Supraspinal, spinal, and motor unit adjustments to fatiguing isometric contractions of the knee extensors at low and high submaximal intensities in males.

Contraction intensity is a key factor determining the development of muscle fatigue and it has been shown to induce distinct changes along the motor pathway. The role of cortical and spinal inputs that regulate motor unit (MU) behaviour during fatiguing contractions is poorly understood. We studied the cortical, spinal, and neuromuscular response to sustained fatiguing isometric tasks performed at 20 and 70% of the maximum isometric voluntary contraction (MVC), together with MUs behaviour of knee extensors in healthy active males. Neuromuscular function was assessed before and after performing both tasks. Cortical and spinal responses during exercise were measured via stimulation of the motor cortex and spinal cord. High density electromyography was used to record individual MUs from the vastus lateralis (VL). Exercise at 70% MVC induced greater decline in MVC (p = 0.023), and potentiated twitch force compared to 20%MVC (p < .001), with no difference in voluntary activation (p = 0.514). Throughout exercise, corticospinal responses were greater during the 20%MVC task (p < 0.001), and spinal responses increased over time in both tasks (p ≤ 0.042). MU discharge rate increased similarly following both tasks (p ≤ 0.043) while recruitment and de-recruitment thresholds were unaffected (p ≥ 0.295). These results suggest that increased excitability of cortical and spinal inputs might be responsible for the increase in MU discharge rate. The increase in evoked responses together with the higher MUs discharge rate might be required to compensate for peripheral adjustments to sustain fatiguing contractions at different intensities.

Toward Impedance Control in Human-Machine Interfaces for Upper-Limb Prostheses.

OBJECTIVES: Adaptation of upper-limb impedance (stiffness, damping, inertia) is crucial for humans to physically interact with the external environment during grasping and manipulation tasks. Here, we present a novel framework for Adaptive Impedance Control of Upper-limb Prosthesis (AIC-UP) based on surface electromyography (sEMG) signals. METHODS: AIC-UP uses muscle-tendon models driven by sEMG signals from agonist-antagonist muscle groups to estimate the human motor intent as joint kinematics, stiffness and damping. These estimates are used to implement a variable impedance controller on a simulated robot. Designed for use by amputees, joint torque or stiffness measurements are not used for model calibration. AIC-UP was evaluated with eight able-bodied subjects and a transradial amputee performing target-reaching tasks in simulation through wrist flexion-extension. The control performance was tested in free space and in the presence of unexpected perturbations. RESULTS: We show that AIC-UP outperformed a neural network that regresses the desired kinematics from sEMG signals, in terms of robustness to muscle coactivations needed to complete the task. These results were in agreement with the qualitative feedback from the participants. Additionally, we observed that AIC-UP enables the user to adapt the stiffness and damping to the tasks at hand.

Specificity of early motor unit adaptations with resistive exercise training.

After exposure of the human body to resistive exercise, the force-generation capacity of the trained muscles increases significantly. Despite decades of research, the neural and muscular stimuli that initiate these changes in muscle force are not yet fully understood. The study of these adaptations is further complicated by the fact that the changes may be partly specific to the training task. For example, short-term strength training does not always influence the neural drive to muscles during the early phase (<100 ms) of force development in rapid isometric contractions. Here we discuss some of the studies that have investigated neuromuscular adaptations underlying changes in maximal force and rate of force development produced by different strength training interventions, with a focus on changes observed at the level of spinal motor neurons. We discuss the different motor unit adjustments needed to increase force or speed, and the specificity of some of the adaptations elicited by differences in the training tasks.

Environmental Chamber Characterization of an Ice Detection Sensor for Aviation Using Graphene and PEDOT:PSS.

In the context of improving aircraft safety, this work focuses on creating and testing a graphene-based ice detection system in an environmental chamber. This research is driven by the need for more accurate and efficient ice detection methods, which are crucial in mitigating in-flight icing hazards. The methodology employed involves testing flat graphene-based sensors in a controlled environment, simulating a variety of climatic conditions that could be experienced in an aircraft during its entire flight. The environmental chamber enabled precise manipulation of temperature and humidity levels, thereby providing a realistic and comprehensive test bed for sensor performance evaluation. The results were significant, revealing the graphene sensors' heightened sensitivity and rapid response to the subtle changes in environmental conditions, especially the critical phase transition from water to ice. This sensitivity is the key to detecting ice formation at its onset, a critical requirement for aviation safety. The study concludes that graphene-based sensors tested under varied and controlled atmospheric conditions exhibit a remarkable potential to enhance ice detection systems for aircraft. Their lightweight, efficient, and highly responsive nature makes them a superior alternative to traditional ice detection technologies, paving the way for more advanced and reliable aircraft safety solutions.

Design, Fabrication and Evaluation of a Stretchable High-Density Electromyography Array.

The adoption of high-density electrode systems for human-machine interfaces in real-life applications has been impeded by practical and technical challenges, including noise interference, motion artefacts and the lack of compact electrode interfaces. To overcome some of these challenges, we introduce a wearable and stretchable electromyography (EMG) array, and present its design, fabrication methodology, characterisation, and comprehensive evaluation. Our proposed solution comprises dry-electrodes on flexible printed circuit board (PCB) substrates, eliminating the need for time-consuming skin preparation. The proposed fabrication method allows the manufacturing of stretchable sleeves, with consistent and standardised coverage across subjects. We thoroughly tested our developed prototype, evaluating its potential for application in both research and real-world environments. The results of our study showed that the developed stretchable array matches or outperforms traditional EMG grids and holds promise in furthering the real-world translation of high-density EMG for human-machine interfaces.

Influence of spatio-temporal filtering on hand kinematics estimation from high-density EMG signals.

Objective.Surface electromyography (sEMG) is a non-invasive technique that records the electrical signals generated by muscles through electrodes placed on the skin. sEMG is the state-of-the-art method used to control active upper limb prostheses because of the association between its amplitude and the neural drive sent from the spinal cord to muscles. However, accurately estimating the kinematics of a freely moving human hand using sEMG from extrinsic hand muscles remains a challenge. Deep learning has been recently successfully applied to this problem by mapping raw sEMG signals into kinematics. Nonetheless, the optimal number of EMG signals and the type of pre-processing that would maximize performance have not been investigated yet.Approach.Here, we analyze the impact of these factors on the accuracy in kinematics estimates. For this purpose, we processed monopolar sEMG signals that were originally recorded from 320 electrodes over the forearm muscles of 13 subjects. We used a previously published deep learning method that can map the kinematics of the human hand with real-time resolution.Main results.While myocontrol algorithms essentially use the temporal envelope of the EMG signal as the only EMG feature, we show that our approach requires the full bandwidth of the signal in the temporal domain for accurate estimates. Spatial filtering however, had a smaller impact and low-order spatial filters may be suitable. Moreover, reducing the number of channels by ablation resulted in large performance losses. The highest accuracy was reached with the highest number of available sensors (n = 320). Importantly and unexpected, our results suggest that increasing the number of channels above those used in this study may further enhance the accuracy in predicting the kinematics of the human hand.Significance.We conclude that full bandwidth high-density EMG systems of hundreds of electrodes are needed for accurate kinematic estimates of the human hand.

NeuroMechanics: Electrophysiological and computational methods to accurately estimate the neural drive to muscles in humans in vivo.

The ultimate neural signal for muscle control is the neural drive sent from the spinal cord to muscles. This neural signal comprises the ensemble of action potentials discharged by the active spinal motoneurons, which is transmitted to the innervated muscle fibres to generate forces. Accurately estimating the neural drive to muscles in humans in vivo is challenging since it requires the identification of the activity of a sample of motor units (MUs) that is representative of the active MU population. Current electrophysiological recordings usually fail in this task by identifying small MU samples with over-representation of higher-threshold with respect to lower-threshold MUs. Here, we describe recent advances in electrophysiological methods that allow the identification of more representative samples of greater numbers of MUs than previously possible. This is obtained with large and very dense arrays of electromyographic electrodes. Moreover, recently developed computational methods of data augmentation further extend experimental MU samples to infer the activity of the full MU pool. In conclusion, the combination of new electrode technologies and computational modelling allows for an accurate estimate of the neural drive to muscles and opens new perspectives in the study of the neural control of movement and in neural interfacing.

A direct spinal cord-computer interface enables the control of the paralysed hand in spinal cord injury.

The paralysis of the muscles controlling the hand dramatically limits the quality of life of individuals living with spinal cord injury (SCI). Here, with a non-invasive neural interface, we demonstrate that eight motor complete SCI individuals (C5-C6) are still able to task-modulate in real-time the activity of populations of spinal motor neurons with residual neural pathways. In all SCI participants tested, we identified groups of motor units under voluntary control that encoded various hand movements. The motor unit discharges were mapped into more than 10 degrees of freedom, ranging from grasping to individual hand-digit flexion and extension. We then mapped the neural dynamics into a real-time controlled virtual hand. The SCI participants were able to match the cue hand posture by proportionally controlling four degrees of freedom (opening and closing the hand and index flexion/extension). These results demonstrate that wearable muscle sensors provide access to spared motor neurons that are fully under voluntary control in complete cervical SCI individuals. This non-invasive neural interface allows the investigation of motor neuron changes after the injury and has the potential to promote movement restoration when integrated with assistive devices.

Consensus for experimental design in electromyography (CEDE) project: Checklist for reporting and critically appraising studies using EMG (CEDE-Check).

The diversity in electromyography (EMG) techniques and their reporting present significant challenges across multiple disciplines in research and clinical practice, where EMG is commonly used. To address these challenges and augment the reproducibility and interpretation of studies using EMG, the Consensus for Experimental Design in Electromyography (CEDE) project has developed a checklist (CEDE-Check) to assist researchers to thoroughly report their EMG methodologies. Development involved a multi-stage Delphi process with seventeen EMG experts from various disciplines. After two rounds, consensus was achieved. The final CEDE-Check consists of forty items that address four critical areas that demand precise reporting when EMG is employed: the task investigated, electrode placement, recording electrode characteristics, and acquisition and pre-processing of EMG signals. This checklist aims to guide researchers to accurately report and critically appraise EMG studies, thereby promoting a standardised critical evaluation, and greater scientific rigor in research that uses EMG signals. This approach not only aims to facilitate interpretation of study results and comparisons between studies, but it is also expected to contribute to advancing research quality and facilitate clinical and other practical applications of knowledge generated through the use of EMG.

Peripheral neural interfaces: Skeletal muscles are hyper-reinnervated according to the axonal capacity of the surgically rewired nerves.

Advances in robotics have outpaced the capabilities of man-machine interfaces to decipher and transfer neural information to and from prosthetic devices. We emulated clinical scenarios where high- (facial) or low-neural capacity (ulnar) donor nerves were surgically rewired to the sternomastoid muscle, which is controlled by a very small number of motor axons. Using retrograde tracing and electrophysiological assessments, we observed a nearly 15-fold functional hyper-reinnervation of the muscle after high-capacity nerve transfer, demonstrating its capability of generating a multifold of neuromuscular junctions. Moreover, the surgically redirected axons influenced the muscle's physiological characteristics, by altering the expression of myosin heavy-chain types in alignment with the donor nerve. These findings highlight the remarkable capacity of skeletal muscles to act as biological amplifiers of neural information from the spinal cord for governing bionic prostheses, with the potential of expressing high-dimensional neural function for high-information transfer interfaces.

Wind Tunnel Characterization of a Graphene-Enhanced PEDOT:PSS Sensing Element for Aircraft Ice Detection Systems.

This study details the development and validation of a graphene-based ice detection system, designed to enhance flight safety by monitoring ice accumulation on aircraft surfaces. The system employs a semiconductive polymer (PEDOT:PSS) with graphene electrodes, interpreting resistance changes to detect water impact and ice formation in real time. The sensor's performance was rigorously tested in a wind tunnel under various temperature and airflow conditions, focusing on resistance signal dependency on air temperature and phase change. The results demonstrate the sensor's ability to distinguish water droplet impacts from ice formation, with a notable correlation between resistance signal amplitude and water droplet impacts leading to ice accretion. Further analysis shows a significant relationship between air temperature and the resistance signal amplitude, particularly at lower temperatures beneficial to ice formation. This underlines the sensor's precision in varied atmospheric conditions. The system's compact design and accurate detection highlight its potential for improving aircraft ice monitoring, offering a path toward a robust and reliable ice detection system.

Measuring and monitoring skill learning in closed-loop myoelectric hand prostheses using speed-accuracy tradeoffs.

Objective.Closed-loop myoelectric prostheses, which combine supplementary sensory feedback and electromyography (EMG) based control, hold the potential to narrow the divide between natural and bionic hands. The use of these devices, however, requires dedicated training. Therefore, it is crucial to develop methods that quantify how users acquire skilled control over their prostheses to effectively monitor skill progression and inform the development of interfaces that optimize this process.Approach.Building on theories of skill learning in human motor control, we measured speed-accuracy tradeoff functions (SAFs) to comprehensively characterize learning-induced changes in skill-as opposed to merely tracking changes in task success across training-facilitated by a closed-loop interface that combined proportional control and EMG feedback. Sixteen healthy participants and one individual with a transradial limb loss participated in a three-day experiment where they were instructed to perform the box-and-blocks task using a timed force-matching paradigm at four specified speeds to reach two target force levels, such that the SAF could be determined.Main results.We found that the participants' accuracy increased in a similar way across all speeds we tested. Consequently, the shape of the SAF remained similar across days, at both force levels. Further, we observed that EMG feedback enabled participants to improve their motor execution in terms of reduced trial-by-trial variability, a hallmark of skilled behavior. We then fit a power law model of the SAF, and demonstrated how the model parameters could be used to identify and monitor changes in skill.Significance.We comprehensively characterized how an EMG feedback interface enabled skill acquisition, both at the level of task performance and movement execution. More generally, we believe that the proposed methods are effective for measuring and monitoring user skill progression in closed-loop prosthesis control.

The neural control of movement: a century of in vivo motor unit recordings is the legacy of Adrian and Bronk.

In two papers dated 1928 to 1929 in The Journal of Physiology, Edgar Adrian and Detlev Bronk described recordings from motor nerve and muscle fibres. The recordings from motor nerve fibres required progressive dissection of the nerve until a few fibres remained, from which isolated single fibre activity could be detected. The muscle fibre recordings were performed in humans during voluntary contractions with an intramuscular electrode - the concentric needle electrode - that they describe for the first time in the second paper. They recognised that muscle fibres would respond to each impulse sent by the innervating motor neurone and that therefore muscle fibre recordings provided information on the times of activation of the motor nerve fibres which were as accurate as a direct record from the nerve. These observations and the description of the concentric needle electrode opened the era of motor unit recordings in humans, which have continued for almost a century and have provided a comprehensive view of the neural control of movement at the motor unit level. Despite important advances in technology, many of the principles of motor unit behaviour that would be investigated in the subsequent decades were canvassed in the two papers by Adrian and Bronk. For example, they described the concomitant motor neurones' recruitment and rate coding for force modulation, synchronisation of motor unit discharges, and the dependence of discharge rate on motor unit recruitment threshold. Here, we summarise their observations and discuss the impact of their work. We highlight the advent of the concentric needle, and its subsequent influence on motor control research.

High Performance Wearable Ultrasound as a Human-Machine Interface for Wrist and Hand Kinematic Tracking.

OBJECTIVE: Non-invasive human machine interfaces (HMIs) have high potential in medical, entertainment, and industrial applications. Traditionally, surface electromyography (sEMG) has been used to track muscular activity and infer motor intention. Ultrasound (US) has received increasing attention as an alternative to sEMG-based HMIs. Here, we developed a portable US armband system with 24 channels and a multiple receiver approach, and compared it with existing sEMG- and US-based HMIs on movement intention decoding. METHODS: US and motion capture data was recorded while participants performed wrist and hand movements of four degrees of freedom (DoFs) and their combinations. A linear regression model was used to offline predict hand kinematics from the US (or sEMG, for comparison) features. The method was further validated in real-time for a 3-DoF target reaching task. RESULTS: In the offline analysis, the wearable US system achieved an average [Formula: see text] of 0.94 in the prediction of four DoFs of the wrist and hand while sEMG reached a performance of [Formula: see text]= 0.60. In online control, the participants achieved an average 93% completion rate of the targets. CONCLUSION: When tailored for HMIs, the proposed US A-mode system and processing pipeline can successfully regress hand kinematics both in offline and online settings with performances comparable or superior to previously published interfaces. SIGNIFICANCE: Wearable US technology may provide a new generation of HMIs that use muscular deformation to estimate limb movements. The wearable US system allowed for robust proportional and simultaneous control over multiple DoFs in both offline and online settings.

Deep Metric Learning With Locality Sensitive Mining for Self-Correcting Source Separation of Neural Spiking Signals.

Automated source separation algorithms have become a central tool in neuroengineering and neuroscience, where they are used to decompose neurophysiological signal into its constituent spiking sources. However, in noisy or highly multivariate recordings these decomposition techniques often make a large number of errors. Such mistakes degrade online human-machine interfacing methods and require costly post-hoc manual cleaning in the offline setting. In this article we propose an automated error correction methodology using a deep metric learning (DML) framework, generating embedding spaces in which spiking events can be both identified and assigned to their respective sources. Furthermore, we investigate the relative ability of different DML techniques to preserve the intraclass semantic structure needed to identify incorrect class labels in neurophysiological time series. Motivated by this analysis, we propose locality sensitive mining, an easily implemented sampling-based augmentation to typical DML losses which substantially improves the local semantic structure of the embedding space. We demonstrate the utility of this method to generate embedding spaces which can be used to automatically identify incorrectly labeled spiking events with high accuracy.

Hand and distal joint tremor are most coherent with the activity of elbow flexors and wrist extensors in persons with essential tremor.

Essential tremor (ET) affects millions of people. Although frontline treatment options (medication, deep brain stimulation, and focused ultrasound ablation) have provided significant relief, many patients are unsatisfied with the outcomes. Peripheral suppression techniques, such as injections of botulinum toxin or sensory electrical stimulation of muscles, are gaining popularity, but could be optimized if the muscles most responsible for a patient's tremor were identified. The purpose of this study was to quantify the relationship between the activity in various upper limb muscles and the resulting tremor in patients with ET. Surface electromyogram (sEMG) from the 15 major superficial muscles of the upper limb and displacement of the hand and upper limb joints were recorded from 22 persons with ET while they performed kinetic and postural tasks representative of activities of daily living. We calculated the peak coherence (frequency-dependent correlation) in the tremor band (4-8 Hz) between the sEMG of each muscle and the displacement in each major degree of freedom (DOF). Averaged across subjects with ET, the highest coherence was found between elbow flexors (particularly biceps brachii and brachioradialis) and the distal DOF (forearm, wrist, and hand motion), and between wrist extensors (extensor carpi radialis and ulnaris) and the same distal DOF. These coherence values represent the upper bound on the proportion of the tremor caused by each muscle. We conclude that, without further information, elbow flexors and wrist extensors should be among the first muscles considered for peripheral suppression techniques in persons with ET.NEW & NOTEWORTHY We characterized the relationships between activity in upper limb muscles and tremor in persons with essential tremor using coherence, which provides an upper bound on the proportion of the tremor due to each muscle. Averaged across subjects and various tasks, tremor in the hand and distal joints was most coherent with elbow flexors and wrist extensors. We conclude that, without further information, these muscle groups should be among the first considered for peripheral suppression techniques.

Motoneuron-driven computational muscle modelling with motor unit resolution and subject-specific musculoskeletal anatomy.

The computational simulation of human voluntary muscle contraction is possible with EMG-driven Hill-type models of whole muscles. Despite impactful applications in numerous fields, the neuromechanical information and the physiological accuracy such models provide remain limited because of multiscale simplifications that limit comprehensive description of muscle internal dynamics during contraction. We addressed this limitation by developing a novel motoneuron-driven neuromuscular model, that describes the force-generating dynamics of a population of individual motor units, each of which was described with a Hill-type actuator and controlled by a dedicated experimentally derived motoneuronal control. In forward simulation of human voluntary muscle contraction, the model transforms a vector of motoneuron spike trains decoded from high-density EMG signals into a vector of motor unit forces that sum into the predicted whole muscle force. The motoneuronal control provides comprehensive and separate descriptions of the dynamics of motor unit recruitment and discharge and decodes the subject's intention. The neuromuscular model is subject-specific, muscle-specific, includes an advanced and physiological description of motor unit activation dynamics, and is validated against an experimental muscle force. Accurate force predictions were obtained when the vector of experimental neural controls was representative of the discharge activity of the complete motor unit pool. This was achieved with large and dense grids of EMG electrodes during medium-force contractions or with computational methods that physiologically estimate the discharge activity of the motor units that were not identified experimentally. This neuromuscular model advances the state-of-the-art of neuromuscular modelling, bringing together the fields of motor control and musculoskeletal modelling, and finding applications in neuromuscular control and human-machine interfacing research.

Mental Tasks Modulate Motor-Units Above 10 Hz and are a Potential Control Signal for Movement Augmentation: a Preliminary Study.

Spinal motor neurons receive a wide range of input frequencies. However, only frequencies below ca. 10 Hz are directly translated into motor output. Frequency components above 10 Hz are filtered out by neural pathways and muscle dynamics. These higher frequency components may have an indirect effect on motor output, or may simply represent movement-independent oscillations that leak down from supraspinal areas such as the motor cortex. If movement-independent oscillations leak down from supraspinal areas, they could provide a potential control signal in movement augmentation applications. We analysed high-density electromyography (HD-EMG) signals from the tibialis anterior muscle while human subjects performed various mental tasks. The subjects performed an isometric dorsiflexion of the right foot at a low level of force while simultaneously (1) imagining a movement of the right foot, (2) imagining a movement of both hands, (3) performing a mathematical task, or (4) performing no additional task. We classified the channel-averaged HD-EMG signals and the cumulative spike train (CST) of motor-units using a filter bank and a linear classifier. We found that in some subjects, the mental task can be classified from the channel-averaged HD-EMG signals and the CST in oscillations above 10 Hz. Furthermore, we found that these oscillation modulations are incompatible with a systematic and task-dependent change in force level. Our preliminary findings from a limited number of subjects suggest that some mental task-induced oscillations from supraspinal areas leak down to spinal motor neurons and are discriminable via EMG or CST signals at the innervated muscle.

Accurate Identification of Motoneuron Discharges from Ultrasound Images Across the Full Muscle Cross-Section.

OBJECTIVE: Non-invasive identification of motoneuron (MN) activity commonly uses electromyography (EMG). However, surface EMG (sEMG) detects only superficial sources, at less than approximately 10-mm depth. Intramuscular EMG can detect deep sources, but it is limited to sources within a few mm of the detection site. Conversely, ultrasound (US) images have high spatial resolution across the whole muscle cross-section. The activity of MNs can be extracted from US images due to the movements that MN activation generates in the innervated muscle fibers. Current US-based decomposition methods can accurately identify the location and average twitch induced by MN activity. However, they cannot accurately detect MN discharge times. METHODS: Here, we present a method based on the convolutive blind source separation of US images to estimate MN discharge times with high accuracy. The method was validated across 10 participants using concomitant sEMG decomposition as the ground truth. RESULTS: 140 unique MN spike trains were identified from US images, with a rate of agreement (RoA) with sEMG decomposition of 87.4 ± 10.3%. Over 50% of these MN spike trains had a RoA greater than 90%. Furthermore, with US, we identified additional MUs well beyond the sEMG detection volume, at up to >30 mm below the skin. CONCLUSION: The proposed method can identify discharges of MNs innervating muscle fibers in a large range of depths within the muscle from US images. SIGNIFICANCE: The proposed methodology can non-invasively interface with the outer layers of the central nervous system innervating muscles across the full cross-section.

Transferring Gait Predictors Across EMG Acquisition Systems with Domain Adaptation.

Lower limb assistive technology (e.g. exoskeletons) can benefit significantly from higher resolution information related to physiological state. High-density electromyography (HD-EMG) grids offer valuable spatial information on muscle activity; however their hardware is impractical, and bipolar electrodes remain the standard in practice. Exploiting information rich HD-EMG datasets to train machine learning models could help overcome the spatial limitations of bipolar electrodes. Unfortunately, differences in signal characteristics across acquisition systems prevent the direct transfer of models without a drop in performance. This study investigated Domain Adaptation (DA) to render EMG-based models invariant to different acquisition systems. This approach was evaluated using a Temporal Convolutional Network (TCN) that mapped EMG signals to the subject's knee angle, using HD-EMG as source data and Delsys bipolar EMG as target data. Furthermore, the feature extraction learnt by the TCN was also applied across muscle groups, evaluating the transferability of the sensor agnostic features. The DA implementation shows promise in both scenarios, with an average increase in accuracy (angular error normalised by the range of motion) of 7.36% for the Rectus Femoris, Biceps Femoris and Tibialis Anterior, as well as a cross-muscle performance increase of up to 10.80%. However, when the domain discrepancy is severe, the model is currently unable to generate a reliable walking trajectory due to inherent limitations related to the applied regression scheme and the chosen Mean Squared Error loss function. Therefore, future research should focus on exploring advanced loss functions and classification-based DA models that prioritise restoring key features of the gait.