article · Bioengineering
Stroke often causes long-term physical complications such as paresis and hemiparesis, impairing hand mobility. To support recovery, a wearable motorised rehabilitation glove has been developed for use both at home and in clinical settings. Built with soft materials and offering a battery life of four to five hours, the device trains individual or grouped fingers using assistive force generated by linear integrated actuators. The device operates on the principles of mirror therapy: four surface electromyography sensors gather muscle signals from the unaffected hand, which are interpreted by deep learning algorithms to direct the glove on the affected hand. Testing on ten distinct hand gestures showed an overall classification accuracy of 90.89 per cent using the InceptionTime algorithm, successfully translating healthy hand movements into targeted rehabilitative assistance.
Stroke-induced hand impairment creates major physical and social challenges that often require prolonged therapy. Automating mirror therapy through a wearable glove driven by muscle signals enables patients to carry out guided finger exercises independently. This approach offers a practical way to expand access to rehabilitation, reducing dependency on continuous direct supervision in both healthcare facilities and domestic settings.
The system represents an applied medical device application for stroke survivors and physical therapists. With a lightweight, soft construction and a four- to five-hour battery life, it is suited for home and clinical therapy products. The system is at an applied and tested prototype stage, having demonstrated mechanical actuation and 90.89 per cent gesture recognition accuracy, though clinical validation trials are not reported.
AI-generated from the published abstract. Always read the original work before citing.
Stroke is one of the most prevalent health issues that people face today, causing long-term complications such as paresis, hemiparesis, and aphasia. These conditions significantly impact a patient's physical abilities and cause financial and social hardships. In order to address these challenges, this paper presents a groundbreaking solution-a wearable rehabilitation glove. This motorized glove is designed to provide comfortable and effective rehabilitation for patients with paresis. Its unique soft materials and compact size make it easy to use in clinical settings and at home. The glove can train each finger individually and all fingers together, using assistive force generated by advanced linear integrated actuators controlled by sEMG signals. The glove is also durable and long-lasting, with 4-5 h of battery life. The wearable motorized glove is worn on the affected hand to provide assistive force during rehabilitation training. The key to this glove's effectiveness is its ability to perform the classified hand gestures acquired from the non-affected hand by integrating four sEMG sensors and a deep learning algorithm (the 1D-CNN algorithm and the InceptionTime algorithm). The InceptionTime algorithm classified ten hand gestures' sEMG signals with an accuracy of 91.60% and 90.09% in the training and verification sets, respectively. The overall accuracy was 90.89%. It showed potential as a tool for developing effective hand gesture recognition systems. The classified hand gestures can be used as a control command for the motorized wearable glove placed on the affected hand, allowing it to mimic the movements of the non-affected hand. This innovative technology performs rehabilitation exercises based on the theory of mirror therapy and task-oriented therapy. Overall, this wearable rehabilitation glove represents a significant step forward in stroke rehabilitation, offering a practical and effective solution to help patients recover from stroke's physical, financial, and social impact.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/bioengineering10050557
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
