Movement analysis is essential for high-level athletes to perform at their best. Such analysis necessarily involves studying the characteristics of one’s own body, whose adaptive processes are crucial for understanding how each athlete responds to sudden changes. In this preliminary exploratory work, the paddling techniques of a limited, heterogeneous cohort of eight athletes were evaluated: four who were non-impaired and four who showed different classes of impairment (two KL3, one KL2, and one KL1). Each non-impaired athlete underwent three test series—one with a footrest, one without a footrest, and another with a modified footrest. KL3 athletes performed two tests, one with the prosthetic leg and one without, while KL2 and KL1 athletes completed a standard sprint. Measurements were obtained using a set of inertial sensors. The results showed a tendency toward greater symmetry in shoulder trajectories when the footrest was removed, and athletes improved their performance when sprinting under a modified configuration. These findings provide insight into how the body compensates for the absence of leg support, including changes in muscle recruitment and a tendency toward the better control of overall movement. Given the inherent constraints of the small sample size (n = 8), these results demonstrate the potential of IMU networks for personalized biomechanical assessment, providing descriptive, case-level insights rather than statistically generalizable trends.

Graviception, the human sensory perception of gravity and body orientation, plays a fundamental, yet often overlooked, role in how individuals interact with interactive systems. Human–computer interaction has traditionally emphasized visual, auditory, and tactile modalities, while comparatively neglecting the influence of gravity perception on embodiment, attention, motor control, and user experience. This paper draws on the field of biomechanics to examine how graviception can impact interaction, such as the impact of vision and gravity on body movements, especially in immersive, hypogravity environments, mobile contexts of use, and accessibility. By positioning graviception as a first-class concern in embodied interaction, we suggest actionable implications for interaction design that consider graviceptive factors for designers and researchers developing future graviceptive-aware interactive systems. Each implication is described by a short statement, a detailed statement, a rationale, and a series of examples illustrating the impact of graviception on design decisions.

The impact of Magnetic Resonance Imaging-guided Focused Ultrasound (MRgFUS) on vocal tremor is largely underexplored. We used artificial intelligence to investigate changes in vocal tremor in ET patients undergoing MRgFUS. Eighty-three controls and ET patients (mean age-SEM 70.0–1.0 years), including 39 patients without and 44 patients with clinically overt voice tremor, were assessed before and 24 h after MRgFUS targeting the ventral intermediate nucleus (Vim). Voice recordings were collected to calculate the receiver operating characteristic (ROC) curves, the likelihood ratios (LRs) for clinical-instrumental correlations, and the oscillatory activity peak by means of artificial intelligence algorithms. We found that before and after Vim-MRgFUS, artificial intelligence discriminated voices in ET and controls objectively with high accuracy. Also, we verified that Vim-MRgFUS improved voice tremor in ET. Moreover, the analysis showed positive correlations between LRs and clinical scores of voice tremor. Lastly, Vim-MRgFUS reduced the 4–6 Hz oscillatory activity peak in ET patients. Therefore, our observations pave the way for objective voice evaluations in ET patients following Vim-MRgFUS, for telemedicine purposes.

The latest research directions have provided a theoretical foundation to the experimental evidence that human walking owns time-harmonic motor patterns: the golden ratio is crucially involved to equal the ratio between the durations of two consecutive walking gait sub-phases within a generalized Fibonacci sequence. The corresponding gait index, named ϕ -bonacci gait number—even involving an intriguing experimental conjecture about the position of the foot relative to the tibia during the double support sub-phase—, is able to fully capture the most reliable and objective (quantitative) outcome measures (and their distortions in pathological subjects) of recursivity, asymmetry, consistency, and self-similarity (harmonicity) of the gait cycle. This paper provides experimental results on healthy and pathological gaits related to Benign Paroxysmal Positional Vertigo (BPPV). They totally support the aforementioned theoretical derivations, especially in the field of walking ability rehabilitation through canalith reposition manoeuvres. Furthermore, the newly introduced concept of (Heart-Rate-Variability-emulating) Harmonic Gait Variability (HGV)—used as a quantitative measure of the distance of the subject’s walking from a corresponding harmonic avatar—further, originally, illustrates in a quantitative fashion, rehabilitation effects.

Background/Objectives: Spatio-temporal gait parameters have been proposed as surrogate markers for objective, remote monitoring of global motor status in Parkinson’s disease (PD). Our observational, cross-sectional pilot study tested whether gait metrics, derived from wearable sensors, reflect dopaminergic responsiveness in both axial and appendicular functions. Methods: Twenty-two PD patients were evaluated both under and not under L-Dopa (ON and OFF states, respectively). Motor performance was assessed using wearable inertial sensors during standardized tasks involving gait and upper/lower limb movements. From the recorded kinematics, measures of movement amplitude, speed, rhythm, and consistency were extracted, and dopaminergic response was compared in appendicular and axial functions. Results: Treatment effects were more pronounced on the more affected body side. Improvements in appendicular amplitude, speed, and consistency closely matched those observed in spatio-temporal gait parameters. In contrast, rhythm measures displayed a divergent pattern, with reduced gait cadence but increased hand movement frequency, showing an inverse correlation. No significant correlations emerged between axial and appendicular domains for amplitude, velocity, or consistency, whereas improvements in step length and gait velocity were associated with MDS-UPDRS III motor scores. Conclusions: These findings overall suggest that specific gait metrics, particularly those reflecting amplitude and velocity, may provide reliable, sensor-based indicators of overall motor status in PD, supporting their use in remote monitoring.

Background: This paper aims to complement the latest contribution in the literature that provides estimates of physiological parameters of a dynamic model for the elbow time profile during walking while linking them to a neurodegenerative disorder (Parkinsons’s disease) characterized by motor symptoms. An upper limb model is here proposed in which an active contractile element is included within a model, viewing the arm as a double pendulum system and muscles as represented by a Kelvin–Voight system. All model parameters characterizing both the shoulder and the elbow of each subject are estimated via a gradient-like identifier whose exponential convergence properties are determined by a non-anticipative Lyapunov function, ensuring robustness features. Methods: Joint angle data from different walking subjects (healthy subjects and patients with Parkinson’s disease) have been recorded using an IMU sensor system and compared with the joint angles obtained by means of the proposed model, which was adapted to each subject using available anthropometric knowledge and relying on the estimated parameters. Results: Experiments show that the reconstruction of shoulder and elbow time profiles can be definitely achieved through the proposed procedure with the estimated stiffness parameters turning out to constitute objective and quantitative indices of muscle stiffness (as a pivotal symptom of the pathology), which are able to track changes due to the therapy. Conclusions: The same dynamic model is actually able to capture the main features of the upper limb movement of both (healthy and pathological) walking subjects, with its parameters, in turn, characterizing the nature and progress of the pathology.

Parkinson’s disease (PD) is a chronic neurodegenerative disorder that progressively impairs motor functions. Clinical assessments have traditionally relied on rating scales such as the Movement Disorder Society Unified Parkinson Disease Rating Scale (MDS-UPDRS); however, these evaluations are susceptible to rater-dependent variability and may miss subtle motor changes. This study explored objective and quantitative methods for assessing motor function in PD patients using the Quantum Metaglove, a sensory glove produced by MANUS®, which was used to record finger movements during three tasks: finger tapping, hand gripping, and pronation–supination. Classic and geometric motor features (the latter based on Clifford algebra, an advanced approach for trajectory shape analysis) were extracted. The resulting data were used to train various machine learning algorithms (k-NN, SVM, and Naive Bayes) to distinguish healthy subjects from PD patients. The integration of traditional kinematic and geometric approaches improves objective hand movement analysis, providing new diagnostic opportunities. In particular, geometric trajectory analysis provides more interpretable information than conventional signal processing methods. This study highlights the value of wearable technologies and Clifford algebra-based algorithms as tools that can complement clinical assessment. They are capable of reducing inter-rater variability and enabling more continuous and precise monitoring of hand motor movements in patients with PD.

Detecting potential alcohol inebriation or intoxication status holds paramount significance for social prevention and security. Beyond its association with long-term health effects, alcohol consumption can lead to immediate consequences, including reduced control over one’s actions, with traffic fatalities representing one of the most tragic outcomes.This study leveraged the Alcohol Language corpus, involving 162 subjects recorded both in sober and inebriated states. Participants provided 60 speech samples while sober and 30 when intoxicated, all within a realistic car setting using head-mounted microphones. Our research endeavors encompassed comprehensive stratified statistical tests to examine the impact of alcohol consumption on speech production while uncovering the influence of covariates such as age, gender, and drinking habits.Additionally, we introduced a speaker-neutral machine learning algorithm, based on the Domain-Adversarial Neural Network architecture. This approach aimed to overcome challenges posed by individual differences that often complicate intoxicated speech analysis. Notably, our findings highlighted the effectiveness of features like the RASTA-filtered auditory spectrum. Nevertheless, the results from statistical tests emphasized the need for techniques that minimize inter-subject variability.As for the automatic classification, the proposed architecture exhibited promising results, yielding a classification accuracy slightly exceeding 70% on an independent test set. Although preliminary, our research demonstrates the potential for detecting alcohol-induced speech changes, benefiting societal well-being and security. It also underscores the importance of developing strategies that account for individual differences while harnessing the power of automatic models to effectively distinguish between sober and intoxicated individuals.

The sensory glove (also known as data or instrumented glove) plays a key role in measuring and tracking hand dexterity. It has been adopted in a variety of different domains, including medical, robotics, virtual reality, and human–computer interaction, to assess hand motor skills and to improve control accuracy. However, no particular technology has been established as the most suitable for all domains, so that different sensory gloves have been developed, adopting different sensors mainly based on optic, electric, magnetic, or mechanical properties. This work investigates the performances of the MANUS Quantum sensory glove that sources an electromagnetic field and measures its changing value at the fingertips during fingers’ flexion. Its performance is determined in terms of measurement repeatability, reproducibility, and reliability during both quasi-static and dynamic hand motor tests.

Hand functions are vital for performing daily activities, ensuring independence, and maintaining quality of life. In Parkinson's disease (PD), impaired hand function affects fine motor skills, dexterity, and coordination, leading to difficulties in self-care, communication, and work-related tasks. As such, correct hand function assessment in PD is among the crucial aspects in evaluating motor impairment, in guiding treatment and tracking disease progression. Here, we report objective results obtained in assessing hand (dys)functionalities using an on-the-shelves fingerless sensory glove, named MANUS Quantum Metaglove, capable of sensing the variations of an electromagnetic field (EMF) sourced on the dorsal part of the hand and revealed by EMF coils at the fingers tips. A total of 65 people (35 PD patients and 30 healthy subjects for reference) were asked to perform standard motor tasks, and both most affected and least affected hands were assessed for opening-closing, grasping and pronation-supination movements. Differing from the generally adopted spatiotemporal analysis, taking a cue from non-linear theory adopted in electronics, we focused on spectral characteristics of the measured signals, specifically examining harmonic content and related harmonic distortions. As a result, we report how the adopted sensory glove, ensemble with spectral analysis, can be able to consistently assess hand motor (in)abilities in PD subjects and healthy subjects. In fact according to our results, PD patients significatively performed with hand motion signals affected by harmonic distortions, which revealed that the greater the complexity of the motor task, the greater the spread of the signal across harmonic frequencies, whilst healthy subjects perform with signals mostly around the fundamental frequency, as a marker of movement smoothness.

Current technologies allow acquiring whatever amount of data (even big data), from whatever system (object, component, mechanism, network, implant, machinery, structure, asset, etc.), during whatever time lapse (secs, hours, weeks, years). Therefore, potentially it is possible to fully characterize any system for any time we need, with the possible consequence of creating a virtual copy, namely the digital twin (DT) of the system. When technology of DT meets an augmented reality scenario, the augmented digital twin (ADT) arises, when DT meets an artificial intelligence environment, the intelligent digital twin (IDT) arises. DTs, ADTs and IDTs are successfully adopted in electronics, mechanics, chemistry, manufacturing, science, sport, and more, but when adopted for the human body it comes out the human digital twin (HDT) or alternatively named virtual human simulator (VHS). When the VHS incorporates information from surroundings (other VHSs and environment), taking a cue from the particle-wave duality (the mix of matter and energy), we can name this super-VHS as the human digi-real duality (HDRD). This work is focused on defining the aforementioned acronyms, on evidencing their differences, advantages and successful case adoptions, but highlighting technology limits too, and on foreseeing new and intriguing possibilities.

Active life monitoring via chemosensitive sensors could hold promise for enhancing athlete monitoring, training optimization, and performance in athletes. The present work investigates a resistive flex sensor (RFS) in the guise of a chemical sensor. Its carbon ‘texture’ has shown to be sensitive to CO2, O2, and RH changes; moreover, different bending conditions can modulate its sensitivity and selectivity for these gases and vapors. A three-step feasibility study is presented including: design and fabrication of the electronic read-out and control; calibration of the sensors to CO2, O2 and RH; and a morphological study of the material when interacting with the gas and vapor molecules. The 0.1 mm−1 curvature performs best among the tested configurations. It shows a linear response curve for each gas, the ranges of concentrations are adequate, and the sensitivity is good for all gases. The curvature can be modulated during data acquisition to tailor the sensitivity and selectivity for a specific gas. In particular, good results have been obtained with a curvature of 0.1 mm−1. For O2 in the range of 20–70%, the sensor has a sensitivity of 0.7 mV/%. For CO2 in the range of 4–80%, the sensitivity is 3.7 mV/%, and for RH the sensitivity is 33 mV/%. Additionally, a working principle, based on observation via scanning electron microscopy, has been proposed to explain the chemical sensing potential of this sensor. Bending seems to enlarge the cracks present in the RFS coverage; this change accounts for the altered selectivity depending on the sensor’s curvature. Further studies are needed to confirm result’s reliability and the correctness of the interpretation.

Pathological voice signals, especially when affected by artifacts such as hoarseness or wetness, can be hard to analyze with traditional transform-based methods. Thus, we employed 3D phase-space attractors stemming from non-linear chaos theory, to build a pipeline for Machine Learning (ML) based classification of dysphonic versus healthy voices. Spatial and analytical features were extracted from the attractors and paired with features related to the F0 of the signal, then two feature selection methodologies were employed and fed four different ML classifiers. Results show how even a small amount of features bring promising classification accuracies, in turn confirming the potential of attractors as descriptors of pathological voices. The best-performing model is a linear SVM fed with 10 features selected using Kruskal Wallis’ test, and attractors related to pathological voices are more erratic, less regular, less prone to being watertight, and with higher volume and face area.

In recent years, the boost in the development of hardware and software resources for building virtual reality environments has fuelled the development of tools to support training in different disciplines. The purpose of this work is to discuss a complete methodology and the supporting algorithms to develop a virtual reality environment to train the use of a sensorized upper-limb prosthesis targeted at amputees. The environment is based on the definition of a digital twin of a virtual prosthesis, able to communicate with the sensors worn by the user and reproduce its dynamic behaviour and the interaction with virtual objects. Several training tasks are developed according to standards, including the Southampton Hand Assessment Procedure, and the usability of the entire system is evaluated, too.

Objective: Although many advancements have been made on myoelectric pattern-recognition, the control of polyarticulated upper-limb prostheses remains insufficiently robust. Electrode-shift, sweat or fatigue degrade the performance of classifiers over time, resulting in unfruitful device usage and frequent re-calibration. To tackle this issue, here we introduce two models - mu P-6 and mu P-8 - that combine Geometric Algebra with nearest-neighbor classification. We aim at reducing both the necessary training data and training time and, unlike most current state-of-the-art algorithms, we exploit an alternative geometric representation (and visualization) of the EMG signal as different polygons for different types of gestures, facilitating the explanation of the decision-making process to a layman. Moreover, we explore four abstention strategies to reduce the number of misclassifications. Methods: We perform an offline analysis on two datasets, alongside two other standard models: nonlinear logistic regression (NLR) and linear discriminant analysis (LDA). Results: Even with few training data, the proposed algorithms achieve high F1-scores (>0.95), significantly higher or non-significantly different from the values obtained with NLR and LDA, while maintaining relatively low abstentions rates and training times (<2 ms). Conclusion: The proposed algorithms allow to reduce the amount of training data and training times without compromising recognition rates. Significance: The proposed algorithms may contribute for a faster prosthesis re-calibration procedure while allowing to re-gain high recognition rates. Furthermore, the decision-making process is explainable and interpretable, potentially improving user trust and acceptance.

This paper deals with the automatic detection of Myotonia from a task based on the sudden opening of the hand. Data have been gathered from 44 subjects, divided into 17 controls and 27 myotonic patients, by measuring a 2-point articulation of each finger thanks to a calibrated sensory glove equipped with a Resistive Flex Sensor (RFS). RFS gloves are proven to be reliable in the analysis of motion for myotonic patients, which is a relevant task for the monitoring of the disease and subsequent treatment. With the focus on a healthy VS pathological comparison, customized features were extracted, and several classifications entailing motion data from single fingers, single articulations and aggregations were prepared. The pipeline employed a Correlation-based feature selector followed by a SVM classifier. Results prove that it’s possible to detect Myotonia, with aggregated data from four fingers and upper/lower articulations providing the most promising accuracies (91.1%).

COPYRIGHT © 2023 Suppa, Costantini, Gomez-Vilda and Saggio. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Editorial: Voice analysis in healthy subjects and patients with neurologic disorders

: Up-to-date technologies make it possible to acquire a considerable amount of data, for a considerable period of time. It follows the possibility to strategically count on the necessary and useful elements to characterize from simple to very complex systems. Acquisition, even prolonged, and characterization of data from a certain source (object, component, system, etc.) make it possible to create a virtual copy of this source, namely Digital Twin (DT). When technology of DT meets smart algorithms of machine learning and artificial intelligence, the Intelligent DT (IDT) arises. DTs and IDTs are successfully adopted in electronics, mechanics, chemistry, but can they be applied for the entire human body so to realize a virtual human simulator (VHS)?.

Sensory gloves convert hand postures and movements of fingers into electric signals. Different technologies can be adopted to achieve this conversion, and different approaches can be used to evaluate its effectiveness. In this study, we adopted two types of sensory gloves based on two types of sensors, namely, the resistive flex sensor (RFS) and the inertial measurement unit (IMU). We evaluated the conversion effectiveness in terms of repeatability, reproducibility, and reliability of quasi-static measurements. In particular, to consider the nonlinear characteristics of sensors, we propose an improvement of the usually adopted measurement test protocol used for assessing the performance of sensory gloves. According to our results, the two sensory gloves have similar reliability. However, the IMU-based glove provides better repeatability, and the RFS-based glove provides better reproducibility. Overall, the average range +/- standard deviation and the intraclass correlation coefficient of the RFS-based glove were 5.66 degrees +/- 2.22 degrees and 0.73 +/- 0.17, respectively, and those of the IMU-based glove were 7.80 degrees +/- 2.47 degrees and 0.76 +/- 0.14, respectively. All in all, the novelty of this work concerns the comparison of two types of sensory gloves in terms of quasi-static measurement reproducibility and reliability and the improvement of an existing standard protocol for sensory glove assessment aimed at providing a more comprehensive analysis.