Biosignal-Based Human–Machine Interfaces for Assistance and Rehabilitation: A Survey

As a definition, Human–Machine Interface (HMI) enables a person to interact with a device. Starting from elementary equipment, the recent development of novel techniques and unobtrusive devices for biosignals monitoring paved the way for a new class of HMIs, which take such biosignals as inputs to control various applications. The current survey aims to review the large literature of the last two decades regarding biosignal-based HMIs for assistance and rehabilitation to outline state-of-the-art and identify emerging technologies and potential future research trends. PubMed and other databases were surveyed by using specific keywords. The found studies were further screened in three levels (title, abstract, full-text), and eventually, 144 journal papers and 37 conference papers were included. Four macrocategories were considered to classify the different biosignals used for HMI control: biopotential, muscle mechanical motion, body motion, and their combinations (hybrid systems). The HMIs were also classified according to their target application by considering six categories: prosthetic control, robotic control, virtual reality control, gesture recognition, communication, and smart environment control. An ever-growing number of publications has been observed over the last years. Most of the studies (about 67%) pertain to the assistive field, while 20% relate to rehabilitation and 13% to assistance and rehabilitation. A moderate increase can be observed in studies focusing on robotic control, prosthetic control, and gesture recognition in the last decade. In contrast, studies on the other targets experienced only a small increase. Biopotentials are no longer the leading control signals, and the use of muscle mechanical motion signals has experienced a considerable rise, especially in prosthetic control. Hybrid technologies are promising, as they could lead to higher performances. However, they also increase HMIs’ complexity, so their usefulness should be carefully evaluated for the specific application.

Dimensionality Reduction of Human Gait for Prosthetic Control

We seek to use dimensionality reduction to simplify the difficult task of controlling a lower limb prosthesis. Though many techniques for dimensionality reduction have been described, it is not clear which is the most appropriate for human gait data. In this study, we first compare how Principal Component Analysis (PCA) and an autoencoder on poses (Pose-AE) transform human kinematics data during flat ground and stair walking. Second, we compare the performance of PCA, Pose-AE and a new autoencoder trained on full human movement trajectories (Move-AE) in order to capture the time varying properties of gait. We compare these methods for both movement classification and identifying the individual. These are key capabilities for identifying useful data representations for prosthetic control. We first find that Pose-AE outperforms PCA on dimensionality reduction by achieving a higher Variance Accounted For (VAF) across flat ground walking data, stairs data, and undirected natural movements. We then find in our second task that Move-AE significantly outperforms both PCA and Pose-AE on movement classification and individual identification tasks. This suggests the autoencoder is more suitable than PCA for dimensionality reduction of human gait, and can be used to encode useful representations of entire movements to facilitate prosthetic control tasks.

Proof of concept for multiple nerve transfers to a single target muscle

Surgical nerve transfers are used to efficiently treat peripheral nerve injuries, neuromas, phantom limb pain or improve bionic prosthetic control. Commonly, one donor nerve is transferred to one target muscle. However, the transfer of multiple nerves onto a single target muscle may increase the number of muscle signals for myoelectric prosthetic control and facilitate the treatment of multiple neuromas. Currently, no experimental models are available for multiple nerve transfers to a common target muscle in the upper extremity. This study describes a novel experimental model to investigate the neurophysiological effects of peripheral double nerve transfers. For this purpose, we developed a forelimb model to enable tension-free transfer of one or two donor nerves in the upper extremity. Anatomic dissections were performed to design the double nerve transfer model (n=8). In 62 male Sprague-Dawley rats the ulnar nerve of the antebrachium alone (n=30) or together with the anterior interosseus nerve (n=32) was transferred to reinnervate the long head of the biceps brachii. Before neurotization, the motor branch to the biceps’ long head was transected at the motor entry point and resected up to its original branch to prevent auto-reinnervation. In all animals, coaptation of both nerves to the motor entry point could be performed tension-free. Mean duration of the procedure was 49 ± 13 min for the single nerve transfer and 78 ± 20 min for the double nerve transfer. Twelve weeks after surgery, muscle response to neurotomy, behavioral testing, retrograde labeling and structural analyses were performed to assess reinnervation. These analyses indicated that all nerves successfully reinnervated the target muscle. No aberrant reinnervation was observed by the originally innervating nerve. Our observations suggest a minimal burden for the animal with no signs of functional deficit in daily activities or auto-mutilation in both procedures. Furthermore, standard neurophysiological analyses for nerve and muscle regeneration were applicable. This newly developed nerve transfer model allows for the reliable and standardized investigation of neural and functional changes following the transfer of multiple donor nerves to one target muscle.

Double nerve transfer to a single target muscle: experimental model in the upper extremity

Surgical nerve transfers are used to efficiently treat peripheral nerve injuries, neuromas, phantom limb pain or improve bionic prosthetic control. Commonly, one donor nerve is transferred to one target muscle. However, the transfer of multiple nerves onto a single target muscle may increase the number of muscle signals for myoelectric prosthetic control and facilitate the treatment of multiple neuromas. Currently, no experimental models are available for multiple nerve transfers to a common target muscle in the upper extremity. This study describes a novel experimental model to investigate the neurophysiological effects of peripheral double nerve transfers. For this purpose, we developed a forelimb model to enable tension-free transfer of one or two donor nerves in the upper extremity. Anatomic dissections were performed to design the double nerve transfer model (n=8). In 62 male Sprague-Dawley rats the ulnar nerve of the antebrachium alone (n=30) or together with the anterior interosseus nerve (n=32) was transferred to reinnervate the long head of the biceps brachii. Before neurotization, the motor branch to the biceps' long head was transected at the motor entry point and resected up to its original branch to prevent auto-reinnervation. In all animals, coaptation of both nerves to the motor entry point could be performed tension-free. Mean duration of the procedure was 49 ± 13 min for the single nerve transfer and 78 ± 20 min for the double nerve transfer. Twelve weeks after surgery, muscle response to neurotomy, behavioral testing, retrograde labeling and structural analyses were performed to assess reinnervation. These analyses indicated that all nerves successfully reinnervated the target muscle. No aberrant reinnervation was observed by the originally innervating nerve. Our observations suggest a minimal burden for the animal with no signs of functional deficit in daily activities or auto-mutilation in both procedures. Furthermore, standard neurophysiological analyses for nerve and muscle regeneration were applicable. This newly developed nerve transfer model allows for the reliable and standardized investigation of neural and functional changes following the transfer of multiple donor nerves to one target muscle.

INTELLIGENT UPPER-LIMB PROSTHETIC CONTROL (iULP) WITH NOVEL FEATURE EXTRACTION METHOD FOR PATTERN RECOGNITION USING EMG

EMG signal-based pattern recognition (EMG-PR) techniques have gained lots of focus to develop myoelectric prosthesis. The performance of the prosthesis control-based applications mainly depends on extraction of eminent features with minimum neural information loss. The machine learning algorithms have a significant role to play for the development of Intelligent upper-limb prosthetic control (iULP) using EMG signal. This paper proposes a new technique of extracting the features known as advanced time derivative moments (ATDM) for effective pattern recognition of amputees. Four heterogeneous datasets have been used for testing and validation of the proposed technique. Out of the four datasets, three datasets have been taken from the standard NinaPro database and the fourth dataset comprises data collected from three amputees. The efficiency of ATDM features is examined with the help of Davies–Bouldin (DB) index for separability, classification accuracy and computational complexity. Further, it has been compared with similar work and the results reveal that ATDM features have excellent classification accuracy of 98.32% with relatively lower time complexity. The lower values of DB criteria prove the good separation of features belonging to various classes. The results are carried out on 2.6[Formula: see text]GHz Intel core i7 processor with MATLAB 2015a platform.