Feasibility study of using a Microsoft Kinect for virtual coaching of wheelchair transfer techniques

2017 ◽  
Vol 62 (3) ◽  
Author(s):  
Seonhong Hwang ◽  
Chung-Ying Tsai ◽  
Alicia M. Koontz
Keyword(s):  
Motion Tracking ◽  
Intraclass Correlation ◽  
Correlation Coefficients ◽  
Transfer Task ◽  
Angle Measurement ◽  
Microsoft Kinect ◽  
Joint Angles ◽  
Wheelchair Users ◽  
Small Standard Error ◽  
Mean Square Errors

AbstractThe purpose of this study was to test the concurrent validity and test-retest reliability of the Kinect skeleton tracking algorithm for measurement of trunk, shoulder, and elbow joint angle measurement during a wheelchair transfer task. Eight wheelchair users were recruited for this study. Joint positions were recorded simultaneously by the Kinect and Vicon motion capture systems while subjects transferred from their wheelchairs to a level bench. Shoulder, elbow, and trunk angles recorded with the Kinect system followed a similar trajectory as the angles recorded with the Vicon system with correlation coefficients that are larger than 0.71 on both sides (leading arm and trailing arm). The root mean square errors (RMSEs) ranged from 5.18 to 22.46 for the shoulder, elbow, and trunk angles. The 95% limits of agreement (LOA) for the discrepancy between the two systems exceeded the clinical significant level of 5°. For the trunk, shoulder, and elbow angles, the Kinect had very good relative reliability for the measurement of sagittal, frontal and horizontal trunk angles, as indicated by the high intraclass correlation coefficient (ICC) values (>0.90). Small standard error of the measure (SEM) values, indicating good absolute reliability, were observed for all joints except for the leading arm’s shoulder joint. Relatively large minimal detectable changes (MDCs) were observed in all joint angles. The Kinect motion tracking has promising performance levels for some upper limb joints. However, more accurate measurement of the joint angles may be required. Therefore, understanding the limitations in precision and accuracy of Kinect is imperative before utilization of Kinect.

scholarly journals Validity of Inertial Sensors for Assessing Balance Kinematics and Mobility during Treadmill-Based Perturbation and Dance Training

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3065
Author(s):  
Ernest Kwesi Ofori ◽  
Shuaijie Wang ◽  
Tanvi Bhatt
Keyword(s):  
Concurrent Validity ◽  
Inertial Sensors ◽  
Intraclass Correlation ◽  
Correlation Coefficients ◽  
Human Motion ◽  
Intraclass Correlation Coefficients ◽  
Dance Training ◽  
Silver Standard ◽  
Mean Square Errors ◽  
Reactive Balance

Inertial sensors (IS) enable the kinematic analysis of human motion with fewer logistical limitations than the silver standard optoelectronic motion capture (MOCAP) system. However, there are no data on the validity of IS for perturbation training and during the performance of dance. The aim of this present study was to determine the concurrent validity of IS in the analysis of kinematic data during slip and trip-like perturbations and during the performance of dance. Seven IS and the MOCAP system were simultaneously used to capture the reactive response and dance movements of fifteen healthy young participants (Age: 18–35 years). Bland Altman (BA) plots, root mean square errors (RMSE), Pearson’s correlation coefficients (R), and intraclass correlation coefficients (ICC) were used to compare kinematic variables of interest between the two systems for absolute equivalency and accuracy. Limits of agreements (LOA) of the BA plots ranged from −0.23 to 0.56 and −0.21 to 0.43 for slip and trip stability variables, respectively. The RMSE for slip and trip stabilities were from 0.11 to 0.20 and 0.11 to 0.16, respectively. For the joint mobility in dance, LOA varied from −6.98–18.54, while RMSE ranged from 1.90 to 13.06. Comparison of IS and optoelectronic MOCAP system for reactive balance and body segmental kinematics revealed that R varied from 0.59 to 0.81 and from 0.47 to 0.85 while ICC was from 0.50 to 0.72 and 0.45 to 0.84 respectively for slip–trip perturbations and dance. Results of moderate to high concurrent validity of IS and MOCAP systems. These results were consistent with results from similar studies. This suggests that IS are valid tools to quantitatively analyze reactive balance and mobility kinematics during slip–trip perturbation and the performance of dance at any location outside, including the laboratory, clinical and home settings.

scholarly journals A Mechanical Sensor Designed for Dynamic Joint Angle Measurement

2017 ◽  
Vol 2017 ◽  
pp. 1-12 ◽  
Author(s):  
Congo Tak-Shing Ching ◽  
Su-Yu Liao ◽  
Teng-Yun Cheng ◽  
Chih-Hsiu Cheng ◽  
Tai-Ping Sun ◽  
...  
Keyword(s):  
Gait Analysis ◽  
Linear Correlation ◽  
Lower Limb ◽  
Joint Angle ◽  
Intraclass Correlation ◽  
Reliability And Validity ◽  
Angle Measurement ◽  
Joint Angles ◽  
Rehabilitation Programs ◽  
Analysis System

Background. The measurement of the functional range of motion (FROM) of lower limb joints is an essential parameter for gait analysis especially in evaluating rehabilitation programs.Aim. To develop a simple, reliable, and affordable mechanical goniometer (MGR) for gait analysis, with six-degree freedom to dynamically assess lower limb joint angles.Design. Randomized control trials, in which a new MGR was developed for the measurements of FROM of lower limb joints.Setting. Reliability of the designed MGR was evaluated and validated by a motion analysis system (MAS).Population. Thirty healthy subjects participated in this study.Methods. Reliability and validity of the new MGR were tested by intraclass correlation coefficient (ICC), Bland-Altman plots, and linear correlation analysis.Results. The MGR has good inter- and intrarater reliability and validity withICC≥0.93(for both). Moreover, measurements made by MGR and MAS were comparable and repeatable with each other, as confirmed by Bland-Altman plots. Furthermore, a very high degree of linear correlation (R≥0.92for all joint angle measurements) was found between the lower limb joint angles measured by MGR and MAS.Conclusion. A simple, reliable, and affordable MGR has been designed and developed to aid clinical assessment and treatment evaluation of gait disorders.

scholarly journals A Validation of Supervised Deep Learning for Gait Analysis in the Cat

2021 ◽  
Vol 15 ◽  
Author(s):  
Charly G. Lecomte ◽  
Johannie Audet ◽  
Jonathan Harnie ◽  
Alain Frigon
Keyword(s):  
Deep Learning ◽  
Gait Analysis ◽  
Correlation Coefficient ◽  
Motion Tracking ◽  
Low Cost ◽  
Intraclass Correlation ◽  
Correlation Coefficients ◽  
Bony Landmarks ◽  
Custom Made ◽  
Adult Cat

Gait analysis in cats and other animals is generally performed with custom-made or commercially developed software to track reflective markers placed on bony landmarks. This often involves costly motion tracking systems. However, deep learning, and in particular DeepLabCutTM (DLC), allows motion tracking without requiring placing reflective markers or an expensive system. The purpose of this study was to validate the accuracy of DLC for gait analysis in the adult cat by comparing results obtained with DLC and a custom-made software (Expresso) that has been used in several cat studies. Four intact adult cats performed tied-belt (both belts at same speed) and split-belt (belts operating at different speeds) locomotion at different speeds and left-right speed differences on a split-belt treadmill. We calculated several kinematic variables, such as step/stride lengths and joint angles from the estimates made by the two software and assessed the agreement between the two measurements using intraclass correlation coefficient or Lin’s concordance correlation coefficient as well as Pearson’s correlation coefficients. The results showed that DLC is at least as precise as Expresso with good to excellent agreement for all variables. Indeed, all 12 variables showed an agreement above 0.75, considered good, while nine showed an agreement above 0.9, considered excellent. Therefore, deep learning, specifically DLC, is valid for measuring kinematic variables during locomotion in cats, without requiring reflective markers and using a relatively low-cost system.

scholarly journals Computer-Aided Cobb Measurement Based on Automatic Detection of Vertebral Slopes Using Deep Neural Network

2017 ◽  
Vol 2017 ◽  
pp. 1-6 ◽  
Author(s):  
Junhua Zhang ◽  
Hongjian Li ◽  
Liang Lv ◽  
Yufeng Zhang
Keyword(s):  
Neural Network ◽  
Cobb Angle ◽  
Deep Neural Network ◽  
Intraclass Correlation ◽  
Correlation Coefficients ◽  
Angle Measurement ◽  
Training Data ◽  
Manual Measurement ◽  
Computer Aided

Objective. To develop a computer-aided method that reduces the variability of Cobb angle measurement for scoliosis assessment. Methods. A deep neural network (DNN) was trained with vertebral patches extracted from spinal model radiographs. The Cobb angle of the spinal curve was calculated automatically from the vertebral slopes predicted by the DNN. Sixty-five in vivo radiographs and 40 model radiographs were analyzed. An experienced surgeon performed manual measurements on the aforementioned radiographs. Two examiners used both the proposed and the manual measurement methods to analyze the aforementioned radiographs. Results. For model radiographs, the intraclass correlation coefficients were greater than 0.98, and the mean absolute differences were less than 3°. This indicates that the proposed system showed high repeatability for measurements of model radiographs. For the in vivo radiographs, the reliabilities were lower than those from the model radiographs, and the differences between the computer-aided measurement and the manual measurement by the surgeon were higher than 5°. Conclusion. The variability of Cobb angle measurements can be reduced if the DNN system is trained with enough vertebral patches. Training data of in vivo radiographs must be included to improve the performance of DNN. Significance. Vertebral slopes can be predicted by DNN. The computer-aided system can be used to perform automatic measurements of Cobb angle, which is used to make reliable and objective assessments of scoliosis.

Measurement of Patellar Proximodistal Positioning with Limited Joint-Angle Sensitivity

2020 ◽  
Vol 33 (02) ◽  
pp. 096-101
Author(s):  
Clara M. Allberg ◽  
James Miles
Keyword(s):  
Joint Angle ◽  
Intraclass Correlation ◽  
Correlation Coefficients ◽  
Reference Intervals ◽  
Joint Angles ◽  
Angle Variation ◽  
Intraclass Correlation Coefficients ◽  
Stifle Joint ◽  
Wide Range ◽  
Coefficients Of Variations

Abstract Objective Patellar luxation can be associated with abnormal proximodistal positioning of the patella. The current gold standard index (Insall–Salvati) for referencing this position is poorly suited to postoperative use, if the tibial tuberosity is moved surgically, but has the advantage of changing minimally with altered joint angles. The aim of this study was to identify an alternative index, which was simple to use, joint-angle insensitive and suitable for postoperative use. Study Design Candidate indices based on the angle between stifle joint landmarks were screened across a wide range of joint angles for insensitivity to joint angle changes using vulpine and canine stifle radiographs. Intraobserver and interobserver agreements were assessed for a single candidate index using canine radiographs. Results An angular index based on the caudal aspect of the femoral and tibial condyles and the apex of the patella was largely insensitive to joint angle variation. Intra- and interobserver agreements appeared suitable for clinical use, with low within-subject standard deviations (<1.3°) and coefficients of variations (<2.2%), and high intraclass correlation coefficients (>0.89). Conclusion Patellar proximodistal position can be acceptably assessed at a variety of caudal joint angles using the described angular index. Further work is required to define reference intervals across a range of canine breeds.

Reproducibility of Plantar Pressure Distribution Data in Barefoot Running

2008 ◽  
Vol 24 (1) ◽  
pp. 14-23 ◽  
Author(s):  
Christian Maiwald ◽  
Stefan Grau ◽  
Inga Krauss ◽  
Marlene Mauch ◽  
Detlef Axmann ◽  
...  
Keyword(s):  
Root Mean Square ◽  
Plantar Pressure ◽  
Intraclass Correlation ◽  
Correlation Coefficients ◽  
Distribution Data ◽  
Mean Square ◽  
Barefoot Running ◽  
Intraclass Correlation Coefficients ◽  
Force Time ◽  
Mean Square Errors

The aim of this study was to provide detailed information on rationales, calculations, and results of common methods used to quantify reproducibility in plantar pressure variables. Recreational runners (N = 95) performed multiple barefoot running trials in a laboratory setup, and pressure variables were analyzed in nine distinct subareas of the foot. Reproducibility was assessed by calculating intraclass correlation coefficients (ICC) and the root mean square error (RMSE). Intraclass correlation coefficients ranged from 0.58 to 0.99, depending on the respective variable and type of ICC. Root mean square errors ranged between 2.3 and 3.1% for relative force–time integrals, between 0.07 and 0.23 for maximum force (Fmax), and between 107 and 278 kPa for maximum pressure (Pmax), depending on the subarea of the foot. Force–time integral variables demonstrated the best within-subject reproducibility. Rear-foot data suffered from slightly increased measurement error and reduced reproducibility compared with the forefoot.

Effect of Knee and Trunk Angle on Kinetic Variables During the Isometric Midthigh Pull: Test–Retest Reliability

2015 ◽  
Vol 10 (1) ◽  
pp. 58-63 ◽  
Author(s):  
Paul Comfort ◽  
Paul. A. Jones ◽  
John J. McMahon ◽  
Robert Newton
Keyword(s):  
Knee Flexion ◽  
Isometric Force ◽  
High Reliability ◽  
Intraclass Correlation ◽  
Correlation Coefficients ◽  
Joint Angles ◽  
Force Development ◽  
Intraclass Correlation Coefficients ◽  
Hip Flexion ◽  
Test Retest Reliability

The isometric midthigh pull (IMTP) has been used to monitor changes in force, maximum rate of force development (mRFD), and impulse, with performance in this task being associated with performance in athletic tasks. Numerous postures have been adopted in the literature, which may affect the kinetic variables during the task; therefore, the aim of this investigation was to determine whether different knee-joint angles (120°, 130°, 140°, and 150°) and hip-joint angles (125° and 145°), including the subjects preferred posture, affect force, mRFD, and impulse during the IMTP. Intraclass correlation coefficients demonstrated high within-session reliability (r ≥ .870, P < .001) for all kinetic variables determined in all postures, excluding impulse measures during the 130° knee-flexion, 125° hip-flexion posture, which showed a low to moderate reliability (r = .666–.739, P < .001), while between-sessions testing demonstrated high reliability (r > .819, P < .001) for all kinetic variables. There were no significant differences in peak force (P > .05, Cohen d = 0.037, power = .408), mRFD (P > .05, Cohen d = 0.037, power = .409), or impulse at 100 ms (P > .05, Cohen d = 0.056, power = .609), 200 ms (P > .05, Cohen d = 0.057, power = .624), or 300 ms (P > .05, Cohen d = 0.061, power = .656) across postures. Smallest detectable differences demonstrated that changes in performance of >1.3% in peak isometric force, >10.3% in mRFD, >5.3% in impulse at 100 ms, >4.4% in impulse at 200 ms, and >7.1% in impulse at 300 ms should be considered meaningful, irrespective of posture.

scholarly journals Radiographic Determination of the Canine Elbow Joint Angle in Collimated Views

2021 ◽  
Vol 71 (1) ◽  
pp. 1-12
Author(s):  
Alves-Pimenta Sofia ◽  
Colaço Bruno ◽  
Ginja Mário
Keyword(s):  
Confidence Interval ◽  
Elbow Joint ◽  
Joint Angle ◽  
Intraclass Correlation ◽  
Angle Measurement ◽  
Intersection Point ◽  
Anatomical Landmarks ◽  
Joint Angles ◽  
Elbow Angle ◽  
Measurement Methodology

Abstract The mediolateral flexed, extended, or neutral elbow radiographic views are commonly used in clinical practice. However, there is currently no standardized methodology to accurately measure the elbow joint angle in mediolateral images that include only the elbow joint and surrounding tissues. The main aim of this work is to compare elbow joint angles obtained from mediolateral radiographs that include the complete arm and forearm of the dog, with angles measured in radiographs including only the elbow. Ninety mediolateral views of elbow joints were obtained from 50 canine thoracic limbs, with 39 joints <90º, 30 ≥90 - ≤120º and 21 >120º. Radiographs were centered on the elbow joint and include the shoulder and carpal joints. For each complete forelimb radiographic image, the elbow angle was measured using the methodology described in previous studies. Then, the digital images were cut to obtain only the joint and surrounding tissues, establishing a new set of anatomical landmarks to measure the joint angles: the lateral humeral epicondyle was used as an angular point, with the linking points being the nutritional orifice of the radius at the antebrachial interosseous space and the intersection point of the lateral supracondylar crest with the cranial humeral endosteum. There was a good agreement observed between the two elbow angle measurement methodologies. The intraclass correlation coefficient was statistically significant, with the lower limits of the 95% confidence interval (CI) at >0.75, and with zero being included in the standard error of the mean 95% confidence interval in the Bland-Altman test. This elbow angle measurement methodology based on anatomic landmarks next to the elbow joint is accurate and may be used for clinical and research purposes.

Within-Session Reliability and Minimum Detectable Differences for Discrete Lower-Extremity Angles and Moments During Walking

2021 ◽  
Vol 37 (5) ◽  
pp. 477-480
Author(s):  
Jillian L. Hawkins ◽  
Clare E. Milner
Keyword(s):  
Lower Extremity ◽  
Intraclass Correlation ◽  
Three Dimensional ◽  
Correlation Coefficients ◽  
Joint Angles ◽  
Cross Sectional ◽  
Intraclass Correlation Coefficients ◽  
Walking Biomechanics ◽  
Lower Extremity Biomechanics ◽  
Better Than

Differences in walking biomechanics between groups or conditions should be greater than the measurement error to be considered meaningful. Reliability and minimum detectable differences (MDDs) have not been determined for lower-extremity angles and moments during walking within a session, as needed for interpreting differences in cross-sectional studies. Thus, the purpose of this study was to determine within-session reliability and MDDs for peak ankle, knee, and hip angles and moments during walking. Three-dimensional gait analysis was used to record walking at 1.25 m/s (±5%) in 18 men, 18–50 years of age. Peak angles and moments were calculated for 2 sets of 3 trials. Intraclass correlation coefficients (3, 3) were used to determine within-session reliability. In addition, MDDs were calculated. Within-session reliability was good to excellent for all variables. The MDDs ranged from 0.9° to 3.6° for joint angles and 0.06 to 0.15 N·m/kg for joint moments. Within-session reliability for peak ankle, knee, and hip angles and moments was better than the between-session reliability reported previously. Overall, our MDDs were similar or smaller than those previously reported for between-session reliability. The authors recommend using these MDDs to aid in the interpretation of cross-sectional comparisons of lower-extremity biomechanics during walking in healthy men.

Interobserver Reliability Using the Phonetic Level Evaluation With Severely and Profoundly Hearing-Impaired Children

1991 ◽  
Vol 34 (5) ◽  
pp. 989-999 ◽  
Author(s):  
Stephanie Shaw ◽  
Truman E. Coggins
Keyword(s):  
Interrater Reliability ◽  
Interobserver Reliability ◽  
Intraclass Correlation ◽  
Correlation Coefficients ◽  
Hearing Impaired ◽  
Intraclass Correlation Coefficients ◽  
Assessment Measure ◽  
Impaired Children ◽  
Speech Assessment ◽  
Hearing Impaired Children

This study examines whether observers reliably categorize selected speech production behaviors in hearing-impaired children. A group of experienced speech-language pathologists was trained to score the elicited imitations of 5 profoundly and 5 severely hearing-impaired subjects using the Phonetic Level Evaluation (Ling, 1976). Interrater reliability was calculated using intraclass correlation coefficients. Overall, the magnitude of the coefficients was found to be considerably below what would be accepted in published behavioral research. Failure to obtain acceptably high levels of reliability suggests that the Phonetic Level Evaluation may not yet be an accurate and objective speech assessment measure for hearing-impaired children.

Sign in / Sign up

Export Citation Format

Share Document