Lower Body Movements Research Articles

Deep Transfer Learning for Detection of Upper and Lower Body Movements: Transformer With Convolutional Neural Network

Deep Transfer Learning for Detection of Upper and Lower Body Movements: Transformer With Convolutional Neural Network

Movement Outcomes Acquired via Markerless Motion Capture Systems Compared with Marker-Based Systems for Adult Patient Populations: A Scoping Review

Mobile motion capture is a promising technology for assessing physical movement; markerless motion capture systems (MLSs) offer great potential in rehabilitation settings, given their accessibility compared to marker-based motion capture systems (MBSs). This review explores the current literature on rehabilitation, for direct comparison of movement-related outcomes captured by MLSs to MBSs and for application of MLSs in movement measurements. Following a scoping review methodology, nine databases were searched (May to August 2023). Eligible articles had to present at least one estimate of the mean difference between a measure of a physical movement assessed by MLS and by MBS. Sixteen studies met the selection criteria and were included. For comparison of MLSs with MBSs, measures of mean joint range of motion (ROM) displacement were found to be similar, while peak joint angle outcomes were significantly different. Upper body movement outcomes were found to be comparable, while lower body movement outcomes were very different. Overall, nearly two-thirds of measurements identified statistical differences between MLS and MBS outcomes. Regarding application, no studies assessed the technology with patient populations. Further MLS-specific research with consideration of patient populations (e.g., intentional error testing, testing in less-than-ideal settings) would be beneficial for utilization of motion capture in rehabilitation contexts.

Technical analysis of basketball players' shooting movements through video images

BackgroundWith the increase in basketball competition intensity, video image analysis-based methods have been increasingly applied to improve the technical level of basketball players. MethodsTaking the example of one-handed set shoulder shooting (the basketball player spreads legs apart at shoulder width, holds the ball over the right shoulder, extends the right hand along with lower body movement, and releases the ball softly using fingers), this study compared the technical differences between 20 level 2 basketball players (level 2 group) and 20 basketball specialized students (specialized group) by capturing video images using a high-speed camera and conducting independent sample t-tests. ResultsThe level 2 group had a significantly higher shooting percentage than the specialized group (p=0.005). Additionally, the level 2 group had shorter dribbling time and longer shooting time compared to the specialized group (p=0.032; p=0.021). The amplitude of variation in the knee, hip, and elbow joints was significantly greater than that of the specialized group (p=0.008/0.016/0.031). The flexion angles of the index finger and middle finger after striking in the level 2 group were significantly higher than those of the specialized group (p=0.021/0.036). The level 2 group also had a smaller striking angle and a larger striking height and speed than the specialized group (p=0.001; p=0.005/0.006). ConclusionAthletes of different levels show differences in phase duration and joint angles when performing one-handed set shoulder shooting, providing a basis for athletes' training.

A Motion Capture Dataset on Human Sitting to Walking Transitions

Sit-to-walk (STW) is a crucial daily task that impacts mobility, independence, and thus quality of life. Existing repositories have limited STW data with small sample sizes (n = 10). Hence, this study presents a STW dataset obtained via the time-up-and-go test, for 65 healthy adults across three age groups – young (19–35 years), middle (36–55 years) and older (above 56 years). The dataset contains lower body motion capture, ground reaction force, surface electromyography, inertial measurement unit data, and responses for the knee injury and osteoarthritis outcome score survey. For validation, the within subjects intraclass correlation coefficients for the maximum and minimum lower body joint angles were calculated with values greater than 0.74, indicating good test-retest reliability. The joint angle trajectories and maximum voluntary contractions are comparable with existing literature, matching in overall trends and range. Accordingly, this dataset allows STW biomechanics, executions, and characteristics to be studied across age groups. Biomechanical trajectories of healthy adults serve as a benchmark in assessing neuromusculoskeletal impairments and when designing assistive technology for treatment or rehabilitation.

A software-based observational coding approach for evaluating paediatric dental pain, anxiety, and fear.

Dental practitioners desire non-pharmacological methods to alleviate anxiety, fear, and pain in children receiving dental care; high-quality evidence, however, is required to evaluate methods' efficacy. This study aimed to develop and validate an observation-based coding approach (paediatric dental pain, anxiety, and fear coding approach [PAFCA]) to evaluate non-pharmacological behavior management techniques for anxiety, fear, and pain. Objective (video-based) and subjective (self-reported) anxiety, fear, and pain data were collected from a pilot clinical trial evaluating animal-assisted therapy (AAT) in paediatric dentistry, in which 37 children aged 7-14 were assigned to AAT or control before dental treatment (restorations or extractions). A coding approach utilizing a codebook, a gold standard calibration video, and a user training guide was developed. Trained examiners coded the gold standard video for inter-rater agreement, and masked, calibrated examiners analyzed videos using the Noldus Observer XT software. A novel, software-based coding approach was developed, with moderately high inter-rater agreement. Using PAFCA, we found children reporting higher levels of pain, fear, and anxiety exhibited treatment-interfering behaviors, including crying/moaning, attempts to dislodge instruments, and more upper and lower body movements. PAFCA shows promise as a reliable tool for assessing anxiety, pain, and fear in behavioral research for paediatric dentistry.

Gait ataxia in alcohol use disorder: A systematic review.

A severe and long-term alcohol use can have adverse effects on lower limb function. Over time, some individuals may develop gait ataxia, which refers to the impairment of controlled lower body movements that are important for walking and maintaining proper gait. Gait ataxia is well-documented in patients who have been diagnosed with alcohol-related Wernicke-Korsakoff syndrome (WKS); however, less is known on how common ataxia is among patients with alcohol use disorder (AUD) without WKS. To date, no study has systematically reviewed the evidence focusing on patients suffering only from AUD. Our aim was to perform a qualitative synthesis of the existing literature examining behavioral signs of gait ataxia among abstinent patients with AUD. Two facets were created encompassing keywords for "alcohol use disorder" and "measures of gait ataxia." Databases, including EMBASE, APA PsycInfo, Medline, and Cochrane Library, were searched for studies, and a quality assessment was performed. Ten studies were identified (37 ≥ ns ≤ 247), which were all rated as being of moderate (N = 7) to good quality (N = 3). The age range was 31.4-53.4 years (weighted mean age: 53.6 years), and 78.3% of the participants were male. Eight studies found that patients with AUD and without WKS exhibited behavioral signs of gait ataxia. Although there is evidence of gait ataxia among patients with AUD, heterogeneous results and methodological shortcomings such as lack of screening for neurocognitive deficits deem these findings preliminary and highlight the need for more research in the future. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Analyzing lower body movements using machine learning to classify autistic children

Autism spectrum disorder is a neurological disorder that affects children at an early age and its symptoms appear in varying degrees. Early detection of ASD and follow-up of treatment by specialists help improve autistic people's lives and reduce the symptoms they suffer from. In the past few years, a group of studies conducted gait analysis to diagnose children with autism, and although the results of these studies showed weak motor skills of Autism Spectrum Disorder children (ASD) compared to their peers of Typically Developing children (TD), there are some challenges facing researchers in this field. The first is the ability to create A safe, effective, friendly environment that reduces tension in ASD children and helps classify children into ASD/TD effectively. And the second is the ability to create an automated ASD diagnosis system. In this work, a system based on machine learning and augmented reality technology has been proposed to create an effective and friendly interactive environment that helps diagnose ASD and classify children to ASD / TD. The movement of the lower limbs of 15 ASD children and 15 TD children are tracked via a marker-less technique through a Kinect v2 sensor when playing a specific game based on kicking the ball task, that is using augmented reality technology. Then the kinematics features are extracted through Linear Discriminant Analysis technology. To determine these features' ability in the classification process, three machine learning algorithms are used, namely Support Vector Machine, Linear Discriminant Analysis, and Decision Tree. The results showed that the obtained kinematics features can classify children into ASD/TD, where the Support Vector Machine classifier obtained a high accuracy of 96.7% with sensitivity equal to 93.3% and specificity equal to 100%. In addition, the Linear Discriminant Analysis classifier obtained less accuracy of 93.3% with sensitivity equal to 93.3% and specificity equal to 93.3% compared with the Support Vector Machine classifier. Where the Decision Tree classifier obtained the lowest accuracy of 80.0% with sensitivity equal to 73.3% and specificity equal to 86.7% compared with the Support Vector Machine and Linear Discriminant Analysis classifiers. In addition to that, when using Linear Discriminant Analysis to reduce dimensions and extract features, the accuracy, sensitivity, and specificity of the Support Vector Machine classifier were increased and achieved by 100%. Based on these results, it has been proven that the proposed method is effective in classifying children to ASD/TD.

Full-Body Motion Reconstruction with Sparse Sensing from Graph Perspective

Estimating 3D full-body pose from sparse sensor data is a pivotal technique employed for the reconstruction of realistic human motions in Augmented Reality and Virtual Reality. However, translating sparse sensor signals into comprehensive human motion remains a challenge since the sparsely distributed sensors in common VR systems fail to capture the motion of full human body. In this paper, we use well-designed Body Pose Graph (BPG) to represent the human body and translate the challenge into a prediction problem of graph missing nodes. Then, we propose a novel full-body motion reconstruction framework based on BPG. To establish BPG, nodes are initially endowed with features extracted from sparse sensor signals. Features from identifiable joint nodes across diverse sensors are amalgamated and processed from both temporal and spatial perspectives. Temporal dynamics are captured using the Temporal Pyramid Structure, while spatial relations in joint movements inform the spatial attributes. The resultant features serve as the foundational elements of the BPG nodes. To further refine the BPG, node features are updated through a graph neural network that incorporates edge reflecting varying joint relations. Our method's effectiveness is evidenced by the attained state-of-the-art performance, particularly in lower body motion, outperforming other baseline methods. Additionally, an ablation study validates the efficacy of each module in our proposed framework.

Reliability of Markerless Motion Capture Systems for Assessing Movement Screenings.

Movement screenings are commonly used to detect unfavorable movement patterns. Markerless motion capture systems have been developed to track 3-dimensional motion. To determine the reliability of movement screenings assessed using a markerless motion capture system when comparing the results of multiple systems and multiple collection periods. Descriptive laboratory study. The inter- and intrarater reliability of a commercially available markerless motion capture system were investigated in 21 recreationally active participants aged between 18 and 22 years. A total of 39 kinematic variables arising from 10 fundamental upper and lower body movements typical of a screening procedure in sports performance were considered. The data were statistically analyzed in terms of relative error via the intraclass correlation coefficient (ICC) and absolute error via the residual standard error (RSE). Both inter- and intrarater reliability ICCs were at least moderate across all variables (ICC, >0.50), with most movements and corresponding variables having excellent reliability (ICC, >0.90). Although maximum knee valgus angles were the kinematic variables with the lowest interrater reliability (ICCs, 0.59-0.82) and moderate relative agreement, there was agreement in absolute terms with an RSE of <1.3°. Findings indicated that markerless motion capture provides reliable measurements of joint position during a movement screen, which allows for a more objective evaluation of the direction and subsequent success of interventions. However, practitioners should consider relative and absolute agreements when applying information provided by these systems. Markerless motion capture systems may assist clinicians by reliably assessing movement screenings using different systems over different collection periods.

The Use of Free Weight Squats in Sports: A Narrative Review—Terminology and Biomechanics

There is substantial evidence indicating that increased maximum strength as a result of training with squats, particularly full and parallel squats, is associated with superior athletic capabilities, such as sprinting, jumping and agility. Although full and parallel squats have been strongly associated with sport performance, there is also some evidence that the use of partial squats may provide angle specific adaptations that are likely advantageous for specific sporting activities. Partial squats may be particularly advantageous when trained in conjunction with full or parallel squats, as this practice results in a greater training effect. There is a paucity of evidence that squatting is associated with excessive injuries to the knees, lower back, or other structures. Evidence does indicate that squatting, including full squats, can be undertaken safely, provided an appropriate training methodology is applied. Indeed, based on scientific data, the cost/benefit ratio indicates that squats should be recommended and should be a central strength training exercise for the preparation of athletes in most sports, particularly those requiring strong and powerful whole body and lower body movements.

Scalable musculoskeletal model for dynamic simulations of lower body movement

A musculoskeletal (MSK) model is an important tool for analysing human motions, calculating joint torques during movement, enhancing sports activity, and developing exoskeletons and prostheses. To enable biomechanical investigation of human motion, this work presents an open-source lower body MSK model. The MSK model of the lower body consists of 7 body segments (pelvis, left/right thigh, left/right leg, and left/right foot). The model has 20 degrees of freedom (DoFs) and 28 muscle torque generators (MTGs), which are developed from experimental data. The model can be modified for different anthropometric measurements and subject body characteristics, including sex, age, body mass, height, physical activity, and skin temperature. The model is validated by simulating the torque within the range of motion (ROM) of isolated movements; all simulation findings exhibit a good level of agreement with the literature.

An investigation of an athlete injury likelihood monitoring system using the random forest algorithm and DWT.

The main goal of sports science is to monitor sports injuries. Nevertheless, the existing sports injury monitoring projects have many expensive instruments and excessively extended monitoring periods, which makes it difficult to expand sports injury monitoring on a large scale. The advancement of machine learning algorithms opens up new avenues for the tracking of sports injuries. A training set of sports injuries was created using the Discrete Wavelet Transform (DWT) and Random Forest algorithms. Next, a basic analytic framework was created based on the lower-body movement of runners, and an athlete's injury likelihood monitoring system was established. First off, the wearable gyroscope device can efficiently plot the motion displacement curve and monitor the three-dimensional mechanics of the athlete's hips, thighs, and calves. Secondly, the system has a higher computational efficiency and an advantage over other classifier-based systems in terms of testing and training times. The suggested system framework identifies athletes' injury propensity, providing preventive recommendations based on displacement curves, and offering a low total cost and high testing accuracy, making it easy to implement and cost-effective. All things considered, the sports injury monitoring device is very accurate and reasonably priced, making it appropriate for widespread use.

Fluctuations in Upper and Lower Body Movement during Walking in Normal Pressure Hydrocephalus and Parkinson's Disease Assessed by Motion Capture with a Smartphone Application, TDPT-GT.

We aimed to capture the fluctuations in the dynamics of body positions and find the characteristics of them in patients with idiopathic normal pressure hydrocephalus (iNPH) and Parkinson's disease (PD). With the motion-capture application (TDPT-GT) generating 30 Hz coordinates at 27 points on the body, walking in a circle 1 m in diameter was recorded for 23 of iNPH, 23 of PD, and 92 controls. For 128 frames of calculated distances from the navel to the other points, after the Fourier transforms, the slopes (the representatives of fractality) were obtained from the graph plotting the power spectral density against the frequency in log-log coordinates. Differences in the average slopes were tested by one-way ANOVA and multiple comparisons between every two groups. A decrease in the absolute slope value indicates a departure from the 1/f noise characteristic observed in healthy variations. Significant differences in the patient groups and controls were found in all body positions, where patients always showed smaller absolute values. Our system could measure the whole body's movement and temporal variations during walking. The impaired fluctuations of body movement in the upper and lower body may contribute to gait and balance disorders in patients.

Assessing changes in range of motion in adolescent patients undergoing myoActivation® for chronic pain related to myofascial dysfunction: a feasibility study

IntroductionmyoActivation® assessment utilizes systemized movement tests to assess for pain and limitations in motion secondary to myofascial dysfunction. myoActivation needling therapy resolves the myofascial components of pain and is associated with immediately observed changes in pain, flexibility, and range of motion. The principal aim of this feasibility study was to objectively characterize the kinematic metrics of upper and lower body motion before and after myoActivation movement tests and therapy.MethodsFive consecutive eligible adolescent participants considered appropriate for myoActivation were consented to receive their myoActivation intervention in a motion laboratory. Clinical motion analysis was used to measure the changes in maximum range of motion (maxROM) and maximum angular speed to maximum ROM (speedROM) of movement tests predicted to change. Metrics were analyzed to assess changes over specified time intervals - i) baseline to after initial myoActivation session, and ii) baseline to after complete myoActivation course. Each participant served as their own control.ResultsWe demonstrated objective evidence of improved maxROM and/or speedROM in 63% of the movement tests predicted to change after just one session of myoActivation and in 77% of movement tests predicted to change over the complete course of treatment. The myoActivation clinician observed positive change in 11/19 of movement tests across all patients, that were predicted to change after the initial myoActivation session; 81% of these positive changes were confirmed by the kinematic data.DiscussionClinical motion analysis provides objective support to clinicians evaluating, treating, and teaching myofascial release. A larger, prospective clinical trial is warranted to explore the impact of myoActivation on movement. Refinement of observation techniques and outcome measures established in this feasibility study will strengthen future clinical motion analysis of the myoActivation process.

Designing Smart Legging for Posture Monitoring Based on Textile Sensing Networks

Running is a highly popular form of exercise, while incorrect running posture over an extended period can lead to severe knee injuries. Smart textiles have recently demonstrated significant potential for continuous motion monitoring. This study involved the design and development of a smart legging with a resistive textile sensor network to monitor lower body motion. The study consists of three main parts. Firstly, we tested textile sensors in terms of linearity and robustness to determine the basic sensor unit that can monitor the characteristics of running postures. Next, optimal sensor placement was determined through comparison experiments, and a sensor network was proposed. Finally, based on the LSTM model with data gathered from 6 participants, we developed the smart legging system that is capable of identifying three types of improper running postures and normal postures with 99.1% accuracy. The evaluation revealed that the smart legging system had the potential to help users adjust their running postures to prevent knee injury through continuous monitoring and multi-modal feedback.

Classifying Tremor Dominant and Postural Instability and Gait Difficulty Subtypes of Parkinson's Disease from Full-Body Kinematics.

Characterizing motor subtypes of Parkinson's disease (PD) is an important aspect of clinical care that is useful for prognosis and medical management. Although all PD cases involve the loss of dopaminergic neurons in the brain, individual cases may present with different combinations of motor signs, which may indicate differences in underlying pathology and potential response to treatment. However, the conventional method for distinguishing PD motor subtypes involves resource-intensive physical examination by a movement disorders specialist. Moreover, the standardized rating scales for PD rely on subjective observation, which requires specialized training and unavoidable inter-rater variability. In this work, we propose a system that uses machine learning models to automatically and objectively identify some PD motor subtypes, specifically Tremor-Dominant (TD) and Postural Instability and Gait Difficulty (PIGD), from 3D kinematic data recorded during walking tasks for patients with PD (MDS-UPDRS-III Score, 34.7 ± 10.5, average disease duration 7.5 ± 4.5 years). This study demonstrates a machine learning model utilizing kinematic data that identifies PD motor subtypes with a 79.6% F1 score (N = 55 patients with parkinsonism). This significantly outperformed a comparison model using classification based on gait features (19.8% F1 score). Variants of our model trained to individual patients achieved a 95.4% F1 score. This analysis revealed that both temporal, spectral, and statistical features from lower body movements are helpful in distinguishing motor subtypes. Automatically assessing PD motor subtypes simply from walking may reduce the time and resources required from specialists, thereby improving patient care for PD treatments. Furthermore, this system can provide objective assessments to track the changes in PD motor subtypes over time to implement and modify appropriate treatment plans for individual patients as needed.

Fit of fire boots: exploring internal morphology using computed tomography

Fit of fire boots is a crucial factor in the safety and performance of firefighters on the hostile fireground. Firefighters have reported that ill-fitting fire boots restrict their lower body movement and sometimes cause very dangerous situations by falling off behind the wearer. By using computed tomography, this study demonstrates the potential to quantify and visualize the fit of fire boots, which previously relied on subjective feedback from the wearers. The high-resolution three-dimensional (3D) models of two fire boot products allowed a detailed observation and measurement of the internal space of the boots. Also, the boot’s internal dimension was compared to the foot measurement of local firefighters, showing the significant differences between the two boots. Lastly, simulation wrapping the 3D scanned foot with the boot revealed large void spaces around the toe box and ankle, as well as the narrower ball width of the boot than the foot.

“I Feel My Abs”: Exploring Non-standing VR Locomotion

Virtual Reality (VR) games and experiences predominantly have the users interact while standing or seated. However, this only represents a fraction of the full diversity of human movement. In this paper, we explore a novel non-standing approach to VR locomotion where the user performs locomotion movements in the air or only slightly touching the ground with their feet. For instance, the user may lie supine on the ground, reminiscent of the Bicycle Crunch, a core training movement common in Pilates and other forms of bodyweight exercise. Although this cannot generally replace traditional VR locomotion, it provides two benefits that we believe can be of use for specific application domains such as VR exergames: First, the user's lower body movement is not impeded by a small real-life space, allowing versatile navigation of large virtual worlds using walking, running, strafing, and jumping. Second, we allow new ways to activate parts of the body that remain passive in most existing VR interactions. We describe and discuss four different variants of the approach, and investigate two prototypes further in a qualitative user study, to better understand their strengths, weaknesses, and application potential.

Learning disentangled representations for controllable human motion prediction

Generative model-based motion prediction techniques have recently realized predicting controlled human motions, such as predicting multiple upper human body motions with similar lower-body motions. However, to achieve this, the state-of-the-art methods require either subsequently learning mapping functions to seek similar motions or training the model repetitively to enable control over the desired portion of body. In this paper, we propose a novel framework to learn disentangled representations for controllable human motion prediction. Our task is to predict multiple future human motions based on the past observed sequence, with the control of partial-body movements. Our network involves a conditional variational auto-encoder (CVAE) architecture to model full-body human motion, and an extra CVAE path to learn only the corresponding partial-body (e.g., lower-body) motion. Specifically, the inductive bias imposed by the extra CVAE path encourages two latent variables in two paths to respectively govern separate representations for each partial-body motion. With a single training, our model is able to provide two types of controls for the generated human motions: (i) strictly controlling one portion of human body and (ii) adaptively controlling the other portion, by sampling from a pair of latent spaces. Additionally, we extend and adapt a sampling strategy to our trained model to diversify the controllable predictions. Our framework also potentially allows new forms of control by flexibly customizing the input for the extra CVAE path. Extensive experimental results and ablation studies demonstrate that our approach is capable of predicting state-of-the-art controllable human motions both qualitatively and quantitatively.

Upper extremity kinematics during walking gait changes through pregnancy

BackgroundThirty percent of adults in the United States use wearable fitness devices as of 2020 [1], such as fitness watches, to monitor and track health and physical activity parameters. Physical changes during pregnancy may impact wrist worn device accuracy. The arms may be needed as compensation during walking because thorax axial rotation may be inhibited by pelvic tilt during pregnancy [2]. MethodsTo examine arm motion changes, twenty-three pregnant women (28 ± 4 y) were tested in four-week intervals ( ± 2 weeks) at 18-, 22-, 26-, 30- and 34-weeks’ gestation. Kinematic data were measured during self-selected speed walking. Segment angles and angular velocities were analyzed over time. Linear regressions were used to analyze the correlations between arm motion and the other kinematic variables. ResultsArm range of motion significantly increased (p = 0.006) over gestation, but leg, thorax, and pelvis range of motions did not significantly change. Arm range of motion was correlated with pelvis (r2 =0.311, p = 0.001, β = 1.724) and leg (r2 = 0.285, p = 0.004, β = 1.520) range of motion and gait velocity (r2 =0.566, p = 0.001, β = 39.110). Arm velocities significantly increased (p < 0.012), as did leg velocities (p < 0.022) over gestation time, but thorax and pelvis rotational velocities did not significantly change over time. Arm velocity was correlated with leg velocity in both flexion (r2 =0.598, p = 0.001, β = 1.61) and extension (r2 =0.568, p = 0.001, β = 1.35). SignificanceArm swing increases over the course of gestation during walking, which does not follow the exact pattern of changes seen in the legs, thorax, and pelvis. These results show that a typical gait analysis of lower body motions may miss important biomechanical changes or compensations at different points over pregnancy. Future studies should examine why these changes may occur. Studies should also be conducted to see if arm changes impact outcome parameters from fitness watches and affect their validity as an exercise tracker during pregnancy.