplegic population a mean classification accuracy (±SD) of 0.97±0.01 and a suitable prediction of HS and TO events, in terms of average mean absolute error (MAE, 14.8±3.2 ms for HS and 17.6±4.2 ms for TO) and F1-score (0.95±0.03 for HS and 0.92±0.07 for TO). These results outperform previous sEMG-based attempts in cerebral-palsy populations and are comparable with outcomes achieved by reference approaches in control populations. In conclusion, the findings of the study prove the feasibility of neural networks in predicting the two main gait events using surface EMG signals, also in condition of high variability of the signal to predict as in hemiplegic cerebral palsy.

Foot progression angle estimation using a single foot-worn inertial sensor

Background

The foot progression angle is an important measure used to help patients reduce their knee adduction moment. Current measurement systems are either lab-bounded or do not function in all environments (e.g., magnetically distorted). This work proposes a novel approach to estimate foot progression angle using a single foot-worn inertial sensor (accelerometer and gyroscope).

Methods

The approach uses a dynamic step frame that is recalculated for the stance phase of each step to calculate the foot trajectory relative to that frame, to minimize effects of drift and to eliminate the need for a magnetometer. The foot progression angle (FPA) is then calculated as the angle between walking direction and the dynamic step frame. This approach was validated by gait measurements with five subjects walking with three gait types (normal, toe-in and toe-out).

Results

The FPA was estimated with a maximum mean error of ~ 2.6° over all gait conditions. Additionally, the proposed inertial approach can significantly differentiate between the three different gait types.

Conclusion

The proposed approach can effectively estimate differences in FPA without requiring a heading reference (magnetometer). This work enables feedback applications on FPA for patients with gait disorders that function in any environment, i.e. outside of a gait lab or in magnetically distorted environments.

Role of AI physical education based on application of functional sports training

The physical health test of college students is an important part of the school physical education work and an important part of the school education evaluation system. It is an educational method that promotes the healthy development of students’ physical fitness and encourages students to actively take physical exercises. It is an individual evaluation standard for students’ physical fitness. It is also one of the necessary conditions for students to graduate. In order to improve the physique and health of college students, this article first introduces functional exercise tests to comprehensively measure the exercise capacity of the main muscle groups and joints of the human body, and integrate flexibility and strength qualities. Secondly, this article quantitatively studies the interaction law between the natural light environment comfort of sports training facilities and architectural design elements, and adopts appropriate dynamic optimization methods to improve the light environment quality of the sports space, thereby enhancing the visual comfort of the sports crowd in the stadium. Finally, the artificial intelligence technology is introduced, through the design of artificial intelligence system, intelligent data collection, and analysis. From the perspective of physical education, the functional exercise test based on artificial intelligence conforms to the essential meaning of the physical fitness test and helps to enhance the awareness of college students’ physical exercise. And the intelligent remote multimedia physical education system based on artificial intelligence makes the physical education process flexible, free from time and place restrictions, and can adopt different teaching strategies according to the different situations of students to implement personalized teaching.

Analysis and Biophysics of Surface EMG for Physiotherapists and Kinesiologists: Toward a Common Language With Rehabilitation Engineers

Recent decades have seen a move toward evidence-based medicine to inform the clinical decision-making process with reproducible findings from high-quality research studies. There is a need for objective, quantitative measurement tools to increase the reliability and reproducibility of studies evaluating the efficacy of healthcare interventions, particularly in the field of physical and rehabilitative medicine. Surface electromyography (sEMG) is a non-invasive measure of muscle activity that is widely used in research but is under-utilized as a clinical tool in rehabilitative medicine. Other types of electrophysiological signals (e.g., electrocardiography, electroencephalography, intramuscular EMG) are commonly recorded by healthcare practitioners, however, sEMG has yet to successfully transition to clinical practice. Surface EMG has clear clinical potential as an indicator of muscle activation, however reliable extraction of information requires knowledge of the appropriate methods for recording and analyzing sEMG and an understanding of the underlying biophysics. These concepts are generally not covered in sufficient depth in the standard curriculum for physiotherapists and kinesiologists to encourage a confident use of sEMG in clinical practice. In addition, the common perception of sEMG as a specialized topic means that the clinical potential of sEMG and the pathways to application in practice are often not apparent. The aim of this paper is to address barriers to the translation of sEMG by emphasizing its benefits as an objective clinical tool and by overcoming its perceived complexity. The many useful clinical applications of sEMG are highlighted and examples provided to illustrate how it can be implemented in practice. The paper outlines how fundamental biophysics and EMG signal processing concepts could be presented to a non-technical audience. An accompanying tutorial with sample data and code is provided which could be used as a tool for teaching or self-guided learning. The importance of observing sEMG in routine use in clinic is identified as an essential part of the effective communication of sEMG recording and signal analysis methods. Highlighting the advantages of sEMG as a clinical tool and reducing its perceived complexity could bridge the gap between theoretical knowledge and practical application and provide the impetus for the widespread use of sEMG in clinic.

Intra-subject approach for gait-event prediction by neural network interpretation of EMG signals

BACKGROUND

Machine learning models were satisfactorily implemented for estimating gait events from surface electromyographic (sEMG) signals during walking. Most of them are based on inter-subject approaches for data preparation. Aim of the study is to propose an intra-subject approach for binary classifying gait phases and predicting gait events based on neural network interpretation of sEMG signals and to test the hypothesis that the intra-subject approach is able to achieve better performances compared to an inter-subject one. To this aim, sEMG signals were acquired from 10 leg muscles in about 10.000 strides from 23 healthy adults, during ground walking, and a multi-layer perceptron (MLP) architecture was implemented.

RESULTS

Classification/prediction accuracy was tested vs. the ground truth, represented by the foot-floor-contact signal provided by three foot-switches, through samples not used during training phase. Average classification accuracy of 96.1 ± 1.9% and mean absolute value (MAE) of 14.4 ± 4.7 ms and 23.7 ± 11.3 ms in predicting heel-strike (HS) and toe-off (TO) timing were provided. Performances of the proposed approach were tested by a direct comparison with performances provided by the inter-subject approach in the same population. Comparison results showed 1.4% improvement of mean classification accuracy and a significant (p < 0.05) decrease of MAE in predicting HS and TO timing (23% and 33% reduction, respectively).

CONCLUSIONS

The study developed an accurate methodology for classification and prediction of gait events, based on neural network interpretation of intra-subject sEMG data, able to outperform more typical inter-subject approaches. The clinically useful contribution consists in predicting gait events from only EMG signals from a single subject, contributing to remove the need of further sensors for the direct measurement of temporal data.

A Review of Gait Phase Detection Algorithms for Lower Limb Prostheses

Fast and accurate gait phase detection is essential to achieve effective powered lower-limb prostheses and exoskeletons. As the versatility but also the complexity of these robotic devices increases, the research on how to make gait detection algorithms more performant and their sensing devices smaller and more wearable gains interest. A functional gait detection algorithm will improve the precision, stability, and safety of prostheses, and other rehabilitation devices. In the past years the state-of-the-art has advanced significantly in terms of sensors, signal processing, and gait detection algorithms. In this review, we investigate studies and developments in the field of gait event detection methods, more precisely applied to prosthetic devices. We compared advantages and limitations between all the proposed methods and extracted the relevant questions and recommendations about gait detection methods for future developments.

Quantitative clinical assessment of motor function during and following LSVT-BIG® therapy

Background

LSVT-BIG® is an intensively delivered, amplitude-oriented exercise therapy reported to improve mobility in individuals with Parkinson’s disease (PD). However, questions remain surrounding the efficacy of LSVT-BIG® when compared with similar exercise therapies. Instrumented clinical tests using body-worn sensors can provide a means to objectively monitor patient progression with therapy by quantifying features of motor function, yet research exploring the feasibility of this approach has been limited to date. The aim of this study was to use accelerometer-instrumented clinical tests to quantify features of gait, balance and fine motor control in individuals with PD, in order to examine motor function during and following LSVT-BIG® therapy.

Methods

Twelve individuals with PD undergoing LSVT-BIG® therapy, eight non-exercising PD controls and 14 healthy controls were recruited to participate in the study. Functional mobility was examined using features derived from accelerometry recorded during five instrumented clinical tests: 10 m walk, Timed-Up-and-Go, Sit-to-Stand, quiet stance, and finger tapping. PD subjects undergoing therapy were assessed before, each week during, and up to 13 weeks following LSVT-BIG®.

Results

Accelerometry data captured significant improvements in 10 m walk and Timed-Up-and-Go times with LSVT-BIG® (p <  0.001), accompanied by increased stride length. Temporal features of the gait cycle were significantly lower following therapy, though no change was observed with measures of asymmetry or stride variance. The total number of Sit-to-Stand transitions significantly increased with LSVT-BIG® (p <  0.001), corresponding to a significant reduction of time spent in each phase of the Sit-to-Stand cycle. No change in measures related to postural or fine motor control was observed with LSVT-BIG®. PD subjects undergoing LSVT-BIG® showed significant improvements in 10 m walk (p <  0.001) and Timed-Up-and-Go times (p = 0.004) over a four-week period when compared to non-exercising PD controls, who showed no week-to-week improvement in any task examined.

Conclusions

This study demonstrates the potential for wearable sensors to objectively quantify changes in motor function in response to therapeutic exercise interventions in PD. The observed improvements in accelerometer-derived features provide support for instrumenting gait and sit-to-stand tasks, and demonstrate a rescaling of the speed-amplitude relationship during gait in PD following LSVT-BIG®.