Subject-specific Calibration Research Articles

ISB recommendations on the definition, estimation, and reporting of joint kinematics in human motion analysis applications using wearable inertial measurement technology

There is widespread and growing use of inertial measurement technology for human motion analysis in biomechanics and clinical research. Due to advancements in sensor miniaturization, inertial measurement units can be used to obtain a description of human body and joint kinematics both inside and outside the laboratory. While algorithms for data processing continue to improve, a lack of standard reporting guidelines compromises the interpretation and reproducibility of results, which hinders advances in research and development of measurement and intervention tools. To address this need, the International Society of Biomechanics approved our proposal to develop recommendations on the use of inertial measurement units for joint kinematics analysis. A collaborative effort that incorporated feedback from the biomechanics community has produced recommendations in five categories: sensor characteristics and calibration, experimental protocol, definition of a kinematic model and subject-specific calibration, analysis of joint kinematics, and quality assessment. We have avoided an overly prescriptive set of recommendations for algorithms and protocols, and instead offer reporting guidelines to facilitate reproducibility and comparability across studies. In addition to a conceptual framework and reporting guidelines, we provide a checklist to guide the design and review of research using inertial measurement units for joint kinematics.

Instant interaction driven adaptive gaze control interface

Gaze estimation is long been recognised as having potential as the basis for human-computer interaction (HCI) systems, but usability and robustness of performance remain challenging . This work focuses on systems in which there is a live video stream showing enough of the subjects face to track eye movements and some means to infer gaze location from detected eye features. Currently, systems generally require some form of calibration or set-up procedure at the start of each user session. Here we explore some simple strategies for enabling gaze based HCI to operate immediately and robustly without any explicit set-up tasks. We explore different choices of coordinate origin for combining extracted features from multiple subjects and the replacement of subject specific calibration by system initiation based on prior models. Results show that referencing all extracted features to local coordinate origins determined by subject start position enables robust immediate operation. Combining this approach with an adaptive gaze estimation model using an interactive user interface enables continuous operation with the 75th percentile gaze errors of 0.7∘\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^\\circ $$\\end{document}, and maximum gaze errors of 1.7∘\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^\\circ $$\\end{document} during prospective testing. There constitute state-of-the-art results and have the potential to enable a new generation of reliable gaze based HCI systems.

A deep learning approach for fast muscle water T2 mapping with subject specific fat T2 calibration from multi-spin-echo acquisitions.

This work presents a deep learning approach for rapid and accurate muscle water T2 with subject-specific fat T2 calibration using multi-spin-echo acquisitions. This method addresses the computational limitations of conventional bi-component Extended Phase Graph fitting methods (nonlinear-least-squares and dictionary-based) by leveraging fully connected neural networks for fast processing with minimal computational resources. We validated the approach through in vivo experiments using two different MRI vendors. The results showed strong agreement of our deep learning approach with reference methods, summarized by Lin's concordance correlation coefficients ranging from 0.89 to 0.97. Further, the deep learning method achieved a significant computational time improvement, processing data 116 and 33 times faster than the nonlinear least squares and dictionary methods, respectively. In conclusion, the proposed approach demonstrated significant time and resource efficiency improvements over conventional methods while maintaining similar accuracy. This methodology makes the processing of water T2 data faster and easier for the user and will facilitate the utilization of the use of a quantitative water T2 map of muscle in clinical and research studies.

T-TIME: Test-Time Information Maximization Ensemble for Plug-and-Play BCIs.

An electroencephalogram (EEG)-based brain-computer interface (BCI) enables direct communication between the human brain and a computer. Due to individual differences and non-stationarity of EEG signals, such BCIs usually require a subject-specific calibration session before each use, which is time-consuming and user-unfriendly. Transfer learning (TL) has been proposed to shorten or eliminate this calibration, but existing TL approaches mainly consider offline settings, where all unlabeled EEG trials from the new user are available. This article proposes Test-Time Information Maximization Ensemble (T-TIME) to accommodate the most challenging online TL scenario, where unlabeled EEG data from the new user arrive in a stream, and immediate classification is performed. T-TIME initializes multiple classifiers from the aligned source data. When an unlabeled test EEG trial arrives, T-TIME first predicts its labels using ensemble learning, and then updates each classifier by conditional entropy minimization and adaptive marginal distribution regularization. Our code is publicized. Extensive experiments on three public motor imagery based BCI datasets demonstrated that T-TIME outperformed about 20 classical and state-of-the-art TL approaches. To our knowledge, this is the first work on test time adaptation for calibration-free EEG-based BCIs, making plug-and-play BCIs possible.

A new method of continuous blood pressure monitoring using multichannel sensing signals on the wrist

Hypertension is a worldwide health problem and a primary risk factor for cardiovascular disease. Continuous monitoring of blood pressure has important clinical value for the early diagnosis and prevention of cardiovascular disease. However, existing technologies for wearable continuous blood pressure monitoring are usually inaccurate, rely on subject-specific calibration and have poor generalization across individuals, which limit their practical applications. Here, we report a new blood pressure measurement method and develop an associated wearable device to implement continuous blood pressure monitoring for new subjects. The wearable device detects cardiac output and pulse waveform features through dual photoplethysmography (PPG) sensors worn on the palmar and dorsal sides of the wrist, incorporating custom-made interface sensors to detect the wearing contact pressure and skin temperature. The detected multichannel signals are fused using a machine-learning algorithm to estimate continuous blood pressure in real time. This dual PPG sensing method effectively eliminates the personal differences in PPG signals caused by different people and different wearing conditions. The proposed wearable device enables continuous blood pressure monitoring with good generalizability across individuals and demonstrates promising potential in personal health care applications.

A transformer-based deep neural network model for SSVEP classification

Steady-state visual evoked potential (SSVEP) is one of the most commonly used control signals in the brain–computer interface (BCI) systems. However, the conventional spatial filtering methods for SSVEP classification highly depend on the subject-specific calibration data. The need for the methods that can alleviate the demand for the calibration data becomes urgent. In recent years, developing the methods that can work in inter-subject scenario has become a promising new direction. As a popular deep learning model nowadays, Transformer has been used in EEG signal classification tasks owing to its excellent performance. Therefore, in this study, we proposed a deep learning model for SSVEP classification based on Transformer architecture in inter-subject scenario, termed as SSVEPformer, which was the first application of Transformer on the SSVEP classification. Inspired by previous studies, we adopted the complex spectrum features of SSVEP data as the model input, which could enable the model to simultaneously explore the spectral and spatial information for classification. Furthermore, to fully utilize the harmonic information, an extended SSVEPformer based on the filter bank technology (FB-SSVEPformer) was proposed to improve the classification performance. Experiments were conducted using two open datasets (Dataset 1: 10 subjects, 12 targets; Dataset 2: 35 subjects, 40 targets). The experimental results show that the proposed models could achieve better results in terms of classification accuracy and information transfer rate than other baseline methods. The proposed models validate the feasibility of deep learning models based on Transformer architecture for SSVEP data classification, and could serve as potential models to alleviate the calibration procedure in the practical application of SSVEP-based BCI systems.

Real-time shimming with FID navigators.

To implement a method for real-time field control using rapid FID navigator (FIDnav) measurements and evaluate the efficacy of the proposed approach for mitigating dynamic field perturbations and improving -weighted image quality. FIDnavs were embedded in a gradient echo sequence and a subject-specific linear calibration model was generated on the scanner to facilitate rapid shim updates in response to measured FIDnav signals. To confirm the accuracy of FID-navigated field updates, phantom and volunteer scans were performed with online updates of the scanner B0 shim settings. To evaluate improvement in -weighted image quality with real-time shimming, 10 volunteers were scanned at 3T while performing deep-breathing and nose-touching tasks designed to modulate the B0 field. Quantitative image quality metrics were compared with and without FID-navigated field control. An additional volunteer was scanned at 7T to evaluate performance at ultra-high field. Applying measured FIDnav shim updates successfully compensated for applied global and linear field offsets in phantoms and across all volunteers. FID-navigated real-time shimming led to a substantial reduction in field fluctuations and a consequent improvement in -weighted image quality in volunteers performing deep-breathing and nose-touching tasks, with 7.57% ± 6.01% and 8.21% ± 10.90% improvement in peak SNR and structural similarity, respectively. FIDnavs facilitate rapid measurement and application of field coefficients for slice-wise B0 shimming. The proposed approach can successfully counteract spatiotemporal field perturbations and substantially improves -weighted image quality, which is important for a variety of clinical and research applications, particularly at ultra-high field.

Estimation of Tidal Volume Using Load Cells on a Hospital Bed.

Although respiratory failure is one of the primary causes of admission to intensive care, the importance placed on measurement of respiratory parameters is commonly overshadowed compared to cardiac parameters. With the increased demand for unobtrusive yet quantifiable respiratory monitoring, many technologies have been proposed recently. However, there are challenges to be addressed for such technologies to enable widespread use. In this work, we explore the feasibility of using load cell sensors embedded on a hospital bed for monitoring respiratory rate (RR) and tidal volume (TV). We propose a globalized machine learning (ML)-based algorithm for estimating TV without the requirement of subject-specific calibration or training. In a study of 15 healthy subjects performing respiratory tasks in four different postures, the outputs from four load cell channels and the reference spirometer were recorded simultaneously. A signal processing pipeline was implemented to extract features that capture respiratory movement and the respiratory effects on the cardiac (i.e., ballistocardiogram, BCG) signals. The proposed RR estimation algorithm achieved a root mean square error (RMSE) of 0.6 breaths per minute (brpm) against the ground truth RR from the spirometer. The TV estimation results demonstrated that combining all three axes of the low-frequency force signals and the BCG heartbeat features best quantifies the respiratory effects of TV. The model resulted in a correlation and RMSE between the estimated and true TV values of 0.85 and 0.23 L, respectively, in the posture independent model without electrocardiogram (ECG) signals. This study suggests that load cell sensors already existing in certain hospital beds can be used for convenient and continuous respiratory monitoring in general care settings.

Assessment of Calibration Models for Cuff-Less Blood Pressure Measurement After One Year of Aging.

Many calibration models for cuff-less blood pressure (BP) measurement must be periodically updated with cuff BP values to account for vascular aging. However, the time period required for these "cuff re-calibrations" is largely unknown. The impact of one year of aging on several calibration models was assessed. Ten humans (6 males, 57±18 years, 3 hypertensives) were studied during multiple recording sessions that occurred one year apart. In each session, electrocardiography (ECG), ear photoplethysmography (PPG), finger PPG, and toe PPG waveforms and manual cuff BP were recorded before and after slow breathing, mental arithmetic, cold pressor, and nitroglycerin. Linear models based on each PPG waveform, which were previously shown to offer value in predicting the intervention-induced BP changes in a larger subject cohort, were employed. The model coefficients were determined for each subject via one session, and the fully-defined, subject-specific calibration models were then evaluated in the corresponding subjects via the session one year later. Only a linear model relating toe pulse arrival time (PAT) - time delay between ECG R-wave and toe PPG foot - to systolic BP (SBP) remained useful. After the year, this model changed little on average (root-mean-squared-error (RMSE) = 1.5 mmHg) and predicted the cuff BP values better than the average of the initial cuff BP values of the subject (RMSE = 9.6±0.8 mmHg vs. 12.7±1.0 mmHg; p < 0.05). These results suggest annual cuff recalibrations for the toe PAT-SBP model. Toe PAT may offer a practical recalibration period that fosters user adherence.

Non-invasive cuffless blood pressure and heart rate monitoring using impedance cardiography

BackgroundContinuous blood pressure (BP) monitoring provides additional information about how changes in BP may correlate with daily activities and sleep patterns. Recommendations from the American Heart Association and American College of Cardiology strongly suggest confirming a diagnosis of hypertension with continuous BP monitoring. Non-invasive and non-intrusive detection of haemodynamic parameters is emerging as a norm, based on self-monitoring wearable medical devices. Researchers have carried out several studies using non-invasive and continuous BP measurements as an alternative to conventional cuff-based measurements. In this work, we proposed a novel method for cuffless estimation of BP using impedance cardiography (ICG). MethodsWe conducted a single-centre, cross-sectional study of 104 subjects (of whom 30 were categorized as controls and the remaining 74 as the disease group) at the Medical College and Hospital, Kolkata. The disease group consisted of patients with confirmed coronary artery disease, while the individuals in the control group were deemed to be healthy. All subjects underwent electrocardiogram recording by on-duty doctors in order to determine their health status. A custom-made device based on the principle of impedance plethysmography was designed to record impedance changes due to subjects’ peripheral blood flow. The device was used to record ICG signals. In this study, we developed a novel auto-adaptive algorithm based on ICG signals for non-invasive, cuffless, continuous monitoring of BP and heart rate. Separate mathematical models were developed for all the estimated parameters (BP and heart rate) for both the study groups (control and disease). The developed models were auto-adaptive and did not require subject-specific calibration. Performance indicators including, r2, error percentage, standard deviation, and mean difference were used to quantify the performance of the models. ResultsThe ICG signal recorded by the device was used to extract features and compute the augmentation index. The calculated augmentation index values showed strong correlations with systolic BP (r=0.99, P<0.05), diastolic BP (r=0.95, P<0.05), and heart rate (r=0.78, P<0.05). The models were also shown to have a high degree of accuracy for systolic and diastolic BP. Error margins were in the range ±2.33 and ±1.79 mmHg for systolic BP in disease and control subjects, respectively, and ±3.60 and ±1.82 mmHg for diastolic BP. However, the accuracy was lower in the prediction of heart rate in disease subjects, with a reported r2 value of 0.72 and an error margin of ±2.88 beats per min; for healthy subjects, the results were marginally better, with an error margin of ±1.82 beats per min. All statistical analyses were performed using MATLAB (R2017a, MathWorksⓇ, USA). ConclusionIn this study, we developed a non-invasive cuffless approach for estimation of systemic peripheral BP and heart rate using ICG. The proposed methodology eliminated any discomfort to patients caused by inflation of the cuff (in the case of cuff-based BP monitoring) or the need to constantly wear a fingertip photoplethysmography device (in the case of cuffless BP monitoring). The results obtained appeared promising and increased the potential scope of ICG for monitoring other haemodynamic parameters related to heart function.

Enabling Continuous Wearable Reflectance Pulse Oximetry at the Sternum.

In light of the recent Coronavirus disease (COVID-19) pandemic, peripheral oxygen saturation (SpO2) has shown to be amongst the vital signs most indicative of deterioration in persons with COVID-19. To allow for the continuous monitoring of SpO2, we attempted to demonstrate accurate SpO2 estimation using our custom chest-based wearable patch biosensor, capable of measuring electrocardiogram (ECG) and photoplethysmogram (PPG) signals with high fidelity. Through a breath-hold protocol, we collected physiological data with a wide dynamic range of SpO2 from 20 subjects. The ratio of ratios (R) used in pulse oximetry to estimate SpO2 was robustly extracted from the red and infrared PPG signals during the breath-hold segments using novel feature extraction and PPGgreen-based outlier rejection algorithms. Through subject independent training, we achieved a low root-mean-square error (RMSE) of 2.64 ± 1.14% and a Pearson correlation coefficient (PCC) of 0.89. With subject-specific calibration, we further reduced the RMSE to 2.27 ± 0.76% and increased the PCC to 0.91. In addition, we showed that calibration is more efficiently accomplished by standardizing and focusing on the duration of breath-hold rather than the resulting range in SpO2. The accurate SpO2 estimation provided by our custom biosensor and the algorithms provide research opportunities for a wide range of disease and wellness monitoring applications.

Opportunistic application of phantom-less calibration methods for fracture risk prediction using QCT/FEA.

Quantitative computed tomography (QCT)-based finite element analysis (FEA) implements a calibration phantom to estimate bone mineral density (BMD) and assign material properties to the models. The objectives of this study were to (1) propose robust phantom-less calibration methods, using subject-specific tissues, to obtain vertebral fracture properties estimations using QCT/FEA; and (2) correlate QCT/FEA predictions to DXA values of areal BMD. Eighty of a cohort of 111 clinical QCT scans were used to obtain subject-specific parameters using a phantom calibration approach and for the development of the phantom-less calibration equations. Equations were developed based on the HU measured from various soft tissues and regions, and using multiple linear regression analyses. Thirty-one additional QCT scans were used for cross-validation of QCT/FEA estimated fracture loads from the L3 vertebrae based on the phantom and phantom-less equations. Finally, QCT/FEA-predicted fracture loads were correlated with aBMD obtained from DXA. Overall, 217 QCT/FEA models from 31 subjects (20 females, 11 men) with mean ages of 69.6 (13.1) and 67.3 (14) were used to cross-validate the phantom-less equations and assess bone strength. The proposed phantom-less equations showed high correlations with phantom-based estimates of BMD (99%). Cross-validation of QCT/FEA-predicted fracture loads from phantom-less equations and phantom-specific outcomes resulted in high correlations for all proposed methods (0.94-0.99). QCT/FEA correlation outcomes from the phantom-less equations and DXA-aBMD were moderately high (0.64-0.68). The proposed QCT/FEA subject-specific phantom-less calibration methods demonstrated the potential to be applied to both prospective and retrospective applications in the clinical setting. • QCT/FEA overcomes the disadvantages of DXA and improves fracture properties predictions of vertebrae. • QCT/FEA fracture estimates using the phantom-less approach highly correlated to values obtained using a calibration phantom. • QCT/FEA prediction using a phantom-less approach is an accurate alternative over phantom-based methods.

Magnetically Counting Hand Movements: Validation of a Calibration-Free Algorithm and Application to Testing the Threshold Hypothesis of Real-World Hand Use after Stroke.

There are few wearable sensors suitable for daily monitoring of wrist and finger movements for hand-related healthcare applications. Here, we describe the development and validation of a novel algorithm for magnetically counting hand movements. We implemented the algorithm on a wristband that senses magnetic field changes produced by movement of a magnetic ring worn on the finger (the “Manumeter”). The “HAND” (Hand Activity estimated by Nonlinear Detection) algorithm assigns a “HAND count” by thresholding the real-time change in magnetic field created by wrist and/or finger movement. We optimized thresholds to achieve a HAND count accuracy of ~85% without requiring subject-specific calibration. Then, we validated the algorithm in a dexterity-impaired population by showing that HAND counts strongly correlate with clinical assessments of upper extremity (UE) function after stroke. Finally, we used HAND counts to test a recent hypothesis in stroke rehabilitation that real-world UE hand use increases only for stroke survivors who achieve a threshold level of UE functional capability. For 29 stroke survivors, HAND counts measured at home did not increase until the participants’ Box and Blocks Test scores exceeded ~50% normal. These results show that a threshold-based magnetometry approach can non-obtrusively quantify hand movements without calibration and also verify a key concept of real-world hand use after stroke.

A Differential Approach for Gaze Estimation

Most non-invasive gaze estimation methods regress gaze directions directly from a single face or eye image. However, due to important variabilities in eye shapes and inner eye structures amongst individuals, universal models obtain limited accuracies and their output usually exhibit high variance as well as subject dependent biases. Thus, increasing accuracy is usually done through calibration, allowing gaze predictions for a subject to be mapped to her actual gaze. In this article, we introduce a novel approach, which works by directly training a differential convolutional neural network to predict gaze differences between two eye input images of the same subject. Then, given a set of subject specific calibration images, we can use the inferred differences to predict the gaze direction of a novel eye sample. The assumption is that by comparing eye images of the same user, annoyance factors (alignment, eyelid closing, illumination perturbations) which usually plague single image prediction methods can be much reduced, allowing better prediction altogether. Furthermore, the differential network itself can be adapted via finetuning to make predictions consistent with the available user reference pairs. Experiments on 3 public datasets validate our approach which constantly outperforms state-of-the-art methods even when using only one calibration sample or those relying on subject specific gaze adaptation.

Learning Invariant Patterns Based on a Convolutional Neural Network and Big Electroencephalography Data for Subject-Independent P300 Brain-Computer Interfaces.

A brain-computer interface (BCI) measures and analyzes brain activity and converts this activity into computer commands to control external devices. In contrast to traditional BCIs that require a subject-specific calibration process before being operated, a subject-independent BCI learns a subject-independent model and eliminates subject-specific calibration for new users. However, building subject-independent BCIs remains difficult because electroencephalography (EEG) is highly noisy and varies by subject. In this study, we propose an invariant pattern learning method based on a convolutional neural network (CNN) and big EEG data for subject-independent P300 BCIs. The CNN was trained using EEG data from a large number of subjects, allowing it to extract subject-independent features and make predictions for new users. We collected EEG data from 200 subjects in a P300-based spelling task using two different types of amplifiers. The offline analysis showed that almost all subjects obtained significant cross-subject and cross-amplifier effects, with an average accuracy of more than 80%. Furthermore, more than half of the subjects achieved accuracies above 85%. These results indicated that our method was effective for building a subject-independent P300 BCI, with which more than 50% of users could achieve high accuracies without subject-specific calibration.

A joint kinematics driven model of the pelvic soft tissue artefact

When skin-markers trajectories are used in human movement analysis, compensating for their relative movement with respect to the underlying bone (soft tissue artefact, STA) is essential for accurate bone-pose estimation; information about the artefact is required in the form of a mathematical model. Such model, not available for pelvic artefacts, could allow pelvic STA compensation in routine gait analysis by embedding it in skeletal kinematics estimators and developing ad-hoc optimization problems for the estimate of subject-specific model parameters. It was developed as driven by adjacent body segment kinematics. Model architecture feasibility was tested; its compensation effectiveness was assessed evaluating the error in pelvic orientation after removing the modelled artefact from the measured one. Five volunteers with a wide body mass range (BMI: 22–37) underwent MRI scans to reconstruct subject-specific pelvic digital bone models. Multiple anatomical calibrations performed in different static postures, as occurring during walking and star-arc movements, registering the bone-models with points digitized through stereophotogrammetry over pelvic bony prominences, allowed to define the relevant poses of a pelvis-embedded anatomical coordinate system. Such approach allowed to measure STAs over several pelvic anatomical landmarks, for each posture and subject. Model parameters were estimated by minimizing the least squares difference between measured and modelled STAs. The measured STAs were appropriately modelled with subject-specific calibrations, both in terms of shape (correlation coefficient: median [inter-quartile-range]: 0.72 [0.36]) and amplitude (root mean square residual: 3.0 [3.2] mm). Consequently, the overall error in pelvic orientation vector (5.1 [4.4] deg) was reduced after removing the modelled artefacts (2.5 [1.9] deg).

Repeatability Study of Local Vascular Stiffness Measurement Using Carotid Surface Acceleration Plethysmogram.

We have developed an accelerometric system with a custom-designed patch probe and signal acquisition hardware to acquire the carotid wall displacement from the soft tissue surface for arterial stiffness evaluation. A subject-specific calibration model was developed to estimate the morphology of accurate carotid diameter waveform, using a standard ultrasound B-mode imaging system as the reference. Following the one-time calibration, the accelerometric system continuously acquired a non-invasive carotid lumen diameter waveform. The capability of the accelerometric system to measure the carotid stiffness index (β) in-vivo was experimentally validated by performing measurements on 8 normotensive subjects in the supine position. The repeatability and reproducibility of the results were investigated and were found to be comparable to those provided by ultrasound imaging systems. Further, the variation of arterial stiffness index measurements on different days was studied to verify the ability of the system to give a stable measure of stiffness. The accuracy of the observed results was confirmed with the state-of-art B-mode ultrasound imaging system. The results were found to be stable over a day, indicating the utility of the system for a reliable measure of non-invasive carotid arterial stiffness.

Indirect measurement of anterior-posterior ground reaction forces using a minimal set of wearable inertial sensors: from healthy to hemiparetic walking

BackgroundThe anterior-posterior ground reaction force (AP-GRF) and propulsion and braking point metrics derived from the AP-GRF time series are indicators of locomotor function across healthy and neurological diagnostic groups. In this paper, we describe the use of a minimal set of wearable inertial measurement units (IMUs) to indirectly measure the AP-GRFs generated during healthy and hemiparetic walking.MethodsTen healthy individuals and five individuals with chronic post-stroke hemiparesis completed a 6-minute walk test over a walking track instrumented with six forceplates while wearing three IMUs securely attached to the pelvis, thigh, and shank. Subject-specific models driven by IMU-measured thigh and shank angles and an estimate of body acceleration provided by the pelvis IMU were used to generate indirect estimates of the AP-GRF time series. Propulsion and braking point metrics (i.e., peaks, peak timings, and impulses) were extracted from the IMU-generated time series. Peaks and impulses were expressed as % bodyweight (%bw) and peak timing was expressed as % stance phase (%sp). A 75%-25% split of 6-minute walk test data was used to train and validate the models. Indirect estimates of the AP-GRF time series and point metrics were compared to direct measurements made by the forceplates.ResultsIndirect measurements of the AP-GRF time series approximated the direct measurements made by forceplates, with low error and high consistency in both the healthy (RMSE= 4.5%bw; R2= 0.93) and post-stroke (RMSE= 2.64%bw; R2= 0.90) cohorts. In the healthy cohort, the average errors between indirect and direct measurements of the peak propulsion magnitude, peak propulsion timing, and propulsion impulse point estimates were 2.37%bw, 0.67%sp, and 0.43%bw. In the post-stroke cohort, the average errors for these point estimates were 1.07%bw, 1.27%sp, and 0.31%bw. Average errors for the braking estimates were higher, but comparable.ConclusionsAccurate estimates of AP-GRF metrics can be generated using three strategically mounted IMUs and subject-specific calibrations. This study advances the development of point-of-care diagnostic systems that can catalyze the routine assessment and management of propulsion and braking locomotor deficits during rehabilitation.

Shear Wave Tensiometry Reveals an Age-Related Deficit in Triceps Surae Work at Slow and Fast Walking Speeds.

Prior studies have observed an age-related decline in net ankle power and work at faster walking speeds. However, the underlying changes in muscle-tendon behavior are not well-understood, and are challenging to infer from joint level analyses. This study used shear wave tensiometry to investigate the modulation of force and work done by the triceps surae across walking speeds. Fourteen healthy young (7F/7M, 26 ± 5 years) and older (7F/7M, 67 ± 5 years) adults were tested. Subjects walked on an instrumented treadmill at four walking speeds (0.75, 1.00, 1.25, and 1.50 m/s) while lower extremity kinematics and Achilles tendon shear wave speeds were collected. Subject-specific calibrations were used to compute Achilles tendon force from wave speed. Excursions of the soleus and gastrocnemius muscle-tendon units were computed from the kinematic data and subject-specific measures of the Achilles tendon moment arm. Work loop plots were then used to assess effective muscle-tendon stiffness during lengthening, and positive, negative, and net work production during stance. Two-way mixed ANOVAs were used to evaluate the effects of age group and walking speed on each outcome measure. Tendon loading during muscle-tendon lengthening (effective stiffness) did not differ between age groups, but did vary with speed. The soleus became effectively stiffer with increasing speed while the gastrocnemius became effectively more compliant. There was a marked age-related deficit in net soleus (−66% on average) and gastrocnemius (−36%) work across all walking speeds. We did not observe an age-speed interaction effect on net work production. These results suggest the age-related deficit in triceps surae output in walking is pervasive across speed, and hence seemingly not linked to absolute mechanical demands of the task.

EEG-Based Driver Drowsiness Estimation Using an Online Multi-View and Transfer TSK Fuzzy System

In the field of intelligent transportation, transfer learning (TL) is often used to recognize EEG-based drowsy driving for a new subject with few subject-specific calibration data. However, most of existing TL-based models are offline, non-transparent, and in which features are only represented from one view (usually only one algorithm is used to extract features). In this paper, we consider an online multi-view regression model with high interpretability. By taking the 1-order TSK fuzzy system as the basic regression component and injecting the nature of the multi-view settings into the existing transfer learning framework and enforcing the consistencies across different views, we propose an online multi-view & transfer TSK fuzzy system for driver drowsiness estimation. In this novel model, features in both the source domain and the target domain are represented from multi-view perspectives such that more pattern information can be utilized during model training. Also, comparing with offline training, the proposed online fuzzy system meets the practical requirements more competently. An experiment on a driving dataset demonstrates that the proposed fuzzy system has smaller drowsiness estimation errors and higher interpretability than introduced benchmarking models.