Post-stroke hand gesture recognition via one-shot transfer learning using prototypical networks.

BACKGROUND: In-home rehabilitation systems are a promising, potential alternative to conventional therapy for stroke survivors. Unfortunately, physiological differences between participants and sensor displacement in wearable sensors pose a significant challenge to classifier performance, particularly for people with stroke who may encounter difficulties repeatedly performing trials. This makes it challenging to create reliable in-home rehabilitation systems that can accurately classify gestures. METHODS: Twenty individuals who suffered a stroke performed seven different gestures (mass flexion, mass extension, wrist volar flexion, wrist dorsiflexion, forearm pronation, forearm supination, and rest) related to activities of daily living. They performed these gestures while wearing EMG sensors on the forearm, as well as FMG sensors and an IMU on the wrist. We developed a model based on prototypical networks for one-shot transfer learning, K-Best feature selection, and increased window size to improve model accuracy. Our model was evaluated against conventional transfer learning with neural networks, as well as subject-dependent and subject-independent classifiers: neural networks, LGBM, LDA, and SVM. RESULTS: Our proposed model achieved 82.2% hand-gesture classification accuracy, which was better (P<0.05) than one-shot transfer learning with neural networks (63.17%), neural networks (59.72%), LGBM (65.09%), LDA (63.35%), and SVM (54.5%). In addition, our model performed similarly to subject-dependent classifiers, slightly lower than SVM (83.84%) but higher than neural networks (81.62%), LGBM (80.79%), and LDA (74.89%). Using K-Best features improved the accuracy in 3 of the 6 classifiers used for evaluation, while not affecting the accuracy in the other classifiers. Increasing the window size improved the accuracy of all the classifiers by an average of 4.28%. CONCLUSION: Our proposed model showed significant improvements in hand-gesture recognition accuracy in individuals who have had a stroke as compared with conventional transfer learning, neural networks and traditional machine learning approaches. In addition, K-Best feature selection and increased window size can further improve the accuracy. This approach could help to alleviate the impact of physiological differences and create a subject-independent model for stroke survivors that improves the classification accuracy of wearable sensors. TRIAL REGISTRATION NUMBER: The study was registered in Chinese Clinical Trial Registry with registration number CHiCTR1800017568 in 2018/08/04.

Automated, IMU-based spine angle estimation and IMU location identification for telerehabilitation.

BACKGROUND: Telerehabilitation is a promising avenue for improving patient outcomes and expanding accessibility. However, there is currently no spine-related assessment for telerehabilitation that covers multiple exercises. METHODS: We propose a wearable system with two inertial measurement units (IMUs) to identify IMU locations and estimate spine angles for ten commonly prescribed spinal degeneration rehabilitation exercises (supine chin tuck head lift rotation, dead bug unilateral isometric hold, pilates saw, catcow full spine, wall angel, quadruped neck flexion/extension, adductor open book, side plank hip dip, bird dog hip spinal flexion, and windmill single leg). Twelve healthy subjects performed these spine-related exercises, and wearable IMU data were collected for spine angle estimation and IMU location identification. RESULTS: Results demonstrated average mean absolute spinal angle estimation errors of 2.59 ∘ and average classification accuracy of 92.97%. The proposed system effectively identified IMU locations and assessed spine-related rehabilitation exercises while demonstrating robustness to individual differences and exercise variations. CONCLUSION: This inexpensive, convenient, and user-friendly approach to spine degeneration rehabilitation could potentially be implemented at home or provide remote assessment, offering a promising avenue to enhance patient outcomes and improve accessibility for spine-related rehabilitation. TRIAL REGISTRATION:  No. E2021013P in Shanghai Jiao Tong University.

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.

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.

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.

Simultaneous Hand Gesture Classification and Finger Angle Estimation via a Novel Dual-Output Deep Learning Model.

Hand gesture classification and finger angle estimation are both critical for intuitive human-computer interaction. However, most approaches study them in isolation. We thus propose a dual-output deep learning model to enable simultaneous hand gesture classification and finger angle estimation. Data augmentation and deep learning were used to detect spatial-temporal features via a wristband with ten modified barometric sensors. Ten subjects performed experimental testing by flexing/extending each finger at the metacarpophalangeal joint while the proposed model was used to classify each hand gesture and estimate continuous finger angles simultaneously. A data glove was worn to record ground-truth finger angles. Overall hand gesture classification accuracy was 97.5% and finger angle estimation R 2 was 0.922, both of which were significantly higher than shallow existing learning approaches used in isolation. The proposed method could be used in applications related to the human-computer interaction and in control environments with both discrete and continuous variables.

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.

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.

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.

Somatotopical feedback versus non-somatotopical feedback for phantom digit sensation on amputees using electrotactile stimulation.

BACKGROUND: Transcutaneous electrical stimulation can provide amputees with tactile feedback for better manipulating an advanced prosthesis. In general, there are two ways to transfer the stimulus to the skin: somatotopical feedback (SF) that stimulates the phantom digit somatotopy on the stump and non-somatotopical feedback (NF) that stimulates other positions on the human body. METHODS: To investigate the difference between SF and NF, electrotactile experiments were conducted on seven amputees. Electrical stimulation was applied via a complete phantom map to the residual limb (SF) and to the upper arm (NF) separately. The behavior results of discrimination accuracy and response time were used to examine: 1) performance differences between SF and NF for discriminating position, type and strength of tactile feedback; 2) performance differences between SF and NF for one channel (1C), three channels (3C), and five channels (5C). NASA-TLX standardized testing was used to determine differences in mental workload between SF and NF. RESULTS: The grand-averaged discrimination accuracy for SF was 6% higher than NF, and the average response time for SF was 600 ms faster than NF. SF is better than NF for position, type, strength, and the overall modality regarding both accuracy and response time except for 1C modality (p<0.001). Among the six modalities of stimulation channels, performance of 1C/SF was the best, which was similar to that of 1C/NF and 3C/SF; performance of 3C/NF was similar to that of 5C/SF; performance of 5C/NF was the worst. NASA-TLX scores indicated that mental workload increased as the number of stimulation channels increased. CONCLUSIONS: We quantified the difference between SF and NF, and the influence of different number of stimulation channels. SF was better than NF in general, but the practical issues such as the limited area of stumps could constrain the use of SF. We found that more channels increased the amount and richness of information to the amputee while fewer channels resulted in higher performance, and thus the 3C/SF modality was a good compromise. Based on this study, we provide possible solutions to the practical problems involving the implementation of tactile feedback for amputees. These results are expected to promote the application of SF and NF tactile feedback for amputees in the future.

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.

EchoGest: Soft Ultrasonic Waveguides Based Sensing Skin for Subject-Independent Hand Gesture Recognition.

Gesture recognition is crucial for enhancing human-computer interaction and is particularly pivotal in rehabilitation contexts, aiding individuals recovering from physical impairments and significantly improving their mobility and interactive capabilities. However, current wearable hand gesture recognition approaches are often limited in detection performance, wearability, and generalization. We thus introduce EchoGest, a novel hand gesture recognition system based on soft, stretchable, transparent artificial skin with integrated ultrasonic waveguides. Our presented system is the first to use soft ultrasonic waveguides for hand gesture recognition. EcoflexTM 00-31 and EcoflexTM 00-45 Near ClearTM silicone elastomers were employed to fabricate the artificial skin and ultrasonic waveguides, while 0.1 mm diameter silver-plated copper wires connected the transducers in the waveguides to the electrical system. The wires are enclosed within an additional elastomer layer, achieving a sensing skin with a total thickness of around 500 µ m. Ten participants wore the EchoGest system and performed static hand gestures from two gesture sets: 8 daily life gestures and 10 American Sign Language (ASL) digits 0-9. Leave-One-Subject-Out Cross-Validation analysis demonstrated accuracies of 91.13% for daily life gestures and 88.5% for ASL gestures. The EchoGest system has significant potential in rehabilitation, particularly for tracking and evaluating hand mobility, which could substantially reduce the workload of therapists in both clinical and home-based settings. Integrating this technology could revolutionize hand gesture recognition applications, from real-time sign language translation to innovative rehabilitation techniques.

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.

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.

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.

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.

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. A real-time, modular LSTM model with four sub-deep neural networks was developed to estimate vGRF and KEM. 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 for model training and evaluation. 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. 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. This investigation could potentially enable in-field, non-contact anterior cruciate ligament injury risk screening and intervention training programs.

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.

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.