Concerto of movement: how expertise shapes the synergistic control of upper limb muscles in complex motor tasks with varying tempo and dynamics.

Objective. This research aims to reveal how the synergistic control of upper limb muscles adapts to varying requirements in complex motor tasks and how expertise shapes the motor modules.Approach. We study the muscle synergies of a complex, highly skilled and flexible task-piano playing-and characterize expertise-related muscle-synergy control that permits the experts to effortlessly execute the same task at different tempo and force levels. Surface EMGs (28 muscles) were recorded from adult novice (N= 10) and expert (N= 10) pianists as they played scales and arpeggios at different tempo-force combinations. Muscle synergies were factorized from EMGs.Main results. We found that experts were able to cover both tempo and dynamic ranges using similar synergy selections and achieved better performance, while novices altered synergy selections more to adapt to the changing tempi and keystroke intensities compared with experts. Both groups relied on fine-tuning the muscle weights within specific synergies to accomplish the different task styles, while the experts could tune the muscles in a greater number of synergies, especially when changing the tempo, and switch tempo over a wider range.Significance. Our study sheds light on the control mechanism underpinning expertise-related motor flexibility in highly skilled motor tasks that require decade-long training. Our results have implications on musical and sports training, as well as motor prosthetic design.

Association between core strength and dynamic balance of throwing hand in professional healthy cricket fast bowlers: A cross sectional study.

BACKGROUND: The core musculature gets activated by feed forward fashion during the movement of upper extremity, as in kinetic chain of throwing, shoulder muscle contributes larger dynamic balance and also in reversed manner. Aim of the current study was to associate the strength of core and the dynamic balance of throwing hand in cricket fast bowlers. METHODS: 72 subjects were initially screened for eligibility, and ultimately, 55 male participants from various cricket coaching academies, aged 19.1 ± 2.6 on average, were included. The mean BMI of the participants was 20.9. The assessments included the Modified Upper Quarter Y Balance Test (mUQYBT)- Medial (M), Supero-Lateral reach (SL), Infero-Lateral reach(IL) along with Core measures- 600 Abdominal flexion test (600 AFT), right side plank test (RSP), Left side plank test (LSP), Beiring Sorenson test (BST), all of which were successfully completed. RESULTS: Based on our findings, we observed a mild positive correlation between the values of mUQYBT and core measures. We employed Pearson's coefficient to evaluate the association, and the R2 values were utilized to quantify the amount of variability. The resulting scores were RSP to SL (r = 0.38, R2 = 0.14), LSP to SL (r = 0.43, R2 = 0.19), LSP to RSP (r = 0.790, R2 = 0.62), BSP to Composite score (r = 0.29, R2 = 0.08), SL to 600 AFT* (r = 0.231, R2 = 0.05) and BMI to IL* (r = -0.107, R2 = 0.01). CONCLUSION: In conclusion, a positive correlation was exhibited between dynamic balance and core strength in healthy cricket fast bowlers. Educating bowlers on proper movement techniques and prescribing targeted exercises can enhance dynamic balance, reducing the risk of injuries.

Short-term effects of Pilates-based exercise on upper limb strength and function in people with Parkinson's disease.

BACKGROUND: People with Parkinson's disease (PD) have impaired upper limb motor coordination, limiting the execution of activities of daily living. This study investigated the feasibility and safety of a short-term Pilates-based exercise program in the treatment of upper limb motor coordination for people with PD. METHODS: Fifteen patients - n (%) 4 women/11 men (27/73), median [interquartile range] age 66 [9] years - participated in this quasi-experimental (before-and-after) clinical trial. Patients underwent a 6-week (30 min/day, 3 days/week) Pilates exercise program using Reformer, Cadillac, Chair, and Barrel equipment. Feasibility was evaluated by adherence to the program and the ability to perform the exercises including progressions on difficulty. Safety was evaluated based on self-reported adverse events. Clinical and functional trends before and after the intervention were also computed regarding handgrip strength (HGS), fine motor coordination (9 Hole Peg Test; 9HPT), bradykinesia (Movement Disorder Society - Unified Parkinson's disease Rating Scale; MDS-UPDRS), and upper limb functionality (Test D'évaluation des Membres Supérieurs des Personnes Âgées, TEMPA). RESULTS: Of the 18 Pilates sessions, exercise adherence was 100%. The only adverse event observed was mild muscle pain. Pre-post differences were observed only for body bradykinesia and hypokinesia (1.0 [0.0] vs. 0.0 [1.0] s, adjusted p = 0.048). CONCLUSIONS: A short-term Pilates-based exercise program in the treatment of upper limb muscle strength, manual dexterity, bradykinesia, and functionality is feasible and safe for people with PD. Changes in upper limb bradykinesia encourage randomized clinical trials.

EMG gesture signal analysis towards diagnosis of upper limb using dual-pathway convolutional neural network.

This research introduces a novel dual-pathway convolutional neural network (DP-CNN) architecture tailored for robust performance in Log-Mel spectrogram image analysis derived from raw multichannel electromyography signals. The primary objective is to assess the effectiveness of the proposed DP-CNN architecture across three datasets (NinaPro DB1, DB2, and DB3), encompassing both able-bodied and amputee subjects. Performance metrics, including accuracy, precision, recall, and F1-score, are employed for comprehensive evaluation. The DP-CNN demonstrates notable mean accuracies of 94.93 ± 1.71% and 94.00 ± 3.65% on NinaPro DB1 and DB2 for healthy subjects, respectively. Additionally, it achieves a robust mean classification accuracy of 85.36 ± 0.82% on amputee subjects in DB3, affirming its efficacy. Comparative analysis with previous methodologies on the same datasets reveals substantial improvements of 28.33%, 26.92%, and 39.09% over the baseline for DB1, DB2, and DB3, respectively. The DP-CNN's superior performance extends to comparisons with transfer learning models for image classification, reaffirming its efficacy. Across diverse datasets involving both able-bodied and amputee subjects, the DP-CNN exhibits enhanced capabilities, holding promise for advancing myoelectric control.

Upper-Limb Movement Quality before and after Surgery in Women with Breast Cancer: An Exploratory Study.

(1) Background: This study aimed to describe upper-limb (UL) movement quality parameters in women after breast cancer surgery and to explore their clinical relevance in relation to post-surgical pain and disability. (2) Methods: UL movement quality was assessed in 30 women before and 3 weeks after surgery for breast cancer. Via accelerometer data captured from a sensor located at the distal end of the forearm on the operated side, various movement quality parameters (local dynamic stability, movement predictability, movement smoothness, movement symmetry, and movement variability) were investigated while women performed a cyclic, weighted reaching task. At both test moments, the Quick Disabilities of the Arm, Shoulder, and Hand (Quick DASH) questionnaire was filled out to assess UL disability and pain severity. (3) Results: No significant differences in movement quality parameters were found between the pre-surgical and post-surgical time points. No significant correlations between post-operative UL disability or pain severity and movement quality were found. (4) Conclusions: From this study sample, no apparent clinically relevant movement quality parameters could be derived for a cyclic, weighted reaching task. This suggests that the search for an easy-to-use, quantitative analysis tool for UL qualitative functioning to be used in research and clinical practice should continue.

Study on the Impact of Implementing an Exercise Program Using Fitlight Technology for the Development of Upper Limb Coordinative Abilities in Basketball Players.

The aim of this study was to evaluate the impact of implementing a basketball-specific exercise program using Fitlight technology on the coordinative abilities (reactive coordination, reactive reaction time, and reactive movement combination capacity) of U14 and U16 junior basketball players. This study included 70 male basketball players, 36 subjects U14 and 34 subjects U16, divided into two equal groups for each age category: the experimental group (EG) and the control group (CG). This study included an initial and a final test, between which, training was conducted over a period of 18 weeks. For the EG, the program aimed to develop coordinative abilities through an experimental program that utilized Fitlight technology, while the control groups underwent an identically timed program, but their training did not include the use of technology. Four tests were adapted and applied: the Reactive Reaction Test, Choice Reactive Reaction Test, Reactive Hand-Eye Coordination Test, and a test to evaluate the reactive capacity for combining movements. The results of this study showed statistically significant progress between the initial and final tests for the experimental group, p < 0.05. The Cohen's d values for the experimental groups were above 0.8, indicating a very large effect size, while for the control group, these values were small to medium. The comparative analysis of the experimental groups U14 and U16 and control groups shows statistically significant differences in favor of the experimental groups U14 and U16. This study highlights the effectiveness of implementing specific training programs that use modern technologies in developing coordinative abilities in the training and evaluation process of junior basketball players.

Inter- and intra-athlete technique variability of conventional new ball swing bowling in elite and pre-elite Australian male fast bowlers.

This study aimed to investigate inter- and intra-athlete technique variability in pre-elite and elite Australian fast bowlers delivering new ball conventional swing bowling. Ball grip angle and pelvis, torso, shoulder, elbow, wrist, upper arm, forearm, and hand kinematics were investigated at the point of ball release for inswing and outswing deliveries. Descriptive evaluations of group and individual data and k-means cluster analyses were used to assess inter- and intra-bowler technique variability. Inter-athlete technique and ball grip variability were identified, demonstrating that skilled bowlers use individualised strategies to generate swing. Functional movement variability was demonstrated by intra-athlete variability in successful swing bowling trials. Bowlers demonstrated stable technique parameters in large proximal body segments of the pelvis and torso, providing a level of repeatability to their bowling action. Greater variation was observed in bowling arm kinematics, allowing athletes to manipulate the finger and ball position to achieve the desired seam orientation at the point of ball release. This study demonstrates that skilled bowlers use individualised techniques and grips to generate swing and employ technique variations in successive deliveries. Coaches should employ individualised training strategies and use constraints-led approaches in training environments to encourage bowlers to seek adaptive movement solutions to generate swing.

Intrinsic and extrinsic variables impacting upper quarter Y-balance test scores in sporting cohorts: A systematic review.

INTRODUCTION: The upper quarter y-balance test (YBT-UQ) is a functional screening tool used to detect musculoskeletal injury risk, aid rehabilitation, and monitor dynamic function, strength and control, yet little is currently known about intrinsic and extrinsic factors that influence reach scores. OBJECTIVES: This systematic review aimed to determine if age, sex, or interventions influenced reach scores and whether between-limb differences were common in non-injured sporting populations, with a secondary aim to identify if sport impacted YBT-UQ reach. METHODS: Web of Science, PubMed, and SportDiscus were systematically searched from January 2012 to November 16, 2023, revealing twenty-three studies satisfying inclusion criteria of published in English between 2012 and 2023, healthy participants of any age including both males and females, athletic populations, YBT-UQ use to assess upper limb mobility/stability, report normalised reach scores, and peer-reviewed full-texts. Methodological quality was evaluated via National Institutes of Health (NIH) quality assessment tools for controlled interventions, observational cohort and cross-sectional designs, and pre-post with no control group. RESULTS: Age, sex, sport, and fatigue were influencing factors; greater reach scores were achieved in older athletes (i.e. >18 years), males, and in a well-rested state. Between-limb differences were not common in sporting populations; therefore, asymmetries may be useful for practitioners to aid injury risk identification. CONCLUSION: This is the first systematic review investigating YBT-UQ influencing factors and thereby provides context for clinicians regarding characteristics that impact reach scores in sporting populations, from which normative values could be determined and further aid clinical decisions or areas to improve regarding injury risk.

The Acute Effects of a Preload Upper-Body Power Exercise on 50-m Freestyle Performance in Youth Swimmers.

ABSTRACT: Hill, V, Patterson, S, Buckthorpe, M, and Legg, HS. The acute effects of a preload upper-body power exercise on 50-m freestyle performance in youth swimmers. J Strength Cond Res 38(7): 1295-1299, 2024-This study aimed to investigate the acute effects of a medicine ball slam and the optimal recovery time required to induce a postactivation performance enhancement (PAPE) response on 50-meter freestyle swimming performance. Twenty-four (13 female, 11 male) competitive, adolescent swimmers (mean ± SD: age, 16.7 ± 1.2 years; height, 173.3 ± 6.7 cm; mass, 63.1 ± 6.4 kg) participated in a randomized crossover study. After the PAPE intervention (3 × 5 medicine ball slams), subjects had 1-minute, 4-minute, and 8-minute recovery periods before a 50-m maximal freestyle swim. A 1-way repeated-measures ANOVA revealed that different recovery times elicited changes in 50-m performance (F = 12.12, p < 0.0005). After 4 minutes of recovery, 50-m performance was 1.6% (0.47 seconds) faster (95% confidence interval [CI] [0.17-0.77], p < 0.001). When the data were split by sex, after 4 minutes of recovery, 50-m performance was 2% (0.64 seconds) faster for women (95% CI [0.279-0.998], p < 0.001). In conclusion, an upper-body power exercise, before performance, can induce a PAPE response and enhance 50-m freestyle performance after a 4-minute recovery period.

Influence of floor inclination on handle push and pull forces production of the upper limb.

Floor inclination can alter hand force production, and lower limb kinetics, affecting control operations, and threatening operator safety in various domains, such as aviation, naval, construction industry, or agriculture. This study investigates the effects of different floor inclinations, on handle push or pull force production. Participants performed maximal isometric contraction tasks requiring to exert a maximal voluntary force either by pulling or pushing a handle, at different floor inclinations from -30° to +30° about the transverse and longitudinal axes. Maximal hand force and Ground Reaction Forces about both feet were recorded. The results revealed non-equivalent variations in hand and feet responses as a function of inclination angle. Specifically, there was a significant reduction in handle push-pull force production, up to 70% (p < 0.001) for extreme inclinations, around both axes. This study provides critical data for design engineers, highlighting the challenge of production forces at steep angles.

Associations of upper- and lower-limb muscle strength, mass, and quality with health-related quality of life in community-dwelling older adults.

AIM: This study aimed to investigate the associations between upper- and lower-limb muscle strength, mass, and quality and health-related quality of life (HRQoL) among community-dwelling older adults. METHODS: A cross-sectional study was conducted with 428 Brazilian community-dwelling older adults aged 60 to 80 years. Upper- and lower-limb muscle strength were evaluated through the handgrip strength (HGS) test and the 30-s chair stand test, respectively. Muscle mass was assessed by dual-energy X-ray absorptiometry (DXA) and bioelectrical impedance analysis (BIA). Muscle quality was evaluated using the muscle quality index (MQI). HRQoL was assessed using the World Health Organization Quality of Life Brief Version questionnaire. RESULTS: Lower-limb, but not upper-limb, muscle strength and quality were independently associated with HRQoL, particularly within the domains of physical capacity, environment, and overall HRQoL for both males and females (P < 0.05). DXA- and BIA-derived analyses provided similar results in relation to muscle mass and muscle quality. CONCLUSIONS: Lower-limb, but not upper-limb, muscle strength and quality were independently associated with HRQoL among community-dwelling older adults. Moreover, the results obtained from both BIA and DXA were similar, highlighting that BIA can serve as a viable surrogate method for estimating body composition in resource-limited clinical settings. Geriatr Gerontol Int 2024; 24: 683-692.

Neuromechanical Differences between Pronated and Supinated Forearm Positions during Upper-Body Wingate Tests.

Arm-cycling is a versatile exercise modality with applications in both athletic enhancement and rehabilitation, yet the influence of forearm orientation remains understudied. Thus, this study aimed to investigate the impact of forearm position on upper-body arm-cycling Wingate tests. Fourteen adult males (27.3 ± 5.8 years) underwent bilateral assessments of handgrip strength in standing and seated positions, followed by pronated and supinated forward arm-cycling Wingate tests. Electromyography (EMG) was recorded from five upper-extremity muscles, including anterior deltoid, triceps brachii lateral head, biceps brachii, latissimus dorsi, and brachioradialis. Simultaneously, bilateral normal and propulsion forces were measured at the pedal-crank interface. Rate of perceived exertion (RPE), power output, and fatigue index were recorded post-test. The results showed that a pronated forearm position provided significantly (p < 0.05) higher normal and propulsion forces and triceps brachii muscle activation patterns during arm-cycling. No significant difference in RPE was observed between forearm positions (p = 0.17). A positive correlation was found between seated handgrip strength and peak power output during the Wingate test while pronated (dominant: p = 0.01, r = 0.55; non-dominant: p = 0.03, r = 0.49) and supinated (dominant: p = 0.03, r = 0.51; don-dominant: p = 0.04, r = 0.47). Fatigue changed the force and EMG profile during the Wingate test. In conclusion, this study enhances our understanding of forearm position's impact on upper-body Wingate tests. These findings have implications for optimizing training and performance strategies in individuals using arm-cycling for athletic enhancement and rehabilitation.

Transhumeral prosthesis use affects upper body kinematics and kinetics.

BACKGROUND: Transhumeral (TH) limb loss leads to loss of body mass and reduced shoulder range of motion. Despite most owning a prosthesis, prosthesis abandonment is common. The consequence of TH limb loss and prosthesis use and disuse during gait may be compensation in the upper body, contributing to back pain or injury. Understanding the impact of not wearing a TH prosthesis on upper body asymmetries and spatial-temporal aspects of gait will inform how TH prosthesis use and disuse affects the body. RESEARCH QUESTION: Does TH limb loss alter upper body asymmetries and spatial-temporal parameters during gait when wearing and not wearing a prosthesis compared to able-bodied controls? METHODS: Eight male TH limb loss participants and eight male control participants completed three gait trials at self-selected speeds. The TH limb loss group performed trials with and without their prosthesis. Arm swing, trunk angular displacement, trunk-pelvis moment, and spatial-temporal aspects were compared using non-parametric statistical analyses. RESULTS: Both TH walking conditions showed greater arm swing in the intact limb compared to the residual (p≤0.001), resulting in increased asymmetry compared to the control group (p≤0.001). Without the prosthesis, there was less trunk flexion and lateral flexion compared to the control group (p≤0.001). Maximum moments between the trunk and pelvis were higher in the TH group than the control group (p≤0.05). Spatial-temporal parameters of gait did not differ between the control group and either TH limb loss condition. SIGNIFICANCE: Prosthesis use affects upper body kinematics and kinetics, but does not significantly impact spatial-temporal aspects of gait, suggesting these are compensatory actions. Wearing a prosthesis helps achieve more normative upper body kinematics and kinetics than not wearing a prosthesis, which may help limit back pain. These findings emphasize the importance of encouraging at least passive use of prostheses for individuals with TH limb loss.

Comparison of multi-task ergonomic assessment methods for risk of upper extremity and low back musculoskeletal disorders.

Work-related musculoskeletal disorder of upper extremity multi-task assessment methods (Revised Strain Index [RSI], Distal Upper Extremity Tool [DUET]) and manual handling multi-task assessment methods (Revised NIOSH Lifting Equation [RNLE], Lifting Fatigue Failure Tool [LiFFT]) were compared. RSI and DUET showed a strong correlation (rs = 0.933, p < 0.001) where increasing risk factor exposure resulted in increasing outputs for both methods. RSI and DUET demonstrated fair agreement (κ = 0.299) in how the two methods classified outputs into risk categories (high, moderate or low) when assessing the same tasks. The RNLE and LiFFT showed a strong correlation (rs = 0.903, p = 0.001) where increasing risk factor exposure resulted in increasing outputs, and moderate agreement (κ = 0.574) in classifying the outputs into risk categories (high, moderate or low) when assessing the same tasks. The multi-task assessment methods provide consistent output magnitude rankings in terms of increasing exposure, however some differences exist between how different methods classify the outputs into risk categories.

Effects of abdominal hollowing and bracing on each intervertebral angle during quadruped upper and lower extremity lift: Three-dimensional motion analysis of the spine.

To investigate the effects of intentionally minimizing spinal motion and abdominal muscle contractions on intervertebral angles during quadruped upper and lower extremity lift (QULEL). Fifteen healthy men performed the QULEL under four conditions: without any special instructions (basic), with the intention to minimize spinal motion (intentional), with abdominal bracing (bracing), and with abdominal hollowing (hollowing). Each intervertebral angle was calculated from the local coordinate system using the marker data obtained from a motion capture system. Shear moduli, as indicators of the activities of the right transversus abdominis (TrA), internal and external oblique, and rectus abdominis muscles, were assessed using shear wave elastography during QULEL. One-way repeated-measures analysis of variance and multiple comparisons among conditions were used to compare each shear modulus of the abdominal muscle and the changes in thoracic kyphosis (Th1-12), lumbar lordosis (L1-5), and lumbar intervertebral angles from the quadruped position to QULEL. The significance level was set at P < 0.05. Changes in lumbar lordosis and L2/L3 and L3/L4 extension angles were significantly lower under hollowing than under other conditions (effect size ηG2: lumbar lordosis, 0.068; L2/L3, 0.072; L3/L4, 0.043). The change in the L1/L2 extension angle significantly decreased in bracing and hollowing compared with the basic (ηG2 = 0.070). Only the TrA shear modulus significantly increased in bracing and hollowing compared with the basic (ηG2 = 0.146). Abdominal hollowing during the QULEL increased TrA activity and suppressed lumbar extension, except at L4/L5, and may be more effective as a rehabilitation exercise for controlling spinal motion.

Research on multi-dimensional intelligent quantitative assessment of upper limb function based on kinematic parameters.

BACKGROUND: Rehabilitation assessment is a critical component of rehabilitation treatment. OBJECTIVE: This study focuses on a comprehensive analysis of patients' movement performance using the upper limb rehabilitation robot. It quantitatively assessed patients' motor control ability and constructed an intelligent grading model of functional impairments. These findings contribute to a deeper understanding of patients' motor ability and provide valuable insights for personalized rehabilitation interventions. METHODS: Patients at different Brunnstrom stages underwent rehabilitation training using the upper limb rehabilitation robot, and data on the distal movement positions of the patients' upper limbs were collected. A total of 22 assessment metrics related to movement efficiency, smoothness, and accuracy were extracted. The performance of these assessment metrics was measured using the Mann-Whitney U test and Pearson correlation analysis. Due to the issue of imbalanced sample categories, data augmentation was performed using the Synthetic Minority Over-sampling Technique (SMOTE) algorithm based on weighted sampling, and an intelligent grading model of functional impairment based on the Extreme Gradient Boosting Tree (XGBoost) algorithm was constructed. RESULTS: Sixteen assessment metrics were screened. These metrics were effectively normalized to their maximum values, enabling the derivation of quantitative assessment scores for motor control ability across the three dimensions through a weighted fusion approach. Notably, when applied to the data-enhanced dataset, the intelligent grading model exhibited remarkable improvement, achieving an accuracy rate exceeding 0.98. Moreover, significant enhancements were observed in terms of precision, recall, and f1-score. CONCLUSION: The research findings demonstrate that this study enables the quantitative assessment of patients' motor control ability and intelligent grading of functional impairments, thereby contributing to the efficiency enhancement of clinical rehabilitation assessment. Moreover, this method resolves the issues associated with the subjectivity and prolonged periods of traditional rehabilitation assessment methods.

Ipsilateral transfer of motor skill from lower to upper limb in healthy adults: A randomized controlled trial.

BACKGROUND AND PURPOSE: Whereas motor skills of the untrained upper limb (UL) can improve following practice with the other UL, it has yet to be determined if an UL motor skill can improve following practice of that skill with the lower limb (LL). METHODS: Forty-five healthy subjects randomly participated in a 10-minute single-session intervention of (1) practicing 50 reaching movement (RM) sequences with the non-dominant left LL toward light switches (LL group); or (2) observing the identical 50 light switches sequences (Switches Observation (SO) group); or (3) observing nature films (Nature Observation (NO) group). RM sequence performance with the left UL toward the light switches was tested before and immediately after the intervention and retested after 24 h. RESULTS: Reaching response time improved in the LL group more than in the SO and NO groups in the posttest (pBonferroni = 0.038 and pBonferroni < 0.001, respectively), and improved in the LL group more than in the NO group in the retest (pBonferroni = 0.004). Percentage of fails did not differ between groups across the timepoints. CONCLUSIONS: It appears that the actual practice of the RM sequence skill with the UL together with the cognitive element embedded in the observation of the RM sequences contributes to ipsilateral transfer from LL to UL.

A multifaceted suite of metrics for comparative myoelectric prosthesis controller research.

Upper limb robotic (myoelectric) prostheses are technologically advanced, but challenging to use. In response, substantial research is being done to develop person-specific prosthesis controllers that can predict a user's intended movements. Most studies that test and compare new controllers rely on simple assessment measures such as task scores (e.g., number of objects moved across a barrier) or duration-based measures (e.g., overall task completion time). These assessment measures, however, fail to capture valuable details about: the quality of device arm movements; whether these movements match users' intentions; the timing of specific wrist and hand control functions; and users' opinions regarding overall device reliability and controller training requirements. In this work, we present a comprehensive and novel suite of myoelectric prosthesis control evaluation metrics that better facilitates analysis of device movement details-spanning measures of task performance, control characteristics, and user experience. As a case example of their use and research viability, we applied these metrics in real-time control experimentation. Here, eight participants without upper limb impairment compared device control offered by a deep learning-based controller (recurrent convolutional neural network-based classification with transfer learning, or RCNN-TL) to that of a commonly used controller (linear discriminant analysis, or LDA). The participants wore a simulated prosthesis and performed complex functional tasks across multiple limb positions. Analysis resulting from our suite of metrics identified 16 instances of a user-facing problem known as the "limb position effect". We determined that RCNN-TL performed the same as or significantly better than LDA in four such problem instances. We also confirmed that transfer learning can minimize user training burden. Overall, this study contributes a multifaceted new suite of control evaluation metrics, along with a guide to their application, for use in research and testing of myoelectric controllers today, and potentially for use in broader rehabilitation technologies of the future.

Classification of Motor Imagery Tasks Derived from Unilateral Upper Limb based on a Weight-optimized Learning Model.

BACKGROUND: The accuracy of decoding fine motor imagery (MI) tasks remains relatively low due to the dense distribution of active areas in the cerebral cortex. METHODS: To enhance the decoding of unilateral fine MI activity in the brain, a weight-optimized EEGNet model is introduced that recognizes six types of MI for the right upper limb, namely elbow flexion/extension, wrist pronation/supination and hand opening/grasping. The model is trained with augmented electroencephalography (EEG) data to learn deep features for MI classification. To address the sensitivity issue of the initial model weights to classification performance, a genetic algorithm (GA) is employed to determine the convolution kernel parameters for each layer of the EEGNet network, followed by optimization of the network weights through backpropagation. RESULTS: The algorithm's performance on the three joint classification is validated through experiment, achieving an average accuracy of 87.97%. The binary classification recognition rates for elbow joint, wrist joint, and hand joint are respectively 93.92%, 90.2%, and 94.64%. Thus, the product of the two-step accuracy value is obtained as the overall capability to distinguish the six types of MI, reaching an average accuracy of 81.74%. Compared to commonly used neural networks and traditional algorithms, the proposed method outperforms and significantly reduces the average error of different subjects. CONCLUSIONS: Overall, this algorithm effectively addresses the sensitivity of network parameters to initial weights, enhances algorithm robustness and improves the overall performance of MI task classification. Moreover, the method is applicable to other EEG classification tasks; for example, emotion and object recognition.

Quantifying the effects of sleep on sensor-derived variables from upper limb accelerometry in people with and without upper limb impairment.

BACKGROUND: Despite the promise of wearable sensors for both rehabilitation research and clinical care, these technologies pose significant burden on data collectors and analysts. Investigations of factors that may influence the wearable sensor data processing pipeline are needed to support continued use of these technologies in rehabilitation research and integration into clinical care settings. The purpose of this study was to investigate the effect of one such factor, sleep, on sensor-derived variables from upper limb accelerometry in people with and without upper limb impairment and across a two-day wearing period. METHODS: This was a secondary analysis of data collected during a prospective, longitudinal cohort study (n = 127 individuals, 62 with upper limb impairment and 65 without). Participants wore a wearable sensor on each wrist for 48 h. Five upper limb sensor variables were calculated over the full wear period (sleep included) and with sleep time removed (sleep excluded): preferred time, non-preferred time, use ratio, non-preferred magnitude and its standard deviation. Linear mixed effects regression was used to quantify the effect of sleep on each sensor variable and determine if the effect differed between people with and without upper limb impairment and across a two-day wearing period. RESULTS: There were significant differences between sleep included and excluded for the variables preferred time (p < 0.001), non-preferred time (p < 0.001), and non-preferred magnitude standard deviation (p = 0.001). The effect of sleep was significantly different between people with and without upper limb impairment for one variable, non-preferred magnitude (p = 0.02). The effect of sleep was not substantially different across wearing days for any of the variables. CONCLUSIONS: Overall, the effects of sleep on sensor-derived variables of upper limb accelerometry are small, similar between people with and without upper limb impairment and across a two-day wearing period, and can likely be ignored in most contexts. Ignoring the effect of sleep would simplify the data processing pipeline, facilitating the use of wearable sensors in both research and clinical practice.