A Multimodal Framework Based on Integration of Cortical and Muscular Activities for Decoding Human Intentions About Lower Limb Motions

Cui, Chengkun; Bian, Gui‐Bin; Hou, Zhongsheng; Zhao, Jun; Zhou, Hao

doi:10.1109/tbcas.2017.2699189

Cited by 37 publications

(9 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By recognizing the patients' active motor abilities or movement intentions, the human-in-the-loop rehabilitation robotic systems are able to optimize participation and support the patients only as little as needed. 3 However, stroke patients' active involvements in the existing rehabilitation robotic systems are mostly considered from biomechanical and bioelectrical viewpoints, where the patients' active force/position signals 4,5 or electrical activities of the brain and the muscles 6,7 were recorded.…”

Section: Introductionmentioning

confidence: 99%

Anxiety detection and training task adaptation in robot-assisted active stroke rehabilitation

Gao

Pan

et al. 2018

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

In the therapist-centered rehabilitation program, the experienced therapists can observe emotional changes of stroke patients and make corresponding decisions on their intervention strategies. Likewise, robotic-assisted stroke rehabilitation systems will be more appreciated if they can also perceive emotional states of the stroke patients and enhance their engagements by exploring emotion-based dynamic difficulty adjustments. Nevertheless, few research have addressed this issue. A two-phase pilot study with anxiety as the target emotion state was conducted in this article. In phase I, the motor performances and the physiological responses to the stroke subject's anxiety with high, medium, and low intensities were statistically analyzed, and anxiety models with three intensities were offline developed using support vector machinebased classifiers. In phase II, anxiety-based closed-loop robot-aided training task adaptation and its impacts on patientrobot interaction engagements were explored. As a comparison, a performance-based robotic behavior adaptation was also implemented. Experimental results with 12 recruited stroke patients conducted on the Barrett WAM TM manipulator verified that the rehabilitation robot can implicitly recognize the anxiety intensities of the stroke survivors and the anxietybased real-time robotic behavior adaptation shows more engagements in the human-robot interactions.

show abstract

Section: Introductionmentioning

confidence: 99%

Anxiety detection and training task adaptation in robot-assisted active stroke rehabilitation

Gao

Pan

et al. 2018

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

show abstract

“…Researchers used statistical methods and machine learning approaches to evaluate the variations in gait and classify the gait features of post-stroke patients and healthy adults. C. Cui et al demonstrated multi-modal physiological features (EMG, motion, and ground reaction force) and machine learning algorithms to discriminate between post-stroke and healthy gait [ 32 , 60 ]. Park et al demonstrated the prediction of stroke-impaired gait using the ground reaction force and acceleration data through a machine learning approach [ 5 , 15 ].…”

Section: Discussionmentioning

confidence: 99%

Prediction of Myoelectric Biomarkers in Post-Stroke Gait

Hussain

Park

2021

Sensors

View full text Add to dashboard Cite

Electromyography (EMG) is sensitive to neuromuscular changes resulting from ischemic stroke and is considered a potential predictive tool of post-stroke gait and rehabilitation management. This study aimed to evaluate the potential myoelectric biomarkers for the classification of stroke-impaired muscular activity of the stroke patient group and the muscular activity of the control healthy adult group. We also proposed an EMG-based gait monitoring system consisting of a portable EMG device, cloud-based data processing, data analytics, and a health advisor service. This system was investigated with 48 stroke patients (mean age 70.6 years, 65% male) admitted into the emergency unit of a hospital and 75 healthy elderly volunteers (mean age 76.3 years, 32% male). EMG was recorded during walking using the portable device at two muscle positions: the bicep femoris muscle and the lateral gastrocnemius muscle of both lower limbs. The statistical result showed that the mean power frequency (MNF), median power frequency (MDF), peak power frequency (PKF), and mean power (MNP) of the stroke group differed significantly from those of the healthy control group. In the machine learning analysis, the neural network model showed the highest classification performance (precision: 88%, specificity: 89%, accuracy: 80%) using the training dataset and highest classification performance (precision: 72%, specificity: 74%, accuracy: 65%) using the testing dataset. This study will be helpful to understand stroke-impaired gait changes and decide post-stroke rehabilitation.

show abstract

“…Contingent visual and proprioceptive feedback about the user's EEG and EMG activity is provided in the form of velocity modulation during functional task training. Participants started the real-time operation task with their paretic arm and hand relaxed in a comfortable rest position to reach one of the three targets around the workspace ( Fig.21(a)-(b)), while supinating the wrist and opening their hands [181,182]. It helped the patients accomplish complicated target task with the EEG-EMG biofeedback system and enhance the motion ability of patients.…”

Section: Eeg-emg Biofeedback To Human Bodiesmentioning

confidence: 99%

Soft human–machine interfaces: design, sensing and stimulation

Dong

Wang

Zhou

et al. 2018

Int J Intell Robot Appl

View full text Add to dashboard Cite

Human-machine interfaces (HMIs) are widely studied to understand the human biomechanics and/or physiology and the interaction between humans and machines/robots. The conventional rigid or invasive HMIs that record/send information from/to human bodies have significant disadvantages in practice for longterm, portable, and comfortable usages. To better adapt to natural soft skins, soft HMIs have been designed to deform into arbitrary shapes, and their bendable, stretchable, compressible and twistable properties offer a huge potential in future personalized applications. This paper presents a survey on various soft HMIs in terms of design, sensing, stimulation as well as their applications. Specifically, tactile / motion / bio-potential sensors are categorized for recording various data from human bodies, while stimulators are discussed for information feedback and motion activation to human bodies. It is anticipated that soft HMIs will promote the interaction among humans, machines/robots and environment to achieve desired coexisting-cooperativecognitive function in a robot system, named as Tri-Co Robot, for the human-centered applications, such as rehabilitation, medical monitoring and human-robot cooperation.

show abstract

A Multimodal Framework Based on Integration of Cortical and Muscular Activities for Decoding Human Intentions About Lower Limb Motions

Cited by 37 publications

References 36 publications

Anxiety detection and training task adaptation in robot-assisted active stroke rehabilitation

Anxiety detection and training task adaptation in robot-assisted active stroke rehabilitation

Prediction of Myoelectric Biomarkers in Post-Stroke Gait

Soft human–machine interfaces: design, sensing and stimulation

Contact Info

Product

Resources

About