Graph-Driven Simultaneous and Proportional Estimation of Wrist Angle and Grasp Force via High-Density EMG

Myoelectric prostheses are generally unable to accurately control the position and force simultaneously, prohibiting natural and intuitive human-machine interaction. This issue is attributed to the limitations of myoelectric interfaces in effectively decoding multi-degree-of-freedom (multi-DoF) kinematic and kinetic information. We thus propose a novel multi-task, spatial-temporal model driven by graphical high-density electromyography (HD-EMG) for simultaneous and proportional control of wrist angle and grasp force. Twelve subjects were recruited to perform three multi-DoF movements, including wrist pronation/supination, wrist flexion/extension, and wrist abduction/adduction while varying grasp force. Experimental results demonstrated that the proposed model outperformed five baseline models, with the normalized root mean square error of 13.2% and 9.7% and the correlation coefficient of 89.6% and 91.9% for wrist angle and grasp force estimation, respectively. In addition, the proposed model still maintained comparable accuracy even with a significant reduction in the number of HD-EMG electrodes. To the best of our knowledge, this is the first study to achieve simultaneous and proportional wrist angle and grasp force control via HD-EMG and has the potential to empower prostheses users to perform a broader range of tasks with greater precision and control, ultimately enhancing their independence and quality of life.

Design of a Wearable Real-Time Hand Motion Tracking System Using an Array of Soft Polymer Acoustic Waveguides

Robust hand motion tracking holds promise for improved human-machine interaction in diverse fields, including virtual reality, and automated sign language translation. However, current wearable hand motion tracking approaches are typically limited in detection performance, wearability, and durability. This article presents a hand motion tracking system using multiple soft polymer acoustic waveguides (SPAWs). The innovative use of SPAWs as strain sensors offers several advantages that address the limitations. SPAWs are easily manufactured by casting a soft polymer shaped as a soft acoustic waveguide and containing a commercially available small ceramic piezoelectric transducer. When used as strain sensors, SPAWs demonstrate high stretchability (up to 100%), high linearity (R2 > 0.996 in all quasi-static, dynamic, and durability tensile tests), negligible hysteresis (<0.7410% under strain of up to 100%), excellent repeatability, and outstanding durability (up to 100,000 cycles). SPAWs also show high accuracy for continuous finger angle estimation (average root-mean-square errors [RMSE] <2.00°) at various flexion-extension speeds. Finally, a hand-tracking system is designed based on a SPAW array. An example application is developed to demonstrate the performance of SPAWs in real-time hand motion tracking in a three-dimensional (3D) virtual environment. To our knowledge, the system detailed in this article is the first to use soft acoustic waveguides to capture human motion. This work is part of an ongoing effort to develop soft sensors using both time and frequency domains, with the goal of extracting decoupled signals from simple sensing structures. As such, it represents a novel and promising path toward soft, simple, and wearable multimodal sensors.

Self-Supervised Learning Improves Accuracy and Data Efficiency for IMU-Based Ground Reaction Force Estimation

OBJECTIVE

Recent deep learning techniques hold promise to enable IMU-driven kinetic assessment; however, they require large extents of ground reaction force (GRF) data to serve as labels for supervised model training. We thus propose using existing self-supervised learning (SSL) techniques to leverage large IMU datasets to pre-train deep learning models, which can improve the accuracy and data efficiency of IMU-based GRF estimation.

METHODS

We performed SSL by masking a random portion of the input IMU data and training a transformer model to reconstruct the masked portion. We systematically compared a series of masking ratios across three pre-training datasets that included real IMU data, synthetic IMU data, or a combination of the two. Finally, we built models that used pre-training and labeled data to estimate GRF during three prediction tasks: overground walking, treadmill walking, and drop landing.

RESULTS

When using the same amount of labeled data, SSL pre-training significantly improved the accuracy of 3-axis GRF estimation during walking compared to baseline models trained by conventional supervised learning. Fine-tuning SSL model with 1-10% of walking data yielded comparable accuracy to training baseline model with 100% of walking data. The optimal masking ratio for SSL is 6.25-12.5%.

CONCLUSION

SSL leveraged large real and synthetic IMU datasets to increase the accuracy and data efficiency of deep-learning-based GRF estimation, reducing the need for labeled data.

SIGNIFICANCE

This work, with its open-source code and models, may unlock broader use cases of IMU-driven kinetic assessment by mitigating the scarcity of GRF measurements in practical applications.

Self-Supervised Learning Improves Accuracy and Data Efficiency for IMU-Based Ground Reaction Force Estimation

Objective

Recent deep learning techniques hold promise to enable IMU-driven kinetic assessment; however, they require large extents of ground reaction force (GRF) data to serve as labels for supervised model training. We thus propose using existing self-supervised learning (SSL) techniques to leverage large IMU datasets to pre-train deep learning models, which can improve the accuracy and data efficiency of IMU-based GRF estimation.

Methods

We performed SSL by masking a random portion of the input IMU data and training a transformer model to reconstruct the masked portion. We systematically compared a series of masking ratios across three pre-training datasets that included real IMU data, synthetic IMU data, or a combination of the two. Finally, we built models that used pre-training and labeled data to estimate GRF during three prediction tasks: overground walking, treadmill walking, and drop landing.

Results

When using the same amount of labeled data, SSL pre-training significantly improved the accuracy of 3-axis GRF estimation during walking compared to baseline models trained by conventional supervised learning. Fine-tuning SSL model with 1-10% of walking data yielded comparable accuracy to training baseline model with 100% of walking data. The optimal masking ratio for SSL is 6.25-12.5%.

Conclusion

SSL leveraged large real and synthetic IMU datasets to increase the accuracy and data efficiency of deep-learning-based GRF estimation, reducing the need for labeled data.

Significance

This work, with its open-source code and models, may unlock broader use cases of IMU-driven kinetic assessment by mitigating the scarcity of GRF measurements in practical applications.

3D Knee and Hip Angle Estimation With Reduced Wearable IMUs via Transfer Learning During Yoga, Golf, Swimming, Badminton, and Dance

Wearable lower-limb joint angle estimation using a reduced inertial measurement unit (IMU) sensor set could enable quick, economical sports injury risk assessment and motion capture; however the vast majority of existing research requires a full IMU set attached to every related body segment and is implemented in only a single movement, typically walking. We thus implemented 3-dimensional knee and hip angle estimation with a reduced IMU sensor set during yoga, golf, swimming (simulated lower body swimming in a seated posture), badminton, and dance movements. Additionally, current deep-learning models undergo an accuracy drop when tested with new and unseen activities, which necessitates collecting large amounts of data for the new activity. However, collecting large datasets for every new activity is time-consuming and expensive. Thus, a transfer learning (TL) approach with long short-term memory neural networks was proposed to enhance the model's generalization ability towards new activities while minimizing the need for a large new-activity dataset. This approach could transfer the generic knowledge acquired from training the model in the source-activity domain to the target-activity domain. The maximum improvement in estimation accuracy (RMSE) achieved by TL is 23.6 degrees for knee flexion/extension and 22.2 degrees for hip flexion/extension compared to without TL. These results extend the application of motion capture with reduced sensor configurations to a broader range of activities relevant to injury prevention and sports training. Moreover, they enhance the capacity of data-driven models in scenarios where acquiring a substantial amount of training data is challenging.

IMU Shoulder Angle Estimation: Effects of Sensor-to-Segment Misalignment and Sensor Orientation Error

Accurate shoulder joint angle estimation is crucial for analyzing joint kinematics and kinetics across a spectrum of movement applications including in athletic performance evaluation, injury prevention, and rehabilitation. However, accurate IMU-based shoulder angle estimation is challenging and the specific influence of key error factors on shoulder angle estimation is unclear. We thus propose an analytical model based on quaternions and rotation vectors that decouples and quantifies the effects of two key error factors, namely sensor-to-segment misalignment and sensor orientation estimation error, on shoulder joint rotation error. To validate this model, we conducted experiments involving twenty-five subjects who performed five activities: yoga, golf, swimming, dance, and badminton. Results showed that improving sensor-to-segment misalignment along the segment's extension/flexion dimension had the most significant impact in reducing the magnitude of shoulder joint rotation error. Specifically, a 1° improvement in thorax and upper arm calibration resulted in a reduction of 0.40° and 0.57° in error magnitude. In comparison, improving IMU heading estimation was only roughly half as effective (0.23° per 1°). This study clarifies the relationship between shoulder angle estimation error and its contributing factors, and identifies effective strategies for improving these error factors. These findings have significant implications for enhancing the accuracy of IMU-based shoulder angle estimation, thereby facilitating advancements in IMU-based upper limb rehabilitation, human-machine interaction, and athletic performance evaluation.

Synthetic EMG Based on Adversarial Style Transfer Can Effectively Attack Biometric-Based Personal Identification Models

Biometric-based personal identification models are generally considered to be accurate and secure because biological signals are too complex and person-specific to be fabricated, and EMG signals, in particular, have been used as biological identification tokens due to their high dimension and non-linearity. We investigate the possibility of effectively attacking EMG-based identification models with adversarial biological input via a novel EMG signal individual-style transformer based on a generative adversarial network and tiny leaked data segments. Since two same EMG segments do not exist in nature; the leaked data can't be used to attack the model directly or it will be easily detected. Therefore, it is necessary to extract the style with the leaked personal signals and generate the attack signals with different contents. With our proposed method and tiny leaked personal EMG fragments, numerous EMG signals with different content can be generated in that person's style. EMG hand gesture data from eighteen subjects and three well-recognized deep EMG classifiers were used to demonstrate the effectiveness of the proposed attack methods. The proposed methods achieved an average of 99.41% success rate on confusing identification models and an average of 91.51% success rate on manipulating identification models. These results demonstrate that EMG classifiers based on deep neural networks can be vulnerable to synthetic data attacks. The proof-of-concept results reveal that synthetic EMG biological signals must be considered in biological identification system design across a vast array of relevant biometric systems to ensure personal identification security for individuals and institutions.

Real-time ground reaction force and knee extension moment estimation during drop landings via modular LSTM modeling and wearable IMUs

OBJECTIVE

This work investigates real-time estimation of vertical ground reaction force (vGRF) and external knee extension moment (KEM) during single- and double-leg drop landings via wearable inertial measurement units (IMUs) and machine learning.

METHODS

A real-time, modular LSTM-based model with four sub-deep neural networks was developed to estimate the vGRF and KEM from wearable IMUs. Sixteen subjects wore eight IMUs on the chest, waist, right and left thighs, shanks, and feet and performed drop landing trials. Ground embedded force plates and an optical motion capture system were used to capture lower extremity biomechanics for model training and evaluation.

RESULTS

During single-leg drop landings, accuracy for the vGRF and KEM estimation was R²=0.88 ±0.12 and R²=0.84 ±0.14, respectively, and during double-leg drop landings, accuracy for the vGRF and KEM estimation was R²=0.85 ±0.11 and R²=0.84 ±0.12, respectively. The best vGRF and KEM estimations of the model with the optimal LSTM unit number (130) require eight IMUs placed on the eight selected locations during single-leg drop landings. During double-leg drop landings, the best estimation on a leg only needs five IMUs placed on the chest, waist, and the leg's shank, thigh, and foot.

CONCLUSION

The proposed modular LSTM-based model with optimally-configurable wearable IMUs can accurately estimate vGRF and KEM in real-time with relatively low computational cost during single- and double-leg drop landing tasks.

SIGNIFICANCE

This investigation could potentially enable in-field, non-contact anterior cruciate ligament injury risk screening and intervention training programs.

Multi-day monitoring of foot progression angles during unsupervised, real-world walking in people with and without knee osteoarthritis

BACKGROUND

Foot progression angle is a biomechanical target in gait modification interventions for knee osteoarthritis. To date, it has only been evaluated within laboratory settings.

METHODS

Adults with symptomatic knee osteoarthritis (n = 30) and healthy adults (n = 15) completed two conditions: 1) treadmill walking in the laboratory (5-min), and 2) real-world walking outside of the laboratory (1-week). Foot progression angle was estimated via shoe-embedded inertial sensing. We calculated the foot progression angle magnitude (median) and variability (interquartile range, coefficient of variation), and used mixed models to compare outcomes between the conditions, participant groups, and disease severities. Reliability was quantified by the intraclass correlation coefficient, standardized error of the measurement, and the minimum detectable change.

FINDINGS

Foot progression angle magnitude did not differ between groups or conditions but variability significantly higher in real-world walking (P < 0.001). Structural and symptomatic severity were unrelated to FPA in either walking condition, except for real-world coefficient of variation which was higher for moderate-severe structural osteoarthritis compared to the treadmill for those with mild structural severity (P < 0.034). All real-world outcomes showed excellent reliability including intraclass correlation coefficients above 0.95. The participants recorded a mean (standard deviation) of 298 (33) and 10,447 (5232) steps in the laboratory and real-world walking conditions, respectively.

INTERPRETATION

This study provides the first characterization of foot progression angles during real-world walking in people with and without symptomatic knee osteoarthritis. These results indicate that foot progression angles can be feasibly and reliably measured in unsupervised real-world walking conditions.

A scoping review of portable sensing for out-of-lab anterior cruciate ligament injury prevention and rehabilitation

Anterior cruciate ligament (ACL) injury and ACL reconstruction (ACLR) surgery are common. Laboratory-based biomechanical assessment can evaluate ACL injury risk and rehabilitation progress after ACLR; however, lab-based measurements are expensive and inaccessible to most people. Portable sensors such as wearables and cameras can be deployed during sporting activities, in clinics, and in patient homes. Although many portable sensing approaches have demonstrated promising results during various assessments related to ACL injury, they have not yet been widely adopted as tools for out-of-lab assessment. The purpose of this review is to summarize research on out-of-lab portable sensing applied to ACL and ACLR and offer our perspectives on new opportunities for future research and development. We identified 49 original research articles on out-of-lab ACL-related assessment; the most common sensing modalities were inertial measurement units, depth cameras, and RGB cameras. The studies combined portable sensors with direct feature extraction, physics-based modeling, or machine learning to estimate a range of biomechanical parameters (e.g., knee kinematics and kinetics) during jump-landing tasks, cutting, squats, and gait. Many of the reviewed studies depict proof-of-concept methods for potential future clinical applications including ACL injury risk screening, injury prevention training, and rehabilitation assessment. By synthesizing these results, we describe important opportunities that exist for clinical validation of existing approaches, using sophisticated modeling techniques, standardization of data collection, and creation of large benchmark datasets. If successful, these advances will enable widespread use of portable-sensing approaches to identify ACL injury risk factors, mitigate high-risk movements prior to injury, and optimize rehabilitation paradigms.

A Novel PPG-FMG-ACC Wristband for Hand Gesture Recognition

Wrist-based hand gesture recognition has the potential to unlock naturalistic human-computer interaction for a vast array of virtual and augmented reality applications. Photoplethysmography (PPG), force myography (FMG), and accelerometry (ACC) have generally been proposed as isolated single sensing modalities for gesture recognition, but any of these alone is inherently limited in the amount of biological information it can collect during finger and hand movements. We thus propose a novel, wrist-based, PPG-FMG-ACC combined sensing approach based on a multi-head attention mechanism fusion convolutional neural network (CNN-AF) for gesture recognition. Nine subjects performed twelve hand gestures involving various wrist and finger postures. Experimental results showed that multi-modal fusion improved classification performance significantly ( ) compared to any single sensing modality, and the F1-score of the combined PPG-FMG-ACC approach was 40.1% higher than PPG alone, 27.4% higher than ACC alone, and 11.9% higher than FMG alone. To the best of our knowledge, this paper is the first to combine wrist-based PPG, FMG, and ACC signals for hand gesture recognition. These results could serve to inform wrist-based gesture recognition design (e.g., via a smartwatch) and thus expand the capabilities of intuitive and ubiquitous human-machine interaction.

Proposal of a Wearable Multimodal Sensing-Based Serious Games Approach for Hand Movement Training After Stroke

Stroke often leads to hand motor dysfunction, and effective rehabilitation requires keeping patients engaged and motivated. Among the existing automated rehabilitation approaches, data glove-based systems are not easy to wear for patients due to spasticity, and single sensor-based approaches generally provided prohibitively limited information. We thus propose a wearable multimodal serious games approach for hand movement training after stroke. A force myography (FMG), electromyography (EMG), and inertial measurement unit (IMU)-based multi-sensor fusion model was proposed for hand movement classification, which was worn on the user’s affected arm. Two movement recognition-based serious games were developed for hand movement and cognition training. Ten stroke patients with mild to moderate motor impairments (Brunnstrom Stage for Hand II-VI) performed experiments while playing interactive serious games requiring 12 activities-of-daily-living (ADLs) hand movements taken from the Fugl Meyer Assessment. Feasibility was evaluated by movement classification accuracy and qualitative patient questionnaires. The offline classification accuracy using combined FMG-EMG-IMU was 81.0% for the 12 movements, which was significantly higher than any single sensing modality; only EMG, only FMG, and only IMU were 69.6, 63.2, and 47.8%, respectively. Patients reported that they were more enthusiastic about hand movement training while playing the serious games as compared to conventional methods and strongly agreed that they subjectively felt that the proposed training could be beneficial for improving upper limb motor function. These results showed that multimodal-sensor fusion improved hand gesture classification accuracy for stroke patients and demonstrated the potential of this proposed approach to be used as upper limb movement training after stroke.

Predicting knee adduction moment response to gait retraining with minimal clinical data

Knee osteoarthritis is a progressive disease mediated by high joint loads. Foot progression angle modifications that reduce the knee adduction moment (KAM), a surrogate of knee loading, have demonstrated efficacy in alleviating pain and improving function. Although changes to the foot progression angle are overall beneficial, KAM reductions are not consistent across patients. Moreover, customized interventions are time-consuming and require instrumentation not commonly available in the clinic. We present a regression model that uses minimal clinical data—a set of six features easily obtained in the clinic—to predict the extent of first peak KAM reduction after toe-in gait retraining. For such a model to generalize, the training data must be large and variable. Given the lack of large public datasets that contain different gaits for the same patient, we generated this dataset synthetically. Insights learned from a ground-truth dataset with both baseline and toe-in gait trials (N = 12) enabled the creation of a large (N = 138) synthetic dataset for training the predictive model. On a test set of data collected by a separate research group (N = 15), the first peak KAM reduction was predicted with a mean absolute error of 0.134% body weight * height (%BW*HT). This error is smaller than the standard deviation of the first peak KAM during baseline walking averaged across test subjects (0.306%BW*HT). This work demonstrates the feasibility of training predictive models with synthetic data and provides clinicians with a new tool to predict the outcome of patient-specific gait retraining without requiring gait lab instrumentation.

Gait retraining is a conservative intervention for knee osteoarthritis shown to reduce pain and improve function. Although customizing a treatment plan for each patient results in a better therapeutic response, customization cannot yet be performed outside of the gait laboratory, preventing research advances from becoming part of clinical practice. Our work aimed to build a model that accurately predicts whether a patient with knee osteoarthritis will benefit from non-invasive gait retraining using measures that can be easily collected in the clinic. To overcome the lack of large datasets required to train predictive models, we generated data synthetically (N = 138) based on limited ground-truth examples, and we provide experimental evidence for the model’s ability to generalize to real data (N = 15). Our results contribute toward a future in which clinicians can use data collected in the clinic to easily identify patients who would respond to therapeutic gait retraining.

Reducing Slip Risk: A Feasibility Study of Gait Training with Semi-Real-Time Feedback of Foot-Floor Contact Angle

Slip-induced falls, responsible for approximately 40% of falls, can lead to severe injuries and in extreme cases, death. A large foot-floor contact angle (FFCA) during the heel-strike event has been associated with an increased risk of slip-induced falls. The goals of this feasibility study were to design and assess a method for detecting FFCA and providing cues to the user to generate a compensatory FFCA response during a future heel-strike event. The long-term goal of this research is to train gait in order to minimize the likelihood of a slip event due to a large FFCA. An inertial measurement unit (IMU) was used to estimate FFCA, and a speaker provided auditory semi-real-time feedback when the FFCA was outside of a 10-20 degree target range following a heel-strike event. In addition to training with the FFCA feedback during a 10-min treadmill training period, the healthy young participants completed pre- and post-training overground walking trials. Results showed that training with FFCA feedback increased FFCA events within the target range by 16% for "high-risk" walkers (i.e., participants that walked with more than 75% of their FFCAs outside the target range) both during feedback treadmill trials and post-training overground trials without feedback, supporting the feasibility of training FFCA using a semi-real-time FFCA feedback system.

Activities of Daily Living-based Rehabilitation System for Arm and Hand Motor Function Retraining after Stroke

Most stroke survivors have difficulties completing activities of daily living (ADLs) independently. However, few rehabilitation systems have focused on ADLs-related training for gross and fine motor function together. We propose an ADLs-based serious game rehabilitation system for the training of motor function and coordination of both arm and hand movement where the user performs corresponding ADLs movements to interact with the target in the serious game. A multi-sensor fusion model based on electromyographic (EMG), force myographic (FMG), and inertial sensing was developed to estimate users' natural upper limb movement. Eight healthy subjects and three stroke patients were recruited in an experiment to validate the system's effectiveness. The performance of different sensor and classifier configurations on hand gesture classification against the arm position variations were analyzed, and qualitative patient questionnaires were conducted. Results showed that elbow extension/flexion has a more significant negative influence on EMG-based, FMG-based, and EMG+FMG-based hand gesture recognition than shoulder abduction/adduction does. In addition, there was no significant difference in the negative influence of shoulder abduction/adduction and shoulder flexion/extension on hand gesture recognition. However, there was a significant interaction between sensor configurations and algorithm configurations in both offline and real-time recognition accuracy. The EMG+FMG-combined multi-position classifier model had the best performance against arm position change. In addition, all the stroke patients reported their ADLs-related ability could be restored by using the system. These results demonstrate that the multi-sensor fusion model could estimate hand gestures and gross movement accurately, and the proposed training system has the potential to improve patients' ability to perform ADLs.

Transfer Learning Improves Accelerometer-Based Child Activity Recognition via Subject-Independent Adult-Domain Adaption

Wearable activity recognition can collate the type, intensity, and duration of each childs physical activity profile, which is important for exploring underlying adolescent health mechanisms. Traditional machine-learning-based approaches require large labeled data sets; however, child activity data sets are typically small and insufficient. Thus, we proposed a transfer learning approach that adapts adult-domain data to train a high-fidelity, subject-independent model for child activity recognition. Twenty children and twenty adults wore an accelerometer wristband while performing walking, running, sitting, and rope skipping activities. Activity classification accuracy was determined via the traditional machine learning approach without transfer learning and with the proposed subject-independent transfer learning approach. Results showed that transfer learning increased classification accuracy to 91.4% as compared to 80.6% without transfer learning. These results suggest that subject-independent transfer learning can improve accuracy and potentially reduce the size of the required child data sets to enable physical activity monitoring systems to be adopted more widely, quickly, and economically for children and provide deeper insights into injury prevention and health promotion strategies.

Wearable Real-Time Haptic Biofeedback Foot Progression Angle Gait Modification to Assess Short-Term Retention and Cognitive Demand

Foot progression angle gait (FPA) modification is an important part of rehabilitation for a variety of neuromuscular and musculoskeletal diseases. While wearable haptic biofeedback could enable FPA gait modification for more widespread use than traditional tethered, laboratory-based approaches, retention, and cognitive demand in FPA gait modification via wearable haptic biofeedback are currently unknown and may be important to real-life implementation. Thus, the purpose of this study was to assess the feasibility of wearable haptic biofeedback to assess short-term retention and cognitive demand during FPA gait modification. Ten healthy participants performed toe-in (target 10 degrees change in internal rotation) and toe-out (target 10 degrees change in external rotation) haptic gait training trials followed by short-term retention trials, and cognitive multitasking trials. Results showed that participants were able to initially respond to the wearable haptic feedback to modify their FPA to adopt the new toe-in (9.7 ± 0.8 degree change in internal rotation) and toe-out (8.9 ± 1.0 degree change in external rotation) gait patterns. Participants retained the modified gait pattern on average within 3.9 ± 3.6 deg of the final haptic gait training FPA values. Furthermore, cognitive multitasking did not influence short-term retention in that there were no differences in gait performance during retention trials with or without cognitive multitasking. These results demonstrate that wearable haptic biofeedback can be used to assess short-term retention and cognitive demand during FPA gait modification without the need for traditional, tethered systems.

Wrist-worn Hand Gesture Recognition while Walking via Transfer Learning

Walking, one of the most common daily activities, causes unwanted movement artifacts which can significantly deteriorate hand gesture recognition accuracy. However, traditional hand gesture recognition algorithms are typically developed and validated with wrist-worn devices only during static human poses, neglecting the critical importance of dynamic effects on gesture accuracy. Thus, we developed and validated a signal decomposition approach via empirical mode decomposition to accurately segment target gestures from coupled raw signals during dynamic walking and a transfer learning method based on distribution adaptation to enable gesture recognition through domain transfer between dynamic walking and static standing scenarios. Ten healthy subjects performed seven hand gestures during both walking and standing experiments while wearing an IMU wrist-worn device. Experimental results showed that the signal decomposition approach reduced the gesture detection error by 83.8%, and the transfer learning approach (20% transfer rate) improved hand gesture recognition accuracy by 15.1%. This ground-breaking work demonstrates the feasibility of hand gesture recognition while walking via wrist-worn sensing. These findings serve to inform real-life and ubiquitous adoption of wrist-worn hand gesture recognition for intuitive human-machine interaction in dynamic walking situations.

IMU-based knee flexion, abduction and internal rotation estimation during drop landing and cutting tasks

Anterior cruciate ligament (ACL) injury is a common and severe knee injury in sports. Knee flexion, abduction and internal rotation angles are considered crucial biomechanical indicators of the ACL injury risk but currently are computed in a laboratory with an optical motion capture. This paper introduces an inertial measurement unit (IMU) based algorithm for knee flexion, abduction and internal rotation estimation during ACL injury risk assessment tests, including drop landing and cutting tasks. This algorithm includes a special two-step complementary-based orientation filter and a special single-pose sensor-to-segment calibration procedure. Fourteen healthy subjects performed double-leg, single-leg drop landing and cutting tasks. Each subject wore four IMUs and reflective marker clusters on their thighs and shanks. For the presented knee angles algorithm with an empirical initial segment orientation, the root mean square errors (RMSEs) of the estimated continuous knee flexion, abduction and internal rotation cross all the movement tasks were 1.07°, 2.87° and 2.64°, and RMSEs of the peak knee flexion and peak knee abduction errors were 1.22° and 3.82°. The knee angles algorithm was capable of estimating knee abduction and internal rotation angles during drop landing and cutting tasks, and knee flexion estimation was substantially more accurate than previously reported approaches. Additionally, we found that for the presented algorithm, the accuracy of initial segment orientation was a critical factor for knee abduction and internal rotation estimations. The presented IMU-based knee angles algorithm could serve as a foundation to enable in-field biomechanical ACL injury risk assessment.

Self-selected running gait modifications reduce acute impact loading, awkwardness, and effort

Impact loading has been associated with running-related injuries, and gait retraining has been suggested as a means of reducing impact loading and lowering the risk of injury. However, gait retraining can lead to increased perceived awkwardness and effort. The influence of specifically trained and self-selected running gait modifications on acute impact loading, perceived awkwardness and effort is currently unclear. Sixteen habitual rearfoot/midfoot runners performed forefoot strike pattern, increased step rate, anterior trunk lean and self-selected running gait modifications on an instrumented treadmill based on real-time biofeedback. Impact loading, perceived awkwardness and effort scores were compared among the four gait retraining conditions. Self-selected gait modification reduced vertical average loading rate (VALR) by 25.3%, vertical instantaneous loading rate (VILR) by 27.0%, vertical impact peak (VIP) by 16.8% as compared with baseline. Forefoot strike pattern reduced VALR, VILR and peak tibial acceleration. Increased step rate reduced VALR. Anterior trunk lean did not reduce any impact loading. Self-selected gait modification was perceived as less awkward and require less effort than the specifically trained gait modification (p < 0.05). These findings suggest that self-selected gait modification could be a more natural and less effortful strategy than specifically trained gait modification to reduce acute impact loading, while the clinical significance remains unknown.

Accurate Impact Loading Rate Estimation During Running via a Subject-Independent Convolutional Neural Network Model and Optimal IMU Placement

OBJECTIVE

Enable accurate estimation of vertical average loading rate (VALR) in runners with one or more wearable inertial measurement units (IMUs).

METHODS

A subject-independent convolutional neural network (CNN) model was developed to estimate VALR from wearable IMUs. Fifteen runners wore IMUs at the trunk, pelvis, thigh, shank, and foot and ran on an instrumented treadmill for combinations of the following conditions: foot-strike (forefoot, mid-foot, rear-foot), step rate (90% to 110% of baseline), running speed (2.4 m/s and 2.8 m/s) and footwear (standard and minimalist running shoes). Thirty-one IMU placement configurations with combinations of one to five IMUs were evaluated. VALR estimations from the wearable IMUs were compared with force-plate VALR measurements.

RESULTS

VALR estimations via the subject-independent CNN model with a single shank-worn IMU were highly correlated (ρ = 0.94) with force-plate VALR measurements and were substantially higher than previously reported peak tibial acceleration correlations with force-plate VALR measurements from shank-worn accelerometers (ρ = 0.44-0.66). Correlation results from the CNN model for a single IMU placed at the foot, pelvis, trunk, and thigh were ρ = 0.91, 0.76, 0.69, and 0.65, respectively. There was no improvement in accuracy from the shank-worn IMU when adding 1-4 additional IMUs from the trunk, pelvis, thigh, or foot.

CONCLUSION

The proposed subject-independent CNN model with a single shank-worn IMU provides more accurate estimation of VALR than previous wearable sensing approaches.

SIGNIFICANCE

This could enable runners to more accurately assess impact loading rates and potentially provide insights into running-related injury risk and prevention.

Feasibility Validation on Healthy Adults of a Novel Active Vibrational Sensing Based Ankle Band for Ankle Flexion Angle Estimation

Goal: In this paper, we introduced a novel ankle band with a vibrational sensor that can achieve low-cost ankle flexion angle estimation, which can be potentially used for automated ankle flexion angle estimation in home-based foot drop rehabilitation scenarios. Methods: Previous ankle flexion angle estimation methods require either professional knowledge or specific equipment and lab environment, which is not feasible for foot drop patients to achieve accurate measurement by themselves in a home-based scenario. To solve the above problems, a prototype was developed based on the assumption that the echo of a vibration signal on the tibialis anterior had different acoustic impedance distribution. By analyzing the frequency spectrum of the echo, the ankle flexion angle can be estimated. Therefore, a surface transducer was utilized to generate frequency-varying active vibration, and a contact microphone was utilized to capture the echo. A portable analog signal processing hub drove the transducer, and was used for echo signal collection from the microphone. Finally, a Random Forest regression model was applied to estimate the ankle flexion angle based on the spectrum amplitude of the echo. Results: Five healthy subjects were recruited in the experiment. The regression estimation error is 4.16 degrees, and the R² is 0.81. Conclusions: These results demonstrate the feasibility of the proposed ankle band for accurate ankle flexion angle estimation.

Magnetometer-Free, IMU-Based Foot Progression Angle Estimation for Real-Life Walking Conditions

Foot progression angle (FPA) is vital in many disease assessment and rehabilitation applications, however previous magneto-IMU-based FPA estimation algorithms can be prone to magnetic distortion and inaccuracies after walking starts and turns. This paper presents a foot-worn IMU-based FPA estimation algorithm comprised of three key components: orientation estimation, acceleration transformation, and FPA estimation via peak foot deceleration. Twelve healthy subjects performed two walking experiments to evaluation IMU algorithm performance. The first experiment aimed to validate the proposed algorithm in continuous straight walking tasks across seven FPA gait patterns (large toe-in, medium toe-in, small toe-in, normal, small toe-out, medium toe-out, and large toe-out). The second experiment was performed to evaluate the proposed FPA algorithm for steps after walking starts and turns. Results showed that FPA estimations from the IMU-based algorithm closely followed marker-based system measurements with an overall mean absolute error of 3.1±1.3 deg, and the estimation results were valid for all steps immediately after walking starts and turns. This work could enable FPA assessment in environments where magnetic distortion is present due to ferrous metal structures and electrical equipment, or in real-life walking conditions when walking starts, stops, and turns commonly occur.

Modeling and Prediction of Wearable Energy Harvesting Sliding Shoes for Metabolic Cost and Energy Rate Outside of the Lab

The recent explosion of wearable electronics has led to widespread interest in harvesting human movement energy, particularly during walking, for clinical and health applications. However, the amount of energy available to harvest and the required metabolic rate for wearable energy harvesting varies across subjects. In this paper, we utilize custom energy harvesting sliding shoes to develop and evaluate multivariate linear regression models to predict metabolic rate and energy harvesting rate during overground walking outside of the lab. Subjects performed 200 m self-selected normal and fast walking trials on flat ground with custom sliding shoes. Metabolic rate was measured with a portable breathing analysis system and energy harvesting rate was measured directly from the generator on the custom sliding shoes. Model performance was determined by comparing the difference between actual and predicted metabolic and energy harvesting rates. Overall, predictive modeling closely matched the actual values, and there was no statistical difference between actual and predicted average metabolic rate or between actual and predicted average energy harvesting rate. Energy harvesting sliding shoes could potentially be used for a variety of wearable devices to reduce onboard energy storage, and these findings could serve to inform expected energy harvesting rates and associated required metabolic cost for a diverse array of medical and health applications.

How foot progression angle affects knee adduction moment and angular impulse in people with and without medial knee osteoarthritis: a meta-analysis

OBJECTIVE

To investigate effects of foot progression angle (FPA) modification on the first and second peaks of external knee adduction moment (EKAM) and knee adduction angular impulse (KAAI) in individuals with and without medial knee osteoarthritis (OA) during level walking.

METHODS

PubMed, Embase, CINAHL, Web of Science and SPORTDiscus were searched from inception to February 2020 by two independent reviewers. Included studies compared FPA modification (toe-in or toe-out gait) interventions to lower EKAM and/or KAAI with natural walking. Studies were required to report the first or second peaks of EKAM or KAAI.

RESULTS

Sixteen studies were included and more than 85% of included patients were graded with Kellgren-Lawrence II-IV knee OA. Toe-in gait reduced the first EKAM peak (standard mean difference (SMD): -0.75; 95%CI: -1.05~-0.45) and KAAI (SMD: -0.46; 95%CI: -0.86~-0.07), while toe-out gait reduced the second EKAM peak (SMD: -1.04; 95%CI: -1.34~-0.75) in healthy individuals. For patients with knee OA, toe-out gait reduced the second EKAM peak (SMD: -0.53; 95%CI: -0.75~-0.31) and KAAI (SMD: -0.26; 95%CI: -0.49~-0.03) while toe-in gait did not affect both EKAM peaks and KAAI.

CONCLUSION

Discrepancy in biomechanical effects of FPA modification was demonstrated between individuals with and without medial knee OA. Compared with natural walking, both toe-in and toe-out gait may be more effective in lowering EKAM and KAAI in healthy individuals. Toe-out gait may reduce EKAM and KAAI in patients with mild to severe knee OA. There is insufficient data from patients with early-stage knee OA, indicating future research is required.

Portable, automated foot progression angle gait modification via a proof-of-concept haptic feedback-sensorized shoe

Modifying the foot progression angle (FPA) is a non-pharmacological, non-surgical treatment option for knee osteoarthritis, however current widespread adoption has been limited by the requirement of laboratory-based motion capture systems. We present the first customized haptic feedback-sensorized shoe for estimating and modifying FPA during walking gait, which includes an electronic inertial and magnetometer module in the sole for estimating FPA, and two vibration motors attached to the medial and lateral shoe lining for providing vibrotactile feedback. Feasibility testing was performed by comparing FPA performance while wearing the haptic feedback-sensorized shoe with the training targets. Participants performed five walking trials with five randomly-presented FPA targets (10° toe-in, 0°, 10° toe-out, 20° toe-out, and 30° toe-out) of 2 min each on a treadmill. Overall average FPA performance error across all conditions was 0.2 ± 4.1°, and the overall mean absolute FPA performance error across all conditions was 3.1 ± 2.6°. Reducing the size of the no-feedback window resulted in less performance error during walking. This study demonstrates that a novel haptic feedback-sensorized shoe can be used to effectively train FPA modifications. The haptic feedback-sensorized shoe could potentially be used for FPA gait modification outside of specialized camera-based motion capture laboratories as a conservative treatment for knee osteoarthritis or other related clinical applications requiring FPA assessment and modification in daily life.

"Controlled Slip" Energy Harvesting While Walking

Rapid development in wearable electronics and systems continues to impose challenges on portable energy storage sustained over time, and thus human energy harvesting is a potentially attractive means of sustainable, long-term energy. We introduce a novel 'controlled slip' energy harvesting approach for capturing energy during human locomotion. While slip is normally considered undesirable, controlled slip holds potential to enable a significant amount of energy harvesting during each step of human gait. Custom-designed 'controlled slip' energy harvesting shoes were fabricated by mounting a sliding plate and a generator with a one-way bearing to the sole of standard walking shoes, which induces controlled forward slip during early stance while energy is harvested. Fourteen healthy subjects performed treadmill walking trials with the 'controlled slip' energy harvesting shoes which generated average electrical power of 1.15-1.44 W at walking speeds of 2.9-4.3 km/h. Interestingly, without prompting, subjects chose to walk with the 'controlled slip' energy harvesting shoes in either one of two distinct ways: landing with the heel first (heel strikers) or landing with the toe first (toe strikers). While heel strikers and toe strikers exhibited similar electrical power output and hip flexion angle at initial foot contact, heel strikers had higher peak ankle power and lower knee flexion angle at initial foot contact than toe strikers. 'Controlled slip' energy harvesting could potentially generate electrical power for a broad spectrum of wearable devices.

Influence of IMU position and orientation placement errors on ground reaction force estimation

Wearable inertial measurement units (IMU) have been proposed to estimate GRF outside of specialized laboratories, however the precise influence of sensor placement error on accuracy is unknown. We investigated the influence of IMU position and orientation placement errors on GRF estimation accuracy.

METHODS

Kinematic data from twelve healthy subjects based on marker trajectories were used to simulate 1848 combinations of sensor position placement errors (range ± 100 mm) and orientation placement errors (range ± 25°) across eight body segments (trunk, pelvis, left/right thighs, left/right shanks, and left/right feet) during normal walking trials for baseline cases when a single sensor was misplaced and for the extreme cases when all sensors were simultaneously misplaced. Three machine learning algorithms were used to estimate GRF for each placement error condition and compared with the no placement error condition to evaluate performance.

RESULTS

Position placement errors for a single misplaced IMU reduced vertical GRF (VGRF), medio-lateral GRF (MLGRF), and anterior-posterior GRF (APGRF) estimation accuracy by up to 1.1%, 2.0%, and 0.9%, respectively and for all eight simultaneously misplaced IMUs by up to 4.9%, 6.0%, and 4.3%, respectively. Orientation placement errors for a single misplaced IMU reduced VGRF, MLGRF, and APGRF estimation accuracy by up to 4.8%, 7.3%, and 1.5%, respectively and for all eight simultaneously misplaced IMUs by up to 20.8%, 23.4%, and 12.3%, respectively.

CONCLUSION

IMU sensor misplacement, particularly orientation placement errors, can significantly reduce GRF estimation accuracy and thus measures should be taken to account for placement errors in implementations of GRF estimation via wearable IMUs.

Soft Wearable Skin-Stretch Device for Haptic Feedback Using Twisted and Coiled Polymer Actuators

Soft and integrated design can enable wearable haptic devices to augment natural human taction. This paper proposes a novel, soft, haptic finger-worn wearable device based on compliant and adhesive silicone skin and lightweight twisted and coiled polymer (TCP) actuators using ultra high molecular weight polyethylene (UHMWPE) fibers to provide lateral skin stretch sensations. Recently, silicone elastomers have been used in wearable sensors and in haptic applications for their high compliance or adhesion. TCP actuators have also demonstrated high power to weight ratios, large stroke length, simple mechanism, and inherent softness. Lateral skin stretch is sensitive to small motions and has been used for intuitive proprioceptive feedback applications. We combined these characteristics to design and manufacture a wearable, functional haptic prototype. Prototype performance was evaluated using an optical tracking system, a force gauge test bench, and compared to vibrotactile haptic feedback in a experiment with 14 healthy participants. Results showed that participant mean reaction times were comparable to those of a vibrotactile feedback system, though task completion times were longer. This paper is the first to employ TCP actuators for haptic stimulation and could serve as a foundation for future applications involving soft wearable haptics in gaming, health, and virtual reality.

Cellphone-Based Automated Fugl-Meyer Assessment to Evaluate Upper Extremity Motor Function After Stroke

The Fugl-Meyer Assessment (FMA) is a widely used evaluation tool for assessing upper extremity motor function during stroke rehabilitation. However, the FMA is a repetitive, time-consuming task that currently must be performed by therapists in a hospital or clinic. We thus propose an alternative automated approach in which patients perform FMA movements while holding a cellphone at the hand and receive automated FMA scores. In the proposed system, features are extracted from cellphone movement data and decision trees are used to automatically score FMA test items. Ten stroke patients with upper extremity dysfunction participated in a validation experiment to compare automated FMA scores with traditional FMA scores from a trained therapist. Results showed that FMA scores from the cellphone-based automated system were highly correlated with FMA scores from the trained therapist (r² = 0.97), and that the average accuracy for individual FMA test items was 85%. These results demonstrate that such a portable, automated FMA system could potentially be used to assess upper extremity function during stroke rehabilitation to remove the repetitive, time-consuming burden from therapists and could potentially be performed in clinic or home-based settings.

Vibrotactile display design: Quantifying the importance of age and various factors on reaction times

Numerous factors affect reaction times to vibrotactile cues. Therefore, it is important to consider the relative magnitudes of these time delays when designing vibrotactile displays for real-time applications. The objectives of this study were to quantify reaction times to typical vibrotactile stimuli parameters through direct comparison within a single experimental setting, and to determine the relative importance of these factors on reaction times. Young (n = 10, 21.9 ± 1.3 yrs) and older adults (n = 13, 69.4 ± 5.0 yrs) performed simple reaction time tasks by responding to vibrotactile stimuli using a thumb trigger while frequency, location, auditory cues, number of tactors in the same location, and tactor type were varied. Participants also performed a secondary task in a subset of the trials. The factors investigated in this study affected reaction times by 20-300 ms (reaction time findings are noted in parentheses) depending on the specific stimuli condition. In general, auditory cues generated by the tactors (<20 ms), vibration frequency (<20 ms), number of tactors in the same location (<30 ms) and tactor type (<50 ms) had relatively small effects on reaction times, while stimulus location (20-120 ms) and secondary cognitive task (>130 ms) had relatively large effects. Factors affected young and older adults' reaction times in a similar manner, but with different magnitudes. These findings can inform the development of vibrotactile displays by enabling designers to directly compare the relative effects of key factors on reaction times.

Resonant Frequency Skin Stretch for Wearable Haptics

Resonant frequency skin stretch uses cyclic lateral skin stretches matching the skin's resonant frequency to create highly noticeable stimuli, signifying a new approach for wearable haptic stimulation. Four experiments were performed to explore biomechanical and perceptual aspects of resonant frequency skin stretch. In the first experiment, effective skin resonant frequencies were quantified at the forearm, shank, and foot. In the second experiment, perceived haptic stimuli were characterized for skin stretch actuations across a spectrum of frequencies. In the third experiment, perceived haptic stimuli were characterized by different actuator masses. In the fourth experiment, haptic classification ability was determined as subjects differentiated haptic stimulation cues while sitting, walking, and jogging. Results showed that subjects perceived stimulations at, above, and below the skin's resonant frequency differently: stimulations lower than the skin resonant frequency felt like distinct impacts, stimulations at the skin resonant frequency felt like cyclic skin stretches, and stimulations higher than the skin resonant frequency felt like standard vibrations. Subjects successfully classified stimulations while sitting, walking, and jogging, perceived haptic stimuli was affected by actuator mass, and classification accuracy decreased with increasing speed, especially for stimulations at the shank. This paper could facilitate more widespread use of wearable skin stretch. Potential applications include gaming, medical simulation, and surgical augmentation, and for training to reduce injury risk or improve sports performance.

Influence of skill level on predicting the success of one's own basketball free throws

Basketball players sometimes claim to know when their shot is good, even before it goes in. This is likely because shooter proprioception can help determine shot outcome, even before their eyes confirm it. This phenomenon, however, has not been systematically explored for collegiate and recreational shooters. This study compared how well collegiate shooters and recreational shooters could predict outcomes of their own free throws without seeing the shot result. Forty collegiate and recreational shooters shot standard free throws while wearing liquid-crystal occlusion glasses that activated to occlude vision immediately following ball release during each shot. After each shot, shooters verbally predicted shot outcome as “in” or “out”, and predicted results were compared with actual outcomes. As anticipated, for made shots, collegiate shooters more accurately predicted their own shots than recreational shooters. However, unexpectedly, for missed shots, collegiate shooters were worse than recreational shooters and were even significantly worse than chance. Further analysis found that collegiate shooters exhibited a significantly higher bias toward predicting their shots as “in”. Understanding how shooters of different skill levels perceive their own shot could inform future training strategies for improving shooter accuracy.

Hand Gesture Recognition and Finger Angle Estimation via Wrist-Worn Modified Barometric Pressure Sensing

This paper presents a new approach to wearable hand gesture recognition and finger angle estimation based on the modified barometric pressure sensing. Barometric pressure sensors were encased and injected with VytaFlex rubber such that the rubber directly contacted the sensing element allowing pressure change detection when the encasing rubber was pressed. A wearable prototype consisting of an array of ten modified barometric pressure sensors around the wrist was developed and validated with experimental testing for three different hand gesture sets and finger flexion/extension trials for each of the five fingers. The overall hand gesture recognition classification accuracy was 94%. Further analysis revealed that the most important sensor location was the underside of the wrist and that when reducing the sensor number to only five optimally placed sensors, classification accuracy was still 90%. For continuous finger angle estimation, aggregate R² values between actual and predicted angles were thumb: 0.81 ± 0.10, index finger: 0.85±0.06, middle finger: 0.77±0.08, ring finger: 0.77 ± 0.12, and pinkie finger: 0.75 ± 0.10, and the overall average was 0.79 ± 0.05. These results demonstrate that a modified barometric pressure wristband can be used to classify hand gestures and to estimate individual finger joint angles. This approach could serve to improve the clinical treatment for upper extremity deficiencies, such as for stroke rehabilitation, by providing objective patient motor control metrics to inform and aid physicians and therapists throughout the rehabilitation process.

Vertical Jump Height Estimation Algorithm Based on Takeoff and Landing Identification Via Foot-Worn Inertial Sensing

Vertical jump height is widely used for assessing motor development, functional ability, and motor capacity. Traditional methods for estimating vertical jump height rely on force plates or optical marker-based motion capture systems limiting assessment to people with access to specialized laboratories. Current wearable designs need to be attached to the skin or strapped to an appendage which can potentially be uncomfortable and inconvenient to use. This paper presents a novel algorithm for estimating vertical jump height based on foot-worn inertial sensors. Twenty healthy subjects performed countermovement jumping trials and maximum jump height was determined via inertial sensors located above the toe and under the heel and was compared with the gold standard maximum jump height estimation via optical marker-based motion capture. Average vertical jump height estimation errors from inertial sensing at the toe and heel were -2.2±2.1 cm and -0.4±3.8 cm, respectively. Vertical jump height estimation with the presented algorithm via inertial sensing showed excellent reliability at the toe (ICC(2,1)=0.98) and heel (ICC(2,1)=0.97). There was no significant bias in the inertial sensing at the toe, but proportional bias (b=1.22) and fixed bias (a=-10.23cm) were detected in inertial sensing at the heel. These results indicate that the presented algorithm could be applied to foot-worn inertial sensors to estimate maximum jump height enabling assessment outside of traditional laboratory settings, and to avoid bias errors, the toe may be a more suitable location for inertial sensor placement than the heel.

Subject-specific toe-in or toe-out gait modifications reduce the larger knee adduction moment peak more than a non-personalized approach

The knee adduction moment (KAM) is a surrogate measure for medial compartment knee loading and is related to the progression of knee osteoarthritis. Toe-in and toe-out gait modifications typically reduce the first and second KAM peaks, respectively. We investigated whether assigning a subject-specific foot progression angle (FPA) modification reduces the peak KAM by more than assigning the same modification to everyone. To explore the effects of motor learning on muscle coordination and kinetics, we also evaluated the peak knee flexion moment and quadriceps-hamstring co-contraction during normal walking, when subjects first learned their subject-specific FPA, and following 20 min of training. Using vibrotactile feedback, we trained 20 healthy adults to toe-in and toe-out by 5° and 10° relative to their natural FPA, then identified the subject-specific FPA as the angle where each subject maximally reduced their larger KAM peak. When walking at their subject-specific FPA, 18 subjects significantly reduced their larger KAM peak; 8 by toeing-in and 10 by toeing-out. On average, subjects reduced their larger KAM peak by 18.6 ± 16.2% when walking at their subject-specific FPA, which was more than the reductions achieved when all subjects toed-in by 10° (10.0 ± 17.1%, p = .013) or toed-out by 10° (11.0 ± 18.3%, p = .002). Quadriceps-hamstring co-contraction and the peak knee flexion moment increased when subjects first learned their subject-specific FPA, but only co-contraction returned to baseline levels following training. These findings demonstrate that subject-specific gait modifications reduce the peak KAM more than uniformly assigned modifications and have the potential to slow the progression of medial compartment knee osteoarthritis.

Configurable, wearable sensing and vibrotactile feedback system for real-time postural balance and gait training: proof-of-concept

BACKGROUND

Postural balance and gait training is important for treating persons with functional impairments, however current systems are generally not portable and are unable to train different types of movements.

METHODS

This paper describes a proof-of-concept design of a configurable, wearable sensing and feedback system for real-time postural balance and gait training targeted for home-based treatments and other portable usage. Sensing and vibrotactile feedback are performed via eight distributed, wireless nodes or "Dots" (size: 22.5 × 20.5 × 15.0 mm, weight: 12.0 g) that can each be configured for sensing and/or feedback according to movement training requirements. In the first experiment, four healthy older adults were trained to reduce medial-lateral (M/L) trunk tilt while performing balance exercises. When trunk tilt deviated too far from vertical (estimated via a sensing Dot on the lower spine), vibrotactile feedback (via feedback Dots placed on the left and right sides of the lower torso) cued participants to move away from the vibration and back toward the vertical no feedback zone to correct their posture. A second experiment was conducted with the same wearable system to train six healthy older adults to alter their foot progression angle in real-time by internally or externally rotating their feet while walking. Foot progression angle was estimated via a sensing Dot adhered to the dorsal side of the foot, and vibrotactile feedback was provided via feedback Dots placed on the medial and lateral sides of the mid-shank cued participants to internally or externally rotate their foot away from vibration.

RESULTS

In the first experiment, the wearable system enabled participants to significantly reduce trunk tilt and increase the amount of time inside the no feedback zone. In the second experiment, all participants were able to adopt new gait patterns of internal and external foot rotation within two minutes of real-time training with the wearable system.

CONCLUSION

These results suggest that the configurable, wearable sensing and feedback system is portable and effective for different types of real-time human movement training and thus may be suitable for home-based or clinic-based rehabilitation applications.

Continuous Movement Tracking Performance for Predictable and Unpredictable Tasks with Vibrotactile Feedback

The purpose of this paper was to determine human movement tracking performance in response to vibrotactile feedback tracking for predictable and unpredictable continuous movement tasks. Thirteen subjects performed elbow flexion/extension and knee flexion/extension continuous movement tracking tasks while receiving tactile stimulation proportional to limb joint position error. Subjects followed 0.2-2.0 Hz desired movements for predictable tasks (single sinusoid) and unpredictable tasks (combination of three sinusoids). Tactile stimulation reaction times at the forearm to induce elbow flexion/extension and at the shank to induce knee flexion/extension were also recorded. Results of frequency tracking showed that 100 percent of participants correctly tracked unpredictable tasks at all frequencies, but only 60-80 percent of participants correctly tracked predictable tasks at frequencies less than 1 Hz and only 20-60 percent of participants correctly tracked predictable tasks at frequencies greater than 1 Hz. Subjects had less phase lag for predictable tasks than for unpredictable tasks. Reaction times at the forearm were 379 ms and at the shank 437 ms. These findings suggest that continuous vibrotactile feedback based on position errors may not be the most effective means of training higher frequency human movements and serve to inform future vibrotactile feedback design related to training human limb movements for predictable and unpredictable tasks.

Validation of a smart shoe for estimating foot progression angle during walking gait

The foot progression angle is an important measurement related to knee loading, pain, and function for individuals with knee osteoarthritis, however current measurement methods require camera-based motion capture or floor-embedded force plates confining foot progression angle assessment to facilities with specialized equipment. This paper presents the validation of a customized smart shoe for estimating foot progression angle during walking. The smart shoe is composed of an electronic module with inertial and magnetometer sensing inserted into the sole of a standard walking shoe. The smart shoe charges wirelessly, and up to 160h of continuous data (sampled at 100Hz) can be stored locally on the shoe. For validation testing, fourteen healthy subjects were recruited and performed treadmill walking trials with small, medium, and large toe-in (internal foot rotation), small, medium, and large toe-out (external foot rotation) and normal foot progression angle at self-selected walking speeds. Foot progression angle calculations from the smart shoe were compared with measurements from a standard motion capture system. In general, foot progression angle values from the smart shoe closely followed motion capture values for all walking conditions with an overall average error of 0.1±1.9deg and an overall average absolute error of 1.7±1.0deg. There were no significant differences in foot progression angle accuracy across the seven different walking gait patterns. The presented smart shoe could potentially be used for knee osteoarthritis or other clinical applications requiring foot progression angle assessment in community settings or in clinics without specialized motion capture equipment.

Validity of FitBit, Jawbone UP, Nike+ and other wearable devices for level and stair walking

BACKGROUND

Increased physical activity can provide numerous health benefits. The relationship between physical activity and health assumes reliable activity measurements including step count and distance traveled. This study assessed step count and distance accuracy for Nike+ FuelBand, Jawbone UP 24, Fitbit One, Fitbit Flex, Fitbit Zip, Garmin Vivofit, Yamax CW-701, and Omron HJ-321 during level, upstairs, and downstairs walking in healthy adults.

METHODS

Forty subjects walked on flat ground (400m), upstairs (176 steps), and downstairs (176 steps), and a subset of 10 subjects performed treadmill walking trials to assess the influence of walking speed on accuracy. Activity monitor measured step count and distance values were compared with actual step count (determined from video recordings) and distance to determine accuracy.

RESULTS

For level walking, step count errors in Yamax CW-701, Fitbit Zip, Fitbit One, Omron HJ-321, and Jawbone UP 24 were within 1% and distance errors in Fitbit Zip and Yamax CW-701 were within 5%. Garmin Vivofit and Omron HJ-321 were the most accurate in estimating step count for stairs with errors less than 4%. An important finding is that all activity monitors overestimated distance for stair walking by at least 45%.

CONCLUSION

In general, there were not accuracy differences among activity monitors for stair walking. Accuracy did not change between moderate and fast walking speeds, though slow walking increased errors for some activity monitors. Nike+ FuelBand was the least accurate step count estimator during all walking tasks. Caution should be taken when interpreting step count and distance estimates for activities involving stairs.

Quantifying Different Tactile Sensations Evoked by Cutaneous Electrical Stimulation Using Electroencephalography Features

Psychophysical tests and standardized questionnaires are often used to analyze tactile sensation based on subjective judgment in conventional studies. In contrast with the subjective evaluation, a novel method based on electroencephalography (EEG) is proposed to explore the possibility of quantifying tactile sensation in an objective way. The proposed experiments adopt cutaneous electrical stimulation to generate two kinds of sensations (vibration and pressure) with three grades (low/medium/strong) on eight subjects. Event-related potentials (ERPs) and event-related synchronization/desynchronization (ERS/ERD) are extracted from EEG, which are used as evaluation indexes to distinguish between vibration and pressure, and also to discriminate sensation grades. Results show that five-phase P1–N1–P2–N2–P3 deflection is induced in EEG. Using amplitudes of latter ERP components (N2 and P3), vibration and pressure sensations can be discriminated on both individual and grand-averaged ERP ([Formula: see text]). The grand-average ERPs can distinguish the three sensations grades, but there is no significant difference on individuals. In addition, ERS/ERD features of mu rhythm (8–13[Formula: see text]Hz) are adopted. Vibration and pressure sensations can be discriminated on grand-average ERS/ERD ([Formula: see text]), but only some individuals show significant difference. The grand-averaged results show that most sensation grades can be differentiated, and most pairwise comparisons show significant difference on individuals ([Formula: see text]). The work suggests that ERP- and ERS/ERD-based EEG features may have potential to quantify tactile sensations for medical diagnosis or engineering applications.

Novel Foot Progression Angle Algorithm Estimation via Foot-Worn, Magneto-Inertial Sensing

OBJECTIVE

The foot progression angle (FPA) is an important clinical measurement but currently can only be computed while walking in a laboratory with a marker-based motion capture system. This paper proposes a novel FPA estimation algorithm based on a single integrated sensor unit, consisting of an accelerometer, gyroscope, and magnetometer, worn on the foot.

METHODS

The algorithm introduces a real-time heading vector with a complementary filter and utilizes a gradient descent method and zero-velocity update correction. Validation testing was performed by comparing FPA estimation from the wearable sensor with the standard FPAs computed from a marker-based motion capture system. Subjects performed nine walking trials of 2.5 min each on a treadmill. During each trial, subjects walked at one speed out of three options (1.0, 1.2, and 1.4 m/s) and walked with one gait pattern out of three options (normal, toe-in, and toe-out).

RESULTS

The algorithm estimated FPA to within 0.2 ^° of error or less for each walking conditions.

CONCLUSION

A novel FPA algorithm has been introduced and described based on a single foot-worn sensor unit, and validation testing showed that FPA estimation was accurate for different walking speeds and foot angles.

SIGNIFICANCE

This study enables future wearable systems gait research to assess or train walking patterns outside a laboratory setting in natural walking environments.

Determining inertial measurement unit placement for estimating human trunk sway while standing, walking and running

Inertial measurement units (IMU) are often used to estimate medial-lateral (M/L) trunk sway for assessing and treating gait disorders, and IMU sensor placement is an important factor effecting estimation accuracy. This study tracked multi-segment spine movements during standing and ambulation tasks to determine optimal IMU placement. Ten young healthy subjects, wearing markers placed along the spine, left/right acromion, and left/right posterior superior iliac spine performed standing and walking trials in a motion capture laboratory. Results showed that movement at the spine location T7-T8 most closely matched the clinical definition of M/L trunk sway for standing trials (0.5 deg error) and at the spine location T9-T10 for walking trials (1.0 deg error), while movement at the lower spine L2-L4 tended to be the least accurate for standing and ambulation tasks (1.5 deg error and 4.0 deg error, respectively). Based on these results, a second study was performed to develop and validate a trunk sway estimation algorithm during walking trials with a single optimally-placed IMU. IMU trunk sway estimation was compared to the clinical definition of trunk sway from motion capture markers and showed root-mean-square errors of 2.5 deg and peak trunk sway errors of 2.0 deg. The results of this study suggest that IMUs should be placed on the mid-back to reduce errors associated with spine movements not matching clinically-defined M/L trunk motion.

Haptic wearables as sensory replacement, sensory augmentation and trainer - a review

Sensory impairments decrease quality of life and can slow or hinder rehabilitation. Small, computationally powerful electronics have enabled the recent development of wearable systems aimed to improve function for individuals with sensory impairments. The purpose of this review is to synthesize current haptic wearable research for clinical applications involving sensory impairments. We define haptic wearables as untethered, ungrounded body worn devices that interact with skin directly or through clothing and can be used in natural environments outside a laboratory. Results of this review are categorized by degree of sensory impairment. Total impairment, such as in an amputee, blind, or deaf individual, involves haptics acting as sensory replacement; partial impairment, as is common in rehabilitation, involves haptics as sensory augmentation; and no impairment involves haptics as trainer. This review found that wearable haptic devices improved function for a variety of clinical applications including: rehabilitation, prosthetics, vestibular loss, osteoarthritis, vision loss and hearing loss. Future haptic wearables development should focus on clinical needs, intuitive and multimodal haptic displays, low energy demands, and biomechanical compliance for long-term usage.