Detection of the Intention to Grasp During Reaching in Stroke Using Inertial Sensing

Abstract

To support stroke survivors in activities of daily living, wearable soft-robotic gloves are being developed. An essential feature for use in daily life is detection of movement intent to trigger actuation without substantial delays. To increase efficacy, the intention to grasp should be detected as soon as possible, while other movements are not detected instead. Therefore, the possibilities to classify reach and grasp movements of stroke survivors, and to detect the intention of grasp movements, were investigated using inertial sensing. Hand and wrist movements of 10 stroke survivors were analyzed during reach and grasp movements using inertial sensing and a Support Vector Machine classifier. The highest mean accuracies of 96.8% and 83.3% were achieved for single-and multiuser classification respectively. Accuracies up to 90% were achieved when using 80% of the movement length, or even only 50% of the movement length after choosing the optimal kernel per person. This would allow for an earlier detection of 300-750ms, but at the expense of accuracy. In conclusion, inertial sensing combined with the Support Vector Machine classifier is a promising method for actuation of graspsupporting devices to aid stroke survivors in activities of daily living. Online implementation should be investigated in future research.

A Review of Hand Gesture Recognition Systems Based on Noninvasive Wearable Sensors

“…This setup is very time‐consuming and costly. [ 116 ] Therefore, advanced unsupervised or semisupervised ML algorithms that can automatically label new data for learning are needed for multimodal to decrease the time and cost of data labeling. [ 117 ]…”

Emerging Wearable Interfaces and Algorithms for Hand Gesture Recognition: A Survey

“…IMUs were placed on the back of the hand, ulnar styloid, and phalanges of fingers to classify the reach and grasp intention and to detect the grasp intention as soon as possible. This then triggered the orthosis to support the patient's grip strength [4]. Forearm sEMG-based intention detection has also been employed to control assistive exoskeletons or hand prostheses [43].…”

“…As the global population ages, the incidence of neurological diseases is causing increasing loss of hand function leading to decreased quality of life [1], [2]. Automated hand gesture recognition can be integrated with games to help assess rehabilitation progress with active engagement [3] or combined with orthoses [4] to support grasp strength. Similarly, upper extremity amputees often retain intention and neural motor control [5], and gesture recognition interfaces can decode human intention commands for prosthesis manipulation movement control [6] force control [7], enabling daily activities without caregivers.…”

Measurement of upper limb function in ALS: a structured review of current methods and future directions

“…Glove-based systems provide quantitative analysis of hand function, which can be used to guide rehabilitation and improve the patient’s recovery, [ 57 , 85 – 88 ]. However, these devices interfere with normal movement as they cover the hand and pose difficulties with respect to hygiene.…”