Showing papers by "Christian Cipriani published in 2022"

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

Abstract: 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 $\mu$m 95% of the time and latency of 12.07 $\mu$s. 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.

Decoding of Multiple Wrist and Hand Movements Using a Transient EMG Classifier

Abstract: The design of prosthetic controllers by means of neurophysiological signals still poses a crucial challenge to bioengineers. State of the art of electromyographic (EMG) continuous pattern recognition controllers rely on the questionable assumption that repeated muscular contractions produce repeatable patterns of steady-state EMG signals. Conversely, we propose an algorithm that decodes wrist and hand movements by processing the signals that immediately follow the onset of contraction (i.e., the $\textit {transient}$ EMG). We collected EMG data from the forearms of 14 non-amputee and 5 transradial amputee participants while they performed wrist flexion/extension, pronation/supination, and four hand grasps (power, lateral, bi-digital, open). We firstly identified the combination of wrist and hand movements that yielded the best control performance for the same participant (intra-subject classification). Then, we assessed the ability of our algorithm to classify participant data that were not included in the training set (cross-subject classification). Our controller achieved a median accuracy of ~96% with non-amputees, while it achieved heterogeneous outcomes with amputees, with a median accuracy of ~89%. Importantly, for each amputee, it produced at least one $\textit {acceptable}$ combination of wrist-hand movements (i.e., with accuracy >85%). Regarding the cross-subject classifier, while our algorithm obtained promising results with non-amputees (accuracy up to ~80%), they were not as good with amputees (accuracy up to ~35%), possibly suggesting further assessments with domain-adaptation strategies. In general, our offline outcomes, together with a preliminary online assessment, support the hypothesis that the transient EMG decoding could represent a viable pattern recognition strategy, encouraging further online assessments.

Feasibility Study on Disentangling Muscle Movements in TMR Patients Through a Myokinetic Control Interface for the Control of Artificial Hands

Abstract: Targeted muscle reinnervation (TMR) is a surgical procedure which allows to restore myoelectric control sources in people with proximal upper-limb amputations. However, the large physical displacement generally provoked by the reinnervated muscles following contraction can represent a drawback for the use of surface electrodes, which are affected by movement artifacts. In this regard, the viability of directly exploiting the physical displacement of muscles as control source would be beneficial. We recently introduced the so called myokinetic interface, aimed at transducing muscle movements into decipherable signals for artificial hands by tracking magnetic markers implanted inside the muscles. This work features the combination of the TMR procedure with such interface, in a non-invasive way. Two participants who underwent TMR surgery following above-the-elbow amputation were enrolled in this study. During two experimental sessions, we assessed the feasibility of: (i) disentangling muscle displacements associated with different degrees of freedom (DoFs) of the missing limb through video analysis, and (ii) discriminating different DoFs by tracking the displacement of five magnetic markers placed on the skin, over the reinnervated sites. A simple logistic regressor proved able to discriminate three different DoFs (six movements), with an average F1-score among classes and testing conditions of 0.84 (0.65) and 0.69 (0.60) for the video and the myokinetic data, for the first (second) participant, respectively. The presented outcomes encourage further investigations, and pave the way towards novel control strategies for artificial hands in TMR patients.

The myokinetic stimulation interface: activation of proprioceptive neural responses with remotely actuated magnets implanted in rodent forelimb muscle

Abstract: Objective. Proprioception is the sense of one’s position, orientation, and movement in space, and it is of fundamental importance for motor control. When proprioception is impaired or absent, motor execution becomes error-prone, leading to poorly coordinated movements. The kinaesthetic illusion, which creates perceptions of limb movement in humans through non-invasively applying vibrations to muscles or tendons, provides an avenue for studying and restoring the sense of joint movement (kinaesthesia). This technique, however, leaves ambiguity between proprioceptive percepts that arise from muscles versus those that arise from skin receptors. Here we propose the concept of a stimulation system to activate kinaesthesia through the untethered application of localized vibration through implanted magnets. Approach. In this proof-of-concept study, we use two simplified one-DoF systems to show the feasibility of eliciting muscle-sensory responses in an animal model across multiple frequencies, including those that activate the kinaesthetic illusion (70–115 Hz). Furthermore, we generalized the concept by developing a five-DoF prototype system capable of generating directional, frequency-selective vibrations with desired displacement profiles. Main results. In-vivo tests with the one-DoF systems demonstrated the feasibility to elicit muscle sensory neural responses in the median nerve of an animal model. Instead, in-vitro tests with the five-DoF prototype demonstrated high accuracy in producing directional and frequency selective vibrations along different magnet axes. Significance. These results provide evidence for a new technique that interacts with the native neuro-muscular anatomy to study proprioception and eventually pave the way towards the development of advanced limb prostheses or assistive devices for the sensory impaired.

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

Abstract: 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.