Shank-mounted Inertial Measurement Units Research Articles

IMU-Based Real-Time Estimation of Gait Phase Using Multi-Resolution Neural Networks.

This work presents a real-time gait phase estimator using thigh- and shank-mounted inertial measurement units (IMUs). A multi-rate convolutional neural network (CNN) was trained to estimate gait phase for a dataset of 16 participants walking on an instrumented treadmill with speeds varying between 0.1 to 1.9 m/s, and conditions such as asymmetric walking, stop-start, and sudden speed changes. One-subject-out cross-validation was used to assess the robustness of the estimator to the gait patterns of new individuals. The proposed model had a spatial root mean square error of 5.00±1.65%, and a temporal mean absolute error of 2.78±0.97% evaluated at the heel strike. A second cross-validation was performed to show that leaving out any of the walking conditions from the training dataset did not result in significant performance degradation. A 2-sample Kolmogorov-Smirnov test showed that there was no significant increase in spatial or temporal error when testing on the abnormal walking conditions left out of the training set. The results of the two cross-validations demonstrate that the proposed model generalizes well across new participants, various walking speeds, and gait patterns, showcasing its potential for use in investigating patient populations with pathological gaits and facilitating robot-assisted walking.

A Potential-Real-Time Thigh Orientation Prediction Method Based on Two Shanks-Mounted IMUs and Its Clinical Application

The detection and evaluation of gait kinematics is vital for patient diagnosis and rehabilitation. Aiming at limitations of commonly used optical capture and wearable sensing systems in clinical applications, this paper proposes a thigh attitude angle prediction method based on the hip error tolerance from the kinematic data of two shank-mounted IMUs (Inertial Measurement Unit). The novelties of the proposed method are summarized as follows: i) It develops a parallel approach to regress variation of hip error tolerance for different subjects. This parallel approach, by simultaneously deconstructing the shank kinematics data via different regression algorithm including support vector machine, boosting tree, and stepwise linearity regression, is able to well accommodate the characteristics of both health subjects and patients. ii) It develops some evaluation indices based on gait symmetry, consistency, and activity to fully evaluate the human lower limbs motion performance in gait by only two IMUs. The effectiveness of the proposed method is verified by the experimental results among 8 healthy subjects and 16 cerebral infarction patients. For the healthy subjects, the estimated error of thigh prediction compared with Xsens and Vicon are <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$3.3 \pm {0.3^ \circ }$</tex-math> </inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$3.5 \pm {0.7^ \circ }$</tex-math> </inline-formula> , respectively. For the patients, the estimated error compared with Xsens-measured angle is <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$4.8 \pm {1.7^ \circ }$</tex-math> </inline-formula> . Its broad significance in actual intelligent healthcare and robotics-assisted rehabilitation is three-fold: First, it is a recursive real-time method as it only needs data from the previous gait cycle to predict the thigh angle. Second, its accuracy meets the actual clinical needs. Third, it is a low-cost method that only needs two IMUs and has high potentials of clinical applications. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Gait is of great significance to quantify the degree of movement disorders in clinical practice, and the existing equipment is rarely able to meet the needs of full dimension, low cost, and low place constraints in clinical practice. This paper presents an innovative gait kinematic prediction method, which only uses two IMUs attached to the shanks to predict the orientation of thigh. Compared with related works, the proposed methods have achieved high-precision, real-time and low-cost acquisition. This paper is inspired by the problems of large number, high motion interference, and high cost of wearable gait measurement devices in clinical practice. The proposed method have potential to be integrated into exoskeletons and medical walking AIDS, which could greatly improve the comfort and control precision of the wearable system.

Monitoring physical activity using wearable technology in people with Achilles tendinopathy undergoing physiotherapy treatment: A feasibility prospective cohort study

ObjectivesPhysical activity modification is an important part of the management of Achilles tendinopathy. However, to our knowledge, there is a lack of evidence on objective physical activity assessment in Achilles tendinopathy. The purpose of this study is to (1) assess feasibility of using an inertial measurement unit (IMU) to monitor physical activity and IMU-derived biomechanical measures over 12-week treatment course by a physiotherapist; (2) conduct a preliminary analysis of changes in physical activity over 12-weeks. DesignA feasibility prospective cohort study SettingA community setting. ParticipantsPeople with Achilles tendinopathy who had recently commenced (≤2 sessions), or were about to commence, treatment with a physiotherapist Main outcome measuresParticipants wore a shank-mounted IMU on the affected side for one week at baseline, 6-, and 12-week follow-ups. The outcomes were pain/symptom severity, IMU-derived physical activity and biomechanical measures (stride rate, peak shank angular velocity, and peak shank acceleration). ResultsThirty participants were recruited. There was a high retention rate (97%), response rate (97%), and IMU wear compliance at each timepoint (>93%). For pain/symptom severity, a significant time effect was observed between baseline and 12-week follow-up. Physical activity and IMU-derived biomechanical measures did not change over 12 weeks. Physical activity decreased at the 6-week follow-up but only returned to the baseline level at 12-week follow-up. ConclusionsA larger-scale cohort study assessing clinical outcomes and physical activity appears feasible. Preliminary data indicate that physical activity may not change significantly over 12-weeks in people undergoing physiotherapy management for Achilles tendinopathy. Contribution of the paper•A larger-scale cohort study assessing physical activity using wearable technology over 12 weeks of treatment by a physiotherapist appears feasible.•Preliminary findings indicate physical activity may not change significantly over 12-weeks of treatment by a physiotherapist for people with Achilles tendinopathy.•Changes in pain and symptom severity after 12 weeks of treatment by a physiotherapist are not correlated with changes in physical activity level.

Prescreening MCI and Dementia Using Shank-Mounted IMU During TUG Task

Detection of mild cognitive impairment (MCI) and dementia (DEM) is an important topic because, unless it is treated early, MCI can progress to DEM, which is an untreatable disease. This article proposes a timed-up-and-go (TUG) task features analysis and classification of MCI and DEM using inertial measurement units (IMUs) in wearable devices. Our goal is to create a generalized model that can be used for preclinical screening. As a result, rather than classifying only one subtype of DEM, such as Alzheimer’s disease (AD) or Parkinson’s disease (PD), we classify all subtypes as DEM. We also utilize feature selection methods on features from TUG tasks to optimize the MCI and DEM classification performance. From the results, our generalized model can outperform other works in normal control (NC)-MCI&DEM classification with an accuracy of 86.94% and sensitivity of 97.40%. For NC-DEM classification, the performance of our generalized model is slightly lower than that of specific-subtype models (e.g., NC versus AD). However, our generalized model can outperform the specific-subtype models when using a diverse variety of subtypes. It is a reasonable tradeoff, and it can be a good first step toward a future where the patient can preclinically self-screening the cognitive impairments using wearable devices in free-living environments. This could allow patients to notice the cognitive impairment early on and seek a comprehensive diagnosis from a doctor.

Walking Distance Estimation Using a Shank-Mounted Inertial Measurement Unit and Vertical Distance Sensor

This paper investigates whether adding a vertical distance sensor to a shank-mounted inertialmeasurement unit can improvewalking distance estimation accuracy. Some important features that can be extracted from the vertical distance sensor and a gyroscope were proposed, and the model was validated with personalized and generalized parameters. Results showthat the vertical distance sensor is unnecessary for personalized model, but can retain the estimation accuracy of generalized model at 96%. As a comparison, many existing methods yield high accuracy for personalized model, but some has the accuracy reduced by 5-10% for generalized model.

Validation of IMU-based gait event detection during curved walking and turning in older adults and Parkinson\u2019s Disease patients

BackgroundIdentification of individual gait events is essential for clinical gait analysis, because it can be used for diagnostic purposes or tracking disease progression in neurological diseases such as Parkinson’s disease. Previous research has shown that gait events can be detected from a shank-mounted inertial measurement unit (IMU), however detection performance was often evaluated only from straight-line walking. For use in daily life, the detection performance needs to be evaluated in curved walking and turning as well as in single-task and dual-task conditions.MethodsParticipants (older adults, people with Parkinson’s disease, or people who had suffered from a stroke) performed three different walking trials: (1) straight-line walking, (2) slalom walking, (3) Stroop-and-walk trial. An optical motion capture system was used a reference system. Markers were attached to the heel and toe regions of the shoe, and participants wore IMUs on the lateral sides of both shanks. The angular velocity of the shank IMUs was used to detect instances of initial foot contact (IC) and final foot contact (FC), which were compared to reference values obtained from the marker trajectories.ResultsThe detection method showed high recall, precision and F1 scores in different populations for both initial contacts and final contacts during straight-line walking (IC: recall = 100%, precision = 100%, F1 score = 100%; FC: recall = 100%, precision = 100%, F1 score = 100%), slalom walking (IC: recall = 100%, precision ge 99%, F1 score =100%; FC: recall = 100%, precision ge 99%, F1 score =100%), and turning (IC: recall ge 85%, precision ge 95%, F1 score ge91%; FC: recall ge 84%, precision ge 95%, F1 score ge89%).ConclusionsShank-mounted IMUs can be used to detect gait events during straight-line walking, slalom walking and turning. However, more false events were observed during turning and more events were missed during turning. For use in daily life we recommend identifying turning before extracting temporal gait parameters from identified gait events.

Reconstructing Walking Dynamics From Two Shank-Mounted Inertial Measurement Units

Inertial measurement unit (IMU)-based sensing systems have received extensive attention for wearable gait measurement due to their small size, low price, and high accuracy. However, reconstructing walking dynamics usually requires a large number of sensor units attached to major body segments, which is generally not suitable for daily-life scenarios. Previous studies showed that two shank-mounted IMUs can detect gait events and estimate many important gait parameters. However, it is unclear whether this simple two-IMU system can be used to reconstruct walking dynamics. In this article, we propose a two-stage method for predicting walking dynamics from measurements of two shank-mounted IMUs. Displacements of ankle joints and shank angles are first estimated from the IMU outputs. Then, a model-based whole-step optimization approach is used to solve the gait dynamics by tracking the estimated shank motion. The proposed method is validated with both normal and asymmetric walking data, achieving a root-mean-square error of 5.3°, 6.1°, and 6.8° in the hip, knee, and ankle joint angle estimation and 3.9% and 12.2% body weight in the fore-aft and vertical ground reaction force estimation. Comparing with the reported results in the literature, the number of IMUs is significantly reduced with similar accuracy. This implies that gait dynamic information may be estimated from very limited measurements and the inherent gait characteristics can be used to reconstruct gait dynamics from the motion of a small number of segments.

American Academy of Sports Physical Therapy Platform Presentation Abstracts SPL1–SPL82

American Academy of Sports Physical Therapy Platform Presentation Abstracts SPL1–SPL82

IMU-Based Gait Normalcy Index Calculation for Clinical Evaluation of Impaired Gait.

Inertial measurement units (IMU) have been used for gait analysis in many clinical studies, as a more convenient, low cost and less restricted alternative to the laboratory-based motion capture systems or instrumented walkways. Spatial-temporal gait parameters such as gait cycle duration and stride length calculated from the IMUs were often used in these studies for evaluating the impaired gait. However, the spatial-temporal information provided by IMUs is limited, and sometime suffers incomplete and less effective evaluation. In this study, we develop a novel IMU-based method for clinical gait evaluation. Nine gait variables including three spatial-temporal parameters and six kinematic parameters are extracted from two shank-mounted IMUs for quantifying patient's gait deviations. Based on those parameters, an IMU-based gait normalcy index (INI) is derived to evaluate the overall gait performance. Eight inpatient subjects with gait impairments caused by n-hexane neuropathy and ten healthy subjects were recruited. The proposed gait variables and INI were examined on the inpatients at three to five time instants during the rehabilitation process until being discharged. A comparison with healthy subjects and statistical analysis for the changes of gait variables and INI demonstrated that the proposed new set of gait variables and INI can provide adequate and effective information for quantifying gait abnormalities, and help understanding the progress of gait and effectiveness of therapy during rehabilitation process.

Combining deep learning and model-based method using Bayesian Inference for walking speed estimation

In this paper, deep learning and model-based method were combined using Bayesian Inference to realize high accuracy and good generalization capability stride-by-stride walking speed estimation by low cost inertial measurement unit (IMU) sensor. Long Short-Term Memory (LSTM) network was applied to train the prediction model because of its ability to consider the temporal correlation of multi-dimensional kinematic parameters during one stride. To improve the performance with unseen subjects, a model-based method was introduced for its relatively good generalization capability. Fusion strategy based on Bayesian Inference was applied to take advantage of the two methods which considered the estimation derived from different methods as abstract sensors. Six healthy young adults performed treadmill walking with shank-mounted IMU and the range of the walking speed was 2.5 km/h to 5 km/h at an increment of 0.5 km/h. Leave-one-subject-out (LOSO) cross-validation was performed to analyze the generalization capability. For deep learning method, the root mean square error (RMSE) of the model trained by all available subjects was 0.026 m/s and the RMSE of LOSO cross-validation was 0.066 m/s which indicated a low generalization capability. After the fusion strategy was applied, RMSE of the model trained by all available subjects was 0.023 m/s which was slightly improved, while the RMSE of LOSO cross-validation was reduced to 0.036 m/s which indicated that accuracy and the generalization capability was greatly improved. In addition, this accurate estimation can be easily realized online which is essential for locomotion interactive systems (e.g. self-paced treadmill).

Two Shank-Mounted IMUs-Based Gait Analysis and Classification for Neurological Disease Patients

Automatic gait measurement and analysis is an enabling tool for intelligent healthcare and robotics-assisted rehabilitation. This letter proposes a novel two shank-mounted inertial measurement units (IMU)-based method on gait analysis and classification for three different neurological diseases. The IMU-based gait analysis and design aims to be applied in personal daily activities and environment for remote diagnosis and rehabilitation guidance. In the design, eight spatial-temporal and kinematic gait parameters are extracted from two shank-mounted IMUs. A support vector machine-based classifier is developed to classify four types of gait patterns with different neurological diseases (healthy control, peripheral neuropathy, post-stroke and Parkinson's disease). A total of 49 subjects are recruited and 93.9% of them are assigned to the right group after the leave-one-subject-out cross validation. The results demonstrate that the proposed IMU-based gait parameters and classifier are capable of differentiating the four types of gait patterns. The analysis and design have great potentials for use in clinical applications.

RNN-Based On-Line Continuous Gait Phase Estimation from Shank-Mounted IMUs to Control Ankle Exoskeletons.

Several research groups have developed and studied powered ankle exoskeletons to improve energetics of healthy subjects and the mobility of elderly subjects, or to reduce asymmetry in gaits induced by strokes. To achieve optimal effect, the timing of assistive torque has been proved to be of crucial importance. Previous studies estimated the onset timings mostly by extrapolating the time horizon from past gait events observed with sensors. Such methods have inherently limited performance when subjects are not walking at steady frequencies. To overcome such limitation and allow the use of exoskeletons in various scenarios in a daily life, we propose to estimate the gait phase as a continuous variable progressing over a gait cycle, hence allowing immediate response to frequency changes rather than iteratively correcting it after each cycle. Our method uses recurrent neural networks to estimate gait phases out of an inertial measurement unit (IMU) every 10 ms. By replacing foot sensors with an IMU we can obtain rich enough information to estimate gait phase continuously as well as avoid physical damage in sensors from ground impacts. Our preliminary tests with 2 healthy subjects showed qualitatively positive outcomes regarding the gait phase estimation and the assistive torque control.

Activity classification in persons with stroke based on frequency features

Recent advances in the use of inertial measurement units (IMUs) for motion analysis suggest the possibility of using this technology for the monitoring of daily activities of individuals during rehabilitation post-stroke. Previous studies have utilized features extracted from accelerometer and gyroscope signals to develop classification models capable of identifying activities performed within large datasets. In this study, nine k-nearest neighbor cross-validated classifiers were developed using frequency-features derived from shank-mounted IMUs on the less-affected and affected limbs of subjects with stroke. These classifiers were evaluated for two separate datasets of post-stroke gait; the first a classification of three separate gait activities (overground walking, stair ascent, and stair descent), and the second a classification of five gait activities, overground walking, stair ascent, and descent with a distinction between stepping pattern used while negotiating stairs (step-over-step (SOS) and step-by-step (SBS)). The comparison showed the highest classification accuracy, 100% for the three-activities and 94% for the five-activities, was obtained using a classifier composed of features derived from accelerometer and gyroscope measurements from both IMUs on less-affected and affected limbs.

Ambulatory running speed estimation using an inertial sensor

Abstract Techniques have been developed to analyze walking gait using accelerometer and gyroscope data from miniature inertial measurement units (IMU), but few attempts have been made to use similar approaches for running gait. The purpose of this study was to develop an algorithm capable of estimating running speed using a single shank-mounted IMU. Raw acceleration and angular velocity were recorded from an IMU sensor attached on the lateral side of the shank in the sagittal plane and a method of reliably detecting the shank vertical and the minimal shank velocity gait event was used to segment a running sequence into individual strides. Through integration, the orientation of the shank segment was determined and an estimate of stride-by-stride running speed was calculated by integrating the acceleration data. The algorithm was verified using data collected from a group of seven volunteers running on a treadmill at speeds between 2.50 m/s and 3.50 m/s. Over the entire speed range, the estimation results gave a percentage root mean square error (%RMSE) of approximately 4.10%. With the accurate estimation capability and portability, the use of the proposed system in outdoor running gait analysis is promising.

Walking speed estimation using a shank-mounted inertial measurement unit

We studied the feasibility of estimating walking speed using a shank-mounted inertial measurement unit. Our approach took advantage of the inverted pendulum-like behavior of the stance leg during walking to identify a new method for dividing up walking into individual stride cycles and estimating the initial conditions for the direct integration of the accelerometer and gyroscope signals. To test its accuracy, we compared speed estimates to known values during walking overground and on a treadmill. The speed estimation method worked well across treadmill speeds and slopes yielding a root mean square speed estimation error of only 7%. It also worked well during overground walking with a 4% error in the estimated travel distance. This accuracy is comparable to that achieved from foot-mounted sensors, providing an alternative in sensor positioning for walking speed estimation. Shank mounted sensors may be of great benefit for estimating speed in walking with abnormal foot motion and for the embedded control of knee-mounted devices such as prostheses and energy harvesters.