[ARTICLE] An Evidence-Based Intelligent Method for Upper-Limb Motor Assessment via a VR Training System on Stroke Rehabilitation – Full Text

Abstract

Recently, virtual-reality (VR) has been an emerging technology, to this regard, it is widely employed by therapists to provide rich training tasks for the purpose of motor rehabilitation in clinics. Meanwhile, along with the progress of sensing technologies as means for the interaction with virtual environment, a large amount of data, such as motor trajectory, foot pressure or electromyography, is measured via VR-based motor training tasks and is considered as important clues for functional evaluations. However, very few study thoroughly applied the sensor-based data for motor assessment, instead, evaluation scales, such as TEMPA or Fugl-Meyer, were highly relied. In this study, a VR upper-limb motor training system was proposed for stroke rehabilitation. Clinical trials with 22 stroke patients were performed to exanimate the effectiveness of the propose VR system. Moreover, a variety of motor indicators derived via motion trajectory were proposed. Further, integrating multi-model data, such as motion trajectory, task performance and evaluation scales, machine-learning method was applied to develop evidence-based assessment models in order to evaluate upper-limb motor function. The results indicated that the proposed VR system was significantly effective for motor rehabilitation. Also, a few motor indicators were found significantly different between pre and post trials and were highly correlated with the evaluation scales. Finally, with the fusion of multi-model data, the accuracy rate of machine-learning assessment model was up to 92.72% which revealed its great potential for clinical use.

A graphical abstract for An Evidence-based Intelligent Method for Upper-limb Motor Assessment via a VR Training System on Stroke Rehabilitation.

SECTION I.

Introduction

Stroke is one of the three leading causes of death in developed countries, accounting for about 10% of global death [1]. Stroke is the leading cause of death and adult disability in the country, and the main disability burden in middle- and high-income countries [2]. Traditional rehabilitation aims to stimulate the relevant nerve tissue of stroke patients through continuous motor training, thereby helping patients maintain the current strength of the body muscles, and restoring their ability for daily life as much as possible [3]–[4][5][6]. Moreover, it assesses the rehabilitation effects with evaluation scale. However, long-term motor training in regard to rehabilitation is boring and lacks real-time feedback. Further, mainstream evaluation scales, like FMA, WMFT, TEMPA, are subjective that require experienced therapists in assessing rehabilitation, which consumes a large amount of time and medical resources.

VR is a computer-based technology that allows users to interact with the simulated environments through multiple sensations and to have “real-time” feedback. Specifically, VR is able to generate a battery of training tasks targeting a variety of rehabilitation goals in the therapy. As a result, a large number of studies have been conducted on the impact of VR technology on motor rehabilitation [7]–[8][9][10][11][12][13]. Also, home-based VR motor training systems were proposed [14]–[15][16][17]. Further, a variety of gamed-based commercial devices, similar to VR characteristics, were promoted [18]–[19][20][21][22][23][24][25]. Results found that VR technology has significant effects on stroke rehabilitation training [26]–[27][28][29][30]. Moreover, the application of VR technology to stroke rehabilitation training can make the boring training process entertaining, thereby reducing the psychological burden of patients, and maintaining their long-term participation enthusiasm [31], [32]. Also, it can highly handle the situation in which patients are unwilling to cooperate with traditional rehabilitation therapy [33]. The patient’s training goals can also be adjusted according to physical conditions [34].

However, the efficacy of previous VR training systems were mostly examined by evaluation scales [35]–[36][37][38], in spite that VR training systems were able to collect a huge amount of sensing data, such as motion trajectory, foot pressure or electromyography, which is considered as a kind of objective data. In a number of studies, the VR system was only used for motor training, and the objective training data collected by the system was not used as the basis for evaluation. The evaluation scale is mainly scored by the therapist, therefore, the data is considered as a kind of subjective data. Even though some studies [39]–[40][41][42][43] have intended to perform further analysis on sensing data in order to derive motor indicators to interpret the progress of motor functions, they did not discuss the correlation between proposed motor indicators and evaluation scales, lacking reliability and validity.

With the improvement of the computing power of computers, machine learning has been developed rapidly in recent years and is widely used in data mining, computer vision, natural language processing, etc. In medical diagnosis, some researchers use machine learning to analyze medical images and detect the patient’s status [44]; some researchers use supervised machine learning algorithms to classify patient movement data. Thereby judging the therapeutic effect of the diagnosis, with high accuracy [45]–[46][47][48][49]. However, these studies didn’t include evaluation scales in the machine learning model, instead, sensing data was solely used. Therefore, the proposed machine model lacked clinical references and wasn’t convincible from therapist perspective.

To address issues mentioned above, the research is composed of designing motor indicators based on VR data, exploring the scientific correlation between proposed motor indicators and evaluation scale, establishing evidence-based grading standards based on multi-dimensional evaluation scale data, and applying machine learning to establish a new data-driven assessment model.[…]

Continue

[Abstract] A Portable Device for Hand Rehabilitation with Force Cognition: Design, Interaction and Experiment

Abstract

Introducing interactive system into portable robots for hand rehabilitation has always been a crucial topic. Moreover, hand rehabilitation with force cognition can make patients participate actively and improve rehabilitation effect. In this paper, we design a portable robotic device with interactive system for patients to rehabilitate with force cognition. Firstly, an exoskeleton glove is designed with a compact mechanical structure which is controlled by a real-time feedback system. The portable device allows patients to rehabilitate not only in hospital. Next, an interactive system including virtual environment and force cognition is introduced to detect the hand motion and collision. At last, clinical tests of our portable device is carried out with 9 subjects after tendon injury to show the effective assistance with our device.

Source

[Abstract] Development of 6 DOF Upper-limb Patient Simulator for Hands-on Rehabilitation Education

Abstract

In rehabilitation treatment, the physiotherapy manual diagnostic method is the most affordable to cure spasticity disorders caused by neural impairments. The proficiency of the rehabilitation therapist is critical to maximizing the treatment effect; therefore the therapist’s training focuses on physical hands-on practice. However, realizing a hands-on training to untrained therapists is not readily allowed because the joint’s spasticity in patients is not standardized quantitatively and the unstable supply of spasticity patients with various rigidness for hands-on training. Therefore, the new 6-DOFs upper-limb patient simulator for hands-on rehabilitation education in this study is developed for use in supporting standardized quantitative levels to untrained therapists. Additionally, the new simulator includes a function of manual diagnosis to embody various spastic rigidity of patients’ joint. For the verification of the proposed system, both trained and untrained therapists evaluate how well the joints’ spasticity of the developed robotic simulator and human patients are similar. Consequently, the developed robotic simulator is validated to be effective for rehabilitation therapy education.

Source

[Abstract + References] Automated Voluntary Finger Lifting Rehabilitation Support Device for Hemiplegic Patients to Use at Home

Abstract

We have been proposing a robotic finger rehabilitation support device for hemiplegic patients that can be used at home. This device instructs a patient to lift a finger voluntarily and provides assistance when the patient is impossible to lift. In previous studies, we have shown an automated evaluation method which monitors the level of involuntary finger movement. However, the detailed procedure of finger rehabilitation has not been clarified. In this paper, we show a practical procedure of finger rehabilitation as well as a hardware design of the device. We also discuss safety issues during finger lift assistance. Our design limits the speed of finger lift so that it avoids unwanted contraction of finger muscles by stretch reflex. Also, the angle of finger lift is limited in our design so that it will not exceed the maximum excursion of an MP joint.

References

1.J. D. Schaechter, “Motor rehabilitation and brain plasticity after hemiparetic stroke”, Progress in Neurobiology, vol. 73, no. 1, pp. 61-72, May 2004.Show Context CrossRef  Google Scholar 2.J. W. Krakauer, “Motor learning: its relevance to stroke recovery and neurorehabilitation”, Current Opinion in Neurology, vol. 19, no. 1, pp. 84, Feb. 2006.Show Context CrossRef  Google Scholar 3.S. Balasubramanian, J. Klein and E. Burdet, “Robot-assisted rehabilitation of hand function”, Current Opinion in Neurology, vol. 23, no. 6, pp. 661-670, Dec. 2010.Show Context CrossRef  Google Scholar 4.L. Bishop, A. M. Gordon and H. Kim, “Hand Robotic Therapy in Children with Hemiparesis: A Pilot Study”, American Journal of Physical Medicine & Rehabilitation, vol. 96, no. 1, pp. 1-7, Jan. 2017.Show Context CrossRef  Google Scholar 5.O. Sandoval-Gonzalez et al., “Design and Development of a Hand Exoskeleton Robot for Active and Passive Rehabilitation”, International Journal of Advanced Robotic Systems, vol. 13, no. 66, pp. 1-12, 2016.Show Context CrossRef  Google Scholar 6.P. Polygerinos, K. C. Galloway, E. Savage, M. Herman, K. O. Donnell and C. J. Walsh, “Soft robotic glove for hand rehabilitation and task specific training”, 2015 IEEE International Conference on Robotics and Automation (ICRA), pp. 2913-2919, 2015.Show Context View Article Full Text: PDF (3804KB) Google Scholar 7.D. Guilherme, N. DeSouza et al., “A pediatric robotic thumb exoskeleton for at-home rehabilitation: The isolated orthosis for thumb actuation (IOTA)”, International Journal of Intelligent Computing and Cybernetics, vol. 7, no. 3, pp. 233-252, 2014.Show Context Google Scholar 8.Y. Furudate, N. Onuki, K. Chiba, Y. Ishida and S. Mikami, “Automated Evaluation of Hand Motor Function Recovery by Using Finger Pressure Sensing Device for Home Rehabilitation”, IEEE BIBE 2018, pp. 207-214, 2018.Show Context View Article Full Text: PDF (500KB) Google Scholar 9.K. Yamamoto, Y. Furudate, K. Chiba, Y. Ishida and S. Mikami, “Home Robotic Device for Rehabilitation of Finger Movement of Hemiplegia Patients”, 2017 IEEE/SICE International Symposium on System Integration, pp. TuE1.3:1-6, 2017.Show Context View Article Full Text: PDF (1305KB) Google Scholar 10.Y. Furudate, K. Yamamoto, K. Chiba, Y. Ishida and S. Mikami, “Quantification Method of Motor Function Recovery of Fingers by Using the Device for Home Rehabilitation”, 2017 IEEE 39th Annual International Conference of the Engineering in Medicine and Biology Society, pp. 3872-3875, 2017.Show Context View Article Full Text: PDF (804KB) Google Scholar 11.K. Chiba et al., “Robotic Finger Rehabilitation Support Device for Home Use – An Analysis of the Effect of Finger Rehabilitation for the Upper Limb Function Recovery”, International Journal of Mechanical Engineering and Robotics Research, vol. 5, no. 4, pp. 288-294, Oct. 2016.Show Context CrossRef  Google Scholar 12.“Joint motion: method of measuring and recording”, Churchill Livingstone, 1965.Show Context Google Scholar 13.S. Werle, J. Goldhahn, S. Drerup, B. R. Simmen, H. Sprott and D. B. Herren, “Age- and Gender-Specific Normative Data of Grip and Pinch Strength in a Healthy Adult Swiss Population”, J Hand Surg Eur Vol, vol. 34, no. 1, pp. 76-84, Feb. 2009.Show Context CrossRef  Google Scholar 14.E. L. Altschuler et al., “Rehabilitation of hemiparesis after stroke with a mirror”, The Lancet, vol. 353, no. 9169, pp. 2035-2036, 1999.Show Context CrossRef  Google Scholar 

Source

[Abstract] Development of a Home-based Hand Rehabilitation Training and Compensation Feedback System

Abstract

Stroke survivors often show a limited recovery in the hand function even after the recovery period (3-6 months after stroke) and at-home hand rehabilitation is common due to the long-term nature of hand rehabilitation and the limited medical resources. We designed a home-based hand rehabilitation training and compensation feedback system. A low-cost simple orthosis glove, a set of hand rehabilitation training games and a compensation detection and feedback module were designed and developed in this system. A preliminary test was carried out on the system and the results showed that the training section (the orthosis glove and the hand rehabilitation training games) of the system was friendly to the subjects and the subjects were more receptive to the system and the compensation detection and feedback module had a promising performance. This system can not only provide high intensity and incentive hand rehabilitation training, but also guide the stroke patients to correct wrong upper body postures during the training process, which can achieve better rehabilitation results. The system has the potential to become an effective home-based hand rehabilitation training and compensation feedback system.

Source

[ARTICLE] Activity-based training with the Myosuit: a safety and feasibility study across diverse gait disorders – Full Text

Abstract

Background

Physical activity is a recommended part of treatment for numerous neurological and neuromuscular disorders. Yet, many individuals with limited mobility are not able to meet the recommended activity levels. Lightweight, wearable robots like the Myosuit promise to facilitate functional ambulation and thereby physical activity. However, there is limited evidence of the safety and feasibility of training with such devices.

Methods

Twelve participants with diverse motor disorders and the ability to walk for at least 10 m were enrolled in this uncontrolled case series study. The study protocol included five training sessions with a net training time of 45 min each. Primary outcomes were the feasibility of engaging in training with the Myosuit, the occurrence of adverse events, and participant retention. As secondary outcomes, we analyzed the walking speed using the 10-m Walk Test (10MWT) and for three participants, walking endurance using the 2-min Walk Tests.

Results

Eight out of 12 participants completed the entire study protocol. Three participants withdrew from the study or were excluded for reasons unrelated to the study. One participant withdrew because of an unsafe feeling when walking with the Myosuit. No adverse events occurred during the study period for any of the participants and all scheduled trainings were completed. For five out of the eight participants that completed the full study, the walking speed when using the Myosuit was higher than to their baseline walking speed.

Conclusions

Activity-based training with the Myosuit appears to be safe, feasible, and well-tolerated by individuals with diverse motor disorders.

Background

Physical inactivity has been identified as the fourth leading risk factor for global mortality, only surpassed by hypertension, tobacco use, and hyperglycemia. To contain the risks associated with physical inactivity, the World Health Organization recommends that all adults engage in moderate intensity physical activity for at least 150 min each week [1].

Physical activity is also a recommended part of treatment for stroke patients [2], and for patients with incomplete spinal cord injury (SCI) [3], inherited neuropathies such Charcot–Marie–Tooth disease [4], heart failure [5], or chronic obstructive pulmonary disease [6]. These wide-ranging recommendations reflect the consistent association between increased physical activity and improved health-related quality of life (e.g. [7,8,9].).

In spite of the evident health benefits of physical activity, a large proportion of elderly individuals and individuals with limited mobility do not meet the recommended dose of physical activity in their daily lives [10]. In many of these cases, neurological, neuromuscular, or cardiovascular deficits prevent individuals from reaching moderate intensity levels during exercise. In some cases, they prohibit any voluntary exercise altogether.

To address this problem, various technological solutions like full-leg, rigid exoskeletons have been developed to assist overground mobility (e.g. [11,12,13,14].). The safety and feasibility of gait training with mobile exoskeletons has been evaluated in several longitudinal training studies for individuals with spinal cord injury [15,16,17] and hemiparesis following stroke [18, 19]. Rigid exoskeletons largely substitute the ambulatory function of severely affected or completely paralyzed individuals and enable them to walk. Electric motors are used to provide large assistive torques to the users’ leg joints via rigid linkages. This allows exoskeletons to support the majority of the users’ weight and advance the users’ legs without a major voluntary contribution from the leg muscles.

The typically large masses of mobile rigid exoskeletons increase limb inertia and thereby hinder walking at higher speeds. The highest walking speed achieved in previous training studies [15,16,17,18,19] was 0.67 m/s, while most speeds were as low as 0.1 m/s to 0.4 m/s. This is well below the speeds required to support individuals with residual mobility during moderate intensity exercise.

To assist this more capable section of the population, more lightweight wearable robots (also known as “exosuits”, “exomuscles” or “dermoskeletons”) have been proposed [20,21,22,23,24]. Unlike exoskeletons that act on all leg joints, these devices allow for—and require—the active participation of the user, and can (partially) assist walking over a larger range of speeds [20, 25]. Thereby, such wearable robots can provide assistance as needed for functional ambulation [25] while simultaneously modulating the cardiovascular load of their users according to exercise recommendations. For example, a soft robotic exosuit unilaterally acting on one ankle joint was shown to reduce the energy expenditure and interlimb asymmetry of individuals with hemiparesis following a stroke during walking at 0.5 to 1.3 m/s [20]. In previous work from our group, we demonstrated that a soft wearable robot actively supporting hip and knee extension, the Myosuit, enabled an individual with incomplete SCI to walk substantially faster when assisted [25]. More recently, we showed that this functional improvement also translates to an increase in exercise intensity and a momentary reduction of the energetic cost of transport [26]. In larger longitudinal studies, training with wearable robots acting on the hip joint was shown to result in an intrinsic reduction of the cost of transport for elderly individuals [23] and individuals following stroke [24].

Further work [27,28,29] has primarily focused on the functional effects of robotic movement assistance. A lightweight wearable robot that assists knee flexion and extension reduced momentary movement performance, but elicited larger intrinsic improvements after 2 weeks of exercise training than when training without the device in users with multiple sclerosis [27]. In larger randomized controlled trials with individuals post-stroke, training with a robotic knee brace was shown to result in only modest functional benefits that were comparable to the control group [28], while training with a hip exoskeleton resulted in more pronounced functional benefits [29].

While it is hard to synthesize common trends out of the limited studies available, it appears that the most pronounced improvements were so far achieved with devices that targeted a very specific motor deficit (e.g. ankle assistance [20] or hip assistance [24, 29] improved hemiparetic gait for individuals after stroke). Other findings with devices that bear promise to work for more diverse gait disorders were based on single-participant observations [22, 25, 26], and it remains unclear to what extend these results generalize to larger populations.

There is limited evidence of how a single wearable robot could effectively assist individuals with diverse neuromuscular and neurological gait disorders during exercise training. Such a wider applicability would be highly desirable considering that in everyday clinical life, patients present with a wide array of different conditions and functional deficits [30].

We believe that the Myosuit is a promising device to assist the training of individuals with diverse gait disorders. The Myosuit assists walking in essential functions [31] by supporting the user’s bodyweight from weight acceptance through mid-stance and assisting swing initiation from terminal stance into early swing (see Fig. 1b). By working in parallel with the user’s hip and knee extensor muscles and exploiting natural synergies [32], the Myosuit supports the muscles with the largest contribution to bodyweight support in that phase of walking [33]. Training with the Myosuit can extend beyond step training and into areas of balance, strength, and coordination.

a Schematic drawing of the Myosuit. On each leg, an actuated cable is routed across the hip and knee joints and driven by electric motors contained in a backpack unit. b The motors tension the cables to apply forces assisting hip and knee extension against gravity during parts of the stance phase of walking. From terminal stance into swing, the springs assist hip flexion. c Exemplary picture of training with the Myosuit

Continue

[Abstract] Attention Enhancement and Motion Assistance for Virtual Reality-Mediated Upper-limb Rehabilitation

Abstract

Dysfunctions of upper limbs caused by diseases such as stroke result in difficulties in conducting day-to-day activities. Studies show that rehabilitation training using virtual reality games is helpful for patients to restore arm functions. It has been found that ensuring active patient participation and effort devoting in the process is very important to obtain better training results. This paper introduces a method to help patients increase their engagement and provide motion assistance in virtual reali-ty-mediated upper-limb rehabilitation training. Attention en-hancement and motion assistance is achieved through an illusion of virtual forces created by altering the drag speed between the cursor and the object presented on a screen to the patient as the only feedback. We present two game forms using the proposed method, including a target-approaching game and a maze-following game. The results of evaluation experiments with human participants showed that the proposed method could provide path guidance that significantly improved path-following performance of users and required more involvement of the users when compared to playing the game without attention enhance-ment and motion assistance.

Source

[Abstract] Design and Implementation of An Interactive Hand Rehabilitation Training System Based on LabVIEW

Abstract

With the development of science and technology in multidisciplinary fields of automation control, rehabilitation medicine and robotics and the improvement of people’s living standards, medical rehabilitation robots are playing an increasingly important role in life. The traditional hand rehabilitation robots are exoskeleton rigid robots with complex structure and small fault tolerance. It is dangerous for the rehabilitation of human finger joints, while soft wearable hand rehabilitation robots have better safety and flexibility. For the rehabilitation needs of stroke fingers, a virtual online game of human-computer interaction is developed using LabVIEW and a soft wearable hand rehabilitation robot, in order to improve the initiative of patients in the process of active rehabilitation training and to increase the interest of patients in active rehabilitation training, which also improves the initiative of patients to participate in active rehabilitation training.

Source

[Abstract] Remote Monitoring of Physical Rehabilitation of Stroke Patients using IoT and Virtual Reality

Abstract

The statistics highlights that physical rehabilitation are required nowadays by increased number of people that are affected by motor impairments caused by accidents or aging. Among the most common causes of disability in adults are strokes or cerebral palsy. To reduce the costs preserving the quality of services new solutions based on current technologies in the area of physiotherapy are emerging. The remote monitoring of physical training sessions could facilitate for physicians and physical therapists’ information about training outcome that may be useful to personalize the exercises helping the patients to achieve better rehabilitation results in short period of time process. This research work aims to apply physical rehabilitation monitoring combining Virtual Reality serious games and Wearable Sensor Network to improve the patient engagement during physical rehabilitation and evaluate their evolution. Serious games based on different scenarios of Virtual Reality, allows a patient with motor difficulties to perform exercises in a highly interactive and non-intrusive way, using a set of wearable devices, contributing to their motivational process of rehabilitation. The system implementation, system validation and experimental results are included in the paper.

Source: https://ieeexplore.ieee.org/abstract/document/9183980

[Abstract + References] Multi-modal Intent Recognition Method for the Soft Hand Rehabilitation Exoskeleton

Abstract

Stroke has become the second most disabling disease in the world. Due to the intensive demand for physical therapists and the severe dependence on hospitals, the cost for the treatment of stroke patients is huge. As the most flexible limb of the human body, the hand faces more severe challenges, which has a much lower degree of recovery than the upper and lower limbs. In the face of these challenges, a new treatment, exoskeleton-based rehabilitation, has demonstrated new vitality. This paper proposes a novel design of the soft hand exoskeleton based on bionics and anatomy and the exoskeleton could help the users bend and extend their fingers, which would greatly improve the motor ability of stroke patients. Through the control of the six drive motors, the exoskeleton could achieve most of the hand’s freedom of training. At the same time, we propose a multi-modal intent recognition method based on machine vision and machine speech. Under specific rehabilitation training scenarios, both healthy subjects and patients could complete grasping tasks in the wearing of the exoskeleton, overcoming potential security risks caused by misidentification due to using the single-modal intent understanding method.

References

1. M. P. Lindsay, B. Norrving, R. L. Sacco, M. Brainin, W. Hacke, S. Martins, et al., “World stroke organization (wso): Global stroke fact sheet 2019”, 2019.CrossRef  Google Scholar 

2. [online] Available: http://www.sohu.com/a/306292195_243428. Show Context

3. K. B. Lee, S. H. Lim, K. H. Kim, K. J. Kim, Y. R. Kim, W. N. Chang, et al., “Six-month functional recovery of stroke patients: a multi-time-point study”, International journal of rehabilitation research. Internationale Zeitschrift fur Rehabilitationsforschung. Revue internationale de recherches de readaptation, vol. 38, no. 2, pp. 173, 2015. Show Context CrossRef  Google Scholar 

4. P. Polygerinos, S. Lyne, Z. Wang, L. F. Nicolini, B. Mosadegh, G. M. Whitesides, et al., “Towards a soft pneumatic glove for hand rehabilitation”, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1512-1517, 2013. Show Context View Article Full Text: PDF (1334KB) Google Scholar 

5. J. Yi, X. Chen and Z. Wang, “A three-dimensional- printed soft robotic glove with enhanced ergonomics and force capability”, IEEE Robotics and Automation Letters, vol. 3, no. 1, pp. 242-248, 2017. Show Context View Article Full Text: PDF (676KB) Google Scholar 

6. N. Ho, K. Tong, X. Hu, K. Fung, X. Wei, W. Rong, et al., “An emg-driven exoskeleton hand robotic training device on chronic stroke subjects: task training system for stroke rehabilitation”, 2011 IEEE international conference on rehabilitation robotics, pp. 1-5, 2011. Show Context View Article Full Text: PDF (848KB) Google Scholar 

7. S. Park, L. Weber, L. Bishop, J. Stein and M. Ciocarlie, “Design and development of effective transmission mechanisms on a tendon driven hand orthosis for stroke patients”, 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 2281-2287, 2018. Show Context View Article Full Text: PDF (2666KB) Google Scholar 

8. L. Gerez and M. Liarokapis, “An underactuated tendon-driven wearable exo-glove with a four-output differential mechanism”, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 6224-6228, 2019. Show Context View Article Full Text: PDF (3125KB) Google Scholar 

9. T. Bützer, J. Dittli, J. Lieber, H. J. van Hedel, A. Meyer-Heim, O. Lambercy, et al., “Pexo- a pediatric whole hand exoskeleton for grasping assistance in task-oriented training”, 2019 IEEE 16th International Conference on Rehabilitation Robotics (ICORR), pp. 108-114, 2019. Show Context View Article Full Text: PDF (1216KB) Google Scholar 

10. M. Mirakhorlo, N. Van Beek, M. Wesseling, H. Maas, H. Veeger and I. Jonkers, “A musculoskeletal model of the hand and wrist: model definition and evaluation”, Computer methods in biomechanics and biomedical engineering, vol. 21, no. 9, pp. 548-557, 2018. Show Context CrossRef  Google Scholar 

11. M. Suarez-Escobar and E. Rendon-Velez, “An overview of robotic/mechanical devices for post-stroke thumb rehabilitation”, Disability and Rehabilitation: Assistive Technology, vol. 13, no. 7, pp. 683-703, 2018. Show Context CrossRef  Google Scholar 

12. M. Li, Z. Liang, B. He, C.-G. Zhao, W. Yao, G. Xu, et al., “Attention-controlled assistive wrist rehabilitation using a low-cost eeg sensor”, IEEE Sensors Journal, vol. 19, no. 15, pp. 6497-6507, 2019. Show Context View Article Full Text: PDF (4401KB) Google Scholar 

13. D. Huggins-Daines, M. Kumar, A. Chan, A. W. Black, M. Ravishankar and A. I. Rudnicky, “Pocketsphinx: A free real-time continuous speech recognition system for hand-held devices”, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings, vol. 1, pp. I-I, 2006. Show Context View Article Full Text: PDF (89KB) Google Scholar 

14. J. Redmon, S. Divvala, R. Girshick and A. Farhadi, “You only look once: Unified real-time object detection”, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779-788, 2016. Show Context View Article Full Text: PDF (1742KB) Google Scholar 

Source: https://ieeexplore.ieee.org/abstract/document/9189174