Estimating three-dimensional orientation of human body parts by inertial/magnetic sensing

Quantifying lumbar mobility using a single tri-axial accelerometer

Background

Lumbar mobility is regarded as important for assessing and managing low back pain (LBP). Inertial Measurement Units (IMUs) are currently the most feasible technology for quantifying lumbar mobility in clinical and research settings. However, their gyroscopes are susceptible to drift errors, limiting their use for long-term remote monitoring.

Research question

Can a single tri-axial accelerometer provide an accurate and feasible alternative to a multi-sensor IMU for quantifying lumbar flexion mobility and velocity?

Methods

In this cross-sectional study, 18 healthy adults performed nine repetitions of full spinal flexion movements. Lumbar flexion mobility and velocity were quantified using a multi-sensor IMU and just the tri-axial accelerometer within the IMU. Correlations between the two methods were assessed for each percentile of the lumbar flexion movement cycle, and differences in measurements were modelled using a Generalised Additive Model (GAM).

Results

Very high correlations (r > 0.90) in flexion angles and velocities were found between the two methods for most of the movement cycle. However, the accelerometer overestimated lumbar flexion angle at the start (-4.7° [95 % CI -7.6° to -1.8°]) and end (-4.8° [95 % CI -7.7° to -1.9°]) of movement cycles, but underestimated angles (maximal difference of 4.3° [95 % CI 1.4° to 7.2°]) between 7 % and 92 % of the movement cycle. For flexion velocity, the accelerometer underestimated at the start (16.6°/s [95%CI 16.0 to 17.2°/s]) and overestimated (-12.3°/s [95%CI -12.9 to -11.7°/s]) at the end of the movement, compared to the IMU.

Significance

Despite the observed differences, the study suggests that a single tri-axial accelerometer could be a feasible tool for continuous remote monitoring of lumbar mobility and velocity. This finding has potential implications for the management of LBP, enabling more accessible and cost-effective monitoring of lumbar mobility in both clinical and research settings.

Automatic Detection of Magnetic Disturbances in Magnetic Inertial Measurement Unit Sensors Based on Recurrent Neural Networks

This paper proposes a new methodology for the automatic detection of magnetic disturbances from magnetic inertial measurement unit (MIMU) sensors based on deep learning. The proposed approach considers magnetometer data as input to a long short-term memory (LSTM) neural network and obtains a labeled time series output with the posterior probabilities of magnetic disturbance. We trained our algorithm on a data set that reproduces a wide range of magnetic perturbations and MIMU motions in a repeatable and reproducible way. The model was trained and tested using 15 folds, which considered independence in sensor, disturbance direction, and signal type. On average, the network can adequately detect the disturbances in 98% of the cases, which represents a significant improvement over current threshold-based detection algorithms.

A global bibliometric and visualized analysis of gait analysis and artificial intelligence research from 1992 to 2022

Gait is an important basic function of human beings and an integral part of life. Many mental and physical abnormalities can cause noticeable differences in a person's gait. Abnormal gait can lead to serious consequences such as falls, limited mobility and reduced life satisfaction. Gait analysis, which includes joint kinematics, kinetics, and dynamic Electromyography (EMG) data, is now recognized as a clinically useful tool that can provide both quantifiable and qualitative information on performance to aid in treatment planning and evaluate its outcome. With the assistance of new artificial intelligence (AI) technology, the traditional medical environment has undergone great changes. AI has the potential to reshape medicine, making gait analysis more accurate, efficient and accessible. In this study, we analyzed basic information about gait analysis and AI articles that met inclusion criteria in the WoS Core Collection database from 1992-2022, and the VosViewer software was used for web visualization and keyword analysis. Through bibliometric and visual analysis, this article systematically introduces the research status of gait analysis and AI. We introduce the application of artificial intelligence in clinical gait analysis, which affects the identification and management of gait abnormalities found in various diseases. Machine learning (ML) and artificial neural networks (ANNs) are the most often utilized AI methods in gait analysis. By comparing the predictive capability of different AI algorithms in published studies, we evaluate their potential for gait analysis in different situations. Furthermore, the current challenges and future directions of gait analysis and AI research are discussed, which will also provide valuable reference information for investors in this field.

Improving Reliability of Magnetic Localization Using Input Space Transformation

Body motion tracking for medical applications has the potential to improve quality of life for people with physical or speech motor disorders. Current solutions available in the market are either inaccurate, not affordable, or are impractical for a medical setting or at home. Magnetic localization can address these issues thanks to its high accuracy, simplicity of use, wearability, and use of inexpensive sensors such as magnetometers. However, sources of unreliability affect magnetometers to such an extent that the localization model trained in a controlled environment might exhibit poor tracking accuracy when deployed to end users. Traditional magnetic calibration methods, such as ellipsoid fit (EF), do not sufficiently attenuate the effect of these sources of unreliability to reach a positional accuracy that is both consistent and satisfactory for our target applications. To improve reliability, we developed a calibration method called post-deployment input space transformation (PDIST) that reduces the distribution shift in the magnetic measurements between model training and deployment. In this paper, we focused on change in magnetization or magnetometer as sources of unreliability. Our results show that PDIST performs better than EF in decreasing positional errors by a factor of ~3 when magnetization is distorted, and up to ~7 when our localization model is tested on a different magnetometer than the one it was trained with. Furthermore, PDIST is shown to perform reliably by providing consistent results across all our data collection that tested various combinations of the sources of unreliability.

Monitoring Resistance Training in Real Time with Wearable Technology: Current Applications and Future Directions

Resistance training is an exercise modality that involves using weights or resistance to strengthen and tone muscles. It has become popular in recent years, with numerous people including it in their fitness routines to ameliorate their strength, muscle mass, and overall health. Still, resistance training can be complex, requiring careful planning and execution to avoid injury and achieve satisfactory results. Wearable technology has emerged as a promising tool for resistance training, as it allows monitoring and adjusting training programs in real time. Several wearable devices are currently available, such as smart watches, fitness trackers, and other sensors that can yield detailed physiological and biomechanical information. In resistance training research, this information can be used to assess the effectiveness of training programs and identify areas for improvement. Wearable technology has the potential to revolutionize resistance training research, providing new insights and opportunities for developing optimized training programs. This review examines the types of wearables commonly used in resistance training research, their applications in monitoring and optimizing training programs, and the potential limitations and challenges associated with their use. Finally, it discusses future research directions, including the development of advanced wearable technologies and the integration of artificial intelligence in resistance training research.

Integrated UWB/MIMU Sensor System for Position Estimation towards an Accurate Analysis of Human Movement: A Technical Review

Integrated Ultra-wideband (UWB) and Magnetic Inertial Measurement Unit (MIMU) sensor systems have been gaining popularity for pedestrian tracking and indoor localization applications, mainly due to their complementary error characteristics that can be exploited to achieve higher accuracies via a data fusion approach. These integrated sensor systems have the potential for improving the ambulatory 3D analysis of human movement (estimating 3D kinematics of body segments and joints) over systems using only on-body MIMUs. For this, high accuracy is required in the estimation of the relative positions of all on-body integrated UWB/MIMU sensor modules. So far, these integrated UWB/MIMU sensors have not been reported to have been applied for full-body ambulatory 3D analysis of human movement. Also, no review articles have been found that have analyzed and summarized the methods integrating UWB and MIMU sensors for on-body applications. Therefore, a comprehensive analysis of this technology is essential to identify its potential for application in 3D analysis of human movement. This article thus aims to provide such a comprehensive analysis through a structured technical review of the methods integrating UWB and MIMU sensors for accurate position estimation in the context of the application for 3D analysis of human movement. The methods used for integration are all summarized along with the accuracies that are reported in the reviewed articles. In addition, the gaps that are required to be addressed for making this system applicable for the 3D analysis of human movement are discussed.

Evaluation of Upper Body and Lower Limbs Kinematics through an IMU-Based Medical System: A Comparative Study with the Optoelectronic System

In recent years, the use of inertial-based systems has been applied to remote rehabilitation, opening new perspectives for outpatient assessment. In this study, we assessed the accuracy and the concurrent validity of the angular measurements provided by an inertial-based device for rehabilitation with respect to the state-of-the-art system for motion tracking. Data were simultaneously collected with the two systems across a set of exercises for trunk and lower limbs, performed by 21 healthy participants. Additionally, the sensitivity of the inertial measurement unit (IMU)-based system to its malpositioning was assessed. Root mean square error (RMSE) was used to explore the differences in the outputs of the two systems in terms of range of motion (ROM), and their agreement was assessed via Pearson's correlation coefficient (PCC) and Lin's concordance correlation coefficient (CCC). The results showed that the IMU-based system was able to assess upper-body and lower-limb kinematics with a mean error in general lower than 5° and that its measurements were moderately biased by its mispositioning. Although the system does not seem to be suitable for analysis requiring a high level of detail, the findings of this study support the application of the device in rehabilitation programs in unsupervised settings, providing reliable data to remotely monitor the progress of the rehabilitation pathway and change in patient's motor function.

Fusion of video and inertial sensing data via dynamic optimization of a biomechanical model

Inertial sensing and computer vision are promising alternatives to traditional optical motion tracking, but until now these data sources have been explored either in isolation or fused via unconstrained optimization, which may not take full advantage of their complementary strengths. By adding physiological plausibility and dynamical robustness to a proposed solution, biomechanical modeling may enable better fusion than unconstrained optimization. To test this hypothesis, we fused video and inertial sensing data via dynamic optimization with a nine degree-of-freedom model and investigated when this approach outperforms video-only, inertial-sensing-only, and unconstrained-fusion methods. We used both experimental and synthetic data that mimicked different ranges of video and inertial measurement unit (IMU) data noise. Fusion with a dynamically constrained model significantly improved estimation of lower-extremity kinematics over the video-only approach and estimation of joint centers over the IMU-only approach. It consistently outperformed single-modality approaches across different noise profiles. When the quality of video data was high and that of inertial data was low, dynamically constrained fusion improved estimation of joint kinematics and joint centers over unconstrained fusion, while unconstrained fusion was advantageous in the opposite scenario. These findings indicate that complementary modalities and techniques can improve motion tracking by clinically meaningful margins and that data quality and computational complexity must be considered when selecting the most appropriate method for a particular application.

Assessment of a New Change of Direction Detection Algorithm Based on Inertial Data

The purpose of this study was to study the validity and reproducibility of an algorithm capable of combining information from Inertial and Magnetic Measurement Units (IMMUs) to detect changes of direction (COD). Five participants wore three devices at the same time to perform five CODs in three different conditions: angle (45°, 90°, 135° and 180°), direction (left and right), and running speed (13 and 18 km/h). For the testing, the combination of different % of smoothing applied to the signal (20%, 30% and 40%) and minimum intensity peak (PmI) for each event (0.8 G, 0.9 G, and 1.0 G) was applied. The values recorded with the sensors were contrasted with observation and coding from video. At 13 km/h, the combination of 30% smoothing and 0.9 G PmI was the one that showed the most accurate values (IMMU1: Cohen's d (d) = -0.29;%Diff = -4%; IMMU2: d = 0.04 %Diff = 0%, IMMU3: d = -0.27, %Diff = 13%). At 18 km/h, the 40% and 0.9 G combination was the most accurate (IMMU1: d = -0.28; %Diff = -4%; IMMU2 = d = -0.16; %Diff = -1%; IMMU3 = d = -0.26; %Diff = -2%). The results suggest the need to apply specific filters to the algorithm based on speed, in order to accurately detect COD.

Classification of static postures with wearable sensors mounted on loose clothing

Inertial Measurement Units (IMUs) are a potential way to monitor the mobility of people outside clinical or laboratory settings at an acceptable cost. To increase accuracy, multiple IMUs can be used. By embedding multiple sensors into everyday clothing, it is possible to simplify having to put on individual sensors, ensuring sensors are correctly located and oriented. This research demonstrates how clothing-mounted IMU readings can be used to identify 4 common postures: standing, sitting, lying down and sitting on the floor. Data were collected from 5 healthy adults, with each providing 1-4 days of data with approximately 5 h each day. Each day, participants performed a fixed set of activities that were video-recorded to provide a ground truth. This is an analysis of accelerometry data from 3 sensors incorporated into right trouser-leg at the waist, thigh and ankle. Data were classified as static/ dynamic activities using a K-nearest neighbour (KNN) algorithm. For static activities, the inclination angles of the three sensors were estimated and used to train a second KNN classifier. For this highly-selected dataset (60000-70000 data points/posture), the static postures were classified with 100% accuracy, illustrating the potential for clothing-mounted sensors to be used in posture classification.

Wearables for Running Gait Analysis: A Systematic Review

BACKGROUND

Running gait assessment has traditionally been performed using subjective observation or expensive laboratory-based objective technologies, such as three-dimensional motion capture or force plates. However, recent developments in wearable devices allow for continuous monitoring and analysis of running mechanics in any environment. Objective measurement of running gait is an important (clinical) tool for injury assessment and provides measures that can be used to enhance performance.

OBJECTIVES

We aimed to systematically review the available literature investigating how wearable technology is being used for running gait analysis in adults.

METHODS

A systematic search of the literature was conducted in the following scientific databases: PubMed, Scopus, Web of Science and SPORTDiscus. Information was extracted from each included article regarding the type of study, participants, protocol, wearable device(s), main outcomes/measures, analysis and key findings.

RESULTS

A total of 131 articles were reviewed: 56 investigated the validity of wearable technology, 22 examined the reliability and 77 focused on applied use. Most studies used inertial measurement units (n = 62) [i.e. a combination of accelerometers, gyroscopes and magnetometers in a single unit] or solely accelerometers (n = 40), with one using gyroscopes alone and 31 using pressure sensors. On average, studies used one wearable device to examine running gait. Wearable locations were distributed among the shank, shoe and waist. The mean number of participants was 26 (± 27), with an average age of 28.3 (± 7.0) years. Most studies took place indoors (n = 93), using a treadmill (n = 62), with the main aims seeking to identify running gait outcomes or investigate the effects of injury, fatigue, intrinsic factors (e.g. age, sex, morphology) or footwear on running gait outcomes. Generally, wearables were found to be valid and reliable tools for assessing running gait compared to reference standards.

CONCLUSIONS

This comprehensive review highlighted that most studies that have examined running gait using wearable sensors have done so with young adult recreational runners, using one inertial measurement unit sensor, with participants running on a treadmill and reporting outcomes of ground contact time, stride length, stride frequency and tibial acceleration. Future studies are required to obtain consensus regarding terminology, protocols for testing validity and the reliability of devices and suitability of gait outcomes.

CLINICAL TRIAL REGISTRATION

CRD42021235527.

Feasibility of Tracking Human Kinematics with Simultaneous Localization and Mapping (SLAM)

We evaluated a new wearable technology that fuses inertial sensors and cameras for tracking human kinematics. These devices use on-board simultaneous localization and mapping (SLAM) algorithms to localize the camera within the environment. Significance of this technology is in its potential to overcome many of the limitations of the other dominant technologies. Our results demonstrate this system often attains an estimated orientation error of less than 1° and a position error of less than 4 cm as compared to a robotic arm. This demonstrates that SLAM's accuracy is adequate for many practical applications for tracking human kinematics.

User-Centered Design Methodologies for the Prototype Development of a Smart Harness and Related System to Provide Haptic Cues to Persons with Parkinson's Disease

This paper describes the second part of the PASSO (Parkinson smart sensory cues for older users) project, which designs and tests an innovative haptic biofeedback system based on a wireless body sensor network using a smartphone and different smartwatches specifically designed to rehabilitate postural disturbances in persons with Parkinson's disease. According to the scientific literature on the use of smart devices to transmit sensory cues, vibrotactile feedback (particularly on the trunk) seems promising for improving people's gait and posture performance; they have been used in different environments and are well accepted by users. In the PASSO project, we designed and developed a wearable device and a related system to transmit vibrations to a person's body to improve posture and combat impairments like Pisa syndrome and camptocormia. Specifically, this paper describes the methodologies and strategies used to design, develop, and test wearable prototypes and the mHealth system. The results allowed a multidisciplinary comparison among the solutions, which led to prototypes with a high degree of usability, wearability, accessibility, and effectiveness. This mHealth system is now being used in pilot trials with subjects with Parkinson's disease to verify its feasibility among patients.

Comparing Loose Clothing-Mounted Sensors with Body-Mounted Sensors in the Analysis of Walking

A person's walking pattern can reveal important information about their health. Mounting multiple sensors onto loose clothing potentially offers a comfortable way of collecting data about walking and other human movement. This research investigates how well the data from three sensors mounted on the lateral side of clothing (on a pair of trousers near the waist, upper thigh and lower shank) correlate with the data from sensors mounted on the frontal side of the body. Data collected from three participants (two male, one female) for two days were analysed. Gait cycles were extracted based on features in the lower-shank accelerometry and analysed in terms of sensor-to-vertical angles (SVA). The correlations in SVA between the clothing- and body-mounted sensor pairs were analysed. Correlation coefficients above 0.76 were found for the waist sensor pairs, while the thigh and lower-shank sensor pairs had correlations above 0.90. The cyclical nature of gait cycles was evident in the clothing data, and it was possible to distinguish the stance and swing phases of walking based on features in the clothing data. Furthermore, simultaneously recording data from the waist, thigh, and shank was helpful in capturing the movement of the whole leg.

Validation of Non-Restrictive Inertial Gait Analysis of Individuals with Incomplete Spinal Cord Injury in Clinical Settings

Inertial Measurement Units (IMUs) have gained popularity in gait analysis and human motion tracking, and they provide certain advantages over stationary line-of-sight-dependent Optical Motion Capture (OMC) systems. IMUs appear as an appropriate alternative solution to reduce dependency on bulky, room-based hardware and facilitate the analysis of walking patterns in clinical settings and daily life activities. However, most inertial gait analysis methods are unpractical in clinical settings due to the necessity of precise sensor placement, the need for well-performed calibration movements and poses, and due to distorted magnetometer data in indoor environments as well as nearby ferromagnetic material and electronic devices. To address these limitations, recent literature has proposed methods for self-calibrating magnetometer-free inertial motion tracking, and acceptable performance has been achieved in mechanical joints and in individuals without neurological disorders. However, the performance of such methods has not been validated in clinical settings for individuals with neurological disorders, specifically individuals with incomplete Spinal Cord Injury (iSCI). In the present study, we used recently proposed inertial motion-tracking methods, which avoid magnetometer data and leverage kinematic constraints for anatomical calibration. We used these methods to determine the range of motion of the Flexion/Extension (F/E) hip and Abduction/Adduction (A/A) angles, the F/E knee angles, and the Dorsi/Plantar (D/P) flexion ankle joint angles during walking. Data (IMU and OMC) of five individuals with no neurological disorders (control group) and five participants with iSCI walking for two minutes on a treadmill in a self-paced mode were analyzed. For validation purposes, the OMC system was considered as a reference. The mean absolute difference (MAD) between calculated range of motion of joint angles was 5.00°, 5.02°, 5.26°, and 3.72° for hip F/E, hip A/A, knee F/E, and ankle D/P flexion angles, respectively. In addition, relative stance, swing, double support phases, and cadence were calculated and validated. The MAD for the relative gait phases (stance, swing, and double support) was 1.7%, and the average cadence error was 0.09 steps/min. The MAD values for RoM and relative gait phases can be considered as clinically acceptable. Therefore, we conclude that the proposed methodology is promising, enabling non-restrictive inertial gait analysis in clinical settings.

The Use of Wearable Sensors for Preventing, Assessing, and Informing Recovery from Sport-Related Musculoskeletal Injuries: A Systematic Scoping Review

Wearable technologies are often indicated as tools that can enable the in-field collection of quantitative biomechanical data, unobtrusively, for extended periods of time, and with few spatial limitations. Despite many claims about their potential for impact in the area of injury prevention and management, there seems to be little attention to grounding this potential in biomechanical research linking quantities from wearables to musculoskeletal injuries, and to assessing the readiness of these biomechanical approaches for being implemented in real practice. We performed a systematic scoping review to characterise and critically analyse the state of the art of research using wearable technologies to study musculoskeletal injuries in sport from a biomechanical perspective. A total of 4952 articles were retrieved from the Web of Science, Scopus, and PubMed databases; 165 were included. Multiple study features-such as research design, scope, experimental settings, and applied context-were summarised and assessed. We also proposed an injury-research readiness classification tool to gauge the maturity of biomechanical approaches using wearables. Five main conclusions emerged from this review, which we used as a springboard to propose guidelines and good practices for future research and dissemination in the field.

Towards Improved Inertial Navigation by Reducing Errors Using Deep Learning Methodology

Autonomous vehicles make use of an Inertial Navigation System (INS) as part of vehicular sensor fusion in many situations including GPS-denied environments such as dense urban places, multi-level parking structures, and areas with thick tree-coverage. The INS unit incorporates an Inertial Measurement Unit (IMU) to process the linear acceleration and angular velocity data to obtain orientation, position, and velocity information using mechanization equations. In this work, we describe a novel deep-learning-based methodology, using Convolutional Neural Networks (CNN), to reduce errors from MEMS IMU sensors. We develop a CNN-based approach that can learn from the responses of a particular inertial sensor while subject to inherent noise errors and provide near real-time error correction. We implement a time-division method to divide the IMU output data into small step sizes to make the IMU outputs fit the input format of the CNN. We optimize the CNN approach for higher performance and lower complexity that would allow its implementation on ultra-low power hardware such as microcontrollers. Our results show that we achieved up to 32.5% error improvement in straight-path motion and up to 38.69% error improvement in oval motion compared with the ground truth. We examined the performance of our CNN approach under various situations with IMUs of various performance grades, IMUs of the same type but different manufactured batch, and controlled, fixed, and uncontrolled vehicle motion paths.

Wearables-Only Analysis of Muscle and Joint Mechanics: An EMG-Driven Approach

Complex sensor arrays prohibit practical deployment of existing wearables-based algorithms for free-living analysis of muscle and joint mechanics. Machine learning techniques have been proposed as a potential solution, however, they are less interpretable and generalizable when compared to physics-based techniques. Herein, we propose a hybrid method utilizing inertial sensor- and electromyography (EMG)-driven simulation of muscle contraction to characterize knee joint and muscle mechanics during walking gait. Machine learning is used only to map a subset of measured muscle excitations to a full set thereby reducing the number of required sensors. We demonstrate the utility of the approach for estimating net knee flexion moment (KFM) as well as individual muscle moment and work during the stance phase of gait across nine unimpaired subjects. Across all subjects, KFM was estimated with 0.91%BW•H RMSE and strong correlations (r = 0.87) compared to ground truth inverse dynamics analysis. Estimates of individual muscle moments were strongly correlated (r = 0.81-0.99) with a reference EMG-driven technique using optical motion capture and a full set of electrodes as were estimates of muscle work (r = 0.88-0.99). Implementation of the proposed technique in the current work included instrumenting only three muscles with surface electrodes (lateral and medial gastrocnemius and vastus medialis) and both the thigh and shank segments with inertial sensors. These sensor locations permit instrumentation of a knee brace/sleeve facilitating a practically deployable mechanism for monitoring muscle and joint mechanics with performance comparable to the current state-of-the-art.

Drift-Free 3D Orientation and Displacement Estimation for Quasi-Cyclical Movements Using One Inertial Measurement Unit: Application to Running

A Drift-Free 3D Orientation and Displacement estimation method (DFOD) based on a single inertial measurement unit (IMU) is proposed and validated. Typically, body segment orientation and displacement methods rely on a constant- or zero-velocity point to correct for drift. Therefore, they are not easily applicable to more proximal segments than the foot. DFOD uses an alternative single sensor drift reduction strategy based on the quasi-cyclical nature of many human movements. DFOD assumes that the quasi-cyclical movement occurs in a quasi-2D plane and with an approximately constant cycle average velocity. DFOD is independent of a constant- or zero-velocity point, a biomechanical model, Kalman filtering or a magnetometer. DFOD reduces orientation drift by assuming a cyclical movement, and by defining a functional coordinate system with two functional axes. These axes are based on the mean acceleration and rotation axes over multiple complete gait cycles. Using this drift-free orientation estimate, the displacement of the sensor is computed by again assuming a cyclical movement. Drift in displacement is reduced by subtracting the mean value over five gait cycle from the free acceleration, velocity, and displacement. Estimated 3D sensor orientation and displacement for an IMU on the lower leg were validated with an optical motion capture system (OMCS) in four runners during constant velocity treadmill running. Root mean square errors for sensor orientation differences between DFOD and OMCS were 3.1 ± 0.4° (sagittal plane), 5.3 ± 1.1° (frontal plane), and 5.0 ± 2.1° (transversal plane). Sensor displacement differences had a root mean square error of 1.6 ± 0.2 cm (forward axis), 1.7 ± 0.6 cm (mediolateral axis), and 1.6 ± 0.2 cm (vertical axis). Hence, DFOD is a promising 3D drift-free orientation and displacement estimation method based on a single IMU in quasi-cyclical movements with many advantages over current methods.

Mobile Health App for Adolescents: Motion Sensor Data and Deep Learning Technique to Examine the Relationship between Obesity and Walking Patterns

With the prevalence of obesity in adolescents, and its long-term influence on their overall health, there is a large body of research exploring better ways to reduce the rate of obesity. A traditional way of maintaining an adequate body mass index (BMI), calculated by measuring the weight and height of an individual, is no longer enough, and we are in need of a better health care tool. Therefore, the current research proposes an easier method that offers instant and real-time feedback to the users from the data collected from the motion sensors of a smartphone. The study utilized the mHealth application to identify participants presenting the walking movements of the high BMI group. Using the feedforward deep learning models and convolutional neural network models, the study was able to distinguish the walking movements between nonobese and obese groups, at a rate of 90.5%. The research highlights the potential use of smartphones and suggests the mHealth application as a way to monitor individual health.

The Validity of Wireless Earbud-Type Wearable Sensors for Head Angle Estimation and the Relationships of Head with Trunk, Pelvis, Hip, and Knee during Workouts

The present study was performed to investigate the validity of a wireless earbud-type inertial measurement unit (Ear-IMU) sensor used to estimate head angle during four workouts. In addition, relationships between head angle obtained from the Ear-IMU sensor and the angles of other joints determined with a 3D motion analysis system were investigated. The study population consisted of 20 active volunteers. The Ear-IMU sensor measured the head angle, while a 3D motion analysis system simultaneously measured the angles of the head, trunk, pelvis, hips, and knees during workouts. Comparison with the head angle measured using the 3D motion analysis system indicated that the validity of the Ear-IMU sensor was very strong or moderate in the sagittal and frontal planes. In addition, the trunk angle in the frontal plane showed a fair correlation with the head angle determined with the Ear-IMU sensor during a single-leg squat, reverse lunge, and standing hip abduction; the correlation was poor in the sagittal plane. Our results indicated that the Ear-IMU sensor can be used to directly estimate head motion and indirectly estimate trunk motion.

Assessment of Stability of MIMU Probes to Skin-Marker-Based Anatomical Reference Frames During Locomotion Tasks: Effect of Different Locations on the Lower Limb

Soft tissue artefacts (STAs) undermine the validity of skin-mounted approaches to measure skeletal kinematics. Magneto-inertial measurement units (MIMU) gained popularity due to their low cost and ease of use. Although the reliability of different protocols for marker-based joint kinematics estimation has been widely reported, there are still no indications on where to place MIMU to minimize STA. This study aims to find the most stable positions for MIMU placement, among four positions on the thigh, four on the shank, and three on the foot. Stability was investigated by measuring MIMU movements against an anatomical reference frame, defined according to a standard marker-based approach. To this aim, markers were attached both on the case of each MIMU (technical frame) and on bony landmarks (anatomical frame). For each MIMU, the nine angles between each versor of the technical frame with each versor of the corresponding anatomical frame were computed. The maximum standard deviation of these angles was assumed as the instability index of MIMU-body coupling. Six healthy subjects were asked to perform barefoot gait, step negotiation, and sit-to-stand. Results showed that (1) in the thigh, the frontal position was the most stable in all tasks, especially in gait; (2) in the shank, the proximal position is the least stable, (3) lateral or medial calcaneus and foot dorsum positions showed equivalent stability performances. Further studies should be done before generalizing these conclusions to different motor tasks and MIMU-body fixation methods. The above results are of interest for both MIMU-based gait analysis and rehabilitation approaches using wearable sensors-based biofeedback.

Portable, open-source solutions for estimating wrist position during reaching in people with stroke

Arm movement kinematics may provide a more sensitive way to assess neurorehabilitation outcomes than existing metrics. However, measuring arm kinematics in people with stroke can be challenging for traditional optical tracking systems due to non-ideal environments, expense, and difficulty performing required calibration. Here, we present two open-source methods, one using inertial measurement units (IMUs) and another using virtual reality (Vive) sensors, for accurate measurements of wrist position with respect to the shoulder during reaching movements in people with stroke. We assessed the accuracy of each method during a 3D reaching task. We also demonstrated each method's ability to track two metrics derived from kinematics-sweep area and smoothness-in people with chronic stroke. We computed correlation coefficients between the kinematics estimated by each method when appropriate. Compared to a traditional optical tracking system, both methods accurately tracked the wrist during reaching, with mean signed errors of 0.09 ± 1.81 cm and 0.48 ± 1.58 cm for the IMUs and Vive, respectively. Furthermore, both methods' estimated kinematics were highly correlated with each other (p < 0.01). By using relatively inexpensive wearable sensors, these methods may be useful for developing kinematic metrics to evaluate stroke rehabilitation outcomes in both laboratory and clinical environments.

Evaluating the Performance of Balance Physiotherapy Exercises Using a Sensory Platform: The Basis for a Persuasive Balance Rehabilitation Virtual Coaching System

Rehabilitation programs play an important role in improving the quality of life of patients with balance disorders. Such programs are usually executed in a home environment, due to lack of resources. This procedure usually results in poorly performed exercises or even complete drop outs from the programs, as the patients lack guidance and motivation. This paper introduces a novel system for managing balance disorders in a home environment using a virtual coach for guidance, instruction, and inducement. The proposed system comprises sensing devices, augmented reality technology, and intelligent inference agents, which capture, recognize, and evaluate a patient's performance during the execution of exercises. More specifically, this work presents a home-based motion capture and assessment module, which utilizes a sensory platform to recognize an exercise performed by a patient and assess it. The sensory platform comprises IMU sensors (Mbientlab MMR^© 9axis), pressure insoles (Moticon^©), and a depth RGB camera (Intel D415^©). This module is designed to deliver messages both during the performance of the exercise, delivering personalized notifications and alerts to the patient, and after the end of the exercise, scoring the overall performance of the patient. A set of proof of concept validation studies has been deployed, aiming to assess the accuracy of the different components for the sub-modules of the motion capture and assessment module. More specifically, Euler angle calculation algorithm in 2D (R² = 0.99) and in 3D (R² = 0.82 in yaw plane and R² = 0.91 for the pitch plane), as well as head turns speed (R² = 0.96), showed good correlation between the calculated and ground truth values provided by experts' annotations. The posture assessment algorithm resulted to accuracy = 0.83, while the gait metrics were validated against two well-established gait analysis systems (R² = 0.78 for double support, R² = 0.71 for single support, R² = 0.80 for step time, R² = 0.75 for stride time (WinTrack^©), R² = 0.82 for cadence, and R² = 0.79 for stride time (RehaGait^©). Validation results provided evidence that the proposed system can accurately capture and assess a physiotherapy exercise within the balance disorders context, thus providing a robust basis for the virtual coaching ecosystem and thereby improve a patient's commitment to rehabilitation programs while enhancing the quality of the performed exercises. In summary, virtual coaching can improve the quality of the home-based rehabilitation programs as long as it is combined with accurate motion capture and assessment modules, which provides to the virtual coach the capacity to tailor the interaction with the patient and deliver personalized experience.

Enhanced PDR-BLE Compensation Mechanism Based on HMM and AWCLA for Improving Indoor Localization

This paper presents an enhanced PDR-BLE compensation mechanism for improving indoor localization, which is considerably resilient against variant uncertainties. The proposed method of ePDR-BLE compensation mechanism (EPBCM) takes advantage of the non-requirement of linearization of the system around its current state in an unscented Kalman filter (UKF) and Kalman filter (KF) in smoothing of received signal strength indicator (RSSI) values. In this paper, a fusion of conflicting information and the activity detection approach of an object in an indoor environment contemplates varying magnitude of accelerometer values based on the hidden Markov model (HMM). On the estimated orientation, the proposed approach remunerates the inadvertent body acceleration and magnetic distortion sensor data. Moreover, EPBCM can precisely calculate the velocity and position by reducing the position drift, which gives rise to a fault in zero-velocity and heading error. The developed EPBCM localization algorithm using Bluetooth low energy beacons (BLE) was applied and analyzed in an indoor environment. The experiments conducted in an indoor scenario shows the results of various activities performed by the object and achieves better orientation estimation, zero velocity measurements, and high position accuracy than other methods in the literature.

Extension of the Rigid-Constraint Method for the Heuristic Suboptimal Parameter Tuning to Ten Sensor Fusion Algorithms Using Inertial and Magnetic Sensing

The orientation of a magneto-inertial measurement unit can be estimated using a sensor fusion algorithm (SFA). However, orientation accuracy is greatly affected by the choice of the SFA parameter values which represents one of the most critical steps. A commonly adopted approach is to fine-tune parameter values to minimize the difference between estimated and true orientation. However, this can only be implemented within the laboratory setting by requiring the use of a concurrent gold-standard technology. To overcome this limitation, a Rigid-Constraint Method (RCM) was proposed to estimate suboptimal parameter values without relying on any orientation reference. The RCM method effectiveness was successfully tested on a single-parameter SFA, with an average error increase with respect to the optimal of 1.5 deg. In this work, the applicability of the RCM was evaluated on 10 popular SFAs with multiple parameters under different experimental scenarios. The average residual between the optimal and suboptimal errors amounted to 0.6 deg with a maximum of 3.7 deg. These encouraging results suggest the possibility to properly tune a generic SFA on different scenarios without using any reference. The synchronized dataset also including the optical data and the SFA codes are available online.

On the impact of the erroneous identification of inertial sensors' locations on segments and whole-body centers of mass accelerations: a sensitivity study in one transfemoral amputee

The kinematics of the body center of mass (bCoM) may provide crucial information supporting the rehabilitation process of people with transfemoral amputation. The use of magneto-inertial measurement units (MIMUs) is promising as it may allow in-the-field bCoM motion monitoring. Indeed, bCoM acceleration might be obtained by fusing the estimated accelerations of body segments' centers of mass (sCoM), the formers being computed from the measured accelerations by segment-mounted MIMUs and the known relative position between each pair of MIMU and underlying sCoM. This paper investigates how erroneous identifications of MIMUs positions impact the accuracy of estimated 3D sCoM and bCoM accelerations in transfemoral amputee gait. Using an experimental design approach, 2¹⁵ simulations of erroneous identifications of MIMUs positions (up to 0.02 m in each direction) were simulated over seven recorded gait cycles of one participant. MIMUs located on the trunk and sound lower limbs were shown to explain up to 77% of the variance in the accuracy of the estimated bCoM acceleration, presumably due to the higher mass and/or angular velocity of these segments during gait of lower-limb amputees. Therefore, a special attention should be paid when identifying the positions of MIMUs located on segments contributing the most to the investigated motion. Sensitivity of the estimated vertical body center of mass acceleration to erroneous identifications of MIMU positions in the anteroposterior (AP), mediolateral (ML), and vertical (V) directions, expressed in percentage of the total variance of the estimation accuracy.

Lower limb joint-specific contributions to standing postural sway in persons with unilateral lower limb loss

BACKGROUND

Individuals with lower limb loss are at an increased risk for falls, likely due to impaired balance control. Standing balance is typically explained by double- or single-inverted pendulum models of the hip and/or ankle, neglecting the knee joint. However, recent work suggests knee joint motion contributes toward stabilizing center-of-mass kinematics during standing balance.

RESEARCH QUESTION

To what extent do hip, knee, and ankle joint motions contribute to postural sway in standing among individuals with lower limb loss?

METHODS

Forty-two individuals (25 m/17f) with unilateral lower limb loss (30 transtibial, 12 transfemoral) stood quietly with eyes open and eyes closed, for 30 s each, while wearing accelerometers on the pelvis, thigh, shank, and foot. Triaxial inertial measurement units were transformed to inertial anterior-posterior components and sway parameters were computed: ellipse area, root-mean-square, and jerk. A state-space model with a Kalman filter calculated hip, knee, and ankle joint flexion-extension angles and ranges of motion. Multiple linear regression predicted postural sway parameters from intact limb joint ranges of motion, with BMI as a covariate (p < 0.05).

RESULTS

With eyes open, intact limb hip flexion predicted larger sway ellipse area, whereas hip flexion and knee extension predicted larger sway root-mean-square, and hip flexion, knee extension, and ankle plantarflexion predicted larger sway jerk. With eyes closed, intact limb hip flexion remained the predictor of sway ellipse area; no other joint motions influenced sway parameters in this condition.

SIGNIFICANCE

Hip, knee, and ankle motions influence postural sway during standing balance among individuals with lower limb loss. Specifically, increasing intact-side hip flexion, knee extension, and ankle plantarflexion motion increased postural sway. With vision removed, a re-weighting of lower limb joint sensory mechanisms may control postural sway, such that increasing sway may be regulated by proximal coordination strategies and vestibular responses, with implications for fall risk.

Test - re-test reliability and concurrent validity of cervical active range of motion in young asymptomatic adults using a new inertial measurement unit device

OBJECTIVES

Cervical range of motion (CROM) is one of the first things evaluated in cervical disorders. DyCare-Lynx is an inertial measurement unit device that was recently designed to measure CROM. Therefore, the objectives of the present study were to test the reliability and validity of the DyCare-Lynx device for active CROM.

MATERIALS AND METHODS

This study included 36 healthy individuals for the reliability study and 31 individuals for the validity study. Test-retest reliability was examined in three different days, by the same examiner with a 4 ± 1-day interval between them in all cervical movements in random order. For validity, the CROM was tested with the Zebris Motion Analysis system and DyCare-Lynx simultaneously.

RESULTS

The interclass correlation coefficient (ICC) of the DyCare-Lynx ranged from 0.54 to 0.90. The standard error of measurement (SEM) ranged from 2.12°-7.65°. The smallest detectable change (SDD) ranged from 11.25% to 29.75%. The Pearson's r correlation of DyCare-Lynx with Zebris ranged from 0.655 to 0.957.

CONCLUSION

DyCare-Lynx showed moderate to excellent reliability and moderate-to-high validity. Moreover, SEM was low with acceptable SDD values for all movements. Overall, it can be suggested that DyCare-Lynx is a reliable and valid tool to evaluate active CROM.

Prediction of gait trajectories based on the Long Short Term Memory neural networks

The forecasting of lower limb trajectories can improve the operation of assistive devices and minimise the risk of tripping and balance loss. The aim of this work was to examine four Long Short Term Memory (LSTM) neural network architectures (Vanilla, Stacked, Bidirectional and Autoencoders) in predicting the future trajectories of lower limb kinematics, i.e. Angular Velocity (AV) and Linear Acceleration (LA). Kinematics data of foot, shank and thigh (LA and AV) were collected from 13 male and 3 female participants (28 ± 4 years old, 1.72 ± 0.07 m in height, 66 ± 10 kg in mass) who walked for 10 minutes at preferred walking speed (4.34 ± 0.43 km.h-1) and at an imposed speed (5km.h-1, 15.4% ± 7.6% faster) on a 0% gradient treadmill. The sliding window technique was adopted for training and testing the LSTM models with total kinematics time-series data of 10,500 strides. Results based on leave-one-out cross validation, suggested that the LSTM autoencoders is the top predictor of the lower limb kinematics trajectories (i.e. up to 0.1s). The normalised mean squared error was evaluated on trajectory predictions at each time-step and it obtained 2.82-5.31% for the LSTM autoencoders. The ability to predict future lower limb motions may have a wide range of applications including the design and control of bionics allowing improved human-machine interface and mitigating the risk of falls and balance loss.

Validity, reliability and accuracy of inertial measurement units (IMUs) to measure angles: application in swimming

The first objective was to test the validity, reliability and accuracy of paired inertial measurement units (IMUs) to assess absolute angles relative to Vicon and OptiTrack systems. The potential impacts of slow vs. rapid and intermittent vs. continuous movements were tested during 2D laboratory analyses and 3D ecological context analysis. The second objective was to test the IMUs alone in an ecological activity (i.e., front crawl) that encompassed the previous independent variables to quantify inter-cyclic variability. Slow and intermittent motion ensured high to reasonable validity, reliability and accuracy. Rapid motion revealed an out-of-phase pattern for temporal reliability and lower validity, which was also visible in 3D. Also, spatial reliability and accuracy decreased in 3D, mainly due to discrepancies in local maximums, whereas temporal reliability remained in-phase. For the second objective, inter-cyclic variability did not exceed 12° based on root mean square error (RMSE). Therefore, IMUs should be considered valuable supplements to optoelectronic systems if users carefully position the sensors in rigid clusters and calibrate them to integrate potential offsets. Drift correction by spline interpolation or normalisation of the absolute data should also be considered as additional techniques that increase IMU performance in ecological contexts of performance.

Estimation of 3D Body Center of Mass Acceleration and Instantaneous Velocity from a Wearable Inertial Sensor Network in Transfemoral Amputee Gait: A Case Study

The analysis of the body center of mass (BCoM) 3D kinematics provides insights on crucial aspects of locomotion, especially in populations with gait impairment such as people with amputation. In this paper, a wearable framework based on the use of different magneto-inertial measurement unit (MIMU) networks is proposed to obtain both BCoM acceleration and velocity. The proposed framework was validated as a proof of concept in one transfemoral amputee against data from force plates (acceleration) and an optoelectronic system (acceleration and velocity). The impact in terms of estimation accuracy when using a sensor network rather than a single MIMU at trunk level was also investigated. The estimated velocity and acceleration reached a strong agreement (ρ > 0.89) and good accuracy compared to reference data (normalized root mean square error (NRMSE) < 13.7%) in the anteroposterior and vertical directions when using three MIMUs on the trunk and both shanks and in all three directions when adding MIMUs on both thighs (ρ > 0.89, NRMSE ≤ 14.0% in the mediolateral direction). Conversely, only the vertical component of the BCoM kinematics was accurately captured when considering a single MIMU. These results suggest that inertial sensor networks may represent a valid alternative to laboratory-based instruments for 3D BCoM kinematics quantification in lower-limb amputees.

Analysis of the Accuracy of Ten Algorithms for Orientation Estimation Using Inertial and Magnetic Sensing under Optimal Conditions: One Size Does Not Fit All

The orientation of a magneto and inertial measurement unit (MIMU) is estimated by means of sensor fusion algorithms (SFAs) thus enabling human motion tracking. However, despite several SFAs implementations proposed over the last decades, there is still a lack of consensus about the best performing SFAs and their accuracy. As suggested by recent literature, the filter parameters play a central role in determining the orientation errors. The aim of this work is to analyze the accuracy of ten SFAs while running under the best possible conditions (i.e., their parameter values are set using the orientation reference) in nine experimental scenarios including three rotation rates and three commercial products. The main finding is that parameter values must be specific for each SFA according to the experimental scenario to avoid errors comparable to those obtained when the default parameter values are used. Overall, when optimally tuned, no statistically significant differences are observed among the different SFAs in all tested experimental scenarios and the absolute errors are included between 3.8 deg and 7.1 deg. Increasing the rotation rate generally leads to a significant performance worsening. Errors are also influenced by the MIMU commercial model. SFA MATLAB implementations have been made available online.

Wearable Sensors in Sports for Persons with Disability: A Systematic Review

The interest and competitiveness in sports for persons with disabilities has increased significantly in the recent years, creating a demand for technological tools supporting practice. Wearable sensors offer non-invasive, portable and overall convenient ways to monitor sports practice. This systematic review aims at providing current evidence on the application of wearable sensors in sports for persons with disability. A search for articles published in English before May 2020 was performed on Scopus, Web-Of-Science, PubMed and EBSCO databases, searching titles, abstracts and keywords with a search string involving terms regarding wearable sensors, sports and disability. After full paper screening, 39 studies were included. Inertial and EMG sensors were the most commonly adopted wearable technologies, while wheelchair sports were the most investigated. Four main target applications of wearable sensors relevant to sports for people with disability were identified and discussed: athlete classification, injury prevention, performance characterization for training optimization and equipment customization. The collected evidence provides an overview on the application of wearable sensors in sports for persons with disability, providing useful indication for researchers, coaches and trainers. Several gaps in the different target applications are highlighted altogether with recommendation on future directions.

Reference Frame Unification of IMU-Based Joint Angle Estimation: The Experimental Investigation and a Novel Method

Inertial measurement unit (IMU)-based joint angle estimation is an increasingly mature technique that has a broad range of applications in clinics, biomechanics and robotics. However, the deviations of different IMUs’ reference frames, referring to IMUs’ individual orientations estimating errors, is still a challenge for improving the angle estimation accuracy due to conceptual confusion, relatively simple metrics and the lack of systematical investigation. In this paper, we clarify the determination of reference frame unification, experimentally study the time-varying characteristics of reference frames’ deviations and accordingly propose a novel method with a comprehensive metric to unify reference frames. To be specific, we firstly define the reference frame unification (RFU) and distinguish it with drift correction that has always been confused with the term RFU. Secondly, we design a mechanical gimbal-based experiment to study the deviations, where sensor-to-body alignment and rotation-caused differences of orientations are excluded. Thirdly, based on the findings of the experiment, we propose a novel method to utilize the consistency of the joint axis under the hinge-joint constraint, gravity acceleration and local magnetic field to comprehensively unify reference frames, which meets the nonlinear time-varying characteristics of the deviations. The results on ten human subjects reveal the feasibility of our proposed method and the improvement from previous methods. This work contributes to a relatively new perspective of considering and improving the accuracy of IMU-based joint angle estimation.

Measurement of Human Walking Movements by Using a Mobile Health App: Motion Sensor Data Analysis

Background

This study presents a new approach to measure and analyze the walking balance of humans by collecting motion sensor data in a smartphone.

Objective

We aimed to develop a mobile health (mHealth) app that can measure the walking movements of human individuals and analyze the differences in the walking movements of different individuals based on their health conditions. A smartphone’s motion sensors were used to measure the walking movements and analyze the rotation matrix data by calculating the variation of each xyz rotation, which shows the variables in walking-related movement data over time.

Methods

Data were collected from 3 participants, that is, 2 healthy individuals (1 female and 1 male) and 1 male with back pain. The participant with back pain injured his back during strenuous exercise but he did not have any issues in walking. The participants wore the smartphone in the middle of their waistline (as the center of gravity) while walking. They were instructed to walk straight at their own pace in an indoor hallway of a building. The walked a distance of approximately 400 feet. They walked for 2-3 minutes in a straight line and then returned to the starting location. A rotation vector in the smartphone, calculated by the rotation matrix, was used to measure the pitch, roll, and yaw angles of the human body while walking. Each xyz-rotation vector datum was recalculated to find the variation in each participant’s walking movement.

Results

The male participant with back pain showed a diminished level of walking balance with a wider range of xyz-axis variations in the rotations compared to those of the healthy participants. The standard deviation in the xyz-axis of the male participant with back pain was larger than that of the healthy male participant. Moreover, the participant with back pain had the widest combined range of right-to-left and forward-to-backward motions. The healthy male participant showed smaller standard deviation while walking than the male participant with back pain and the female healthy participant, indicating that the healthy male participant had a well-balanced walking movement. The walking movement of the female healthy participant showed symmetry in the left-to-right (x-axis) and up-to-down (y-axis) motions in the x-y variations of rotation vectors, indicating that she had lesser bias in gait than the others.

Conclusions

This study shows that our mHealth app based on smartphone sensors and rotation vectors can measure the variations in the walking movements of different individuals. Further studies are needed to measure and compare walking movements by age, gender, as well as types of health problems or disease. This app can help in finding differences in gait in people with diseases that affect gait.

Sleeve for Knee Angle Monitoring: An IMU-POF Sensor Fusion System

The knee flexion-extension angle is an important variable to be monitored in various clinical scenarios, for example, during physical rehabilitation assessment. The purpose of this work is to develop and validate a sensor fusion system based on a knee sleeve for monitoring of physical therapy. The system consists of merging data from two inertial measurement units (IMUs) and an intensity-variation based Polymer Optical Fiber (POF) curvature sensor using a quaternion-based Multiplicative Extended Kalman Filter (MEKF). The proposed data fusion method is magnetometer-free and deals with sensors' uncertainties through reliability intervals defined during gait. Walking trials were performed by twelve healthy participants using our knee sleeve system and results were validated against a gold standard motion capture system. Additionally, a comparison with other three knee angle estimation methods, which are exclusively based on IMUs, was carried out. The proposed system presented better performance (mean RMSE 3.3 ^°, LFM coefficients, a₁ = 0.99 ± 0.04, a₀ = 0.70 ± 2.29, R² = 0.98 ± 0.01 and ρ_C 0.99) when compared to the other evaluated methods. Experimental results demonstrate the usability and feasibility of our system to estimate knee motion with high accuracy, repeatability, and reproducibility. This wearable system may be suitable for motion assessment in rehabilitation labs in future studies.

Synergy-Based Sensor Reduction for Recording the Whole Hand Kinematics

Simultaneous measurement of the kinematics of all hand segments is cumbersome due to sensor placement constraints, occlusions, and environmental disturbances. The aim of this study is to reduce the number of sensors required by using kinematic synergies, which are considered the basic building blocks underlying hand motions. Synergies were identified from the public KIN-MUS UJI database (22 subjects, 26 representative daily activities). Ten synergies per subject were extracted as the principal components explaining at least 95% of the total variance of the angles recorded across all tasks. The 220 resulting synergies were clustered, and candidate angles for estimating the remaining angles were obtained from these groups. Different combinations of candidates were tested and the one providing the lowest error was selected, its goodness being evaluated against kinematic data from another dataset (KINE-ADL BE-UJI). Consequently, the original 16 joint angles were reduced to eight: carpometacarpal flexion and abduction of thumb, metacarpophalangeal and interphalangeal flexion of thumb, proximal interphalangeal flexion of index and ring fingers, metacarpophalangeal flexion of ring finger, and palmar arch. Average estimation errors across joints were below 10% of the range of motion of each joint angle for all the activities. Across activities, errors ranged between 3.1% and 16.8%.

Estimating Movement Smoothness From Inertial Measurement Units

Inertial measurement units (IMUs) are increasingly used to estimate movement quality and quantity to the infer the nature of motor behavior. The current literature contains several attempts to estimate movement smoothness using data from IMUs, many of which assume that the translational and rotational kinematics measured by IMUs can be directly used with the smoothness measures spectral arc length (SPARC) and log dimensionless jerk (LDLJ-V). However, there has been no investigation of the validity of these approaches. In this paper, we systematically evaluate the use of these measures on the kinematics measured by IMUs. We show that: (a) SPARC and LDLJ-V are valid measures of smoothness only when used with velocity; (b) SPARC and LDLJ-V applied on translational velocity reconstructed from IMU is highly error prone due to drift caused by integration of reconstruction errors; (c) SPARC can be applied directly on rotational velocities measured by a gyroscope, but LDLJ-V can be error prone. For discrete translational movements, we propose a modified version of the LDLJ-V measure, which can be applied to acceleration data (LDLJ-A). We evaluate the performance of these measures using simulated and experimental data. We demonstrate that the accuracy of LDLJ-A depends on the time profile of IMU orientation reconstruction error. Finally, we provide recommendations for how to appropriately apply these measures in practice under different scenarios, and highlight various factors to be aware of when performing smoothness analysis using IMU data.

PyTHang: an open-source wearable sensor system for real-time monitoring of head-torso angle for ambulatory applications

This article presents the realization of a low-cost wearable sensor system and its Python-based software that can measure and record relative head-torso angle, especially in sagittal plane. The system is mainly developed to track head-torso angle during walk in a clinical study. The open-hardware part of the system is composed of a pair of triaxial digital accelerometers, a microprocessor, a Bluetooth module and a rechargeable battery unit. The reception of the transmitted acceleration data, visualization, interactive sensor alignment, angle estimation and data-logging are realized by the developed open-source graphical user interface. The system is tested on a tripod for verification and on a subject for practical demonstration. Developed system can be constructed and used for ambulatory monitoring and analysis of relative head-torso angle. Open-source user interface can be downloaded and developed for further (different) algorithms and device hardware.

A Kalman Filter for Nonlinear Attitude Estimation Using Time Variable Matrices and Quaternions

The nonlinear problem of sensing the attitude of a solid body is solved by a novel implementation of the Kalman Filter. This implementation combines the use of quaternions to represent attitudes, time-varying matrices to model the dynamic behavior of the process and a particular state vector. This vector was explicitly created from measurable physical quantities, which can be estimated from the filter input and output. The specifically designed arrangement of these three elements and the way they are combined allow the proposed attitude estimator to be formulated following a classical Kalman Filter approach. The result is a novel estimator that preserves the simplicity of the original Kalman formulation and avoids the explicit calculation of Jacobian matrices in each iteration or the evaluation of augmented state vectors.

AI Therapist Realizing Expert Verbal Cues for Effective Robot-Assisted Gait Training

Repetitive and specific verbal cues by a therapist are essential in aiding a patient's motivation and improving the motor learning process. The verbal cues comprise various expressions, sentences, volumes, and timings, depending on the therapist's proficiency. This paper proposes an AI therapist (AI-T) that implements the verbal cues of professional therapists having extensive experience with robot-assisted gait training using the SUBAR for stroke patients. The AI-T was developed using a neuro-fuzzy system, a machine learning technique leveraging the benefits of fuzzy logic and artificial neural networks. The AI-T was trained with the professional therapist's verbal cue data, as well as clinical and robotic data collected from robot-assisted gait training with real stroke patients. Ten clinical data and 16 robotic data are input variables, and six verbal cues are output variables. Fifty-eight stroke patients wore the SUBAR, a gait training robot, and participated in the robot-assisted gait training. A total of 9059 verbal cue data, 580 clinical data of stroke patients, and 144 944 robotic data were collected from 693 training sessions. Test results show that the trained AI-T can implement six types of verbal cues with 93.7% accuracy for the 1812 verbal cue data of the professional therapist. Currently, the trained AI-T is deployed in the SUBAR and provides six verbal cues to stroke patients in robot-assisted gait training.

Gait analysis in neurological populations: Progression in the use of wearables

Gait assessment is an essential tool for clinical applications not only to diagnose different neurological conditions but also to monitor disease progression as it contributes to the understanding of underlying deficits. There are established methods and models for data collection and interpretation of gait assessment within different pathologies. This narrative review aims to depict the evolution of gait assessment from observation and rating scales to wearable sensors and laboratory technologies and provide limitations and possible future directions in the field of gait assessment. In this context, we first present an extensive review of current clinical outcomes and gait models. Then, we demonstrate commercially available wearable technologies with their technical capabilities along with their use in gait assessment studies for various neurological conditions. In the next sections, a descriptive knowledge for existing inertial and EMG based algorithms and a sign based guide that shows the outcomes of previous neurological gait assessment studies are presented. Finally, we state a discussion for the use of wearables in gait assessment and speculate the possible research directions by revealing the limitations and knowledge gaps in the literature.

Measuring upper arm elevation using an inertial measurement unit: An exploration of sensor fusion algorithms and gyroscope models

Many sensor fusion algorithms for analyzing human motion information collected with inertial measurement units have been reported in the scientific literature. Selecting which algorithm to use can be a challenge for ergonomists that may be unfamiliar with the strengths and limitations of the various options. In this paper, we describe fundamental differences among several algorithms, including differences in sensor fusion approach (e.g., complementary filter vs. Kalman Filter) and gyroscope error modeling (i.e., inclusion or exclusion of gyroscope bias). We then compare different sensor fusion algorithms considering the fundamentals discussed using laboratory-based measurements of upper arm elevation collected under three motion speeds. Results indicate peak displacement errors of <4.5° with a computationally efficient, non-proprietary complementary filter that did not account for gyroscope bias during each of the one-minute trials. Controlling for gyroscope bias reduced peak displacement errors to <3.0°. The complementary filters were comparable (<1° peak displacement difference) to the more complex Kalman filters.