System Architecture for VR Yoga Therapy Platform with 6-DoF Whole-Body Avatar Tracking.

Chronic pain is a leading cause of morbidity among children and adolescents affecting 35% of the global population. Pediatric chronic pain management requires integrative health methods spanning physical and psychological subsystems through various mind-body interventions. Yoga therapy is one such method, known for its ability to improve the quality of life both physically and psychologically in chronic pain conditions. However, maintaining the clinical outcomes of personalized yoga therapy sessions at-home is challenging due to fear of movement, lack of motivation, and boredom. Virtual Reality (VR) has the potential to bridge the gap between the clinic and home by motivating engagement and mitigating pain-related anxiety or fear of movement. We developed a multi-modal algorithmic architecture for fusing real-time 3D human body pose estimation models with custom developed inverse kinematics models of physical movement to render biomechanically informed 6-DoF whole-body avatars capable of embodying an individual's real-time yoga poses within the VR environment. Experiments conducted among control participants demonstrated superior movement tracking accuracy over existing commercial off-the-shelf avatar tracking solutions, leading to successful embodiment and engagement. These findings demonstrate the feasibility of rendering virtual avatar movements that embody complex physical poses such as those encountered in yoga therapy. The impact of this work moves the field one step closer to an interactive system to facilitate at-home individual or group yoga therapy for children with chronic pain conditions.

Classification performance of sEMG and kinematic parameters for distinguishing between non-lame and induced lameness conditions in horses.

Despite its proven research applications, it remains unknown whether surface electromyography (sEMG) can be used clinically to discriminate non-lame from lame conditions in horses. This study compared the classification performance of sEMG absolute value (sEMGabs) and asymmetry (sEMGasym) parameters, alongside validated kinematic upper-body asymmetry parameters, for distinguishing non-lame from induced fore- (iFL) and hindlimb (iHL) lameness. Bilateral sEMG and 3D-kinematic data were collected from clinically non-lame horses (n = 8) during in-hand trot. iFL and iHL (2-3/5 AAEP) were induced on separate days using a modified horseshoe, with baseline data initially collected each day. sEMG signals were DC-offset removed, high-pass filtered (40 Hz), and full-wave rectified. Normalized, average rectified value (ARV) was calculated for each muscle and stride (sEMGabs), with the difference between right and left-side ARV representing sEMGasym. Asymmetry parameters (MinDiff, MaxDiff, Hip Hike) were calculated from poll, withers, and pelvis vertical displacement. Receiver-operating-characteristic (ROC) and area under the curve (AUC) analysis determined the accuracy of each parameter for distinguishing baseline from iFL or iHL. Both sEMG parameters performed better for detecting iHL (0.97 ≥ AUC ≥ 0.48) compared to iFL (0.77 ≥ AUC ≥ 0.49). sEMGabs performed better (0.97 ≥ AUC ≥ 0.49) than sEMGasym (0.76 ≥ AUC ≥ 0.48) for detecting both iFL and iHL. Like previous studies, MinDiff Poll and Pelvis asymmetry parameters (MinDiff, MaxDiff, Hip Hike) demonstrated excellent discrimination for iFL and iHL, respectively (AUC > 0.95). Findings support future development of multivariate lameness-detection approaches that combine kinematics and sEMG. This may provide a more comprehensive approach to diagnosis, treatment, and monitoring of equine lameness, by measuring the underlying functional cause(s) at a neuromuscular level.

A Virtual Reality Exergame: Clinician-Guided Breathing and Relaxation for Children with Muscular Dystrophy.

This study introduces a VR-based breathing and relaxation exergame tailored for individuals with Duchenne muscular dystrophy (DMD). DMD is a rare neuromuscular disease that leads to respiratory muscle dysfunction with anxiety being a common comorbidity. Clinical management requires frequent visits to rare disease specialists to manage symptom progression. Limited availability and/or proximity of rare disease experts present challenges to care and can lead to missed care opportunities and reduced quality of life. We propose a breathing and relaxation exergame with remote telehealth applicability that incorporates shared patient-clinician VR interaction, and physiological sensors that provide both real-time feedback to the patient and health analytics for the clinician. The game focuses on two key aspects of DMD clinical care that can be mediated through control of breathing: relaxation/mindfulness training and respiratory muscle exercise. The system was evaluated among 13 individuals, including 4 participants with DMD. Feedback surveys, interviews, and focus group discussions with participants, accompanying family members, and clinicians demonstrated the feasibility of this VR tool for telehealth or as part of a home exercise program.

Electromyographic and Kinematic Comparison of the Leading and Trailing Fore- and Hindlimbs of Horses during Canter.

This study compared muscle activity and movement between the leading (Ld) and trailing (Tr) fore- (F) and hindlimbs (H) of horses cantering overground. Three-dimensional kinematic and surface electromyography (sEMG) data were collected from right triceps brachii, biceps femoris, middle gluteal, and splenius from 10 ridden horses during straight left- and right-lead canter. Statistical parametric mapping evaluated between-limb (LdF vs. TrF, LdH vs. TrH) differences in time- and amplitude-normalized sEMG and joint angle-time waveforms over the stride. Linear mixed models evaluated between-limb differences in discrete sEMG activation timings, average rectified values (ARV), and spatio-temporal kinematics. Significantly greater gluteal ARV and activity duration facilitated greater limb retraction, hip extension, and stifle flexion (p < 0.05) in the TrH during stance. Earlier splenius activation during the LdF movement cycle (p < 0.05), reflected bilateral activation during TrF/LdH diagonal stance, contributing to body pitching mechanisms in canter. Limb muscles were generally quiescent during swing, where significantly greater LdF/H protraction was observed through greater elbow and hip flexion (p < 0.05), respectively. Alterations in muscle activation facilitate different timing and movement cycles of the leading and trailing limbs, which justifies equal training on both canter leads to develop symmetry in muscular strength, enhance athletic performance, and mitigate overuse injury risks.

Effects of Timed Frontal Plane Pelvic Moments During Overground Walking With a Mobile TPAD System.

Robotic gait training may improve overground ambulation for individuals with poor control over pelvic motion. However, there is a need for an overground gait training robotic device that allows full control of pelvic movement and synchronizes applied forces to the user's gait. This work evaluates an overground robotic gait trainer that applies synchronized forces on the user's pelvis, the mobile Tethered Pelvic Assist Device. To illustrate one possible control scheme, we apply assistive frontal plane pelvic moments synchronized with the user's continuous gait in real-time. Ten healthy adults walked with the robotic device, with and without frontal plane moments. The frontal plane moments corresponded to 10% of the user's body weight with a moment arm of half their pelvic width. The frontal plane moments significantly increased the range of frontal plane pelvic angles from 2.6° to 9.9° and the sagittal and transverse planes from 4.6° to 10.1° and 3.0° to 8.3°, respectively. The frontal plane moments also significantly increased the activation of the left gluteus medius muscle, which assists in regulating pelvic obliquity. The right gluteus medius muscle activation did not significantly differ when frontal plane moments were applied. This work highlights the ability of the mobile Tethered Pelvic Assist Device to apply a continuous pelvic moment that is synchronized with the user's gait cycle. This capability could change how overground robotic gait training strategies are designed and applied. The potential for gait training interventions that target gait deficits or muscle weakness can now be explored with the mobile Tethered Pelvic Assist Device.

Adaptations in equine axial movement and muscle activity occur during induced fore- and hindlimb lameness: A kinematic and electromyographic evaluation during in-hand trot.

BACKGROUND: The inter-relationship between equine thoracolumbar motion and muscle activation during normal locomotion and lameness is poorly understood. OBJECTIVE: To compare thoracolumbar and pelvic kinematics and longissimus dorsi (longissimus) activity of trotting horses between baseline and induced forelimb (iFL) and hindlimb (iHL) lameness. STUDY DESIGN: Controlled experimental cross-over study. METHODS: Three-dimensional kinematic data from the thoracolumbar vertebrae and pelvis, and bilateral surface electromyography (sEMG) data from longissimus at T14 and L1, were collected synchronously from clinically nonlame horses (n = 8) trotting overground during a baseline evaluation, and during iFL and iHL conditions (2-3/5 AAEP), induced on separate days using a lameness model (modified horseshoe). Motion asymmetry parameters, maximal thoracolumbar flexion/extension and lateral bending angles, and pelvis range of motion (ROM) were calculated from kinematic data. Normalised average rectified value (ARV) and muscle activation onset, offset and activity duration were calculated from sEMG signals. Mixed model analysis and statistical parametric mapping compared discrete and continuous variables between conditions (α = 0.05). RESULTS: Asymmetry parameters reflected the degree of iFL and iHL. Maximal thoracolumbar flexion and pelvis pitch ROM increased significantly following iFL and iHL. During iHL, peak lateral bending increased towards the nonlame side (NLS) and decreased towards the lame side (LS). Longissimus ARV significantly increased bilaterally at T14 and L1 for iHL, but only at LS L1 for iFL. Longissimus activation was significantly delayed on the NLS and precipitated on the LS during iHL, but these clear phasic shifts were not observed in iFL. MAIN LIMITATIONS: Findings should be confirmed in clinical cases. CONCLUSIONS: Distinctive, significant adaptations in thoracolumbar and pelvic motion and underlying longissimus activity occur during iFL and iHL and are detectable using combined motion capture and sEMG. For iFL, these adaptations occur primarily in a cranio-caudal direction, whereas for iHL, lateral bending and axial rotation are also involved.

CONTEXTO: O relacionamento entre a movimentação toracolombar e a ativação muscular durante a locomoção normal e quando há claudicação é pouco compreendido. OBJETIVOS: Comparar a cinemática toracolombar e pélvica e a atividade do músculo longissimus dorsi (longissimus) em cavalos ao trote entre o momento inicial (baseline) e claudicação induzida no membro torácico (iFL) e pélvico (iHL). DELINEAMENTO DO ESTUDO: Estudo experimental controlado cruzado. METODOLOGIA: Dados cinemáticos tridimensionais das vertebras toracolombar e pelve, e eletromiografia de superfície (sEMG) bilateral do longissimus na T14 e L1 foram coletados de forma síncrona de cavalos clinicamente não claudicantes (n = 8) trotando no momento inicial (baseline), e durante iFL e iHL (2-3/5 AAEP), induzidos separadamente em dias distintos utilizando um modelo de claudicação (ferradura modificada). Parâmetros de movimentação assimétrica, flexão/extensão máxima da toracolombar e ângulos de virada lateral, e amplitude de movimento da pelve (ROM) foram calculados a partir dos dados de cinemática. O valor médio normalizado retificado (ARV) e início da ativação muscular, e término e duração da atividade foram calculados utilizando sinais de sEMG. Análise de modelo misto e mapeamento paramétrico estatístico compararam variáveis discretas e contínuas entre condições (α=0.05). RESULTADOS: Parâmetros de assimetria refletiram o nível de iFL e iHL. A flexão toracolombar máxima e a ROM da pelve aumentaram significativamente com iFL e iHL. Durante iHL, o pico de flexão lateral aumentou em direção ao lado não-claudicante (NSL) e diminuiu em direção ao lado claudicante (LS). Longissimus ARV aumentou significativamente para ambos os lados na T14 e L1 para iHL, mas apenas no LS para iFL. A ativação do longissimus foi significativamente retardado no NLS e precipitado no LS durante iHL, mas essa mudança de fase clara não foi observada no iFL. PRINCIPAIS LIMITAÇÕES: Esses achados precisam ser confirmados em casos clínicos. CONCLUSÕES: Adaptações significantes e distintas na movimentação toracolombar e pélvica e atividade do músculo longissimus ocorre durante iFL e iHL e são detectadas utilizando captura de movimento e sEMG. Para iFL, essas adaptações ocorrem primariamente na direção cranio-caudal, enquanto que em iHL, movimento lateral e rotação axial também estão envolvidos.

Adaptations in equine appendicular muscle activity and movement occur during induced fore- and hindlimb lameness: An electromyographic and kinematic evaluation.

The relationship between lameness-related adaptations in equine appendicular motion and muscle activation is poorly understood and has not been studied objectively. The aim of this study was to compare muscle activity of selected fore- and hindlimb muscles, and movement of the joints they act on, between baseline and induced forelimb (iFL) and hindlimb (iHL) lameness. Three-dimensional kinematic data and surface electromyography (sEMG) data from the fore- (triceps brachii, latissimus dorsi) and hindlimbs (superficial gluteal, biceps femoris, semitendinosus) were bilaterally and synchronously collected from clinically non-lame horses (n = 8) trotting over-ground (baseline). Data collections were repeated during iFL and iHL conditions (2-3/5 AAEP), induced on separate days using a modified horseshoe. Motion asymmetry parameters and continuous joint and pro-retraction angles for each limb were calculated from kinematic data. Normalized average rectified value (ARV) and muscle activation onset, offset and activity duration were calculated from sEMG signals. Mixed model analysis and statistical parametric mapping, respectively, compared discrete and continuous variables between conditions (α= 0.05). Asymmetry parameters reflected the degree of iFL and iHL. Increased ARV occurred across muscles following iFL and iHL, except non-lame side forelimb muscles that significantly decreased following iFL. Significant, limb-specific changes in sEMG ARV, and activation timings reflected changes in joint angles and phasic shifts of the limb movement cycle following iFL and iHL. Muscular adaptations during iFL and iHL are detectable using sEMG and primarily involve increased bilateral activity and phasic activation shifts that reflect known compensatory movement patterns for reducing weightbearing on the lame limb. With further research and development, sEMG may provide a valuable diagnostic aid for quantifying the underlying neuromuscular adaptations to equine lameness, which are undetectable through human observation alone.

Ability-based Keyboards for Augmentative and Alternative Communication: Understanding How Individuals' Movement Patterns Translate to More Efficient Keyboards: Methods to Generate Keyboards Tailored to User-specific Motor Abilities.

This study presents the evaluation of ability-based methods extended to keyboard generation for alternative communication in people with dexterity impairments due to motor disabilities. Our approach characterizes user-specific cursor control abilities from a multidirectional point-select task to configure letters on a virtual keyboard based on estimated time, distance, and direction of movement. These methods were evaluated in three individuals with motor disabilities against a generically optimized keyboard and the ubiquitous QWERTY keyboard. We highlight key observations relating to the heterogeneity of the manifestation of motor disabilities, perceived importance of communication technology, and quantitative improvements in communication performance when characterizing an individual's movement abilities to design personalized AAC interfaces.

Ability-Based Methods for Personalized Keyboard Generation.

This study introduces an ability-based method for personalized keyboard generation, wherein an individual's own movement and human-computer interaction data are used to automatically compute a personalized virtual keyboard layout. Our approach integrates a multidirectional point-select task to characterize cursor control over time, distance, and direction. The characterization is automatically employed to develop a computationally efficient keyboard layout that prioritizes each user's movement abilities through capturing directional constraints and preferences. We evaluated our approach in a study involving 16 participants using inertial sensing and facial electromyography as an access method, resulting in significantly increased communication rates using the personalized keyboard (52.0 bits/min) when compared to a generically optimized keyboard (47.9 bits/min). Our results demonstrate the ability to effectively characterize an individual's movement abilities to design a personalized keyboard for improved communication. This work underscores the importance of integrating a user's motor abilities when designing virtual interfaces.

Surface Electromyography-Based Recognition, Synthesis, and Perception of Prosodic Subvocal Speech.

Purpose This study aimed to evaluate a novel communication system designed to translate surface electromyographic (sEMG) signals from articulatory muscles into speech using a personalized, digital voice. The system was evaluated for word recognition, prosodic classification, and listener perception of synthesized speech. Method sEMG signals were recorded from the face and neck as speakers with (n = 4) and without (n = 4) laryngectomy subvocally recited (silently mouthed) a speech corpus comprising 750 phrases (150 phrases with variable phrase-level stress). Corpus tokens were then translated into speech via personalized voice synthesis (n = 8 synthetic voices) and compared against phrases produced by each speaker when using their typical mode of communication (n = 4 natural voices, n = 4 electrolaryngeal [EL] voices). Naïve listeners (n = 12) evaluated synthetic, natural, and EL speech for acceptability and intelligibility in a visual sort-and-rate task, as well as phrasal stress discriminability via a classification mechanism. Results Recorded sEMG signals were processed to translate sEMG muscle activity into lexical content and categorize variations in phrase-level stress, achieving a mean accuracy of 96.3% (SD = 3.10%) and 91.2% (SD = 4.46%), respectively. Synthetic speech was significantly higher in acceptability and intelligibility than EL speech, also leading to greater phrasal stress classification accuracy, whereas natural speech was rated as the most acceptable and intelligible, with the greatest phrasal stress classification accuracy. Conclusion This proof-of-concept study establishes the feasibility of using subvocal sEMG-based alternative communication not only for lexical recognition but also for prosodic communication in healthy individuals, as well as those living with vocal impairments and residual articulatory function. Supplemental Material https://doi.org/10.23641/asha.14558481.

Muscle Function and Kinematics during Submaximal Equine Jumping: What Can Objective Outcomes Tell Us about Athletic Performance Indicators?

Selection and training practices for jumping horses have not yet been validated using objective performance analyses. This study aimed to quantify the differences and relationships between movement and muscle activation strategies in horses with varying jump technique to identify objective jumping performance indicators. Surface electromyography (sEMG) and three-dimensional kinematic data were collected from horses executing a submaximal jump. Kinematic variables were calculated based on equestrian-derived performance indicators relating to impulsion, engagement and joint articulation. Horses were grouped using an objective performance indicator-center of mass (CM) elevation during jump suspension (ZCM). Between-group differences in kinematic variables and muscle activation timings, calculated from sEMG data, were analyzed using one-way ANOVA. Statistical parametric mapping (SPM) evaluated between-group differences in time and amplitude-normalized sEMG waveforms. Relationships between movement and muscle activation were evaluated using Pearson correlation coefficients. Horses with the greatest ZCM displayed significantly (p < 0.05) shorter gluteal contractions at take-off, which were significantly correlated (p < 0.05) with a faster approach and more rapid hindlimb shortening and CM vertical displacement and velocity, as well as shorter hindlimb stance duration at take-off. Findings provide objective support for prioritizing equestrian-derived performance indicators related to the generation of engagement, impulsion and hindlimb muscle power when selecting or training jumping horses.

Motor unit drive: a neural interface for real-time upper limb prosthetic control.

OBJECTIVE: Modern prosthetic limbs have made strident gains in recent years, incorporating terminal electromechanical devices that are capable of mimicking the human hand. However, access to these advanced control capabilities has been prevented by fundamental limitations of amplitude-based myoelectric neural interfaces, which have remained virtually unchanged for over four decades. Consequently, nearly 23% of adults and 32% of children with major traumatic or congenital upper-limb loss abandon regular use of their myoelectric prosthesis. To address this healthcare need, we have developed a noninvasive neural interface technology that maps natural motor unit increments of neural control and force into biomechanically informed signals for improved prosthetic control. APPROACH: Our technology, referred to as motor unit drive (MU Drive), utilizes real-time machine learning algorithms for directly measuring motor unit firings from surface electromyographic signals recorded from residual muscles of an amputated or congenitally missing limb. The extracted firings are transformed into biomechanically informed signals based on the force generating properties of individual motor units to provide a control source that represents the intended movement. MAIN RESULTS: We evaluated the characteristics of the MU Drive control signals and compared them to conventional amplitude-based myoelectric signals in healthy subjects as well as subjects with congenital or traumatic trans-radial limb-loss. Our analysis established a vital proof-of-concept: MU Drive provides a more responsive real-time signal with improved smoothness and more faithful replication of intended limb movement that overcomes the trade-off between performance and latency inherent to amplitude-based myoelectric methods. SIGNIFICANCE: MU Drive is the first neural interface for prosthetic control that provides noninvasive real-time access to the natural motor control mechanisms of the human nervous system. This new neural interface holds promise for improving prosthetic function by achieving advanced control that better reflects the user intent. Beyond the immediate advantages in the field of prosthetics, MU Drive provides an innovative alternative for advancing the control of exoskeletons, assistive devices, and other robotic rehabilitation applications.

Development of sEMG sensors and algorithms for silent speech recognition.

OBJECTIVE: Speech is among the most natural forms of human communication, thereby offering an attractive modality for human-machine interaction through automatic speech recognition (ASR). However, the limitations of ASR-including degradation in the presence of ambient noise, limited privacy and poor accessibility for those with significant speech disorders-have motivated the need for alternative non-acoustic modalities of subvocal or silent speech recognition (SSR). APPROACH: We have developed a new system of face- and neck-worn sensors and signal processing algorithms that are capable of recognizing silently mouthed words and phrases entirely from the surface electromyographic (sEMG) signals recorded from muscles of the face and neck that are involved in the production of speech. The algorithms were strategically developed by evolving speech recognition models: first for recognizing isolated words by extracting speech-related features from sEMG signals, then for recognizing sequences of words from patterns of sEMG signals using grammar models, and finally for recognizing a vocabulary of previously untrained words using phoneme-based models. The final recognition algorithms were integrated with specially designed multi-point, miniaturized sensors that can be arranged in flexible geometries to record high-fidelity sEMG signal measurements from small articulator muscles of the face and neck. MAIN RESULTS: We tested the system of sensors and algorithms during a series of subvocal speech experiments involving more than 1200 phrases generated from a 2200-word vocabulary and achieved an 8.9%-word error rate (91.1% recognition rate), far surpassing previous attempts in the field. SIGNIFICANCE: These results demonstrate the viability of our system as an alternative modality of communication for a multitude of applications including: persons with speech impairments following a laryngectomy; military personnel requiring hands-free covert communication; or the consumer in need of privacy while speaking on a mobile phone in public.

Silent Speech Recognition as an Alternative Communication Device for Persons with Laryngectomy.

Each year thousands of individuals require surgical removal of their larynx (voice box) due to trauma or disease, and thereby require an alternative voice source or assistive device to verbally communicate. Although natural voice is lost after laryngectomy, most muscles controlling speech articulation remain intact. Surface electromyographic (sEMG) activity of speech musculature can be recorded from the neck and face, and used for automatic speech recognition to provide speech-to-text or synthesized speech as an alternative means of communication. This is true even when speech is mouthed or spoken in a silent (subvocal) manner, making it an appropriate communication platform after laryngectomy. In this study, 8 individuals at least 6 months after total laryngectomy were recorded using 8 sEMG sensors on their face (4) and neck (4) while reading phrases constructed from a 2,500-word vocabulary. A unique set of phrases were used for training phoneme-based recognition models for each of the 39 commonly used phonemes in English, and the remaining phrases were used for testing word recognition of the models based on phoneme identification from running speech. Word error rates were on average 10.3% for the full 8-sensor set (averaging 9.5% for the top 4 participants), and 13.6% when reducing the sensor set to 4 locations per individual (n=7). This study provides a compelling proof-of-concept for sEMG-based alaryngeal speech recognition, with the strong potential to further improve recognition performance.

Decomposition of surface EMG signals from cyclic dynamic contractions.

Over the past 3 decades, various algorithms used to decompose the electromyographic (EMG) signal into its constituent motor unit action potentials (MUAPs) have been reported. All are limited to decomposing EMG signals from isometric contraction. In this report, we describe a successful approach to decomposing the surface EMG (sEMG) signal collected from cyclic (repeated concentric and eccentric) dynamic contractions during flexion/extension of the elbow and during gait. The increased signal complexity introduced by the changing shapes of the MUAPs due to relative movement of the electrodes and the lengthening/shortening of muscle fibers was managed by an incremental approach to enhancing our established algorithm for decomposing sEMG signals obtained from isometric contractions. We used machine-learning algorithms and time-varying MUAP shape discrimination to decompose the sEMG signal from an increasingly challenging sequence of pseudostatic and dynamic contractions. The accuracy of the decomposition results was assessed by two verification methods that have been independently evaluated. The firing instances of the motor units had an accuracy of ∼90% with a MUAP train yield as high as 25. Preliminary observations from the performance of motor units during cyclic contractions indicate that during repetitive dynamic contractions, the control of motor units is governed by the same rules as those evidenced during isometric contractions. Modifications in the control properties of motoneuron firings reported by previous studies were not confirmed. Instead, our data demonstrate that the common drive and hierarchical recruitment of motor units are preserved during concentric and eccentric contractions.

Dynamical learning and tracking of tremor and dyskinesia from wearable sensors.

We have developed and evaluated several dynamical machine-learning algorithms that were designed to track the presence and severity of tremor and dyskinesia with 1-s resolution by analyzing signals collected from Parkinson's disease (PD) patients wearing small numbers of hybrid sensors with both 3-D accelerometeric and surface-electromyographic modalities. We tested the algorithms on a 44-h signal database built from hybrid sensors worn by eight PD patients and four healthy subjects who carried out unscripted and unconstrained activities of daily living in an apartment-like environment. Comparison of the performance of our machine-learning algorithms against independent clinical annotations of disorder presence and severity demonstrates that, despite their differing approaches to dynamic pattern classification, dynamic neural networks, dynamic support vector machines, and hidden Markov models were equally effective in keeping error rates of the dynamic tracking well below 10%. A common set of experimentally derived signal features were used to train the algorithm without the need for subject-specific learning. We also found that error rates below 10% are achievable even when our algorithms are tested on data from a sensor location that is different from those used in algorithm training.

High-resolution tracking of motor disorders in Parkinson's disease during unconstrained activity.

Parkinson's disease (PD) can present with a variety of motor disorders that fluctuate throughout the day, making assessment a challenging task. Paper-based measurement tools can be burdensome to the patient and clinician and lack the temporal resolution needed to accurately and objectively track changes in motor symptom severity throughout the day. Wearable sensor-based systems that continuously monitor PD motor disorders may help to solve this problem, although critical shortcomings persist in identifying multiple disorders at high temporal resolution during unconstrained activity. The purpose of this study was to advance the current state of the art by (1) introducing hybrid sensor technology to concurrently acquire surface electromyographic (sEMG) and accelerometer data during unconstrained activity and (2) analyzing the data using dynamic neural network algorithms to capture the evolving temporal characteristics of the sensor data and improve motor disorder recognition of tremor and dyskinesia. Algorithms were trained (n=11 patients) and tested (n=8 patients; n=4 controls) to recognize tremor and dyskinesia at 1-second resolution based on sensor data features and expert annotation of video recording during 4-hour monitoring periods of unconstrained daily activity. The algorithms were able to make accurate distinctions between tremor, dyskinesia, and normal movement despite the presence of diverse voluntary activity. Motor disorder severity classifications averaged 94.9% sensitivity and 97.1% specificity based on 1 sensor per symptomatic limb. These initial findings indicate that new sensor technology and software algorithms can be effective in enhancing wearable sensor-based system performance for monitoring PD motor disorders during unconstrained activities.

Preferred sensor sites for surface EMG signal decomposition.

Technologies for decomposing the electromyographic (EMG) signal into its constituent motor unit action potential trains have become more practical by the advent of a non-invasive methodology using surface EMG (sEMG) sensors placed on the skin above the muscle of interest (De Luca et al 2006 J. Neurophysiol. 96 1646-57 and Nawab et al 2010 Clin. Neurophysiol. 121 1602-15). This advancement has widespread appeal among researchers and clinicians because of the ease of use, reduced risk of infection, and the greater number of motor unit action potential trains obtained compared to needle sensor techniques. In this study we investigated the influence of the sensor site on the number of identified motor unit action potential trains in six lower limb muscles and one upper limb muscle with the intent of locating preferred sensor sites that provided the greatest number of decomposed motor unit action potential trains, or motor unit yield. Sensor sites rendered varying motor unit yields throughout the surface of a muscle. The preferred sites were located between the center and the tendinous areas of the muscle. The motor unit yield was positively correlated with the signal-to-noise ratio of the detected sEMG. The signal-to-noise ratio was inversely related to the thickness of the tissue between the sensor and the muscle fibers. A signal-to-noise ratio of 3 was found to be the minimum required to obtain a reliable motor unit yield.

Inter-electrode spacing of surface EMG sensors: reduction of crosstalk contamination during voluntary contractions.

We investigated the influence of inter-electrode spacing on the degree of crosstalk contamination in surface electromyographic (sEMG) signals in the tibialis anterior (target muscle), generated by the triceps surae (crosstalk muscle), using bar and disk electrode arrays. The degree of crosstalk contamination was assessed for voluntary constant-force isometric contractions and for dynamic contractions during walking. Single-differential signals were acquired with inter-electrode spacing ranging from 5 mm to 40 mm. Additionally, double differential signals were acquired at 10 mm spacing using the bar electrode array. Crosstalk contamination at the target muscle was expressed as the ratio of the detected crosstalk signal to that of the target muscle signal. The crosstalk contamination ratio approached a mean of 50% for the 40 mm spacing for triceps surae muscle contractions at 80% MVC and tibialis anterior muscle contractions at 10% MVC. For single differential recordings, the minimum crosstalk contamination was obtained from the 10 mm spacing. The results showed no significant differences between the bar and disk electrode arrays. During walking, the crosstalk contamination on the tibialis anterior muscle reached levels of 23% for a commonly used 22 mm spacing single-differential disk sensor, 17% for a 10 mm spacing single-differential bar sensor, and 8% for a 10 mm double-differential bar sensor. For both studies the effect of electrode spacing on crosstalk contamination was statistically significant. Crosstalk contamination and inter-electrode spacing should therefore be a serious concern in gait studies when the sEMG signal is collected with single differential sensors. The contamination can distort the target muscle signal and mislead the interpretation of its activation timing and force magnitude.

Resolving signal complexities for ambulatory monitoring of motor function in Parkinson's disease.

Automatic tracking of movement disorders in patients with Parkinson's disease (PD) is dependent on the ability of machine learning algorithms to resolve the complex and unpredictable characteristics of wearable sensor data. The challenge reflects the variety of movement disorders that fluctuate throughout the day which can be confounded by voluntary activities of daily life. Our approach is the development of multiple dynamic neural network (DNN) classifiers whose application are governed by a rule-based controller within the Integrated Processing and Understanding of Signals (IPUS) framework. Solutions are described for time-varying occurrences of tremor and dyskinesia, classified at 1 s resolution from surface electromyographic (sEMG) and tri-axial accelerometer (ACC) data acquired from patients with PD. The networks were trained and tested on separate datasets, respectively, while subjects performed unscripted and unconstrained activities in a home-like setting. Performance of the classifiers achieved an overall global error rate of less than 10%.