Control of hand prostheses using peripheral information

An efficient approach for EMG controlled pattern recognition system based on MUAP identification and segregation

An Electromyography (EMG) based pattern recognition system constitutes various steps of signal processing and control engineering from signal acquisition to real-time control. Efficient control of external devices largely depends on the signal processing steps executed before the final output. This work presents a new approach to signal processing using Motor Unit Action Potential (MUAP) based signal decomposition and segmentation. An MUAP is a neurological response during muscle contraction. Due to the higher contact area of surface electrodes, MUAPs from multiple muscles are captured. An MUAP generated from a single muscle usually has identical waveshapes and similar discharging rates and usually lasts for 8-15 ms. These are known as primary MUAPs. The proposed algorithm identifies and uses the primary observed MUAPs for feature extraction and classification. Firstly, noise signals are eliminated by a determined noise margin, which also separates the active muscle movement signals. Next, a novel MUAP identification algorithm is implemented to detect the MUAP trains. Then, identified primary MUAPs are used to make segments with variable widths to extract feature vectors. Based on the correlation score of all the primary MUAPs, the segmentation is performed, which results in segmentation width varying from 110-200 ms. The achieved segmentation width is lesser than the conventional overlapping and non-overlapping methods - the proposed approach results in a 20 to 50% reduction in the segmentation width. Four different classifiers are tested during the machine learning stage to investigate the performance of the proposed approach. The obtained feature sets are then used to train the Linear Discriminant Analysis (LDA), K-Nearest Neighbor (kNN), Decision Tree (DT), and Random Forest (RF) classifiers. The classifiers are tested with precision, recall, F1 score, and accuracy. The kNN and DT classifiers performed better than the LDA and RF classifiers. The maximum precision and recall are 100% while the maximum achieved accuracy is 98.56%. The comparative results show higher accuracy even at lower segmentation widths than the conventional constant window scheme. The kNN and DT classifiers provide a 5% to 15% increment in accuracy compared to the constant window segmentation-based approach.

Perspectives, Challenges, and the Future of Biomedical Technology and Artificial Intelligence

Biomedical technologies are the compound of engineering principles and technologies used to diagnose, treat, monitor, and prevent illness [...]

An open-source toolbox for enhancing the assessment of muscle activation patterns during cyclical movements

Objective.The accurate temporal analysis of muscle activations is of great importance in several research areas spanning from the assessment of altered muscle activation patterns in orthopaedic and neurological patients to the monitoring of their motor rehabilitation. Several studies have highlighted the challenge of understanding and interpreting muscle activation patterns due to the high cycle-by-cycle variability of the sEMG data. This makes it difficult to interpret results and to use sEMG signals in clinical practice. To overcome this limitation, this study aims at presenting a toolbox to help scientists easily characterize and assess muscle activation patterns during cyclical movements.Approach.CIMAP(Clustering for the Identification of Muscle Activation Patterns) is an open-source Python toolbox based on agglomerative hierarchical clustering that aims at characterizing muscle activation patterns during cyclical movements by grouping movement cycles showing similar muscle activity.Main results.From muscle activation intervals to the graphical representation of the agglomerative hierarchical clustering dendrograms, the proposed toolbox offers a complete analysis framework for enabling the assessment of muscle activation patterns. The toolbox can be flexibly modified to comply with the necessities of the scientist.CIMAPis addressed to scientists of any programming skill level working in different research areas such as biomedical engineering, robotics, sports, clinics, biomechanics, and neuroscience. CIMAP is freely available on GitHub (https://github.com/Biolab-PoliTO/CIMAP).Significance.CIMAPtoolbox offers scientists a standardized method for analyzing muscle activation patterns during cyclical movements.

Phasor-Based Myoelectric Synergy Features: A Fast Hand-Crafted Feature Extraction Scheme for Boosting Performance in Gait Phase Recognition

Gait phase recognition systems based on surface electromyographic signals (EMGs) are crucial for developing advanced myoelectric control schemes that enhance the interaction between humans and lower limb assistive devices. However, machine learning models used in this context, such as Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM), typically experience performance degradation when modeling the gait cycle with more than just stance and swing phases. This study introduces a generalized phasor-based feature extraction approach (PHASOR) that captures spatial myoelectric features to improve the performance of LDA and SVM in gait phase recognition. A publicly available dataset of 40 subjects was used to evaluate PHASOR against state-of-the-art feature sets in a five-phase gait recognition problem. Additionally, fully data-driven deep learning architectures, such as Rocket and Mini-Rocket, were included for comparison. The separability index (SI) and mean semi-principal axis (MSA) analyses showed mean SI and MSA metrics of 7.7 and 0.5, respectively, indicating the proposed approach's ability to effectively decode gait phases through EMG activity. The SVM classifier demonstrated the highest accuracy of 82% using a five-fold leave-one-trial-out testing approach, outperforming Rocket and Mini-Rocket. This study confirms that in gait phase recognition based on EMG signals, novel and efficient muscle synergy information feature extraction schemes, such as PHASOR, can compete with deep learning approaches that require greater processing time for feature extraction and classification.

Development of a Motion Estimation Method Using a Piezoelectric wire sensor

Numerous studies have aimed to create an electric prosthesis that allows free finger movement without delay. However, a device with these capabilities has yet to be developed. Research on electric prostheses has been conducted not only with myoelectric prostheses but also with other biological signals. Our focus was on muscle sounds detectable on the skin during mechanical activity. Muscle sound, a biological signal, remains unaffected by skin impedance and can be measured on the skin surface. This study defined Muscle Vibration as the amalgamation of muscle sound and bulge, both detected as micro-vibrations during muscle deformation. Motion was estimated utilizing a piezoelectric wire sensor with a diameter of 0.5 mm. However, using muscle sound for motion estimation is a concern because ambient sound changes may reduce the accuracy of discrimination. Thus, this study aimed to compare the accuracy of motion estimation using a piezoelectric wire sensor. Even amid an ambient noise level of 80 dB, an average discrimination rate of 85.7% was achieved. Discriminators developed under different ambient noise conditions also exhibited a discrimination rate exceeding 90% for movements. Therefore, ambient noise does not affect motion estimation using a piezoelectric wire sensor. In conclusion, an electric prosthesis that uses Muscle Vibration measured with a piezoelectric wire sensor is a robust measurement model that is unaffected by changes in environmental sounds during use and discrimination.

Dual Stream Long Short-Term Memory Feature Fusion Classifier for Surface Electromyography Gesture Recognition

Gesture recognition using electromyography (EMG) signals has prevailed recently in the field of human-computer interactions for controlling intelligent prosthetics. Currently, machine learning and deep learning are the two most commonly employed methods for classifying hand gestures. Despite traditional machine learning methods already achieving impressive performance, it is still a huge amount of work to carry out feature extraction manually. The existing deep learning methods utilize complex neural network architectures to achieve higher accuracy, which will suffer from overfitting, insufficient adaptability, and low recognition accuracy. To improve the existing phenomenon, a novel lightweight model named dual stream LSTM feature fusion classifier is proposed based on the concatenation of five time-domain features of EMG signals and raw data, which are both processed with one-dimensional convolutional neural networks and LSTM layers to carry out the classification. The proposed method can effectively capture global features of EMG signals using a simple architecture, which means less computational cost. An experiment is conducted on a public DB1 dataset with 52 gestures, and each of the 27 subjects repeats every gesture 10 times. The accuracy rate achieved by the model is 89.66%, which is comparable to that achieved by more complex deep learning neural networks, and the inference time for each gesture is 87.6 ms, which can also be implied in a real-time control system. The proposed model is validated using a subject-wise experiment on 10 out of the 40 subjects in the DB2 dataset, achieving a mean accuracy of 91.74%. This is illustrated by its ability to fuse time-domain features and raw data to extract more effective information from the sEMG signal and select an appropriate, efficient, lightweight network to enhance the recognition results.

Real-time vibrotactile pattern generation and identification using discrete event-driven feedback

This study assesses human identification of vibrotactile patterns by using real-time discrete event-driven feedback. Previously acquired force and bend sensor data from a robotic hand were used to predict movement-type (stationary, flexion, contact, extension, release) and object-type (no object, hard object, soft object) states by using decision tree (DT) algorithms implemented in a field-programmable gate array (FPGA). Six able-bodied humans performed a 2- and 3-step sequential pattern recognition task in which state transitions were signaled as vibrotactile feedback. The stimuli were generated according to predicted classes represented by two frequencies (F1: 80 Hz, F2: 180 Hz) and two magnitudes (M1: low, M2: high) calibrated psychophysically for each participant; and they were applied by two actuators (Haptuators) placed on upper arms. A soft/hard object was mapped to F1/F2; and manipulating it with low/high force was assigned to M1/M2 in the left actuator. On the other hand, flexion/extension movement was mapped to F1/F2 in the right actuator, with movement in air as M1 and during object manipulation as M2. DT algorithm performed better for the object-type (97%) than the movement-type (88%) classification in real time. Participants could recognize feedback associated with 14 discrete-event sequences with low-to-medium accuracy. The performance was higher (76 ± 9% recall, 76 ± 17% precision, 78 ± 4% accuracy) for recognizing any one event in the sequences. The results show that FPGA implementation of classification for discrete event-driven vibrotactile feedback can be feasible in haptic devices with additional cues in the physical context.

Intelligent Human-Computer Interaction: Combined Wrist and Forearm Myoelectric Signals for Handwriting Recognition

Recent studies have highlighted the possibility of using surface electromyographic (EMG) signals to develop human-computer interfaces that are also able to recognize complex motor tasks involving the hand as the handwriting of digits. However, the automatic recognition of words from EMG information has not yet been studied. The aim of this study is to investigate the feasibility of using combined forearm and wrist EMG probes for solving the handwriting recognition problem of 30 words with consolidated machine-learning techniques and aggregating state-of-the-art features extracted in the time and frequency domains. Six healthy subjects, three females and three males aged between 25 and 40 years, were recruited for the study. Two tests in pattern recognition were conducted to assess the possibility of classifying fine hand movements through EMG signals. The first test was designed to assess the feasibility of using consolidated myoelectric control technology with shallow machine-learning methods in the field of handwriting detection. The second test was implemented to assess if specific feature extraction schemes can guarantee high performances with limited complexity of the processing pipeline. Among support vector machine, linear discriminant analysis, and K-nearest neighbours (KNN), the last one showed the best classification performances in the 30-word classification problem, with a mean accuracy of 95% and 85% when using all the features and a specific feature set known as TDAR, respectively. The obtained results confirmed the validity of using combined wrist and forearm EMG data for intelligent handwriting recognition through pattern recognition approaches in real scenarios.

Accelerometry as a tool for measuring the effects of transcranial magnetic stimulation

OBJECTIVE

We predicted that accelerometry would be a viable alternative to electromyography (EMG) for assessing fundamental Transcranial Magnetic Stimulation (TMS) measurements (e.g. Resting Motor Threshold (RMT), recruitment curves, latencies).

NEW METHOD

21 participants were tested. TMS evoked responses were recorded with EMG on the First Dorsal Interosseus muscle and an accelerometer on the index fingertip. TMS was used to determine the (EMG-defined) RMT, then delivered at a range of intensities allowing determination of both the accelerometry-defined RMT and measurement of recruitment curves.

RESULTS

RMT assessed by EMG was significantly lower than for accelerometry (t(19)=-3.84, p<.001, mean±SD EMG = 41.1±5.28% MSO (maximum stimulator output), Jerk = 44.55±5.82% MSO), though RMTs calculated for each technique were highly correlated (r(18)=.72, p<.001). EMG/Accelerometery recruitment curves were strongly correlated (r(14)=.98, p<.001), and Bayesian model comparison indicated they were equivalent (BF01>9). Latencies measured with EMG were lower and more consistent than those identified using accelerometry (χ2(1)=80.38, p<.001, mean±SD EMG=27.01±4.58 ms, Jerk=48.4±15.33 ms).

COMPARISON WITH EXISTING METHODS

EMG is used as standard by research groups that study motor control and neurophysiology, but accelerometry has not yet been considered as a potential tool to assess measurements such as the overall magnitude and latency of the evoked response.

CONCLUSIONS

While EMG provides more sensitive and reliable measurements of RMT and latency, accelerometry provides a reliable alternative to measure of the overall magnitude of TMS evoked responses.

A Sensory Feedback Neural Stimulator Prototype for Both Implantable and Wearable Applications

The restoration of sensory feedback is one of the current challenges in the field of prosthetics. This work, following the analysis of the various types of sensory feedback, aims to present a prototype device that could be used both for implantable applications to perform PNS and for wearable applications, performing TENS, to restore sensory feedback. The two systems are composed of three electronic boards that are presented in detail, as well as the bench tests carried out. To the authors' best knowledge, this work presents the first device that can be used in a dual scenario for restoring sensory feedback. Both the implantable and wearable versions respected the expected values regarding the stimulation parameters. In its implantable version, the proposed system allows simultaneous and independent stimulation of 30 channels. Furthermore, the capacity of the wearable version to elicit somatic sensations was evaluated on healthy participants demonstrating performance comparable with commercial solutions.

A Minimal and Multi-Source Recording Setup for Ankle Joint Kinematics Estimation During Walking Using Only Proximal Information From Lower Limb

In this study, a minimal setup for the ankle joint kinematics estimation is proposed relying only on proximal information of the lower-limb, i.e. thigh muscles activity and joint kinematics. To this purpose, myoelectric activity of Rectus Femoris (RF), Biceps Femoris (BF), and Vastus Medialis (VM) were recorded by surface electromyography (sEMG) from six healthy subjects during unconstrained walking task. For each subject, the angular kinematics of hip and ankle joints were synchronously recorded with sEMG signal for a total of 288 gait cycles. Two feature sets were extracted from sEMG signals, i.e. time domain (TD) and wavelet (WT) and compared to have a compromise between the reliability and computational capacity, they were used for feeding three regression models, i.e. Artificial Neural Networks, Random Forest, and Least Squares - Support Vector Machine (LS-SVM). BF together with LS-SVM provided the best ankle angle estimation in both TD and WT domains (RMSE < 5.6 deg). The inclusion of Hip joint trajectory significantly enhanced the regression performances of the model (RMSE < 4.5 deg). Results showed the feasibility of estimating the ankle trajectory using only proximal and limited information from the lower limb which would maximize a potential transfemoral amputee user's comfortability while facing the challenge of having a small amount of information thus requiring robust data-driven models. These findings represent a significant step towards the development of a minimal setup useful for the control design of ankle active prosthetics and rehabilitative solutions.

Stimulation of peroneal nerves reveals maintained somatosensory representation in transtibial amputees

Introduction

Several studies have found changes in the organization of the primary somatosensory cortex (SI) after amputation. This SI reorganization was mainly investigated by stimulating neighboring areas to amputation. Unexpectedly, the somatosensory representation of the deafferented limb has rarely been directly tested.

Methods

We stimulated the truncated peroneal nerve in 24 unilateral transtibial amputees and 15 healthy controls. The stimulation intensity was adjusted to make the elicited percept comparable between both stimulation sides. Neural sources of the somatosensory-evoked magnetic fields (SEFs) to peroneal stimulation were localized in the contralateral foot/leg areas of SI in 19 patients and 14 healthy controls.

Results

We demonstrated the activation of functionally preserved cortical representations of amputated lower limbs. None of the patients reported evoked phantom limb pain (PLP) during stimulation. Stimulation that evoked perceptions in the foot required stronger intensities on the amputated side than on the intact side. In addition to this, stronger stimulation intensities were required for amputees than for healthy controls. Exploratorily, PLP intensity was neither associated with stimulation intensity nor dipole strength nor with differences in Euclidean distances (between SEF sources of the healthy peroneus and mirrored SEF sources of the truncated peroneus).

Discussion

Our results provide hope that the truncated nerve may be used to establish both motor control and somatosensory feedback via the nerve trunk when a permanently functional connection between the nerve trunk and the prosthesis becomes available.

Continuous Motion Estimation of Knee Joint Based on a Parameter Self-Updating Mechanism Model

Estimation of continuous motion of human joints using surface electromyography (sEMG) signals has a critical part to play in intelligent rehabilitation. Traditional methods always use sEMG signals as inputs to build regression or biomechanical models to estimate continuous joint motion variables. However, it is challenging to accurately estimate continuous joint motion in new subjects due to the non-stationarity and individual differences in sEMG signals, which greatly limits the generalisability of the method. In this paper, a continuous motion estimation model for the human knee joint with a parameter self-updating mechanism based on the fusion of particle swarm optimization (PSO) and deep belief network (DBN) is proposed. According to the original sEMG signals of different subjects, the method adaptively optimized the parameters of the DBN model and completed the optimal reconstruction of signal feature structure in high-dimensional space to achieve the optimal estimation of continuous joint motion. Extensive experiments were conducted on knee joint motions. The results suggested that the average root mean square errors (RMSEs) of the proposed method were 9.42° and 7.36°, respectively, which was better than the results obtained by common neural networks. This finding lays a foundation for the human-robot interaction (HRI) of the exoskeleton robots based on the sEMG signals.

Recent trends and challenges of surface electromyography in prosthetic applications

Surface electromyography (sEMG) meets extensive applications in the field of prosthesis in the current period. The effectiveness of sEMG in prosthesis applications has been verified by numerous revolutionary developments and extensive research attempts. A large volume of research and literature works have explored and validated the vast use of these signals in prostheses as an assistive technology. The objective of this paper is to conduct a systematic review and offer a detailed overview of the work record in the prosthesis and myoelectric interfaces framework. This review utilized a systematic search strategy to identify published articles discussing the state-of-the-art applications of sEMG in prostheses (including upper limb prosthesis and lower limb prostheses). Relevant studies were identified using electronic databases such as PubMed, IEEE Explore, SCOPUS, ScienceDirect, Google Scholar and Web of Science. Out of 3791 studies retrieved from the databases, 188 articles were found to be potentially relevant (after screening of abstracts and application of inclusion-exclusion criteria) and included in this review. This review presents an investigative analysis of sEMG-based prosthetic applications to assist the readers in making further advancements in this field. It also discusses the fundamental advantages and disadvantages of using sEMG in prosthetic applications. It also includes some important guidelines to follow in order to improve the performance of sEMG-based prosthesis. The findings of this study support the widespread use of sEMG in prosthetics. It is concluded that sEMG-based prosthesis technology, still in its sprouting phase, requires significant explorations for further development. Supplementary investigations are necessary in the direction of making a seamless mechanism of biomechatronics for sEMG-based prosthesis by cohesive efforts of robotic researchers and biomedical engineers.

Wearable High-Density MXene-Bioelectronics for Neuromuscular Diagnostics, Rehabilitation, and Assistive Technologies

High-density surface electromyography (HDsEMG) allows noninvasive muscle monitoring and disease diagnosis. Clinical translation of current HDsEMG technologies is hampered by cost, limited scalability, low usability, and minimal spatial coverage. Here, this study presents, validates, and demonstrates the broad clinical applicability of dry wearable MXene HDsEMG arrays (MXtrodes) fabricated from safe and scalable liquid-phase processing of Ti3 C2 Tx . The fabrication scheme allows easy customization of array geometry to match subject anatomy, while the gel-free and minimal skin preparation enhance usability and comfort. The low impedance and high conductivity of the MXtrode arrays allow detection of the activity of large muscle groups at higher quality and spatial resolution than state-of-the-art wireless electromyography  sensors, and in realistic clinical scenarios. To demonstrate the clinical applicability of MXtrodes in the context of neuromuscular diagnostics and rehabilitation, simultaneous HDsEMG and biomechanical mapping of muscle groups across the whole calf during various tasks, ranging from controlled contractions to walking is shown. Finally, the integration of HDsEMG acquired with MXtrodes with a machine learning pipeline and the accurate prediction of the phases of human gait are shown. The results underscore the advantages and translatability of MXene-based wearable bioelectronics for studying neuromuscular function and disease, as well as for precision rehabilitation.

Regenerative Peripheral Nerve Interface Surgery: Anatomic and Technical Guide

Regenerative peripheral nerve interface (RPNI) surgery has been demonstrated to be an effective tool as an interface for neuroprosthetics. Additionally, it has been shown to be a reproducible and reliable strategy for the active treatment and for prevention of neuromas. The purpose of this article is to provide a comprehensive review of RPNI surgery to demonstrate its simplicity and empower reconstructive surgeons to add this to their armamentarium. This article discusses the basic science of neuroma formation and prevention, as well as the theory of RPNI. An anatomic review and discussion of surgical technique for each level of amputation and considerations for other etiologies of traumatic neuromas are included. Lastly, the authors discuss the future of RPNI surgery and compare this with other active techniques for the treatment of neuromas.

Communicative capital: a key resource for human-machine shared agency and collaborative capacity

In this work, we present a perspective on the role machine intelligence can play in supporting human abilities. In particular, we consider research in rehabilitation technologies such as prosthetic devices, as this domain requires tight coupling between human and machine. Taking an agent-based view of such devices, we propose that human-machine collaborations have a capacity to perform tasks which is a result of the combined agency of the human and the machine. We introduce communicative capital as a resource developed by a human and a machine working together in ongoing interactions. Development of this resource enables the partnership to eventually perform tasks at a capacity greater than either individual could achieve alone. We then examine the benefits and challenges of increasing the agency of prostheses by surveying literature which demonstrates that building communicative resources enables more complex, task-directed interactions. The viewpoint developed in this article extends current thinking on how best to support the functional use of increasingly complex prostheses, and establishes insight toward creating more fruitful interactions between humans and supportive, assistive, and augmentative technologies.

A multi-Kalman filter-based approach for decoding arm kinematics from EMG recordings

BACKGROUND

Remarkable work has been recently introduced to enhance the usage of Electromyography (EMG) signals in operating prosthetic arms. Despite the rapid advancements in this field, providing a reliable, naturalistic myoelectric prosthesis remains a significant challenge. Other challenges include the limited number of allowed movements, lack of simultaneous, continuous control and the high computational power that could be needed for accurate decoding. In this study, we propose an EMG-based multi-Kalman filter approach to decode arm kinematics; specifically, the elbow angle (θ), wrist joint horizontal (X) and vertical (Y) positions in a continuous and simultaneous manner.

RESULTS

Ten subjects were examined from which we recorded arm kinematics and EMG signals of the biceps, triceps, lateral and anterior deltoid muscles corresponding to a randomized set of movements. The performance of the proposed decoder is assessed using the correlation coefficient (CC) and the normalized root-mean-square error (NRMSE) computed between the actual and the decoded kinematic. Results demonstrate that when training and testing the decoder using same-subject data, an average CC of 0.68 ± 0.1, 0.67 ± 0.12 and 0.64 ± 0.11, and average NRMSE of 0.21 ± 0.06, 0.18 ± 0.03 and 0.24 ± 0.07 were achieved for θ, X, and Y, respectively. When training the decoder using the data of one subject and decoding the data of other subjects, an average CC of 0.61 ± 0.19, 0.61 ± 0.16 and 0.48 ± 0.17, and an average NRMSE of 0.23 ± 0.07, 0.2 ± 0.05 and 0.38 ± 0.15 were achieved for θ, X, and Y, respectively.

CONCLUSIONS

These results suggest the efficacy of the proposed approach and indicates the possibility of obtaining a subject-independent decoder.

Reimagining Prosthetic Control: A Novel Body-Powered Prosthetic System for Simultaneous Control and Actuation

Globally, the most popular upper-limb prostheses are powered by the human body. For body-powered (BP) upper-limb prostheses, control is provided by changing the tension of (Bowden) cables to open or close the terminal device. This technology has been around for centuries, and very few BP alternatives have been presented since. This paper introduces a new BP paradigm that can overcome certain limitations of the current cabled systems, such as a restricted operation space and user discomfort caused by the harness to which the cables are attached. A new breathing-powered system is introduced to give the user full control of the hand motion anywhere in space. Users can regulate their breathing, and this controllable airflow is then used to power a small Tesla turbine that can accurately control the prosthetic finger movements. The breathing-powered device provides a novel prosthetic option that can be used without limiting any of the user’s body movements. Here we prove that it is feasible to produce a functional breathing-powered prosthetic hand and show the models behind it along with a preliminary demonstration. This work creates a step-change in the potential BP options available to patients in the future.

Evaluation of Simple Algorithms for Proportional Control of Prosthetic Hands Using Intramuscular Electromyography

Although seemingly effortless, the control of the human hand is backed by an elaborate neuro-muscular mechanism. The end result is typically a smooth action with the precise positioning of the joints of the hand and an exerted force that can be modulated to enable precise interaction with the surroundings. Unfortunately, even the most sophisticated technology cannot replace such a comprehensive role but can offer only basic hand functionalities. This issue arises from the drawbacks of the prosthetic hand control strategies that commonly rely on surface EMG signals that contain a high level of noise, thus limiting accurate and robust multi-joint movement estimation. The use of intramuscular EMG results in higher quality signals which, in turn, lead to an improvement in prosthetic control performance. Here, we present the evaluation of fourteen common/well-known algorithms (mean absolute value, variance, slope sign change, zero crossing, Willison amplitude, waveform length, signal envelope, total signal energy, Teager energy in the time domain, Teager energy in the frequency domain, modified Teager energy, mean of signal frequencies, median of signal frequencies, and firing rate) for the direct and proportional control of a prosthetic hand. The method involves the estimation of the forces generated in the hand by using different algorithms applied to iEMG signals from our recently published database, and comparing them to the measured forces (ground truth). The results presented in this paper are intended to be used as a baseline performance metric for more advanced algorithms that will be made and tested using the same database.

Non-Invasive Stable Sensory Feedback for Closed-Loop Control of Hand Prosthesis

The absence of somatotopic sensory feedback limits the function of conventional prosthetic hands. In this study, we integrated a non-invasive sensory feedback system into a commercial Bebionic hand with new customized surface stimulation electrodes. Multiple modalities of tactile and hand aperture sensory information were conveyed to the amputee via the technique of evoked tactile sensation (ETS) elicited at projected finger map (PFM) of residual limb and an additional electrotactile stimulation in the ipsilateral upper arm. A previously developed anti-stimulus artifact module was used to remove the stimulus artifact from surface electromyographic (sEMG) signals, and the filtered sEMG envelops controlled the speed of open/close of the Bebionic hand. The Ag/AgCl surface stimulation electrode in 10-mm diameter was specially designed to fit the restricted PFM areas for stable perception. We evaluated the alternating-current (AC) impedance magnitude of this electrode stimulated over 12 hours. The perceptual and upper thresholds in pulse-width over 200 days at PFM areas were recorded to assess the stability of the non-invasive sensory neural interface. The efficacy of multi-modality feedback for identification of physical properties of objects was also assessed. Results showed that the AC impedance of customized surface stimulation electrode was stable over 12 hours of stimulation. The perceptual and upper thresholds were stable over 200 days. This non-invasive sensory feedback enabled a forearm amputee to identify the compliance and length of grasped objects with an accuracy of 100 %. Results illustrated that the multi-modality sensory feedback system provided stable and sufficient sensory information for perceptual discrimination of physical features of grasped objects. Clinical Relevance- This study demonstrated a promising and novel way to restore stable sensory feedback non-invasively for commercial hand prostheses.

Improving the Robustness of Human-Machine Interactive Control for Myoelectric Prosthetic Hand During Arm Position Changing

Robust classification of natural hand grasp type based on electromyography (EMG) still has some shortcomings in the practical prosthetic hand control, owing to the influence of dynamic arm position changing during hand actions. This study provided a framework for robust hand grasp type classification during dynamic arm position changes, improving both the “hardware” and “algorithm” components. In the hardware aspect, co-located synchronous EMG and force myography (FMG) signals are adopted as the multi-modal strategy. In the algorithm aspect, a sequential decision algorithm is proposed by combining the RNN-based deep learning model with a knowledge-based post-processing model. Experimental results showed that the classification accuracy of multi-modal EMG-FMG signals was increased by more than 10% compared with the EMG-only signal. Moreover, the classification accuracy of the proposed sequential decision algorithm improved the accuracy by more than 4% compared with other baseline models when using both EMG and FMG signals.

Electrotactile feedback improves grip force control and enables object stiffness recognition while using a myoelectric hand

Current myoelectric hands are limited in their ability to provide effective sensory feedback to the users, which highly affects their functionality and utility. Although the sensory information of a myoelectric hand can be acquired with equipped sensors, transforming the sensory signals into effective tactile sensations on users for functional tasks is a largely unsolved challenge. The purpose of this study aims to demonstrate that electrotactile feedback of the grip force improves the sensorimotor control of a myoelectric hand and enables object stiffness recognition. The grip force of a sensorized myoelectric hand was delivered to its users via electrotactile stimulation based on four kinds of typical encoding strategies, including graded (G), linear amplitude (LA), linear frequency (LF), and biomimetic (B) modulation. Object stiffness was encoded with the change of electrotactile sensations triggered by final grip force, as the prosthesis grasped the objects. Ten able-bodied subjects and two transradial amputees were recruited to participate in a dual-task virtual eggs test (VET) and an object stiffness discrimination test (OSDT) to quantify the prosthesis users' ability to handle fragile objects and recognize object stiffnesses, respectively. The quantified results showed that with electrotactile feedback enabled, the four kinds of encoding strategies allowed subjects to better able to handle fragile objects with similar performance, and the subjects were able to differentiate four levels of object stiffness at favorable accuracies (>86%) and high manual efficiency. Strategy LA presented the best stiffness discrimination performance, while strategy B was able to reduce the discrimination time but the discrimination accuracy was not better than the other three strategies. Electrotactile feedback also enhanced prosthesis embodiment and improved the users' confidence in prosthetic control. Outcomes indicate electrotactile feedback can be effectively exploited by the prosthesis users for grip force control and object stiffness recognition, proving the feasibility of functional sensory restoration of myoelectric prostheses equipped with electrotactile feedback.

Clinical Basis for Creating an Osseointegrated Neural Interface

As technology continues to improve within the neuroprosthetic landscape, there has been a paradigm shift in the approach to amputation and surgical implementation of haptic neural prosthesis for limb restoration. The Osseointegrated Neural Interface (ONI) is a proposed solution involving the transposition of terminal nerves into the medullary canal of long bones. This design combines concepts of neuroma formation and prevention with osseointegration to provide a stable environment for conduction of neural signals for sophisticated prosthetic control. While this concept has previously been explored in animal models, it has yet to be explored in humans. This anatomic study used three upper limb and three lower limb cadavers to assess the clinical feasibility of creating an ONI in humans. Anatomical measurement of the major peripheral nerves- circumference, length, and depth- were performed as they are critical for electrode design and rerouting of the nerves into the long bones. CT imaging was used for morphologic bone evaluation and virtual implantation of two osseointegrated implants were performed to assess the amount of residual medullary space available for housing the neural interfacing hardware. Use of a small stem osseointegrated implant was found to reduce bone removal and provide more intramedullary space than a traditional implant; however, the higher the amputation site, the less medullary space was available regardless of implant type. Thus the stability of the endoprosthesis must be maximized while still maintaining enough residual space for the interface components. The results from this study provide an anatomic basis required for establishing a clinically applicable ONI in humans. They may serve as a guide for surgical implementation of an osseointegrated endoprosthesis with intramedullary electrodes for prosthetic control.

Data-Driven Real-Time Magnetic Tracking Applied to Myokinetic Interfaces

A new concept of human-machine interface to control hand prostheses based on displacements of multiple magnets implanted in the limb residual muscles, the myokinetic control interface, has been recently proposed. In previous works, magnets localization has been achieved following an optimization procedure to find an approximate solution to an analytical model. To simplify and speed up the localization problem, here we employ machine learning models, namely linear and radial basis functions artificial neural networks, which can translate measured magnetic information to desired commands for active prosthetic devices. They were developed offline and then implemented on field-programmable gate arrays using customized floating-point operators. We optimized computational precision, execution time, hardware, and energy consumption, as they are essential features in the context of wearable devices. When used to track a single magnet in a mockup of the human forearm, the proposed data-driven strategy achieved a tracking accuracy of 720 μm 95% of the time and latency of 12.07 μs. The proposed system architecture is expected to be more power-efficient compared to previous solutions. The outcomes of this work encourage further research on improving the devised methods to deal with multiple magnets simultaneously.

Wearable Sensor for Forearm Motion Detection Using a Carbon-Based Conductive Layer-Polymer Composite Film

In this study, we developed a fabrication method for a bracelet-type wearable sensor to detect four motions of the forearm by using a carbon-based conductive layer-polymer composite film. The integral material used for the composite film is a polyethylene terephthalate polymer film with a conductive layer composed of a carbon paste. It is capable of detecting the resistance variations corresponding to the flexion changes of the surface of the body due to muscle contraction and relaxation. To effectively detect the surface resistance variations of the film, a small sensor module composed of mechanical parts mounted on the film was designed and fabricated. A subject wore the bracelet sensor, consisting of three such sensor modules, on their forearm. The surface resistance of the film varied corresponding to the flexion change of the contact area between the forearm and the sensor modules. The surface resistance variations of the film were converted to voltage signals and used for motion detection. The results demonstrate that the thin bracelet-type wearable sensor, which is comfortable to wear and easily applicable, successfully detected each motion with high accuracy.

Intention Detection Strategies for Robotic Upper-Limb Orthoses: A Scoping Review Considering Usability, Daily Life Application, and User Evaluation

Wearable robotic upper limb orthoses (ULO) are promising tools to assist or enhance the upper-limb function of their users. While the functionality of these devices has continuously increased, the robust and reliable detection of the user's intention to control the available degrees of freedom remains a major challenge and a barrier for acceptance. As the information interface between device and user, the intention detection strategy (IDS) has a crucial impact on the usability of the overall device. Yet, this aspect and the impact it has on the device usability is only rarely evaluated with respect to the context of use of ULO. A scoping literature review was conducted to identify non-invasive IDS applied to ULO that have been evaluated with human participants, with a specific focus on evaluation methods and findings related to functionality and usability and their appropriateness for specific contexts of use in daily life. A total of 93 studies were identified, describing 29 different IDS that are summarized and classified according to a four-level classification scheme. The predominant user input signal associated with the described IDS was electromyography (35.6%), followed by manual triggers such as buttons, touchscreens or joysticks (16.7%), as well as isometric force generated by residual movement in upper-limb segments (15.1%). We identify and discuss the strengths and weaknesses of IDS with respect to specific contexts of use and highlight a trade-off between performance and complexity in selecting an optimal IDS. Investigating evaluation practices to study the usability of IDS, the included studies revealed that, primarily, objective and quantitative usability attributes related to effectiveness or efficiency were assessed. Further, it underlined the lack of a systematic way to determine whether the usability of an IDS is sufficiently high to be appropriate for use in daily life applications. This work highlights the importance of a user- and application-specific selection and evaluation of non-invasive IDS for ULO. For technology developers in the field, it further provides recommendations on the selection process of IDS as well as to the design of corresponding evaluation protocols.

A Way of Bionic Control Based on EI, EMG, and FMG Signals

Creating highly functional prosthetic, orthotic, and rehabilitation devices is a socially relevant scientific and engineering task. Currently, certain constraints hamper the development of such devices. The primary constraint is the lack of an intuitive and reliable control interface working between the organism and the actuator. The critical point in developing these devices and systems is determining the type and parameters of movements based on control signals recorded on an extremity. In the study, we investigate the simultaneous acquisition of electric impedance (EI), electromyography (EMG), and force myography (FMG) signals during basic wrist movements: grasping, flexion/extension, and rotation. For investigation, a laboratory instrumentation and software test setup were made for registering signals and collecting data. The analysis of the acquired signals revealed that the EI signals in conjunction with the analysis of EMG and FMG signals could potentially be highly informative in anthropomorphic control systems. The study results confirm that the comprehensive real-time analysis of EI, EMG, and FMG signals potentially allows implementing the method of anthropomorphic and proportional control with an acceptable delay.

Determination of the Geometric Parameters of Electrode Systems for Electrical Impedance Myography: A Preliminary Study

The electrical impedance myography method is widely used in solving bionic control problems and consists of assessing the change in the electrical impedance magnitude during muscle contraction in real time. However, the choice of electrode systems sizes is not always properly considered when using the electrical impedance myography method in the existing approaches, which is important in terms of electrical impedance signal expressiveness and reproducibility. The article is devoted to the determination of acceptable sizes for the electrode systems for electrical impedance myography using the Pareto optimality assessment method and the electrical impedance signals formation model of the forearm area, taking into account the change in the electrophysical and geometric parameters of the skin and fat layer and muscle groups when performing actions with a hand. Numerical finite element simulation using anthropometric models of the forearm obtained by volunteers' MRI 3D reconstructions was performed to determine a sufficient degree of the forearm anatomical features detailing in terms of the measured electrical impedance. For the mathematical description of electrical impedance relationships, a forearm two-layer model, represented by the skin-fat layer and muscles, was reasonably chosen, which adequately describes the change in electrical impedance when performing hand actions. Using this model, for the first time, an approach that can be used to determine the acceptable sizes of electrode systems for different parts of the body individually was proposed.

Fabrication of High-Density Out-of-Plane Microneedle Arrays with Various Heights and Diverse Cross-Sectional Shapes

Out-of-plane microneedle structures are widely used in various applications such as transcutaneous drug delivery and neural signal recording for brain machine interface. This work presents a novel but simple method to fabricate high-density silicon (Si) microneedle arrays with various heights and diverse cross-sectional shapes depending on photomask pattern designs. The proposed fabrication method is composed of a single photolithography and two subsequent deep reactive ion etching (DRIE) steps. First, a photoresist layer was patterned on a Si substrate to define areas to be etched, which will eventually determine the final location and shape of each individual microneedle. Then, the 1st DRIE step created deep trenches with a highly anisotropic etching of the Si substrate. Subsequently, the photoresist was removed for more isotropic etching; the 2nd DRIE isolated and sharpened microneedles from the predefined trench structures. Depending on diverse photomask designs, the 2nd DRIE formed arrays of microneedles that have various height distributions, as well as diverse cross-sectional shapes across the substrate. With these simple steps, high-aspect ratio microneedles were created in the high density of up to 625 microneedles mm^-2 on a Si wafer. Insertion tests showed a small force as low as ~ 172 µN/microneedle is required for microneedle arrays to penetrate the dura mater of a mouse brain. To demonstrate a feasibility of drug delivery application, we also implemented silk microneedle arrays using molding processes. The fabrication method of the present study is expected to be broadly applicable to create microneedle structures for drug delivery, neuroprosthetic devices, and so on.

Long short-term memory (LSTM) recurrent neural network for muscle activity detection

BACKGROUND

The accurate temporal analysis of muscle activation is of great interest in many research areas, spanning from neurorobotic systems to the assessment of altered locomotion patterns in orthopedic and neurological patients and the monitoring of their motor rehabilitation. The performance of the existing muscle activity detectors is strongly affected by both the SNR of the surface electromyography (sEMG) signals and the set of features used to detect the activation intervals. This work aims at introducing and validating a powerful approach to detect muscle activation intervals from sEMG signals, based on long short-term memory (LSTM) recurrent neural networks.

METHODS

First, the applicability of the proposed LSTM-based muscle activity detector (LSTM-MAD) is studied through simulated sEMG signals, comparing the LSTM-MAD performance against other two widely used approaches, i.e., the standard approach based on Teager-Kaiser Energy Operator (TKEO) and the traditional approach, used in clinical gait analysis, based on a double-threshold statistical detector (Stat). Second, the effect of the Signal-to-Noise Ratio (SNR) on the performance of the LSTM-MAD is assessed considering simulated signals with nine different SNR values. Finally, the newly introduced approach is validated on real sEMG signals, acquired during both physiological and pathological gait. Electromyography recordings from a total of 20 subjects (8 healthy individuals, 6 orthopedic patients, and 6 neurological patients) were included in the analysis.

RESULTS

The proposed algorithm overcomes the main limitations of the other tested approaches and it works directly on sEMG signals, without the need for background-noise and SNR estimation (as in Stat). Results demonstrate that LSTM-MAD outperforms the other approaches, revealing higher values of F1-score (F1-score > 0.91) and Jaccard similarity index (Jaccard > 0.85), and lower values of onset/offset bias (average absolute bias < 6 ms), both on simulated and real sEMG signals. Moreover, the advantages of using the LSTM-MAD algorithm are particularly evident for signals featuring a low to medium SNR.

CONCLUSIONS

The presented approach LSTM-MAD revealed excellent performances against TKEO and Stat. The validation carried out both on simulated and real signals, considering normal as well as pathological motor function during locomotion, demonstrated that it can be considered a powerful tool in the accurate and effective recognition/distinction of muscle activity from background noise in sEMG signals.

Development and Implementation of an Anthropomorphic Underactuated Prosthesis with Adaptive Grip

This paper describes the design of a prosthetic hand for wrist amputations. The mechanism considers the use of three actuators: one each for the movement of the little finger, annular finger, and middle finger. The second actuator controls the index finger, and the third controls the thumb. The prototype is considered relevant as it is able to move the distal phalanx in all fingers; the little, annular, and middle fingers are able to adapt to the shape of the object being gripped (adaptive grip). The sequence of movements achieved with the thumb emulate the opposition/reposition and flexion/extension movements, commanded by a single actuator. The proposed design was built by additive manufacturing and effortlessly achieves a large number of grips. Additionally, the prosthesis could perform specific movements, such as holding a needle, although this grip demands higher precision in the control of the fingers. Due to the manufacturing method, the prosthesis weighs only 200 g, increasing to 450 g when the actuators are included, therefore weighing less than an average adult’s hand.

Advanced Bioelectrical Signal Processing Methods: Past, Present, and Future Approach-Part III: Other Biosignals

Analysis of biomedical signals is a very challenging task involving implementation of various advanced signal processing methods. This area is rapidly developing. This paper is a Part III paper, where the most popular and efficient digital signal processing methods are presented. This paper covers the following bioelectrical signals and their processing methods: electromyography (EMG), electroneurography (ENG), electrogastrography (EGG), electrooculography (EOG), electroretinography (ERG), and electrohysterography (EHG).

Conducting Polymer-Ionic Liquid Electrode Arrays for High-Density Surface Electromyography

Surface electromyography (EMG) is used as a medical diagnostic and to control prosthetic limbs. Electrode arrays that provide large-area, high density recordings have the potential to yield significant improvements in both fronts, but the need remains largely unfulfilled. Here, digital fabrication techniques are used to make scalable electrode arrays that capture EMG signals with mm spatial resolution. Using electrodes made of poly(3,4-ethylenedioxythiophene) polystyrene sulfonate (PEDOT:PSS) composites with the biocompatible ionic liquid (IL) cholinium lactate, the arrays enable high quality spatiotemporal recordings from the forearm of volunteers. These recordings allow to identify the motions of the index, little, and middle fingers, and to directly visualize the propagation of polarization/depolarization waves in the underlying muscles. This work paves the way for scalable fabrication of cutaneous electrophysiology arrays for personalized medicine and highly articulate prostheses.

The Need to Work Arm in Arm: Calling for Collaboration in Delivering Neuroprosthetic Limb Replacements

Over the last few decades there has been a push to enhance the use of advanced prosthetics within the fields of biomedical engineering, neuroscience, and surgery. Through the development of peripheral neural interfaces and invasive electrodes, an individual's own nervous system can be used to control a prosthesis. With novel improvements in neural recording and signal decoding, this intimate communication has paved the way for bidirectional and intuitive control of prostheses. While various collaborations between engineers and surgeons have led to considerable success with motor control and pain management, it has been significantly more challenging to restore sensation. Many of the existing peripheral neural interfaces have demonstrated success in one of these modalities; however, none are currently able to fully restore limb function. Though this is in part due to the complexity of the human somatosensory system and stability of bioelectronics, the fragmentary and as-yet uncoordinated nature of the neuroprosthetic industry further complicates this advancement. In this review, we provide a comprehensive overview of the current field of neuroprosthetics and explore potential strategies to address its unique challenges. These include exploration of electrodes, surgical techniques, control methods, and prosthetic technology. Additionally, we propose a new approach to optimizing prosthetic limb function and facilitating clinical application by capitalizing on available resources. It is incumbent upon academia and industry to encourage collaboration and utilization of different peripheral neural interfaces in combination with each other to create versatile limbs that not only improve function but quality of life. Despite the rapidly evolving technology, if the field continues to work in divided "silos," we will delay achieving the critical, valuable outcome: creating a prosthetic limb that is right for the patient and positively affects their life.

Data Management for Transfer Learning Approaches to Elbow EMG-Torque Modeling

The performance of single-use subject-specific electromyogram (EMG)-torque models degrades significantly when used on a new subject, or even the same subject on a second day. Improving the generalization performance of models is essential but challenging. In this work, we investigate how data management strategies contribute to the performance of elbow joint EMG-torque models in cross-subject evaluation. Data management can be divided into two parts, namely data acquisition and data utilization. For data acquisition, analysis of data from 65 subjects shows that training set data diversity (number of subjects) is more important than data size (total data duration). For data utilization, we propose a correlation-based data weighting (COR-W) method for model calibration which is unsupervised in the modeling stage. We first evaluated the domain shift level between data in each training trial (source domain) and data acquired from a new subject (target domain) via the mismatch of feature correlation, using only EMG signals in the target domain without the synchronized torque values (hence unsupervised during model training). Data weights were assigned to each training trial according to different domain shift levels. The weighted least squares method using the obtained data weights was then employed to develop a calibrated EMG-torque model for the new subject. The COR-W method can achieve a low root mean square error (9.29% maximum voluntary contraction) in cross-subject evaluation, with significant performance improvement compared to models without calibration. Both the data acquisition and utilization strategies contribute to the performance of EMG-torque models in cross-subject evaluation.

Simultaneous decoding of cardiovascular and respiratory functional changes from pig intraneural vagus nerve signals

Objective. Bioelectronic medicine is opening new perspectives for the treatment of some major chronic diseases through the physical modulation of autonomic nervous system activity. Being the main peripheral route for electrical signals between central nervous system and visceral organs, the vagus nerve (VN) is one of the most promising targets. Closed-loop VN stimulation (VNS) would be crucial to increase effectiveness of this approach. Therefore, the extrapolation of useful physiological information from VN electrical activity would represent an invaluable source for single-target applications. Here, we present an advanced decoding algorithm novel to VN studies and properly detecting different functional changes from VN signals.Approach. VN signals were recorded using intraneural electrodes in anaesthetized pigs during cardiovascular and respiratory challenges mimicking increases in arterial blood pressure, tidal volume and respiratory rate. We developed a decoding algorithm that combines discrete wavelet transformation, principal component analysis, and ensemble learning made of classification trees.Main results. The new decoding algorithm robustly achieved high accuracy levels in identifying different functional changes and discriminating among them. Interestingly our findings suggest that electrodes positioning plays an important role on decoding performances. We also introduced a new index for the characterization of recording and decoding performance of neural interfaces. Finally, by combining an anatomically validated hybrid neural model and discrimination analysis, we provided new evidence suggesting a functional topographical organization of VN fascicles.Significance. This study represents an important step towards the comprehension of VN signaling, paving the way for the development of effective closed-loop VNS systems.

Inter-Subject Domain Adaptation for CNN-Based Wrist Kinematics Estimation Using sEMG

Recently, convolutional neural network (CNN) has been widely investigated to decode human intentions using surface Electromyography (sEMG) signals. However, a pre-trained CNN model usually suffers from severe degradation when testing on a new individual, and this is mainly due to domain shift where characteristics of training and testing sEMG data differ substantially. To enhance inter-subject performances of CNN in the wrist kinematics estimation, we propose a novel regression scheme for supervised domain adaptation (SDA), based on which domain shift effects can be effectively reduced. Specifically, a two-stream CNN with shared weights is established to exploit source and target sEMG data simultaneously, such that domain-invariant features can be extracted. To tune CNN weights, both regression losses and a domain discrepancy loss are employed, where the former enable supervised learning and the latter minimizes distribution divergences between two domains. In this study, eight healthy subjects were recruited to perform wrist flexion-extension movements. Experiment results illustrated that the proposed regression SDA outperformed fine-tuning, a state-of-the-art transfer learning method, in both single-single and multiple-single scenarios of kinematics estimation. Unlike fine-tuning which suffers from catastrophic forgetting, regression SDA can maintain much better performances in original domains, which boosts the model reusability among multiple subjects.

sEMG-Based Continuous Estimation of Finger Kinematics via Large-Scale Temporal Convolutional Network

Since continuous motion control can provide a more natural, fast and accurate man–machine interface than that of discrete motion control, it has been widely used in human–robot cooperation (HRC). Among various biological signals, the surface electromyogram (sEMG)—the signal of actions potential superimposed on the surface of the skin containing the temporal and spatial information—is one of the best signals with which to extract human motion intentions. However, most of the current sEMG control methods can only perform discrete motion estimation, and thus fail to meet the requirements of continuous motion estimation. In this paper, we propose a novel method that applies a temporal convolutional network (TCN) to sEMG-based continuous estimation. After analyzing the relationship between the convolutional kernel’s size and the lengths of atomic segments (defined in this paper), we propose a large-scale temporal convolutional network (LS-TCN) to overcome the TCN’s problem: that it is difficult to fully extract the sEMG’s temporal features. When applying our proposed LS-TCN with a convolutional kernel size of 1 × 31 to continuously estimate the angles of the 10 main joints of fingers (based on the public dataset Ninapro), it can achieve a precision rate of 71.6%. Compared with TCN (kernel size of 1 × 3), LS-TCN (kernel size of 1 × 31) improves the precision rate by 6.6%.

In-silico development and assessment of a Kalman filter motor decoder for prosthetic hand control

Up to 50% of amputees abandon their prostheses, partly due to rapid degradation of the control systems, which require frequent recalibration. The goal of this study was to develop a Kalman filter-based approach to decoding motoneuron activity to identify movement kinematics and thereby provide stable, long-term, accurate, real-time decoding. The Kalman filter-based decoder was examined via biologically varied datasets generated from a high-fidelity computational model of the spinal motoneuron pool. The estimated movement kinematics controlled a simulated MuJoCo prosthetic hand. This clear-box approach showed successful estimation of hand movements under eight varied physiological conditions with no retraining. The mean correlation coefficient of 0.98 and mean normalized root mean square error of 0.06 over these eight datasets provide proof of concept that this decoder would improve long-term integrity of performance while performing new, untrained movements. Additionally, the decoder operated in real-time (~0.3 ms). Further results include robust performance of the Kalman filter when re-trained to more severe post-amputation limitations in the type and number of motoneurons remaining. An additional analysis shows that the decoder achieves better accuracy when using the firing of individual motoneurons as input, compared to using aggregate pool firing. Moreover, the decoder demonstrated robustness to noise affecting both the trained decoder parameters and the decoded motoneuron activity. These results demonstrate the utility of a proof of concept Kalman filter decoder that can support prosthetics' control systems to maintain accurate and stable real-time movement performance.

A closed-loop hand prosthesis with simultaneous intraneural tactile and position feedback

Current myoelectric prostheses allow transradial amputees to regain voluntary motor control of their artificial limb by exploiting residual muscle function in the forearm. However, the overreliance on visual cues resulting from a lack of sensory feedback is a common complaint. Recently, several groups have provided tactile feedback in upper limb amputees using implanted electrodes, surface nerve stimulation, or sensory substitution. These approaches have led to improved function and prosthesis embodiment. Nevertheless, the provided information remains limited to a subset of the rich sensory cues available to healthy individuals. More specifically, proprioception, the sense of limb position and movement, is predominantly absent from current systems. Here, we show that sensory substitution based on intraneural stimulation can deliver position feedback in real time and in conjunction with somatotopic tactile feedback. This approach allowed two transradial amputees to regain high and close-to-natural remapped proprioceptive acuity, with a median joint angle reproduction precision of 9.1° and a median threshold to detection of passive movements of 9.5°, which was comparable with results obtained in healthy participants. The simultaneous delivery of position information and somatotopic tactile feedback allowed both amputees to discriminate the size and compliance of four objects with high levels of performance (75.5%). These results demonstrate that tactile information delivered via somatotopic neural stimulation and position information delivered via sensory substitution can be exploited simultaneously and efficiently by transradial amputees. This study paves a way to more sophisticated bidirectional bionic limbs conveying richer, multimodal sensations.

Improvement of hand functions of spinal cord injury patients with electromyography-driven hand exoskeleton: A feasibility study

We have developed a one-of-a-kind hand exoskeleton, called Maestro, which can power finger movements of those surviving severe disabilities to complete daily tasks using compliant joints. In this paper, we present results from an electromyography (EMG) control strategy conducted with spinal cord injury (SCI) patients (C5, C6, and C7) in which the subjects completed daily tasks controlling Maestro with EMG signals from their forearm muscles. With its compliant actuation and its degrees of freedom that match the natural finger movements, Maestro is capable of helping the subjects grasp and manipulate a variety of daily objects (more than 15 from a standardized set). To generate control commands for Maestro, an artificial neural network algorithm was implemented along with a probabilistic control approach to classify and deliver four hand poses robustly with three EMG signals measured from the forearm and palm. Increase in the scores of a standardized test, called the Sollerman hand function test, and enhancement in different aspects of grasping such as strength shows feasibility that Maestro can be capable of improving the hand function of SCI subjects.

Decoding hindlimb kinematics from descending and ascending neural signals during cat locomotion

OBJECTIVE

The main objective of this research is to record both sensory and motor information from the ascending and descending tracts within the spinal cord for decoding the hindlimb kinematics during walking on the treadmill.

APPROACH

Two different experimental paradigms (i.e., active and passive) were used in the current study. During active experiments, five cats were trained to walk bipedally while their hands kept on the front frame of the treadmill for balance or to walk quadrupedally. During passive experiments, the limb was passively moved by the experimenter. Local field potential (LFP) activity was recorded using a microwire array implanted in the dorsal column (DC) and lateral column (LC) of the L3-L4 spinal segments. The amplitude and frequency components of the LFP formed the feature set and the elastic net regularization was used to decode the hindlimb joint angles.

MAIN RESULTS

The results show that there is no significant difference between the information content of the signals recorded from the DC and LC regions during walking on the treadmill, but the information content of the DC is significantly higher than that of the LC during passively applied movement of the hindlimb in the anesthetized cats. Moreover, the decoding performance obtained using the recorded signals from the DC is comparable with that from the LC during locomotion. But, the decoding performance obtained using the recording channels in the DC is significantly better than that obtained using the signals recorded from the LC. The long-term analysis shows that robust decoding performance can be achieved over 2-3 months without a significant decrease in performance.

SIGNIFICANCE

This work presents a promising approach to developing a natural and robust motor neuroprosthesis device using descending neural signals to execute the movement and ascending neural signals as the feedback information for control of the movement.

Long exposure convolutional memory network for accurate estimation of finger kinematics from surface electromyographic signals

OBJECTIVE

Estimation of finger kinematics is an important function of an intuitive human-machine interface, such as gesture recognition. Here, we propose a novel deep learning method, named Long Exposure Convolutional Memory Network (LE-ConvMN), and use it to proportionally estimate finger joint angles through surface electromyographic (sEMG) signals.

APPROACH

We use a convolution structure to replace the neuron structure of traditional Long Short-Term Memory (LSTM) networks, and use the long exposure data structure which retains the spatial and temporal information of the electrodes as input. The Ninapro database, which contains continuous finger gestures and corresponding sEMG signals was used to verify the efficiency of the proposed deep learning method. The proposed method was compared with LSTM and Sparse Pseudo-input Gaussian Process (SPGP) on this database to predict the 10 main joint angles on the hand based on sEMG. The correlation coefficient (CC) was evaluated using the three methods on eight healthy subjects, and all the methods adopted the root mean square (RMS) features.

MAIN RESULTS

The experimental results showed that the average CC, RMSE, NRMSE of the proposed LE-ConvMN method (0.82±0.03,11.54±1.89,0.12±0.013) was significantly higher than SPGP (0.65±0.05, p＜0.001; 15.51±2.82, p＜0.001; 0.16±0.01, p＜0.001) and LSTM (0.64±0.06, p＜0.001; 14.77±3.21, p＜0.001; 0.15±0.02, p=＜0.001). Furthermore, the proposed real-time-estimation method has a computation cost of only approximately 82 ms to output one state of ten joints (average value of 10 tests on TitanV GPU).

SIGNIFICANCE

The proposed LE-ConvMN method could efficiently estimate the continuous movement of fingers with sEMG, and its performance is significantly superior to two established deep learning methods.

Systematic analysis of wavelet denoising methods for neural signal processing

Objective.Among the different approaches for denoising neural signals, wavelet-based methods are widely used due to their ability to reduce in-band noise. All wavelet denoising algorithms have a common structure, but their effectiveness strongly depends on several implementation choices, including the mother wavelet, the decomposition level, the threshold definition, and the way it is applied (i.e. the thresholding). In this work, we investigated these factors to quantitatively assess their effects on neural signals in terms of noise reduction and morphology preservation, which are important when spike sorting is required downstream.Approach.Based on the spectral characteristics of the neural signal, according to the sampling rate of the signals, we considered two possible decomposition levels and identified the best-performing mother wavelet. Then, we compared different threshold estimation and thresholding methods and, for the best ones, we also evaluated their effect on clearing the approximation coefficients. The assessments were performed on synthetic signals that had been corrupted by different types of noise and on a murine peripheral nervous system dataset, both of which were sampled at about 16 kHz. The results were statistically analysed in terms of their Pearson's correlation coefficients, root-mean-square errors, and signal-to-noise ratios.Main results.As expected, the wavelet implementation choices greatly influenced the processing performance. Overall, the Haar wavelet with a five-level decomposition, hard thresholding method, and the threshold proposed by Hanet al(2007) achieved the best outcomes. Based on the adopted performance metrics, wavelet denoising with these parametrizations outperformed conventional 300-3000 Hz linear bandpass filtering.Significance.These results can be used to guide the reasoned and accurate selection of wavelet denoising implementation choices in the context of neural signal processing, particularly when spike-morphology preservation is required.