Quality and Quantity of Rehabilitation Exercises Delivered By A 3-D Motion Controlled Camera: A Pilot Study

Komatireddy, Ravi; Chokshi, Anang; Basnett, Jeanna; Casale, Michael; Goble, Daniel J.; Shubert, Tiffany E.

doi:10.4172/2329-9096.1000214

Cited by 41 publications

(45 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, Lin and Kulic [20] employed a data set consisting of deep squats, sit to stand, knee flexion, hip flexion and straight leg raise movements for the development of a machine learning method for automated segmentation of the repetitions in each exercise. Komatireddy et al [21] proposed an approach for evaluation of the consistency in completing the following physical therapy exercises: deep squats, inline lunge, sitting knee extension, and standing knee extension. Similar movements were employed in other related research within the published literature [17, 18].…”

Section: Data Descriptionmentioning

confidence: 99%

A Data Set of Human Body Movements for Physical Rehabilitation Exercises

Vakanski

Jun

Paul

et al. 2018

Data

View full text Add to dashboard Cite

The article presents University of Idaho – Physical Rehabilitation Movement Data (UI-PRMD) — a publically available data set of movements related to common exercises performed by patients in physical rehabilitation programs. For the data collection, 10 healthy subjects performed 10 repetitions of different physical therapy movements, with a Vicon optical tracker and a Microsoft Kinect sensor used for the motion capturing. The data are in a format that includes positions and angles of full-body joints. The objective of the data set is to provide a basis for mathematical modeling of therapy movements, as well as for establishing performance metrics for evaluation of patient consistency in executing the prescribed rehabilitation exercises.

show abstract

Section: Data Descriptionmentioning

confidence: 99%

A Data Set of Human Body Movements for Physical Rehabilitation Exercises

Vakanski

Jun

Paul

et al. 2018

Data

View full text Add to dashboard Cite

show abstract

“…The physiotherapist supervised treatments represent only a fraction of the total rehabilitation treatment; over 90% of the exercises are performed by patients in a home-based setting, also known as home exercise programs [12]. In this case, a physiotherapist instructs a patient on the type of physical exercises to be performed, and the patient is expected to perform the exercises, and continuously record their progress in a logbook.…”

Section: Physical Rehabilitationmentioning

confidence: 99%

“…The recent emergence of low cost non-intrusive motion capture sensors, such as Microsoft's Kinect, stimulated a wave of research and proliferation of applications in this domain [16,17]. KiReS (Kinect Rehabilitation System) [18] and VERA (Virtual Exercise Rehabilitation Assistant) [12] are examples of systems that employ a Kinect sensor for tracking a patient's movements, and provide a graphical interface with avatars showing the desired exercise as prescribed by the physiotherapist and the current motions of the patient. Such visualization tools are conducive toward improved adherence to the prescribed physical therapy by allowing review of the exercises by the patients and correcting the performance, as well as by providing a means for remote review of the patient's progress by the physiotherapist.…”

Section: Physical Rehabilitationmentioning

confidence: 99%

“…The existing clinical evaluation metrics, such as Fugl-Meyer assessment (FMA), Wolf motor function test (WMFT), and the ratio of optimal versus sub-optimal motion execution [12,18], were primarily designed for assessment performed by a physiotherapist. The development of performance evaluation metrics based on sensor captured motions in outpatient setting remains an open research topic.…”

Section: Physical Rehabilitationmentioning

confidence: 99%

“…With regards to the requirement for the mixing coefficients π l ≥ 0 and , the connections in MDN leading to the mixing coefficients are defined as soft max functions of the corresponding network output activations a l,m , i.e., (9) For the standard deviations, the requirement is satisfied by employing exponential functions of the network activations as follow (10) Lastly, the means are connected directly to the network activation by a linear projection layer (11) The output parameters of the network can be used for estimating the conditional average of a data sequence Y n given a sequence X n as (12) as well as the expected variance of the conditional density function as (13) …”

Section: Mixture Density Networkmentioning

confidence: 99%

See 2 more Smart Citations

Mathematical Modeling and Evaluation of Human Motions in Physical Therapy Using Mixture Density Neural Networks

Vakanski¹,

Ferguson²,

S³

2016

Physiother Rehabil

View full text Add to dashboard Cite

Objective-The objective of the proposed research is to develop a methodology for modeling and evaluation of human motions, which will potentially benefit patients undertaking a physical rehabilitation therapy (e.g., following a stroke or due to other medical conditions). The ultimate aim is to allow patients to perform home-based rehabilitation exercises using a sensory system for capturing the motions, where an algorithm will retrieve the trajectories of a patient's exercises, will perform data analysis by comparing the performed motions to a reference model of prescribed motions, and will send the analysis results to the patient's physician with recommendations for improvement.Methods-The modeling approach employs an artificial neural network, consisting of layers of recurrent neuron units and layers of neuron units for estimating a mixture density function over the spatio-temporal dependencies within the human motion sequences. Input data are sequences of motions related to a prescribed exercise by a physiotherapist to a patient, and recorded with a motion capture system. An autoencoder subnet is employed for reducing the dimensionality of captured sequences of human motions, complemented with a mixture density subnet for probabilistic modeling of the motion data using a mixture of Gaussian distributions.Results-The proposed neural network architecture produced a model for sets of human motions represented with a mixture of Gaussian density functions. The mean log-likelihood of observed sequences was employed as a performance metric in evaluating the consistency of a subject's performance relative to the reference dataset of motions. A publically available dataset of human motions captured with Microsoft Kinect was used for validation of the proposed method. Conclusion-The article presents a novel approach for modeling and evaluation of human motions with a potential application in home-based physical therapy and rehabilitation. The described approach employs the recent progress in the field of machine learning and neural networks in developing a parametric model of human motions, by exploiting the representational power of these algorithms to encode nonlinear input-output dependencies over long temporal horizons.

show abstract

AMIE: Automatic Monitoring of Indoor Exercises

Decroos

Schütte

Beéck

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Patients with sports-related injuries need to learn to perform rehabilitative exercises with correct movement patterns. Unfortunately, the feedback a physiotherapist can provide is limited by the number of physical therapy appointments. We study the feasibility of a system that automatically provides feedback on correct movement patterns to patients using a Microsoft Kinect camera and Machine Learning techniques. We discuss several challenges related to the Kinect's proprietary software, the Kinect data's heterogeneity, and the Kinect data's temporal component. We introduce AMIE, a machine learning pipeline that detects the exercise being performed, the exercise's correctness, and if applicable, the mistake that was made. To evaluate AMIE, ten participants were instructed to perform three types of typical rehabilitation exercises (squats, forward lunges and side lunges) demonstrating both correct movement patterns and frequent types of mistakes, while being recorded with a Kinect. AMIE detects the type of exercise almost perfectly with 99% accuracy and the type of mistake with 73% accuracy.

show abstract

Quality and Quantity of Rehabilitation Exercises Delivered By A 3-D Motion Controlled Camera: A Pilot Study

Cited by 41 publications

References 13 publications

A Data Set of Human Body Movements for Physical Rehabilitation Exercises

A Data Set of Human Body Movements for Physical Rehabilitation Exercises

Mathematical Modeling and Evaluation of Human Motions in Physical Therapy Using Mixture Density Neural Networks

AMIE: Automatic Monitoring of Indoor Exercises

Contact Info

Product

Resources

About