Recognition of Upper Limb Action Intention Based on IMU

Abstract

Using motion information of the upper limb to control the prosthetic hand has become a hotspot of current research. The operation of the prosthetic hand must also be coordinated with the user’s intention. Therefore, identifying action intention of the upper limb based on motion information of the upper limb is key to controlling the prosthetic hand. Since a wearable inertial sensor bears the advantages of small size, low cost, and little external environment interference, we employ an inertial sensor to collect angle and angular velocity data during movement of the upper limb. Aiming at the action classification for putting on socks, putting on shoes and tying shoelaces, this paper proposes a recognition model based on the Dynamic Time Warping (DTW) algorithm of the motion unit. Based on whether the upper limb is moving, the complete motion data are divided into several motion units. Considering the delay associated with controlling the prosthetic hand, this paper only performs feature extraction on the first motion unit and the second motion unit, and recognizes action on different classifiers. The experimental results reveal that the DTW algorithm based on motion unit bears a higher recognition rate and lower running time. The recognition rate reaches as high as 99.46%, and the average running time measures 8.027 ms. In order to enable the prosthetic hand to understand the grasping intention of the upper limb, this paper proposes a Generalized Regression Neural Network (GRNN) model based on 10-fold cross-validation. The motion state of the upper limb is subdivided, and the static state is used as the sign of controlling the prosthetic hand. This paper applies a 10-fold cross-validation method to train the neural network model to find the optimal smoothing parameter. In addition, the recognition performance of different neural networks is compared. The experimental results show that the GRNN model based on 10-fold cross-validation exhibits a high accuracy rate, capable of reaching 98.28%. Finally, the two algorithms proposed in this paper are implemented in an experiment of using the prosthetic hand to reproduce an action, and the feasibility and practicability of the algorithm are verified by experiment.

Integrated Sensor Fusion and Multi-Modal Hierarchical Neural Network for Activity Recognition in Lower Limb Prosthetics

“…Existing systems often exhibit limitations regarding accuracy, adaptability, then robustness. Challenges arise from complexity for capturing nuanced human movements, variations in environmental conditions, and the dynamic nature of daily activities [5,11]. Conventional methods often struggle to discern between normal activities and genuine fall events, leading to false alarms or missed detections [20].…”

“…This paper delves into the transformative landscape of activity recognition in lower limb prosthetics, where technological strides intersect with the human experience, reshaping the possibilities for those seeking enhanced mobility [3]. The rising incidence of lower limb amputations, attributed to diverse factors such as chronic diseases and accidents, has underscored the need for prosthetic solutions that go beyond mere functionality [4,5]. Restoring a sense of natural, intuitive movement has become a paramount goal, pushing researchers to explore novel avenues in the field of activity recognition [6].…”

Upper-Limb Kinematic Behavior and Performance Fatigability of Elderly Participants Performing an Isometric Task: A Quasi-Experimental Study

“…Research on the application of IMUs for upper-limb movement analysis has grown in recent years, though their application is still at an early development stage and is especially targeted to the validation of specific protocols and proof-of-concept systems [26,34,36] and to movement analysis and characterization in specific clinical conditions [31,37]. As far as we are aware, there are only a few studies that have used IMUs to assess performance fatigability directly or indirectly during upper-limb [38,39] tasks, and none, during isometric tasks performed by elderly populations.…”

The Middleware for an Exoskeleton Assisting Upper Limb Movement

“…The primary one is to support the patient's motion. The control of such a device is frequently implemented based on force sensors [36,37] and position tracking is based on accelerometers and gyroscopes [38]. This feature is useful for conditions that impair the patient's ability to move.…”