An Automatic Gait Feature Extraction Method for Identifying Gait Asymmetry Using Wearable Sensors

Gait asymmetrical evaluation of lower limb amputees using wearable inertial sensors

This study presents an analysis and evaluation of gait asymmetry (GA) based on the temporal gait parameters identified using a portable gait event detection system, placed on the lateral side of the shank of both lower extremities of the participants. Assessment of GA was carried out with seven control subjects (CS), one transfemoral amputee (TFA) and one transtibial amputee (TTA) while walking at different speeds on overground (OG) and treadmill (TM). Gait cycle duration (GCD), stance phase duration (SPD), swing phase duration (SwPD), and the sub-phases of the gait cycle (GC) such as Loading-Response (LR), Foot-Flat (FF), and Push-Off (PO), Swing-1 (SW-1) and Swing-2 (SW-2) were evaluated. The results revealed that GCD showed less asymmetry as compared to other temporal parameters in both groups. A significant difference (p < 0.05) was observed between the groups for SPD and SwPD with lower limb amputees (LLA) having a longer stance and shorter swing phase for their intact side compared to their amputated side, resulting, large GA for TFA compared to CS and TTA. The findings could potentially contribute towards a better understanding of gait characteristics in LLA and provide a guide in the design and control of lower limb prosthetics/orthotics.

Machine learning approach to classifying declines of physical function and muscle strength associated with cognitive function in older women: gait characteristics based on three speeds

Background

The aging process is associated with a cognitive and physical declines that affects neuromotor control, memory, executive functions, and motor abilities. Previous studies have made efforts to find biomarkers, utilizing complex factors such as gait as indicators of cognitive and physical health in older adults. However, while gait involves various complex factors, such as attention and the integration of sensory input, cognitive-related motor planning and execution, and the musculoskeletal system, research on biomarkers that simultaneously considers multiple factors is scarce. This study aimed to extract gait features through stepwise regression, based on three speeds, and evaluate the accuracy of machine-learning (ML) models based on the selected features to solve classification problems caused by declines in cognitive function (Cog) and physical function (PF), and in Cog and muscle strength (MS).

Methods

Cognitive assessments, five times sit-to-stand, and handgrip strength were performed to evaluate the Cog, PF, and MS of 198 women aged 65 years or older. For gait assessment, all participants walked along a 19-meter straight path at three speeds [preferred walking speed (PWS), slower walking speed (SWS), and faster walking speed (FWS)]. The extracted gait features based on the three speeds were selected using stepwise regression.

Results

The ML model accuracies were revealed as follows: 91.2% for the random forest model when using all gait features and 91.9% when using the three features (walking speed and coefficient of variation of the left double support phase at FWS and the right double support phase at SWS) selected for the Cog+PF+ and Cog-PF- classification. In addition, support vector machine showed a Cog+MS+ and Cog-MS- classification problem with 93.6% accuracy when using all gait features and two selected features (left step time at PWS and gait asymmetry at SWS).

Conclusion

Our study provides insights into the gait characteristics of older women with decreased Cog, PF, and MS, based on the three walking speeds and ML analysis using selected gait features, and may help improve objective classification and evaluation according to declines in Cog, PF, and MS among older women.

A Movement Classification of Polymyalgia Rheumatica Patients Using Myoelectric Sensors

Gait disorder is common among people with neurological disease and musculoskeletal disorders. The detection of gait disorders plays an integral role in designing appropriate rehabilitation protocols. This study presents a clinical gait analysis of patients with polymyalgia rheumatica to determine impaired gait patterns using machine learning models. A clinical gait assessment was conducted at KATH hospital between August and September 2022, and the 25 recruited participants comprised 18 patients and 7 control subjects. The demographics of the participants follow: age 56 years ± 7, height 175 cm ± 8, and weight 82 kg ± 10. Electromyography data were collected from four strained hip muscles of patients, which were the rectus femoris, vastus lateralis, biceps femoris, and semitendinosus. Four classification models were used-namely, support vector machine (SVM), rotation forest (RF), k-nearest neighbors (KNN), and decision tree (DT)-to distinguish the gait patterns for the two groups. SVM recorded the highest accuracy of 85% among the classifiers, while KNN had 75%, RF had 80%, and DT had the lowest accuracy of 70%. Furthermore, the SVM classifier had the highest sensitivity of 92%, while RF had 86%, DT had 90%, and KNN had the lowest sensitivity of 84%. The classifiers achieved significant results in discriminating between the impaired gait pattern of patients with polymyalgia rheumatica and control subjects. This information could be useful for clinicians designing therapeutic exercises and may be used for developing a decision support system for diagnostic purposes.

Comparing Inertial Measurement Units to Markerless Video Analysis for Movement Symmetry in Quarter Horses

BACKGROUND

With an increasing number of systems for quantifying lameness-related movement asymmetry, between-system comparisons under non-laboratory conditions are important for multi-centre or referral-level studies. This study compares an artificial intelligence video app to a validated inertial measurement unit (IMU) gait analysis system in a specific group of horses.

METHODS

Twenty-two reining Quarter horses were equipped with nine body-mounted IMUs while being videoed with a smartphone app. Both systems quantified head and pelvic movement symmetry during in-hand trot (hard/soft ground) and on the lunge (left/right rein, soft ground). Proportional limits of agreement (pLoA) were established.

RESULTS

Widths of pLoA were larger for head movement (29% to 50% in-hand; 22% to 38% on lunge) than for pelvic movement (13% to 24% in-hand; 14% to 24% on lunge).

CONCLUSION

The between-system pLoAs exceed current "lameness thresholds" aimed at identifying the affected limb(s) in lame horses. They also exceed published limits of agreement for stride-matched data but are similar to repeatability values and "lameness thresholds" from "non-lame" horses. This is encouraging for multi-centre studies and referral-level veterinary practice. The narrower pLoA values for pelvic movement asymmetry are particularly encouraging, given the difficulty of grading hind limb lameness "by eye".

Camera-Based Short Physical Performance Battery and Timed Up and Go Assessment for Older Adults With Cancer

This paper presents an automatic camera-based device to monitor and evaluate the gait speed, standing balance, and 5 times sit-stand (5TSS) tests of the Short Physical Performance Battery (SPPB) and the Timed Up and Go (TUG) test. The proposed design measures and calculates the parameters of the SPPB tests automatically. The SPPB data can be used for physical performance assessment of older patients under cancer treatment. This stand-alone device has a Raspberry Pi (RPi) computer, three cameras, and two DC motors. The left and right cameras are used for gait speed tests. The center camera is used for standing balance, 5TSS, and TUG tests and for angle positioning of the camera platform toward the subject using DC motors by turning the camera left/right and tilting it up/down. The key algorithm for operating the proposed system is developed using Channel and Spatial Reliability Tracking in the cv2 module in Python. Graphical User Interfaces (GUIs) in the RPi are developed to run tests and adjust cameras, controlled remotely via smartphone and its Wi-Fi hotspot. We have tested the implemented camera setup prototype and extracted all SPPB and TUG parameters by conducting several experiments on a human subject population of 8 volunteers (male and female, light and dark complexions) in 69 test runs. The measured data and calculated outputs of the system consist of tests of gait speed (0.041 to 1.92 m/s with average accuracy of >95%), and standing balance, 5TSS, TUG, all with average time accuracy of >97%.

Adaptive Control Method for Gait Detection and Classification Devices with Inertial Measurement Unit

Cueing and feedback training can be effective in maintaining or improving gait in individuals with Parkinson's disease. We previously designed a rehabilitation assist device that can detect and classify a user's gait at only the swing phase of the gait cycle, for the ease of data processing. In this study, we analyzed the impact of various factors in a gait detection algorithm on the gait detection and classification rate (GDCR). We collected acceleration and angular velocity data from 25 participants (1 male and 24 females with an average age of 62 ± 6 years) using our device and analyzed the data using statistical methods. Based on these results, we developed an adaptive GDCR control algorithm using several equations and functions. We tested the algorithm under various virtual exercise scenarios using two control methods, based on acceleration and angular velocity, and found that the acceleration threshold was more effective in controlling the GDCR (average Spearman correlation -0.9996, p < 0.001) than the gyroscopic threshold. Our adaptive control algorithm was more effective in maintaining the target GDCR than the other algorithms (p < 0.001) with an average error of 0.10, while other tested methods showed average errors of 0.16 and 0.28. This algorithm has good scalability and can be adapted for future gait detection and classification applications.

An Enhanced Ensemble Deep Neural Network Approach for Elderly Fall Detection System Based on Wearable Sensors

Fatal injuries and hospitalizations caused by accidental falls are significant problems among the elderly. Detecting falls in real-time is challenging, as many falls occur in a short period. Developing an automated monitoring system that can predict falls before they happen, provide safeguards during the fall, and issue remote notifications after the fall is essential to improving the level of care for the elderly. This study proposed a concept for a wearable monitoring framework that aims to anticipate falls during their beginning and descent, activating a safety mechanism to minimize fall-related injuries and issuing a remote notification after the body impacts the ground. However, the demonstration of this concept in the study involved the offline analysis of an ensemble deep neural network architecture based on a Convolutional Neural Network (CNN) and a Recurrent Neural Network (RNN) and existing data. It is important to note that this study did not involve the implementation of hardware or other elements beyond the developed algorithm. The proposed approach utilized CNN for robust feature extraction from accelerometer and gyroscope data and RNN to model the temporal dynamics of the falling process. A distinct class-based ensemble architecture was developed, where each ensemble model identified a specific class. The proposed approach was evaluated on the annotated SisFall dataset and achieved a mean accuracy of 95%, 96%, and 98% for Non-Fall, Pre-Fall, and Fall detection events, respectively, outperforming state-of-the-art fall detection methods. The overall evaluation demonstrated the effectiveness of the developed deep learning architecture. This wearable monitoring system will prevent injuries and improve the quality of life of elderly individuals.

Multidimensional Biomechanics-Based Score to Assess Disease Progression in Duchenne Muscular Dystrophy

(1) Background: Duchenne (DMD) is a rare neuromuscular disease that progressively weakens muscles, which severely impairs gait capacity. The Six Minute-Walk Test (6MWT), which is commonly used to evaluate and monitor the disease's evolution, presents significant variability due to extrinsic factors such as patient motivation, fatigue, and learning effects. Therefore, there is a clear need for the establishment of precise clinical endpoints to measure patient mobility. (2) Methods: A novel score (6M+ and 2M+) is proposed, which is derived from the use of a new portable monitoring system capable of carrying out a complete gait analysis. The system includes several biomechanical sensors: a heart rate band, inertial measurement units, electromyography shorts, and plantar pressure insoles. The scores were obtained by processing the sensor signals and via gaussian-mixture clustering. (3) Results: The 6M+ and 2M+ scores were evaluated against the North Star Ambulatory Assessment (NSAA), the gold-standard for measuring DMD, and six- and two-minute distances. The 6M+ and 2M+ tests led to superior distances when tested against the NSAA. The 6M+ test and the 2M+ test in particular were the most correlated with age, suggesting that these scores better characterize the gait regressions in DMD. Additionally, the 2M+ test demonstrated an accuracy and stability similar to the 6M+ test. (4) Conclusions: The novel monitoring system described herein exhibited good usability with respect to functional testing in a clinical environment and demonstrated an improvement in the objectivity and reliability of monitoring the evolution of neuromuscular diseases.

Biomechanics beyond the lab: Remote technology for osteoarthritis patient data-A scoping review

The objective of this project is to produce a review of available and validated technologies suitable for gathering biomechanical and functional research data in patients with osteoarthritis (OA), outside of a traditionally fixed laboratory setting. A scoping review was conducted using defined search terms across three databases (Scopus, Ovid MEDLINE, and PEDro), and additional sources of information from grey literature were added. One author carried out an initial title and abstract review, and two authors independently completed full-text screenings. Out of the total 5,164 articles screened, 75 were included based on inclusion criteria covering a range of technologies in articles published from 2015. These were subsequently categorised by technology type, parameters measured, level of remoteness, and a separate table of commercially available systems. The results concluded that from the growing number of available and emerging technologies, there is a well-established range in use and further in development. Of particular note are the wide-ranging available inertial measurement unit systems and the breadth of technology available to record basic gait spatiotemporal measures with highly beneficial and informative functional outputs. With the majority of technologies categorised as suitable for part-remote use, the number of technologies that are usable and fully remote is rare and they usually employ smartphone software to enable this. With many systems being developed for camera-based technology, such technology is likely to increase in usability and availability as computational models are being developed with increased sensitivities to recognise patterns of movement, enabling data collection in the wider environment and reducing costs and creating a better understanding of OA patient biomechanical and functional movement data.

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

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

Gait Classification with Gait Inherent Attribute Identification from Ankle's Kinematics

The human ankle joint interacts with the environment during ambulation to provide mobility and maintain stability. This association changes depending on the different gait patterns of day-to-day life. In this study, we investigated this interaction and extracted kinematic information to classify human walking mode into upstairs, downstairs, treadmill, overground and stationary in real-time using a single-DoF IMU axis. The proposed algorithm's uniqueness is twofold - it encompasses components of the ankle's biomechanics and subject-specificity through the extraction of inherent walking attributes and user calibration. The performance analysis with forty healthy participants (mean age: 26.8 ± 5.6 years yielded an accuracy of 89.57% and 87.55% in the left and right sensors, respectively. The study, also, portrays the implementation of heuristics to combine predictions from sensors at both feet to yield a single conclusive decision with better performance measures. The simplicity yet reliability of the algorithm in healthy participants and the observation of inherent multimodal walking features, similar to young adults, in elderly participants through a case study, demonstrate our proposed algorithm's potential as a high-level automatic switching framework in robotic gait interventions for multimodal walking.

A multimodal Parkinson quantification by fusing eye and gait motion patterns, using covariance descriptors, from non-invasive computer vision

BACKGROUND AND OBJECTIVE

Parkinson's disease (PD) is a motor neurodegenerative disease principally manifested by motor disabilities, such as postural instability, bradykinesia, tremor, and stiffness. In clinical practice, there exist several diagnostic rating scales that coarsely allow the measurement, characterization and classification of disease progression. These scales, however, are only based on strong changes in kinematic patterns, and the classification remains subjective, depending on the expertise of physicians. In addition, even for experts, disease analysis based on independent classical motor patterns lacks sufficient sensitivity to establish disease progression. Consequently, the disease diagnosis, stage, and progression could be affected by misinterpretations that lead to incorrect or inefficient treatment plans. This work introduces a multimodal non-invasive strategy based on video descriptors that integrate patterns from gait and eye fixation modalities to assist PD quantification and to support the diagnosis and follow-up of the patient. The multimodal representation is achieved from a compact covariance descriptor that characterizes postural and time changes of both information sources to improve disease classification.

METHODS

A multimodal approach is introduced as a computational method to capture movement abnormalities associated with PD. Two modalities (gait and eye fixation) are recorded in markerless video sequences. Then, each modality sequence is represented, at each frame, by primitive features composed of (1) kinematic measures extracted from a dense optical flow, and (2) deep features extracted from a convolutional network. The spatial distributions of these characteristics are compactly coded in covariance matrices, making it possible to map each particular dynamic in a Riemannian manifold. The temporal mean covariance is then computed and submitted to a supervised Random Forest algorithm to obtain a disease prediction for a particular patient. The fusion of the covariance descriptors and eye movements integrating deep and kinematic features is evaluated to assess their contribution to disease quantification and prediction. In particular, in this study, the gait quantification is associated with typical patterns observed by the specialist, while ocular fixation, associated with early disease characterization, complements the analysis.

RESULTS

In a study conducted with 13 control subjects and 13 PD patients, the fusion of gait and ocular fixation, integrating deep and kinematic features, achieved an average accuracy of 100% for early and late fusion. The classification probabilities show high confidence in the prediction diagnosis, the control subjects probabilities being lower than 0.27 with early fusion and 0.3 with late fusion, and those of the PD patients, being higher than 0.62 with early fusion and 0.51 with late fusion. Furthermore, it is observed that higher probability outputs are correlated with more advanced stages of the disease, according to the H&Y scale.

CONCLUSIONS

A novel approach for fusing motion modalities captured in markerless video sequences was introduced. This multimodal integration had a remarkable discrimination performance in a study conducted with PD and control patients. The representation of compact covariance descriptors from kinematic and deep features suggests that the proposed strategy is a potential tool to support diagnosis and subsequent monitoring of the disease. During fusion it was observed that devoting major attention to eye fixational patterns may contribute to a better quantification of the disease, especially at stage 2.

Method for Estimating Temporal Gait Parameters Concerning Bilateral Lower Limbs of Healthy Subjects Using a Single In-Shoe Motion Sensor through a Gait Event Detection Approach

To expand the potential use of in-shoe motion sensors (IMSs) in daily healthcare or activity monitoring applications for healthy subjects, we propose a real-time temporal estimation method for gait parameters concerning bilateral lower limbs (GPBLLs) that uses a single IMS and is based on a gait event detection approach. To validate the established methods, data from 26 participants recorded by an IMS and a reference 3D motion analysis system were compared. The agreement between the proposed method and the reference system was evaluated by the intraclass correlation coefficient (ICC). The results showed that, by averaging over five continuous effective strides, all time parameters achieved precisions of no more than 30 ms and agreement at the “excellent” level, and the symmetry indexes of the stride time and stance phase time achieved precisions of 1.0% and 3.0%, respectively, and agreement at the “good” level. These results suggest our method is effective and shows promise for wide use in many daily healthcare or activity monitoring applications for healthy subjects.

Validation of a smartphone application and wearable sensor for measurements of wrist motions

We developed a smartphone application to measure wrist motion using the mobile device's built-in motion sensors or connecting it via Bluetooth to a wearable sensor. Measurement of wrist motion with this method was assessed in 33 participants on two occasions and compared with those obtained with a standard goniometer. The test-retest reproducibility in healthy individuals ranged from good to excellent (intraclass correlation (ICC) 0.76-0.95) for all motions, both with and without the wearable sensor. These results improved to excellent (ICC 0.90-0.96) on the second test day, suggesting a learning effect. The day-to-day reproducibility was overall better with the wearable sensor (mean ICC 0.87) compared with the application without using sensor or goniometer (mean ICC 0.82 and 0.60, respectively). This study suggests that smartphone-based measurements of wrist range of motion are feasible and highly accurate, making it a powerful tool for outcome studies after wrist surgery.

Single sensor measurement of heel-height during the push-off phase of gait

Objective. In healthy gait a forceful push-off is needed to get an efficient leg swing and propulsion, and a high heel lift makes a forceful push-off possible. The power of the push-off is decreased with increased age and in persons with impaired balance and gait. The aim of this study was to evaluate whether a wearable equipment (Striton) and algorithms to estimate vertical heel-height during gait from a single optical distance sensor is reliable and feasible for clinical applications.Approach. To assess heel-height with the Striton system an optical distance sensor was used to measure the distance to the floor along the shank. An algorithm was created to transform this measure to a vertical distance. The heel-height was validated in an experimental setup, against a 3D motion capture system (MCS), and test-retest and day-to-day tests were performed on 10 elderly persons. As a reference material 83 elderly persons were included, and heel-height was measured before and after surgery in four patients with the neurological disorder idiopathic normal pressure hydrocephalus (iNPH).Main results. In the experimental setup the accuracy was high with a maximum error of 2% at all distances, target colours and inclination angles, and the correlation to the MCS wasR= 0.94. Test-retest and day-to-day tests were equal within ±1.2 cm. Mean heel-height of the elderly persons was 16.5 ± 0.6 cm and in the patients with iNPH heel-height was increased from 11.2 cm at baseline to 15.3 cm after surgery.Significance. Striton can reliably measure heel-height during gait, with low test-retest and day-to-day variability. The system was easy to attach, and simple to use, which makes it suitable for clinical applications.

Gait and Axial Spondyloarthritis: Comparative Gait Analysis Study Using Foot-Worn Inertial Sensors

Background

Axial spondyloarthritis (axSpA) can lead to spinal mobility restrictions associated with restricted lower limb ranges of motion, thoracic kyphosis, spinopelvic ankylosis, or decrease in muscle strength. It is well known that these factors can have consequences on spatiotemporal gait parameters during walking. However, no study has assessed spatiotemporal gait parameters in patients with axSpA. Divergent results have been obtained in the studies assessing spatiotemporal gait parameters in ankylosing spondylitis, a subgroup of axSpA, which could be partly explained by self-reported pain intensity scores at time of assessment. Inertial measurement units (IMUs) are increasingly popular and may facilitate gait assessment in clinical practice.

Objective

This study compared spatiotemporal gait parameters assessed with foot-worn IMUs in patients with axSpA and matched healthy individuals without and with pain intensity score as a covariate.

Methods

A total of 30 patients with axSpA and 30 age- and sex-matched healthy controls performed a 10-m walk test at comfortable speed. Various spatiotemporal gait parameters were computed from foot-worn inertial sensors including gait speed in ms^–1 (mean walking velocity), cadence in steps/minute (number of steps in a minute), stride length in m (distance between 2 consecutive footprints of the same foot on the ground), swing time in percentage (portion of the cycle during which the foot is in the air), stance time in percentage (portion of the cycle during which part of the foot touches the ground), and double support time in percentage (portion of the cycle where both feet touch the ground).

Results

Age, height, and weight were not significantly different between groups. Self-reported pain intensity was significantly higher in patients with axSpA than healthy controls (P<.001). Independent sample t tests indicated that patients with axSpA presented lower gait speed (P<.001) and cadence (P=.004), shorter stride length (P<.001) and swing time (P<.001), and longer double support time (P<.001) and stance time (P<.001) than healthy controls. When using pain intensity as a covariate, spatiotemporal gait parameters were still significant with patients with axSpA exhibiting lower gait speed (P<.001), shorter stride length (P=.001) and swing time (P<.001), and longer double support time (P<.001) and stance time (P<.001) than matched healthy controls. Interestingly, there were no longer statistically significant between-group differences observed for the cadence (P=.17).

Conclusions

Gait was significantly altered in patients with axSpA with reduced speed, cadence, stride length, and swing time and increased double support and stance time. Taken together, these changes in spatiotemporal gait parameters could be interpreted as the adoption of a so-called cautious gait pattern in patients with axSpA. Among factors that may influence gait in patients with axSpA, patient self-reported pain intensity could play a role. Finally, IMUs allowed computation of spatiotemporal gait parameters and are usable to assess gait in patients with axSpA in clinical routine.

Trial Registration

ClinicalTrials.gov NCT03761212; https://clinicaltrials.gov/ct2/show/NCT03761212

International Registered Report Identifier (IRRID)

RR2-10.1007/s00296-019-04396-4

Joint Constraints Based Dynamic Calibration of IMU Position on Lower Limbs in IMU-MoCap

The position calibration of inertial measurement units (IMUs) is an important part of human motion capture, especially in wearable systems. In realistic applications, static calibration is quickly invalid during the motions for IMUs loosely mounted on the body. In this paper, we propose a dynamic position calibration algorithm for IMUs mounted on the waist, upper leg, lower leg, and foot based on joint constraints. To solve the problem of IMUs’ position displacement, we introduce the Gauss–Newton (GN) method based on the Jacobian matrix, the dynamic weight particle swarm optimization (DWPSO), and the grey wolf optimizer (GWO) to realize IMUs’ position calibration. Furthermore, we establish the coordinate system of human lower limbs to estimate each joint angle and use the fusion algorithm in the field of quaternions to improve the attitude calibration performance of a single IMU. The performances of these three algorithms are analyzed and evaluated by gait tests on the human body and comparisons with a high-precision IMU-Mocap reference device. The simulation results show that the three algorithms can effectively calibrate the IMU’s position for human lower limbs. Additionally, when the degree of freedom (DOF) of a certain dimension is limited, the performances of the DWPSO and GWO may be better than GN, when the joint changes sufficiently, the performances of the three are close. The results confirm that the dynamic calibration algorithm based on joint constraints can effectively reduce the position offset errors of IMUs on upper or lower limbs in practical applications.

Comparison of different symmetry indices for the quantification of dynamic joint angles

BACKGROUND

Symmetry is a sign of physiological and healthy movements, as pathologies are often described by increased asymmetries. Nevertheless, based on precisely measured data, even healthy individuals will show small asymmetries in their movements. However, so far there do not exist commonly accepted methods and reference values for gait symmetry in a healthy collective. Therefore, a comparison and presentation of reference values calculated by 3 different methods of symmetry indices for lower limb joint angles during walking, ascending, and descending stairs were shown.

METHODS

Thirty-five healthy participants were analyzed during walking, ascending, and descending stairs with the help of the inertial measurement system MyoMotion. Using the normalized symmetry index (SI_norm), the symmetry index (SI) as the integral of the symmetry function, and another normalized symmetry index (NSI), the symmetry of joint angles was evaluated. For statistical evaluation of differences, repeated measurement models and Bland-Altman-Plots were used.

RESULTS

Apart from a bias between the symmetry indices, they were comparable in the predefined limits of 5%. For all parameters, significantly higher asymmetry was found for ankle dorsi/-plantarflexion, compared with the hip and knee flexion. Moreover, the interaction effect of the joint and movement factors was significant, with an increased asymmetry of the hip and knee during descending stairs greater than while ascending stairs or walking, but a reduced symmetry of the ankle during walking when compared to descending. The movement only showed significant effects when analyzing the SI_norm.

CONCLUSION

Even for healthy individuals, small asymmetries of movements were found and presented as reference values using 3 different symmetry indices for dynamic lower limb joint angles during 3 different movements. For the quantification of symmetrical movements differences between the joints, movements, and especially their interaction, are necessary to be taken into account. Moreover, a bias between the methods should be noted. The potential for each presented symmetry index to identify pathological movements or track a rehabilitation process was shown but has to be proven in further research.

TRIAL REGISTRATION

DRKS00025878.

The effects of a secondary task on gait in axial spondyloarthritis

Studies on the effects of dual tasking in patients with chronic inflammatory rheumatic diseases are limited. The aim of this study was to assess dual tasking while walking in patients with axial spondyloarthritis (axSpA) in comparison to healthy controls. Thirty patients with axSpA and thirty healthy controls underwent a 10-m walk test at a self-selected comfortable walking speed in single- and dual-task conditions. Foot-worn inertial sensors were used to compute spatiotemporal gait parameters. Analysis of spatiotemporal gait parameters showed that the secondary manual task negatively affected walking performance in terms of significantly decreased mean speed (p < 0.001), stride length (p < 0.001) and swing time (p = 0.008) and increased double support (p = 0.002) and stance time (p = 0.008). No significant interaction of group and condition was observed. Both groups showed lower gait performance in dual task condition by reducing speed, swing time and stride length, and increasing double support and stance time. Patients with axSpA were not more affected by the dual task than matched healthy controls, suggesting that the secondary manual task did not require greater attention in patients with axSpA. Increasing the complexity of the walking and/or secondary task may increase the sensitivity of the dual-task design to axial spondyloarthritis.

Estimation of Various Walking Intensities Based on Wearable Plantar Pressure Sensors Using Artificial Neural Networks

Walking has been demonstrated to improve health in people with diabetes and peripheral arterial disease. However, continuous walking can produce repeated stress on the plantar foot and cause a high risk of foot ulcers. In addition, a higher walking intensity (i.e., including different speeds and durations) will increase the risk. Therefore, quantifying the walking intensity is essential for rehabilitation interventions to indicate suitable walking exercise. This study proposed a machine learning model to classify the walking speed and duration using plantar region pressure images. A wearable plantar pressure measurement system was used to measure plantar pressures during walking. An Artificial Neural Network (ANN) was adopted to develop a model for walking intensity classification using different plantar region pressure images, including the first toe (T1), the first metatarsal head (M1), the second metatarsal head (M2), and the heel (HL). The classification consisted of three walking speeds (i.e., slow at 0.8 m/s, moderate at 1.6 m/s, and fast at 2.4 m/s) and two walking durations (i.e., 10 min and 20 min). Of the 12 participants, 10 participants (720 images) were randomly selected to train the classification model, and 2 participants (144 images) were utilized to evaluate the model performance. Experimental evaluation indicated that the ANN model effectively classified different walking speeds and durations based on the plantar region pressure images. Each plantar region pressure image (i.e., T1, M1, M2, and HL) generates different accuracies of the classification model. Higher performance was achieved when classifying walking speeds (0.8 m/s, 1.6 m/s, and 2.4 m/s) and 10 min walking duration in the T1 region, evidenced by an F1-score of 0.94. The dataset T1 could be an essential variable in machine learning to classify the walking intensity at different speeds and durations.

Development of a Low-Cost Open-Source Measurement System for Joint Angle Estimation

The use of inertial measurement units (IMUs) is a low-cost alternative for measuring joint angles. This study aims to present a low-cost open-source measurement system for joint angle estimation. The system is modular and has hardware and software. The hardware was developed using a low-cost IMU and microcontroller. The IMU data analysis software was developed in Python and has three fusion filters: Complementary Filter, Kalman Filter, and Madgwick Filter. Three experiments were performed for the proof of concept of the system. First, we evaluated the knee joint of Lokomat, with a predefined average range of motion (ROM) of 60∘. In the second, we evaluated our system in a real scenario, evaluating the knee of a healthy adult individual during gait. In the third experiment, we evaluated the software using data from gold standard devices, comparing the results of our software with Ground Truth. In the evaluation of the Lokomat, our system achieved an average ROM of 58.28∘, and during evaluation in a real scenario it achieved an average ROM of 44.62∘. In comparing our software with Ground Truth, we achieved a root-mean-square error of 0.04 and a mean average percentage error of 2.95%. These results encourage the use of this system in other scenarios.

Asymmetric Gait Analysis Using a DTW Algorithm with Combined Gyroscope and Pressure Sensor

Walking is one of the most basic human activities. Various diseases may be caused by abnormal walking, and abnormal walking is mostly caused by disease. There are various characteristics of abnormal walking, but in general, it can be judged as asymmetric walking. Generally, spatiotemporal parameters can be used to determine asymmetric walking. The spatiotemporal parameter has the disadvantage that it does not consider the influence of the diversity of patterns and the walking speed. Therefore, in this paper, we propose a method to analyze asymmetric walking using Dynamic Time Warping (DTW) distance, a time series analysis method. The DTW distance was obtained by combining gyroscope data and pressure data. The experiment was carried out by performing symmetrical walking and asymmetrical walking, and asymmetric walking was performed as a simulation of hemiplegic walking by fixing one ankle using an auxiliary device. The proposed method was compared with the existing asymmetric gait analysis method. As a result of the experiment, a p-value lower than 0.05 was obtained, which proved that there was a statistically significant difference.

The effect of levodopa on bilateral coordination and gait asymmetry in Parkinson's disease using inertial sensor

This study aimed to evaluate the effect of levodopa on the phase coordination index (PCI) and gait asymmetry (GA) of patients with Parkinson's disease (PD) and to investigate correlations between the severity of motor symptoms and gait parameters measured using an inertial sensor. Twenty-six patients with mild-to-moderate-stage PD who were taking levodopa participated in this study. The Unified Parkinson's Disease Rating Scale part III (UPDRS III) was used to assess the severity of motor impairment. The Postural Instability and Gait Difficulty (PIGD) subscore was calculated from UPDRS III. Patients were assessed while walking a 20-m corridor in both "OFF" and "ON" levodopa medication states, and gait analysis was performed using inertial sensors. We investigated the changes in gait parameters after taking levodopa and the correlations between UPDRS III, PIGD, and gait parameters. There was a significant improvement in PCI after taking levodopa. No significant effect of levodopa on GA was found. In "OFF" state, PCI and GA were not correlated with UPDRS III and PIGD. However, in "ON" state, PCI was the only gait parameter correlating with UPDRS III, and it was also highly correlated with PIGD compared to other gait parameters. Significant improvement in bilateral-phase coordination was identified in patients with PD after taking levodopa, without significant change in gait symmetricity. Considering the high correlation with UDPRS III and PIGD in "ON" states, PCI may be a useful and quantitative parameter to measure the severity of motor symptoms in PD patients who are on medication.

Spatio-temporal gait parameters obtained from foot-worn inertial sensors are reliable in healthy adults in single- and dual-task conditions

Inertial measurement units (IMUs) are increasingly popular and may be usable in clinical routine to assess gait. However, assessing their intra-session reliability is crucial and has not been tested with foot-worn sensors in healthy participants. The aim of this study was to assess the intra-session reliability of foot-worn IMUs for measuring gait parameters in healthy adults. Twenty healthy participants were enrolled in the study and performed the 10-m walk test in single- and dual-task ('carrying a full cup of water') conditions, three trials per condition. IMUs were used to assess spatiotemporal gait parameters, gait symmetry parameters (symmetry index (SI) and symmetry ratio (SR)), and dual task effects parameters. The relative and the absolute reliability were calculated for each gait parameter. Results showed that spatiotemporal gait parameters measured with foot-worn inertial sensors were reliable; symmetry gait parameters relative reliability was low, and SR showed better absolute reliability than SI; dual task effects were poorly reliable, and taking the mean of the second and the third trials was the most reliable. Foot-worn IMUs are reliable to assess spatiotemporal and symmetry ratio gait parameters but symmetry index and DTE gait parameters reliabilities were low and need to be interpreted with cautious by clinicians and researchers.

Objective falls-risk prediction using wearable technologies amongst patients with and without neurogenic gait alterations: a narrative review of clinical feasibility

OBJECTIVES

The present narrative review aims to collate the literature regarding the current use of wearable gait measurement devices for falls-risk assessment in neurological and non-neurological populations. Thereby, this review seeks to determine the extent to which the aforementioned barriers inhibit clinical use.

BACKGROUND

Falls contribute a significant disease burden in most western countries, resulting in increased morbidity and mortality with substantial therapeutic costs. The recent development of gait analysis sensor technologies has enabled quantitative measurement of several gait features related to falls risk. However, three main barriers to implementation exist: accurately measuring gait-features associated with falls, differentiating between fallers and non-fallers using these gait features, and the accuracy of falls predictive algorithms developed using these gait measurements.

METHODS

Searches of Medline, PubMed, Embase and Scopus were screened to identify 46 articles relevant to the present study. Studies performing gait assessment using any wearable gait assessment device and analysing correlation with the occurrence of falls during a retrospective or prospective study period were included. Risk of Bias was assessed using the Centre for Evidence Based Medicine (CEBM) Criteria.

CONCLUSIONS

Falls prediction algorithms based entirely, or in-part, on gait data have shown comparable or greater success of predicting falls than existing stratification scoring systems such as the 10-meter walk test or timed-up-and-go. However, data is lacking regarding their accuracy in neurological patient populations. Inertial measurement units (IMU) have displayed competency in obtaining and interpreting gait metrics relevant to falls risk. They have the potential to enhance the accuracy and efficiency of falls risk assessment in inpatient and outpatient setting.

Foot-Worn Inertial Sensors Are Reliable to Assess Spatiotemporal Gait Parameters in Axial Spondyloarthritis under Single and Dual Task Walking in Axial Spondyloarthritis

The aim of this study was (1) to evaluate the relative and absolute reliability of gait parameters during walking in single- and dual-task conditions in patients with axial spondyloarthritis (axSpA), (2) to evaluate the absolute and relative reliability of dual task effects (DTE) parameters, and (3) to determine the number of trials required to ensure reliable gait assessment, in patients with axSpA. Twenty patients with axSpa performed a 10-m walk test in single- and dual-task conditions, three times for each condition. Spatiotemporal, symmetry, and DTE gait parameters were calculated from foot-worn inertial sensors. The relative reliability (intraclass correlation coefficients-ICC) and absolute reliability (standard error of measurement-SEM and minimum detectable change-MDC) were calculated for these parameters in each condition. Spatiotemporal gait parameters showed good to excellent reliability in both conditions (0.59 < ICC < 0.90). The reliability of symmetry and DTE parameters was low. ICC, SEM, and MDC were better when using the mean of the second and the third trials. Spatiotemporal gait parameters obtained from foot-worn inertial sensors assessed in patients with axSpA in single- and dual-task conditions are reliable. However, symmetry and DTE parameters seem less reliable and need to be interpreted with caution. Finally, better reliability of gait parameters was found when using the mean of the 2nd and the 3rd trials.

Evaluation of Inertial Sensor Data by a Comparison with Optical Motion Capture Data of Guitar Strumming Gestures

Computing technologies have opened up a myriad of possibilities for expanding the sonic capabilities of acoustic musical instruments. Musicians nowadays employ a variety of rather inexpensive, wireless sensor-based systems to obtain refined control of interactive musical performances in actual musical situations like live music concerts. It is essential though to clearly understand the capabilities and limitations of such acquisition systems and their potential influence on high-level control of musical processes. In this study, we evaluate one such system composed of an inertial sensor (MetaMotionR) and a hexaphonic nylon guitar for capturing strumming gestures. To characterize this system, we compared it with a high-end commercial motion capture system (Qualisys) typically used in the controlled environments of research laboratories, in two complementary tasks: comparisons of rotational and translational data. For the rotations, we were able to compare our results with those that are found in the literature, obtaining RMSE below 10° for 88% of the curves. The translations were compared in two ways: by double derivation of positional data from the mocap and by double integration of IMU acceleration data. For the task of estimating displacements from acceleration data, we developed a compensative-integration method to deal with the oscillatory character of the strumming, whose approximative results are very dependent on the type of gestures and segmentation; a value of 0.77 was obtained for the average of the normalized covariance coefficients of the displacement magnitudes. Although not in the ideal range, these results point to a clearly acceptable trade-off between the flexibility, portability and low cost of the proposed system when compared to the limited use and cost of the high-end motion capture standard in interactive music setups.

Novel, clinically applicable method to measure step-width during the swing phase of gait

OBJECTIVE

Step-width during walking is an indicator of stability and balance in patients with neurological disorders, and development of objective tools to measure this clinically would be a great advantage. The aim of this study was to validate an in-house-developed gait analysis system (Striton), based on optical and inertial sensors and a novel method for stride detection, for measuring step-width during the swing phase of gait and temporal parameters.

APPROACH

The step-width and stride-time measurements were validated in an experimental setup, against a 3D motion capture system and on an instrumented walkway. Further, test-retest and day-to-day variability were evaluated, and gait parameters were collected from 87 elderly persons (EP) and four individuals with idiopathic normal pressure hydrocephalus (iNPH) before/after surgery.

MAIN RESULTS

Accuracy of the step-width measurement was high: in the experimental setup mean error was 0.08 ± 0.25 cm (R = 1.00) and against the 3D motion capture system 0.04 ± 1.12 cm (R = 0.98). Test-retest and day-to-day measurements were equal within ±0.5 cm. Mean difference in stride time was -0.003 ± 0.008 s between Striton and the instrumented walkway. The Striton system was successfully applied in the clinical setting on individuals with iNPH, which had larger step-width (6.88 cm, n = 4) compared to EP (5.22 cm, n = 87).

SIGNIFICANCE

We conclude that Striton is a valid, reliable and wearable system for quantitative assessment of step-width and temporal parameters during gait. Initial measurements indicate that the newly defined step-width parameter differs between EP and patients with iNPH and before/after surgery. Thus, there is potential for clinical applicability in patients with reduced gait stability.

Measuring Gait Variables Using Computer Vision to Assess Mobility and Fall Risk in Older Adults With Dementia

Fall risk is high for older adults with dementia. Gait impairment contributes to increased fall risk, and gait changes are common in people with dementia, although the reliable assessment of gait is challenging in this population. This study aimed to develop an automated approach to performing gait assessments based on gait data that is collected frequently and unobtrusively, and analysed using computer vision methods. Recent developments in computer vision have led to the availability of open source human pose estimation algorithms, which automatically estimate the joint locations of a person in an image. In this study, a pre-existing pose estimation model was applied to 1066 walking videos collected of 31 older adults with dementia as they walked naturally in a corridor on a specialized dementia unit over a two week period. Using the tracked pose information, gait features were extracted from video recordings of gait bouts and their association with clinical mobility assessment scores and future falls data was examined. A significant association was found between extracted gait features and a clinical mobility assessment and the number of future falls, providing concurrent and predictive validation of this approach.

A Personalized Approach to Improve Walking Detection in Real-Life Settings: Application to Children with Cerebral Palsy

Although many methods have been developed to detect walking by using body-worn inertial sensors, their performances decline when gait patterns become abnormal, as seen in children with cerebral palsy (CP). The aim of this study was to evaluate if fine-tuning an existing walking bouts (WB) detection algorithm by various thresholds, customized at the individual or group level, could improve WB detection in children with CP and typical development (TD). Twenty children (10 CP, 10 TD) wore 4 inertial sensors on their lower limbs during laboratory and out-laboratory assessments. Features extracted from the gyroscope signals recorded in the laboratory were used to tune thresholds of an existing walking detection algorithm for each participant (individual-based personalization: Indiv) or for each group (population-based customization: Pop). Out-of-laboratory recordings were analyzed for WB detection with three versions of the algorithm (i.e., original fixed thresholds and adapted thresholds based on the Indiv and Pop methods), and the results were compared against video reference data. The clinical impact was assessed by quantifying the effect of WB detection error on the estimated walking speed distribution. The two customized Indiv and Pop methods both improved WB detection (higher, sensitivity, accuracy and precision), with the individual-based personalization showing the best results. Comparison of walking speed distribution obtained with the best of the two methods showed a significant difference for 8 out of 20 participants. The personalized Indiv method excluded non-walking activities that were initially wrongly interpreted as extremely slow walking with the initial method using fixed thresholds. Customized methods, particularly individual-based personalization, appear more efficient to detect WB in daily-life settings.

Identification of Gait Motion Patterns Using Wearable Inertial Sensor Network

Gait signifies the walking pattern of an individual. It may be normal or abnormal, depending on the health condition of the individual. This paper considers the development of a gait sensor network system that uses a pair of wireless inertial measurement unit (IMU) sensors to monitor the gait cycle of a user. The sensor information is used for determining the normality of movement of the leg. The sensor system places the IMU sensors on one of the legs to extract the three-dimensional angular motions of the hip and knee joints while walking. The wearable sensor is custom-made at San Diego State University with wireless data transmission capability. The system enables the user to collect gait data at any site, including in a non-laboratory environment. The paper also presents the mathematical calculations to decompose movements experienced by a pair of IMUs into individual and relative three directional hip and knee joint motions. Further, a new approach of gait pattern classification based on the phase difference angles between hip and knee joints is presented. The experimental results show a potential application of the classification method in the areas of smart detection of abnormal gait patterns.

Augmenting Clinical Outcome Measures of Gait and Balance with a Single Inertial Sensor in Age-Ranged Healthy Adults

Gait and balance impairments are linked with reduced mobility and increased risk of falling. Wearable sensing technologies, such as inertial measurement units (IMUs), may augment clinical assessments by providing continuous, high-resolution data. This study tested and validated the utility of a single IMU to quantify gait and balance features during routine clinical outcome tests, and evaluated changes in sensor-derived measurements with age, sex, height, and weight. Age-ranged, healthy individuals (N = 49, 20-70 years) wore a lower back IMU during the 10 m walk test (10MWT), Timed Up and Go (TUG), and Berg Balance Scale (BBS). Spatiotemporal gait parameters computed from the sensor data were validated against gold standard measures, demonstrating excellent agreement for stance time, step time, gait velocity, and step count (intraclass correlation (ICC) > 0.90). There was good agreement for swing time (ICC = 0.78) and moderate agreement for step length (ICC = 0.68). A total of 184 features were calculated from the acceleration and angular velocity signals across these tests, 36 of which had significant correlations with age. This approach was also demonstrated for an individual with stroke, providing higher resolution information about balance, gait, and mobility than the clinical test scores alone. Leveraging mobility data from wireless, wearable sensors can help clinicians and patients more objectively pinpoint impairments, track progression, and set personalized goals during and after rehabilitation.

Quantitative analysis of the bilateral coordination and gait asymmetry using inertial measurement unit-based gait analysis

Inertial measurement unit (IMU)-based gait analysis can be used to quantitatively analyze the bilateral coordination and gait asymmetry (GA). The purpose of this study was to investigate changes in bilateral coordination and GA due to gait speed using an IMU based gait analysis and identify spatiotemporal factors affecting bilateral coordination and GA. Eighty healthy adults (40 men and 40 women) participated in the study. The mean age was 26.2 years, and the mean body mass index was 22.8 kg/m2. Three different walking speeds (80%, 100%, and 120% of preferred walking speed) on a treadmill were applied for 1 min of continuous level walking using a shoe-type IMU-based gait analysis system. The phase coordination index (PCI) and GA were calculated on three different walking speeds. Several variables (gait speed, height, body mass index, cadence, and step length) were analyzed as possible factors affecting the PCI and GA. Bilateral coordination and GA improved during fast walking (p = 0.005 and p = 0.019, respectively) and deteriorated during slow walking (p<0.001 and p = 0.008, respectively), compared with the participants' preferred walking speeds. The correlation analysis revealed that PCI was negatively correlated with step length at each walking condition and lower gait speed was negatively correlated with PCI and GA during slow walking. Both bilateral coordination and GA had a negative linear relationship with gait speed, showing an improvement in the fast walking condition and deterioration in the slow walking condition. Step length was the factor associated with the change in the bilateral coordination.

Smoother-Based 3-D Foot Trajectory Estimation Using Inertial Sensors

OBJECTIVE

Measuring three-dimensional (3-D) foot trajectories with foot-worn inertial measurement units (IMUs) is essential for a variety of applications, such as gait analysis and fall risk assessment. IMU-based foot trajectory is usually reconstructed by double integrating the global coordinate acceleration, in which drifts of signals are accumulated and lead to unbounded error increase. To reduce drift errors, a smoother-based method is proposed in this paper.

METHODS

The smoother-based method not only corrects initial values of integrations, but also smooths integrating processes through a backward update. Both the orientation estimation and the velocity estimation are improved in this concept, which contribute to the improvement of the trajectory estimation.

RESULTS

The final results are compared with an optical motion capture system as reference. Accuracy is evaluated with ground level walking of nine adult participants, 2302 strides in total. Errors are reduced by 62% on stride length and 44% on stride width of the estimation without our method, with final errors [Formula: see text] and [Formula: see text].

CONCLUSION/SIGNIFICANCE

Results prove that our method can improve the accuracy of 3-D foot trajectory estimation. Furthermore, this smoother-based method can reduce drift-related errors when estimating trajectories, which will allow it to expand its applications into other IMU-based measurements.

Gait Evaluation Using Procrustes and Euclidean Distance Matrix Analysis

Objective assessment of gait is important in the treatment and rehabilitation of patients with different diseases. In this paper, we propose a gait evaluation system using the Procrustes and Euclidean distance matrix analysis. We design and develop an android app to collect real time synchronous accelerometer and gyroscope data from two inertial measurement unit sensors through Bluetooth connectivity. The data is collected from 12 young (ten for modeling and two for validation) and 20 older subjects. We analyze the data collected from real world for stride, step, stance, and swing gait features. We validate our method with the measurements of gait features. The generalized Procrustes analysis is used to estimate a standard normal mean gait shape (NMGS) for ten young subjects. Each gait feature of both young and older subjects is then converted to find the best match with the NMGS using the ordinary Procrustes analysis. The shape distance between the NMGS and each gait shape is estimated using Riemannian shape distance, Riemannian size-and-shape distance, Procrustes size-and-shape distance, and root-mean-square deviation. A t-test is performed to provide statistical evidence of gait shape differences between young and older gaits. A mean form, which is considered as a standard normal mean gait form (NMGF), and inter-feature distances are estimated from the set of ten young subjects. The form difference is estimated between the NMGF and individual gaits of young and older. The degree of abnormality is then estimated for individual features and the result is plotted to visualize the feature in a gait. Experimental results demonstrate the performance of the proposed method.

Detection of Infantile Movement Disorders in Video Data Using Deformable Part-Based Model

Movement analysis of infants' body parts is momentous for the early detection of various movement disorders such as cerebral palsy. Most existing techniques are either marker-based or use wearable sensors to analyze the movement disorders. Such techniques work well for adults, however they are not effective for infants as wearing such sensors or markers may cause discomfort to them, affecting their natural movements. This paper presents a method to help the clinicians for the early detection of movement disorders in infants. The proposed method is marker-less and does not use any wearable sensors which makes it ideal for the analysis of body parts movement in infants. The algorithm is based on the deformable part-based model to detect the body parts and track them in the subsequent frames of the video to encode the motion information. The proposed algorithm learns a model using a set of part filters and spatial relations between the body parts. In particular, it forms a mixture of part-filters for each body part to determine its orientation which is used to detect the parts and analyze their movements by tracking them in the temporal direction. The model is represented using a tree-structured graph and the learning process is carried out using the structured support vector machine. The proposed framework will assist the clinicians and the general practitioners in the early detection of infantile movement disorders. The performance evaluation of the proposed method is carried out on a large dataset and the results compared with the existing techniques demonstrate its effectiveness.

Automatic Classification of Gait Impairments Using a Markerless 2D Video-Based System

Systemic disorders affecting an individual can cause gait impairments. Successful acquisition and evaluation of features representing such impairments make it possible to estimate the severity of those disorders, which is important information for monitoring patients' health evolution. However, current state-of-the-art systems perform the acquisition and evaluation of these features in specially equipped laboratories, typically limiting the periodicity of evaluations. With the objective of making health monitoring easier and more accessible, this paper presents a system that performs automatic detection and classification of gait impairments, based on the acquisition and evaluation of biomechanical gait features using a single 2D video camera. The system relies on two different types of features to perform classification: (i) feet-related features, such as step length, step length symmetry, fraction of foot flat during stance phase, normalized step count, speed; and (ii) body-related features, such as the amount of movement while walking, center of gravity shifts and torso orientation. The proposed system uses a support vector machine to decide whether the observed gait is normal or if it belongs to one of three different impaired gait groups. Results show that the proposed system outperforms existing markerless 2D video-based systems, with a classification accuracy of 98.8%.