Search

The voice results in acoustic signals analyzed and synthetized at first for telecommunication matters, and more recently investigated for medical purposes. In particular, voice signal characteristics can evidence individual health conditions useful for screening, diagnostic and remote monitoring aims. Within this frame, the knowledge of baseline features of healthy voice is mandatory, in order to balance a comparison with their unhealthy counterpart. However, the baseline features of the human voice depend on gender, age-range and ethnicity and, as far as we know, no work reports as those features spread worldwide. This paper intends to cover this lack. Our database research yielded 179 relevant published studies, retrieved using digital libraries of IEEE Xplore, Scopus, Web of Science, Iop Science, Taylor and Francis Online, and Scitepress. These relevant studies report different features, among which here we consider the most investigated ones, within the most investigated age-range. In particular, the features are the fundamental frequency, the jitter, the shimmer, the harmonic-to-noise ratio, and the cepstral peak prominence, the most investigated age-range is within 20–40 years and, related to the ethnicity, 20 countries are considered. [ABSTRACT FROM AUTHOR]

Many virological tests have been implemented during the Coronavirus Disease 2019 (COVID-19) pandemic for diagnostic purposes, but they appear unsuitable for screening purposes. Furthermore, current screening strategies are not accurate enough to effectively curb the spread of the disease. Therefore, the present study was conducted within a controlled clinical environment to determine eventual detectable variations in the voice of COVID-19 patients, recovered and healthy subjects, and also to determine whether machine learning-based voice assessment (MLVA) can accurately discriminate between them, thus potentially serving as a more effective mass-screening tool. Three different subpopulations were consecutively recruited: positive COVID-19 patients, recovered COVID-19 patients and healthy individuals as controls. Positive patients were recruited within 10 days from nasal swab positivity. Recovery from COVID-19 was established clinically, virologically and radiologically. Healthy individuals reported no COVID-19 symptoms and yielded negative results at serological testing. All study participants provided three trials for multiple vocal tasks (sustained vowel phonation, speech, cough). All recordings were initially divided into three different binary classifications with a feature selection, ranking and cross-validated RBF-SVM pipeline. This brough a mean accuracy of 90.24%, a mean sensitivity of 91.15%, a mean specificity of 89.13% and a mean AUC of 0.94 across all tasks and all comparisons, and outlined the sustained vowel as the most effective vocal task for COVID discrimination. Moreover, a three-way classification was carried out on an external test set comprised of 30 subjects, 10 per class, with a mean accuracy of 80% and an accuracy of 100% for the detection of positive subjects. Within this assessment, recovered individuals proved to be the most difficult class to identify, and all the misclassified subjects were declared positive; this might be related to mid and short-term vocal traces of COVID-19, even after the clinical resolution of the infection. In conclusion, MLVA may accurately discriminate between positive COVID-19 patients, recovered COVID-19 patients and healthy individuals. Further studies should test MLVA among larger populations and asymptomatic positive COVID-19 patients to validate this novel screening technology and test its potential application as a potentially more effective surveillance strategy for COVID-19. [ABSTRACT FROM AUTHOR]

Resistive flex sensors were increasingly used in different areas for their interesting property to change their resistance when bent. In particular, they can be applied to human segment in biomedical devices to register static and dynamic postures. In spite of their interesting properties, such as robustness, low price and long life, they often demonstrate non-linear response and lower sensitivity at small bending angles. This paper provides investigation to improve flex sensors linearity and sensitivity to measure body joint angles with better accuracy. To this aim, an empirical model of the sheet (or surface) resistance of the active layer, to simulate its behavior against the layer shape and size as well as the bending angle, was provided, to investigate whether changes of the standard rectangular shape can improve sensitivity and linearity. In addition, to date commercial flex sensors have been characterized only against the bending angle with a radius of curvature smaller than the device length, so limiting the application to small joints such as finger or knee. In order to extend the flex sensor applications, for instance, to measure the trunk posture in back disease and rehabilitation monitoring, the sensor response against a radius of curvature greater than the sensor length was analyzed. Finally, a new modeling technique, based on the inverse model of the sensor characteristic, to enable fast measurements of the bending angle or the radius of curvature from sensor response also in real time, and fast calibration procedures, fitting the same model to measurements with different joint size and even device, were developed. [ABSTRACT FROM AUTHOR]

The preliminary diagnosis and evaluation of the presence and/or severity of Parkinson's disease is crucial in controlling the progress of the disease. Real-time, non-invasive methodologies based on machine learning-enhanced voice analysis are gathering more interest as the potential of this field unveils. Specifically, acoustic features are employed in many machine learning techniques, and could also function as indicators of the overall state of the subjects' voice: this review aims at identifying the most widely employed and promising feature-based machine learning methodologies, evidencing baselines and state-of-the-art solutions. A total of 102 works plus 5 review articles were selected from the IEEE Xplore, PubMed, Elsevier, and Web of Science electronic databases. A statistical assessment is performed identifying the most frequently used features as well as those deemed as most effective; an overview of algorithms, public datasets, toolboxes, and general metadata is also performed. According to our results, Jitter, Shimmer, Harmonic-to-Noise Ratio, Fundamental Frequency, and Mel Frequency Cepstral Coefficients are the mostly adopted features. In addition, it is worth noting a fair prevalence of glottal-like models and additional filtering options, such as Detrended Fluctuation Analysis. © 2017 Elsevier Inc. All rights reserved. [ABSTRACT FROM AUTHOR]

Extra-Vehicular Activity (EVA) plays such a key role that more and more time is devoted to it in space missions. Nevertheless, EVA presents so many intrinsic critical aspects to result highly hazardous for the human operators. This is why a convenient alternative can be offered by telerobotic manipulations, with multi-fingered robotic hands working in teleoperated mode, to safely and remotely replicate the capabilities of the operator's hands. But at present, remotely controlled robotic hands cannot provide the same dexterity of humans, so this work is intended to experimentally evaluate their feasibility and technological limits when operator's hand gestures are one-to-one mapped directly to a robotic hand device. In particular we demonstrated how state-of-the art sensory gloves, used to measure angles of human finger's joints, can introduce averaged errors of 4.6 degrees in angles, and that these errors increase to 6.5 degrees when remotely replicated by standard anthropomorphic robotic hands. [ABSTRACT FROM AUTHOR]

Abstract: A real time FFT-based impedance meter is here presented. It is realized simply by a standard PC in addition to a low cost two channels hardware device, and is based on a cost-effective algorithm to meaningfully reduce the known problem of the bias introduced by the relative phase and amplitude error between channels. The impedance meter exploits the implementation of an ad hoc cost-effective algorithm and a synchronous sampling allows eliminating the leakage error. The aliasing and the spectral interference are eliminated by means of an anti-aliasing filter and the use of very low distortion sinusoidal signals. Automatic measurements can be managed too, capturing different measures at different test frequencies and displaying them graphically on the PC screen. To validate the measured results comparative test were performed with respect to certified and calibrated commercially available multimeters known with good accuracies. Finally, this novel impedance meter integrates a home-made software, previously reported capable to implement real time virtual instruments. [Copyright &y& Elsevier]

Introduction: Adductor-type spasmodic dysphonia is a task-specific focal dystonia characterized by involuntary laryngeal muscle spasms. Due to the lack of quantitative instrumental tools, voice assessment in patients with adductor-type spasmodic dysphonia is mainly based on qualitative neurologic examination. We evaluated patients with cepstral analysis and specific machine-learning algorithms and compared the results with those collected in healthy subjects. In patients, we also used cepstral analysis and machine-learning algorithms to investigate the effect of botulinum neurotoxin type A.Methods: We investigated 60 patients affected by adductor-type spasmodic dysphonia before botulinum neurotoxin type A therapy and 60 age and gender-matched healthy subjects. A subgroup of 35 patients was also evaluated after botulinum neurotoxin type A therapy. We recorded the sustained emission of a vowel and a sentence by means of a high-definition audio recorder. Voice samples underwent cepstral analysis as well as machine-learning algorithm classification techniques.Results: Cepstral analysis was able to differentiate between healthy subjects and patients, but receiver operating characteristic curve analysis demonstrated that machine-learning algorithms achieved better results than cepstral analysis in differentiating healthy subjects and patients affected by adductor-type spasmodic dysphonia. Similar results were obtained when differentiating patients before and after botulinum neurotoxin type A therapy. Cepstral analysis and machine-learning measures correlated with the severity of voice impairment in patients before and after botulinum neurotoxin type A therapy.Conclusions: Cepstral analysis and machine-learning algorithms are new tools that offer meaningful support to clinicians in the diagnosis and treatment of adductor-type spasmodic dysphonia. [ABSTRACT FROM AUTHOR]

Although many advancements have been made on myoelectric pattern-recognition, the control of poly-articulated 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 − µP6 and µP8 − 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. We perform an offline analysis on two datasets, alongside two other standard models: nonlinear logistic regression (NLR) and linear discriminant analysis (LDA). 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). The proposed algorithms allow to reduce the amount of training data and training times without compromising recognition rates. 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. [ABSTRACT FROM AUTHOR]

In this work, we present a novel multisensory electronic architecture that can work with very low voltage requirements thus enabling power management directly from harvesting-based low-voltage sources. The harvesting system here proposed relays on thermoelectric generator cells useful for furnishing additional power to an electronic system made of a home-made sensory glove, an inertial measuring unit, and an electromyography device, aimed at providing full measures of the arm-hand dexterities. The thermoelectric generator cells are optimized to work as an array configuration up to 10 cells series-connected and the energy conversion is managed with a commercial DC/DC with MPPT algorithm. Experimental results demonstrate that the harvester can provide a maximum open-circuit voltage of 600 mV and a maximum power level of 9.9 mW for a standard human body temperature of 37 °C and a room temperature of 22 °C. Moreover, the system is able to fully charge an 800 mA/h, single-cell Li-Po battery within 35 h, showing a 30% efficiency loss. Since all the electronics in the multisensory architecture can run with voltages as low as the 3.7 V Li-Po battery, the harvesting system can be suitable to feed the device with an ad-hoc, high-efficiency boost conversion, thus replacing the USB-oriented built-in supply and recharge. [ABSTRACT FROM AUTHOR]

Tetraplegic people need continuous assistance in every daily activity. Assistive technologies can improve, to a certain degree, their quality of life allowing partial autonomy with powering their residual capability of movements. In this work, we propose a novel wire-free low-cost user-friendly battery-operated sensory headwear, which allows home automation controlled by head movements. The headwear is equipped with an inertial measurement unit (IMU), a low power microcontroller and a transmission module to measure, condition and wireless transmit data related to head movements. Such a sensory headwear allows the subject, simply by head movements, either to select one computer icon among an ensemble or to select one actuator, among a number of others. Each icon and each actuator drive a specific physical action in a home or work environment. We devoted particular efforts to increase the battery autonomy, by means of radio frequency energy harvesting solutions, for lasting operational mode. The harvester, based on commercial chipsets, was optimized in the 2.4–2.5 GHz range to exploit headwear itself radiated energy and environmental energy, in particular from Wi-Fi and Bluetooth surrounding devices. An average efficiency, calculated as output to input power ratio, of around 60% at −5dBm input power level has been obtained. [ABSTRACT FROM AUTHOR]

Abstract Developmental coordination disorder (DCD) and attention-deficit hyperactivity disorder (ADHD) are neuro-developmental disorders, starting in childhood, which can affect the planning of movements and the coordination. We investigated how and in which measure a system based on wearable inertial measurement units (IMUs) can provide an objective support to the diagnosis of motor impairments in school-aged children. The IMUs measured linear and rotational movements of 37 schoolchildren, 7−10yo, 17 patients and 20 control subjects, during the execution of motor exercises, performed under medical and psychiatric supervision, to assess different aspects of the motor coordination. The measured motor parameters showed a high degree of significance in discriminating the ADHD/DCD patients from the healthy subjects, pointing out which motor tasks are worth focusing on. So, medical doctors have a novel key lecture to state a diagnosis, gaining in objectivity with respect to the standard procedures which mainly involve subjective human judgment. Differently to other works, we propose a novel approach in terms of number of used IMUs and of performed motor tasks. Moreover, we demonstrate the meaningful parameters to be considered as more discriminant in supporting the medical diagnosis. [ABSTRACT FROM AUTHOR]

Human maintain their body balance by sensorimotor controls mainly based on information gathered from vision, proprioception and vestibular systems. When there is a lack of information, caused by pathologies, diseases or aging, the subject may fall. In this context, we developed a system to augment information gathering, providing the subject with warning audio-feedback signals related to his/her equilibrium. The system comprises an inertial measurement unit (IMU), a data processing unit, a headphone audio device and a software application. The IMU is a low-weight, small-size wireless instrument that, body-back located between the L2 and L5 lumbar vertebrae, measures the subject's trunk kinematics. The application drives the data processing unit to feeding the headphone with electric signals related to the kinematic measures. Consequently, the user is audio-alerted, via headphone, of his/her own equilibrium, hearing a pleasant sound when in a stable equilibrium, or an increasing bothering sound when in an increasing unstable condition. Tests were conducted on a group of six older subjects (59y-61y, SD = 2.09y) and a group of four young subjects (21y-26y, SD = 2.88y) to underline difference in effectiveness of the system, if any, related to the age of the users. For each subject, standing balance tests were performed in normal or altered conditions, such as, open or closed eyes, and on a solid or foam surface. The system was evaluated in terms of usability, reliability, and effectiveness in improving the subject's balance in all conditions. As a result, the system successfully helped the subjects in reducing the body swaying within 10.65%-65.90%, differences depending on subjects’ age and test conditions. [ABSTRACT FROM AUTHOR]