Design and Analysis of Cloud Upper Limb Rehabilitation System Based on Motion Tracking for Post-Stroke Patients

Abstract

In order to improve the convenience and practicability of home rehabilitation training for post-stroke patients, this paper presents a cloud-based upper limb rehabilitation system based on motion tracking. A 3-dimensional reachable workspace virtual game (3D-RWVG) was developed to achieve meaningful home rehabilitation training. Five movements were selected as the criteria for rehabilitation assessment. Analysis was undertaken of the upper limb performance parameters: relative surface area (RSA), mean velocity (MV), logarithm of dimensionless jerk (LJ) and logarithm of curvature (LC). A two-headed convolutional neural network (TCNN) model was established for the assessment. The experiment was carried out in the hospital. The results show that the RSA, MV, LC and LJ could reflect the upper limb motor function intuitively from the graphs. The accuracy of the TCNN models is 92.6%, 80%, 89.5%, 85.1% and 87.5%, respectively. A therapist could check patient training and assessment information through the cloud database and make a diagnosis. The system can realize home rehabilitation training and assessment without the supervision of a therapist, and has the potential to become an effective home rehabilitation system.

Serious Gaming Technology in Upper Extremity Rehabilitation: Scoping Review

“…It is worth noting that several studies monitored other kinematic indicators of the patient’s health condition that are not included in the game target classes for describing the patient’s overall improvement [ 21 , 68 , 124 , 126 , 128 , 135 , 137 , 164 ]. Specifically, five studies [ 68 , 124 , 128 , 137 , 164 ] referred to the smoothness of the hand movement, or hand steadiness (jerk), during therapy sessions as the main feature. This jerk behavior is mainly described as abrupt changes in the direction of the hand’s motion, and the way it is calculated may slightly differ from one study to another regarding the mathematical procedure employed.…”

“…Kinect seems to be the most preferred sensor for capturing body parts and following their movement in space, which was used by 15.4% (26/169) of the studies included in the review. Some of the studies used only the Kinect sensor for their systems [26,[62][63][64][65][66][67][68][69][70][71][72][73], whereas others combined it with biosignal capturing devices such as electromyogram (EMG) [24,41,74,75] or a sensing jacket [52] to gain better control of the user's movement for the final goal (ie, rehabilitation). In addition, some studies have used Kinect combined with gaming devices such as VR headsets [76] and a Wii balance board [77] or other devices such as goniometers [78][79][80], Tyromotion Timo plate [77], Xsen 3D sensor [81], body markers [82], and a customized haptic glove [83].…”

Convolutional neural network in upper limb functional motion analysis after stroke

“…This type of research can contribute to the development of an objective tool for qualification of the patient for rehabilitation and gives the opportunity to monitor rehabilitation progress and also enables to program task-based rehabilitation (Bai, Song & Li, 2019). On the other hand it contributes to the identification of the most sensitive places in the kinematic chain, which are the most suitable for sensors placement.…”

“…In Panwar et al (2019), the effective classification of three upper arm movements is presented. The ANN methods were used to assess rehabilitation based on Cao et al (2019), assess the progress of rehabilitation under the influence of a computer game (Bai, Song & Li, 2019) and analysis of the myoelectric signal during movement of upper limbs (Mukhopadhyay & Samui, 2020).…”

Design and Analysis of a Wearable Upper Limb Rehabilitation Robot with Characteristics of Tension Mechanism

“…In addition, the pneumatic muscle is used as a driver to realize four degrees of freedom active auxiliary motion RUPERT robot [11], hydraulic drive robot LIMPACT [12], suspended rope drive robot CAREX [13]. After that, researchers developed and designed the upper limb rehabilitation robot based on pneumatic muscle drive, unpowered upper limb rehabilitation robot, hybrid drive upper limb rehabilitation robot and under drive exoskeleton upper limb rehabilitation robot [14][15][16][17][18][19][20][21][22]. The exoskeleton rehabilitation robot solves the problem of controlling the motion amplitude and moment of each joint of human body in the process of rehabilitation training, and overcomes the disadvantage that the end guided rehabilitation robot can only perform simple rehabilitation training (linear motion or circular motion) with small motion amplitude.…”