Wearable Inertial Measurement Units Research Articles

Wearable IMU-based real-time motion warning system for construction workers' musculoskeletal disorders prevention

Abstract The prevalent work-related musculoskeletal disorders (WMSDs) around lower back and neck amongst construction workers are precursors of operational injury in the construction industry. As a significant risk factor of WMSDs, time spent in insecure operational postures should be proactively prevented. This study developed a real-time motion warning personal protective equipment (PPE) that enables workers' self-awareness and self-management of ergonomically hazardous operational pattern for the prevention of WMSDs based on wearable Inertial Measurement Units (WIMUs). Data processing and real-time warning algorithms are proposed for automatically risk postures assessment and warning through a connected smartphone application as soon as dangerous operational patterns are detected. The system was tested and validated with robust clinical motion data output and effective alarm ringing in both laboratory and field experiments on a construction site in Hong Kong. The proposed PPE provides an alternative to help construction workers prevent WMSDs without disturbance and distraction in operations.

Regression Model-Based Walking Speed Estimation Using Wrist-Worn Inertial Sensor.

Walking speed is widely used to study human health status. Wearable inertial measurement units (IMU) are promising tools for the ambulatory measurement of walking speed. Among wearable inertial sensors, the ones worn on the wrist, such as a watch or band, have relatively higher potential to be easily incorporated into daily lifestyle. Using the arm swing motion in walking, this paper proposes a regression model-based method for longitudinal walking speed estimation using a wrist-worn IMU. A novel kinematic variable is proposed, which finds the wrist acceleration in the principal axis (i.e. the direction of the arm swing). This variable (called pca-acc) is obtained by applying sensor fusion on IMU data to find the orientation followed by the use of principal component analysis. An experimental evaluation was performed on 15 healthy young subjects during free walking trials. The experimental results show that the use of the proposed pca-acc variable can significantly improve the walking speed estimation accuracy when compared to the use of raw acceleration information (p<0.01). When Gaussian process regression is used, the resulting walking speed estimation accuracy and precision is about 5.9% and 4.7%, respectively.

Context-aware fall detection using inertial sensors and time-of-flight transceivers.

Automatic detection of falls is important for enabling people who are older to safely live independently longer within their homes. Current automated fall detection systems are typically designed using inertial sensors positioned on the body that generate an alert if there is an abrupt change in motion. These inertial sensors provide no information about the context of the person being monitored and are prone to false positives that can limit their ongoing usage. We describe a fall-detection system consisting of a wearable inertial measurement unit (IMU) and an RF time-of-flight (ToF) transceiver that ranges with other ToF beacons positioned throughout a home. The ToF ranging enables the system to track the position of the person as they move around a home. We describe and show results from three machine learning algorithms that integrate context-related position information with IMU based fall detection to enable a deeper understanding of where falls are occurring and also to improve the specificity of fall detection. The beacons used to localize the falls were able to accurately track to within 0.39 meters of specific waypoints in a simulated home environment. Each of the three algorithms was evaluated with and without the context-based false alarm detection on simulated falls done by 3 volunteer subjects in a simulated home. False positive rates were reduced by 50% when including context.

Characterization of multi-joint upper limb movements in a single task to assess bradykinesia

Bradykinesia is a disabling symptom of Parkinson's disease (PD) which presents with slowness of movement. Visual assessment using clinical rating scales is currently the gold standard to assess bradykinesia. Such assessments require multiple separate movements, are subjective, and rely on the ability of the rater to determine frequency and amplitude features of excursion of multiple joints simultaneously.The current study introduces the use of wearable inertial measurement units (IMUs) to characterize full-arm repetitive movements and provide a new index score for bradykinesia severity (BKI) in the upper limbs. The BKI provides an approach to measuring bradykinesia reliably and objectively. Importantly, this index is needed to demonstrate separability between healthy individuals and PD participants, and also between bradykinetic and non-bradykinetic PD participants.Thirteen PD participants and ten age-matched healthy control participants were studied. Using a single upper limb task that activated multiple joints and recordings from angular displacements from all joints, features relevant to demonstrating bradykinesia were extracted and systematically combined to create the total BKI. A strong correlation coefficient was obtained comparing BKI to upper limb UPDRS bradykinesia scores (rs=−0.626, p=0.001). The BKI successfully identified differences between control and PD participants (p=0.018). The BKI was also sensitive enough to identify differences within the PD population, separating PD participants with and without bradykinesia (p<0.001).This study demonstrates the feasibility of using IMU-based motion capture systems and employing the new BKI for quantitative assessment of bradykinesia. This approach when generalized to lower extremity and truncal movements would be able to provide an objective and reproducible whole body bradykinesia index.

The feasibility of shoulder motion tracking during activities of daily living using inertial measurement units

Measurements of shoulder kinematics during activities of daily living (ADL) can be used to evaluate patient function before and after treatment and help define device testing conditions. The purpose of this study was to demonstrate the feasibility of using wearable inertial measurement units (IMUs) to track shoulder joint angles while performing actual ADLs outside of laboratory simulations. IMU data of 5 subjects with normal shoulders was collected for 4h at the subjects’ workplace and up to 4h off-work. An Unscented Kalman Filter (UKF) enhanced with gyroscope bias modeling and zero velocity updates demonstrated an accuracy of about 2° and was used to estimate relative upper arm angles from the IMU data. The overall averaged 95th percentile angles were: flexion 128.8°, abduction 128.4°, and external rotation 69.5°. These peaks angles are similar to other investigator’s reports using laboratory simulations of ADLs measured with optical and electromagnetic technologies. Additionally, with a Fourier transform the 50th percentile frequency was determined and used to extrapolate the typical number of arm cycles in a 10year period to be 649,000. Application of the UKF with the additional drift correction made substantial improvements in shoulder tracking performance and this feasibility data suggests that IMUs with the UKF are suitable for extended use outside of laboratory settings. The data provides a novel description of arm motion during ADLs including an estimate for the 10 year cycle count of upper arm motion.

Semi-supervised near-miss fall detection for ironworkers with a wearable inertial measurement unit

Accidental falls (slips, trips, and falls from height) are the leading cause of occupational death and injury in construction. As a proactive accident prevention measure, near miss can provide valuable data about the causes of accidents, but collecting near-miss information is challenging because current data collection systems can largely be affected by retrospective and qualitative decisions of individual workers. In this context, this study aims to develop a method that can automatically detect and document near-miss falls based upon a worker's kinematic data captured from wearable inertial measurement units (WIMUs). A semi-supervised learning algorithm (i.e., one-class support vector machine) was implemented for detecting the near-miss falls in this study. Two experiments were conducted for collecting the near-miss falls of ironworkers, and these data were used to test developed near-miss fall detection approach. This WIMU-based approach will help identify ironworker near-miss falls without disrupting jobsite work and can help prevent fall accidents.

Balancing noise sensitivity, response latency, and posture accuracy for a computer-assisted canine posture training system

This paper describes a canine posture detection system composed of wearable sensors and instrumented devices that detect the postures sit, stand, and eat. The system consists of a customized harness outfitted with wearable Inertial Measurement Units (IMUs) and a base station for processing IMU data to classify canine postures. Research in operant conditioning, the science of behavior change, indicates that successful animal training requires consistent and accurate feedback on behavior. Properly designed computer systems excel at timeliness and accuracy, which are two characteristics most amateur trainers struggle with and professionals strive for. Therefore, in addition to the system being ergonomically designed to ensure the dog's comfort and well-being, it is engineered to provide posture detection with timing and accuracy on par with a professional trainer. We contend that providing a system with these characteristics will one day aid dogs in learning from humans by overcoming poor or ineffective timing during training. We present the initial steps in the development and validation of a computer-assisted training system designed to work outside of laboratory environments.The main contributions of this work are (a) to explore the trade-off between low-latency responses to changes in time-series IMU data representative of posture changes while maintaining accuracy and timing similar to a professional trainer, and (b) to provide a model for future ACI technologies by documenting the user-centered approach we followed to create a computer-assisted training system that met the criteria identified in (a). Accordingly, in addition to describing our system, we present the results of three experiments to characterize the performance of the system at capturing sit postures of dogs and providing timely reinforcement. These trade-offs are illustrated through the comparison of two algorithms. The first is Random Forest classification and the second is an algorithm which uses a Variance-based Threshold for classification of postures. Results indicate that with proper parameter tuning, our system can successfully capture and reinforce postures to provide computer-assisted training of dogs.

Inertial Measurement Unit-Based Wearable Computers for Assisted Living Applications: A signal processing perspective

There has been a very rapid growth in wearable computers over the past few years. Assisted living applications leveraging wearable computers will enable a healthier lifestyle and independence in a variety of target populations, including those suffering from neurological disorders, patients in need of rehabilitation after surgical procedures or injury, the elderly, individuals who might be at high risk of emotional stress, and those who are looking for a healthier lifestyle. Application paradigms for assisted living include activities of daily living (ADLs) monitoring, indoor localization, emergency and fall detection, and rehabilitation. All of these applications require monitoring of movements and physical activities for individuals. Wearable inertial measurement unit (IMU)-based sensors can offer low-cost and ubiquitous monitoring solutions for physical activities. Signal processing techniques with a focus on enhancing accuracy, lowering computational complexity, reducing power consumption, and improving the unobtrusiveness of the wearable computers are of interest in this article, which constitutes the first attempt made at reviewing the literature of wearable IMU-based signal processing techniques for assisted living applications. Various signal processing techniques with the aforementioned performance metrics in mind are reviewed here.

Estimation of foot trajectory during human walking by a wearable inertial measurement unit mounted to the foot

To establish a supportive technology for reducing the risk of falling in older people, it is essential to clarify gait characteristics in elderly individuals that are possibly linked to the risk of falling during actual daily activities. In this study, we developed a system to monitor human gait in an outdoor environment using an inertial measurement unit consisting of a tri-axial accelerometer and tri-axial gyroscope. Step-by-step foot trajectories were estimated from the sensor unit attached to the dorsum of the foot. Specifically, stride length and foot clearance were calculated by integrating the gravity-compensated translational acceleration over time during the swing phase. Zero vertical velocity and displacement corrections were applied to obtain the final trajectory, assuming the slope of the walking surface is negligible. Short, normal, and long stride-length walking of 10 healthy participants was simultaneously measured using the proposed system and a conventional motion capture system to evaluate the accuracy of the estimated foot trajectory. Mean accuracy and precision were approximately 20±50mm, for stride length, and 2±7mm for foot clearance, indicating that the swing phase trajectory of the sensor unit attached to the foot was reconstructed more accurately and precisely using the proposed system than with previously published methods owing to the flat floor assumption. Although some methodological limitations certainly apply, this system will serve as a useful tool to monitor human walking during daily activities.

Front-crawl stroke descriptors variability assessment for skill characterisation

ABSTRACTThe goal of this article is to characterise front-crawl swimming skill based on variability pattern of technique descriptors. Nine national level and nine recreational swimmers performed three 300 m trials in a 50 m outdoor pool, at 70%, 80% and 90% of their front-crawl 400 m personal best time. Using wearable inertial measurement units (IMUs) and validated algorithms we assessed the variability of technique descriptors at each arm cycle (139 ± 17 per trial). We calculated the duration of pull, push and non-propulsive phases, index of coordination (IdC), stroke length, stroke rate and intra-cyclic velocity variation. To track intra-trial technique variability, we calculated the Cauchy index to quantify the stability of multidimensional technique descriptors in space–time. Skilled swimmers, having access to divers motor solutions, achieved significantly higher velocities at similar intensities and similar IdC (P < 0.01) with more stable motor pattern (smaller Cauchy index). Besides, the similarity of intra-cyclic velocity variation at different intensities denotes that skilled swimmers used a wider dynamic range of velocity. We also introduced cycle velocity variation as a new metric of propulsive pattern repeatability and showed cycle velocity variation changes is correlated to the Cauchy index (rx,y = 0.72, P < 0.01). These findings indicate that IdC can be used as a predictor of performance only when swimmers of homogeneous expertise level are studied and suggest the scrutiny of both intra-cyclic velocity variation and cycle velocity variation as a requisite to study the motor adaptations of the swimmer in facing new constraints.

Objective Assessment of Upper-Limb Mobility for Poststroke Rehabilitation.

The assessment of the limb mobility of stroke patients is an essential part of poststroke rehabilitation. Conventionally, the assessment is manually performed by clinicians using chart-based ordinal scales, which can be subjective and inefficient. By introducing quantitative evaluation measures, the sensitivity and efficiency of the assessment process can be significantly improved. In this paper, a novel single-index-based assessment approach for quantitative upper-limb mobility evaluation has been proposed for poststroke rehabilitation. Instead of the traditional human-observation-based measures, the proposed assessment system utilizes the kinematic information automatically collected during a regular rehabilitation training exercise using a wearable inertial measurement unit. By calculating a single index, the system can efficiently generate objective and consistent quantitative results that can reflect the stroke patient's upper-limb mobility. In order to verify and validate the proposed assessment system, experiments have been conducted using 145 motion samples collected from 21 stroke patients (12 males, nine females, mean age 58.7±19.3) and eight healthy participants. The results have suggested that the proposed assessment index can not only differentiate the levels of limb function impairment clearly (p < 0.001, two-tailed Welch's t-test), but also strongly correlate with the Brunnstrom stages of recovery (r = 0.86, p < 0.001). The assessment index is also proven to have great potential in automatic Brunnstrom stage classification application with an 82.1% classification accuracy, while using a K-nearest-neighbor classifier.

Experimental Design and Its Posterior Efficiency for the Calibration of Wearable Sensors

This paper investigates experimental design (DoE) for the calibration of the triaxial accelerometers embedded in a wearable micro Inertial Measurement Unit (μ-IMU). Firstly, a new linearization strategy is proposed for the accelerometer model associated with the so-called autocalibration scheme. Then, an effective Icosahedron design is developed, which can achieve both D-optimality and G-optimality for linearized accelerometer model in ideal experimental settings. However, due to various technical limitations, it is often infeasible for the users of wearable sensors to fully implement the proposed experimental scheme. To assess the efficiency of each individual experiment, an index is given in terms of desired experimental characteristic. The proposed experimental scheme has been applied for the autocalibration of a newly developed μ-IMU.

Ambulatory assessment of shoulder abduction strength curve using a single wearable inertial sensor.

The aim of the present article was to assess the reliability of strength curves as determined from tridimensional linear accelerations and angular velocities measured by a single inertial measurement unit (IMU) fixed on the upper arm during a shoulder abduction movement performed holding a 1 kg dumbbell in the hand. Within-subject repeatability of the task was assessed on 45 subjects performing four trials consisting of one maximal shoulder abduction-adduction movement. Intraclass correlation coefficient (ICC) was computed on the average movement angular velocity (VEL) and range of movement (ROM) across the four trials. Within-subject repeatability of torque curves was assessed in terms of waveform similarities by computing the coefficient of multiple determination (CMD). Accuracy of the estimated ROM was assessed using an isokinetic dynamometer. High ICC values of ROM (0.955) and VEL (0.970) indicated a high within-subject repeatability of the task. A high waveform similarity of torque curves was also found between trials (CMD = 0.867). Accuracy with respect to isokinetic dynamometer in estimating ROM was always <1 degree (p = 0.37). This study showed the effectiveness of using a single wearable IMU for the assessment of strength curve during isoinertial movements in a way that complies with the needs of clinicians in an ambulatory setting.

The effect of levodopa on postural stability evaluated by wearable inertial measurement units for idiopathic and vascular Parkinson's disease

BackgroundPostural stability analysis has shown that postural control is impaired in untreated idiopathic Parkinson's disease (IPD), even in the early stages of the disease. Vascular Parkinson's disease (VPD) lacks consensus clinical criteria or diagnostic tests. Moreover, the levodopa effect on postural balance remains undefined for IPD and even less so for VPD. ObjectiveTo characterize postural stability, using kinematic analysis with wearable inertial measurement units, in IPD and VPD patients without clinical PI, and to subsequently analyze the response to levodopa. MethodsTen patients with akinetic-rigid IPD and five patients with VPD were included. Clinical and postural stability kinematic analysis was performed before and after levodopa challenge, on different standing tasks: normal stance (NS), Romberg eyes open (REO) and Romberg eyes closed. ResultsIn the “off state”, VPD patients had higher mean distances and higher maximal distance of postural sway on NS and REO tasks, respectively. VPD patients maintained a higher range of anterior–posterior (AP) postural sway after levodopa. In the absence of PI and non-significant differences in UPDRS-III, a higher mPIGD score in the VPD patients was mainly due to gait disturbance. Gait disturbance, and not UPDRS-III, influenced the degree of postural sway response to levodopa for VPD patients. ConclusionQuantitative postural sway evaluation is useful in the investigation of Parkinsonian syndromes. VPD patients have higher AP postural sway that is correlated with their gait disturbance burden and also not responsive to levodopa. These observations corroborate the interconnection of postural control and locomotor networks.

Computational state space models for activity and intention recognition. A feasibility study.

BackgroundComputational state space models (CSSMs) enable the knowledge-based construction of Bayesian filters for recognizing intentions and reconstructing activities of human protagonists in application domains such as smart environments, assisted living, or security. Computational, i. e., algorithmic, representations allow the construction of increasingly complex human behaviour models. However, the symbolic models used in CSSMs potentially suffer from combinatorial explosion, rendering inference intractable outside of the limited experimental settings investigated in present research. The objective of this study was to obtain data on the feasibility of CSSM-based inference in domains of realistic complexity.MethodsA typical instrumental activity of daily living was used as a trial scenario. As primary sensor modality, wearable inertial measurement units were employed. The results achievable by CSSM methods were evaluated by comparison with those obtained from established training-based methods (hidden Markov models, HMMs) using Wilcoxon signed rank tests. The influence of modeling factors on CSSM performance was analyzed via repeated measures analysis of variance.ResultsThe symbolic domain model was found to have more than states, exceeding the complexity of models considered in previous research by at least three orders of magnitude. Nevertheless, if factors and procedures governing the inference process were suitably chosen, CSSMs outperformed HMMs. Specifically, inference methods used in previous studies (particle filters) were found to perform substantially inferior in comparison to a marginal filtering procedure.ConclusionsOur results suggest that the combinatorial explosion caused by rich CSSM models does not inevitably lead to intractable inference or inferior performance. This means that the potential benefits of CSSM models (knowledge-based model construction, model reusability, reduced need for training data) are available without performance penalty. However, our results also show that research on CSSMs needs to consider sufficiently complex domains in order to understand the effects of design decisions such as choice of heuristics or inference procedure on performance.

Toward Real-Time Automated Detection of Turns during Gait Using Wearable Inertial Measurement Units

Previous studies have presented algorithms for detection of turns during gait using wearable sensors, but those algorithms were not built for real-time use. This paper therefore investigates the optimal approach for real-time detection of planned turns during gait using wearable inertial measurement units. Several different sensor positions (head, back and legs) and three different detection criteria (orientation, angular velocity and both) are compared with regard to their ability to correctly detect turn onset. Furthermore, the different sensor positions are compared with regard to their ability to predict the turn direction and amplitude. The evaluation was performed on ten healthy subjects who performed left/right turns at three amplitudes (22, 45 and 90 degrees). Results showed that turn onset can be most accurately detected with sensors on the back and using a combination of orientation and angular velocity. The same setup also gives the best prediction of turn direction and amplitude. Preliminary measurements with a single amputee were also performed and highlighted important differences such as slower turning that need to be taken into account.

Human–robot interaction based on wearable IMU sensor and laser range finder

Service robots are not only expected to navigate within the environment, as they also will may with people. Human tracking by mobile robots is essential for service robots and human interaction applications. In this work, the goal is to add a more natural robot–human following in front based on the normal human gait model. This approach proposes implementing and evaluating a human–robot interaction strategy, using the integration of a LRF (Laser Range Finder) tracking of human legs with wearable IMU (Inertial Measurement Unit) sensors for capturing the human movement during the gait. The work was carried out in four stages: first, the definition of the model of human–robot interaction and the control proposal were developed. Second, the parameters based on the human gait were estimated. Third, the robot and sensor integration setup are also proposed. Finally, the description of the algorithm for parameters detection is presented. In the experimental study, despite of the continuous oscillation during the walking, the parameters estimation was precise and unbiased, showing also repeatability with human linear velocities changes. The controller was evaluated with an eight-shaped curve, showing the stability of the controller even with sharp changes in the human path during real experiments.

Estimation of Front-Crawl Energy Expenditure Using Wearable Inertial Measurement Units

Energy expenditure measurement is crucial to understand the biophysics of any kind of human locomotion. Despite the promising application of inertial measurement unit (IMU) for quantification of the energy expenditure during human on-land activities, it has never been deployed before to calculate the aquatic activities energy expenditure. Wearable IMUs were used in this paper to capture biomechanically interpretable descriptors of swimming. These descriptors were fed as inputs to a Bayesian linear model for estimation of the energy expenditure. To enhance generalization capacity of the estimator, a non-linear adjustment of the Bayesian model was devised using swimmer's anthropometric parameters. We used a set of four waterproofed IMUs worn on forearms, sacrum, and right shank of eighteen swimmers to extract the main spatiotemporal determinants of the front-crawl energy expenditure. The swimmers performed three 300-m trials at 70%, 80%, and 90% of their 400-m personal best time. At the end of each 300 m, the reference value of energy expenditure was measured based on indirect calorimetry and blood lactate concentration. The assessment of the proposed model on the test data shows a strong association between the estimated and reference energy expenditure (Spearman's rho=0.93, ) and a high relative precision of 9.4%. The backward elimination of model parameters with minimum rms error criterion shows that by excluding the features extracted from forearm sensors, i.e., using only two IMUs, we can still achieve an error of 0.9±11.3%.

A Bayesian approach for pervasive estimation of breaststroke velocity using a wearable IMU

A ubiquitous assessment of swimming velocity (main metric of the performance) is essential for the coach to provide a tailored feedback to the trainee. We present a probabilistic framework for the data-driven estimation of the swimming velocity at every cycle using a low-cost wearable inertial measurement unit (IMU). The statistical validation of the method on 15 swimmers shows that an average relative error of 0.1 ± 9.6% and high correlation with the tethered reference system (rX,Y=0.91) is achievable. Besides, a simple tool to analyze the influence of sacrum kinematics on the performance is provided.

Measuring the Effects of Lighting Distribution on Walking Speed and Head Pitch With Wearable Inertial Measurement Units

A comparative human performance evaluation of a miner's walking speed and head pitch was conducted on miners wearing two types of LED cap lamps. Walking speed and head pitch are indirect indicators of improved lighting. The better that miners can see the floor, the faster they can walk and the less they pitch their heads downward to illuminate the floor with their cap lamps. NIOSH researchers developed a non-contact way to quantify human performance by using two small wireless, wearable inertial measurement units. Data were collected in the field from nine coal miners in an underground coal mine. The field results showed no statistical difference between the two cap lamps for walking speed. However, there was a trend of 2 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">°</sup> lower head pitch for one of the cap lamps. The field testing procedures were then replicated in a controlled laboratory environment and the results indicated a 5-degree lower head tilt when using the same cap lamp and a corresponding difference in walking speed. A novel application of magnetometers for distance flagging is also presented. Finally, study limitations and a follow-up study are discussed.