sEMG Measurements Research Articles

Evaluation of the Power Assist Effect of Muscle Suit for Lower Back Support

In order to reduce the burden on the lower back, we have been developing a compact and lightweight “Muscle Suit” that uses McKibben artificial muscles, a type of soft pneumatic actuator. The Muscle Suit for lower back assist has been commercialized and sold over 13,000 units so far; the evaluation of the assist effect is a key point for further development and marketing of the Muscle Suit. In this study, we focus on the assistive effects of two Muscle Suit models: the standard model and the standalone model. The former generates assistive force actively using the actuator, but the latter equips a mechanism generating assistive force passively without the actuator. In the experiments, we first conducted surface electromyogram (sEMG) measurement to examine muscle usage in lifting motion of a heavy weight with or without the Muscle Suit assists. Besides, we estimated the assist force of the Muscle Suit from the perspective of muscle usage ratio. As the result, the evaluation of the overall muscle usage of all measured muscles revealed that the both models of the Muscle Suit reduced muscle usage. We then examined whether the dynamic length of body sways (DLNG) could be used as an indicator of fatigue progressed with performing the lifting motion repeatedly under assist or non-assist conditions. The experimental results confirmed that the reduction of physical fatigue by the Muscle Suit suppressed the change of DLNG value.

The Reliability of Pelvic Floor Muscle Bioelectrical Activity (sEMG) Assessment Using a Multi-Activity Measurement Protocol in Young Women.

The aim of the study was to determine the between-trial and between-day reliability of the Glazer protocol and our multi-activity surface electromyography (sEMG) measurement protocol for pelvic floor muscle (PFM) evaluation. The bioelectrical activity of PFM was collected using an endovaginal electrode in 30 young, Caucasian, nulliparous women (age 22–27, 168.6 ± 5.1 cm, 57.1 ± 11.8 kg). The between-trial and between-day reliability of the original Glazer protocol and the new multi-activity sEMG protocol were assessed during the following phases: pre-baseline rest, phasic (flick) contractions, tonic contractions, endurance contraction, and post-baseline rest. The Glazer protocol was characterized by poor and moderate measurement reliability. The time-domain parameters for the rise and fall of the signal amplitude and median frequency showed poor between-trial and between-day reliability. The mean and peak amplitudes indicated mainly good between-trial and moderate between-days reliability. Our protocol showed moderate to excellent reliability of both time-domain and quantitative parameters of muscle recruitment. In our protocol, the frequency-domain parameters describing muscle fatigue demonstrated much higher reliability than in the case of the Glazer protocol. The most important information obtained in this study was the significant improvement of diagnostic validity in PFM bioelectrical activity evaluation. The higher reliability of our sEMG protocol compared to original Glazer protocol allowed us to suggest that protocol modifications and changes in sEMG signal processing methods were effective in the improvement of PFM assessment quality. The new parameters calculated from the sEMG signal proposed in our sEMG protocol allowed us to obtain additional clinically important information about PFM dysfunctions regarding specific deficits of muscle contraction such as decrease in muscle strength; endurance or coordination related to, e.g., stress urinary incontinence; or pelvic floor muscle imbalance after childbirth.

Identification of muscle innervation zones using linear electrode arrays: a fundamental step to measure fibers conduction velocity

Fiber conduction velocity (CV) is a parameter correlated to the physiological membrane properties of the skeletal muscle fibers. Changes in muscle fiber CV are correlated to the gradation of force and fatigue, and can be measured by means of surface electromyography EMG (sEMG). sEMG measurement of CV during muscle contractions requires the correct identification of the skeletal muscle innervation zone (IZ). In superficial muscles, IZ location can be detected using linear electrode arrays and visually identified as the point of inversion of the detected motor unit action potential (MUAP) propagation. In the present work, we present a method for the effective and fast detection of the IZ location, through the following procedures: (1) identification of the target superficial muscle considering the muscle fiber architecture; (2) electrode array selection based on interelectrode distance and number of electrodes; (3) subject training to perform submaximal isometric contractions of the target muscle/s; (4) electrode array positioning along the muscle surface to investigate the IZ position during the contractions by visual identification of MUAP patterns.

Surface Electromyography Meets Biomechanics: Correct Interpretation of sEMG-Signals in Neuro-Rehabilitation Needs Biomechanical Input.

Coordinated activation of muscles is the basis for human locomotion. Impaired muscular activation is related to poor movement performance and disability. To restore movement performance, information about the subject's individual muscular activation is of high relevance. Surface electromyography (sEMG) allows the pain-free assessment of muscular activation and many ready-to-use technologies are available. They enable the usage of sEMG measurements in several applications. However, due to the fact that in most rehabilitation applications dynamic conditions are analyzed, the correct interpretation of sEMG signals remains difficult which hinders the spread of sEMG in clinical applications. From biomechanics it is well-known that the sEMG signal depends on muscle fiber length, contraction velocity, contraction type and on the muscle's biomechanical moment. In non-isometric conditions these biomechanical factors have to be considered when analyzing sEMG signals. Additionally, the central nervous system control strategies used to activate synergistic and antagonistic muscles have to be taken into consideration. These central nervous system activation strategies are rarely known in physiology and are hard to manage in pathology. In this perspective report we discuss how the consideration of biomechanical factors leads to more reliable information extraction from sEMG signals and how the limitations of sEMG can be overcome in dynamic conditions. This is a prerequisite if the use of sEMG in rehabilitation applications is to extend. Examples will be given showing how the integration of biomechanical knowledge into the interpretation of sEMG helps to identify the central nervous system activation strategies involved and leads to relevant clinical information.

Adaptive Driver-Automation Shared Steering Control via Forearm Surface Electromyography Measurement

Shared steering control has been developed to reduce driver workload while keeping the driver in the control loop. A driver could integrate visual sensory information from the road ahead and haptic sensory information from the steering wheel to achieve better driving performance. Previous studies suggest that, compared with adaptive automation authority, fixed automation authority is not always appropriate with respect to human factors. This paper focuses on designing an adaptive shared steering control system via sEMG (surface electromyography) measurement from the forearm of the driver, and evaluates the effect of the system on driver behavior during a double lane change task. The shared steering control was achieved through a haptic guidance system which provided active assistance torque on the steering wheel. Ten subjects participated in a high-fidelity driving simulator experiment. Two types of adaptive algorithms were investigated: haptic guidance decreases when driver grip strength increases (HG-Decrease), and haptic guidance increases when driver grip strength increases (HG-Increase). These two algorithms were compared to manual driving and two levels of fixed authority haptic guidance, for a total of five experimental conditions. Evaluation of the driving systems was based on two sets of dependent variables: objective measures of driver behavior and subjective measures of driver workload. The results indicate that the adaptive authority of HG-Decrease yielded lower driver workload and reduced the lane departure risk compared to manual driving and fixed authority haptic guidance.

Validity and Reliability of StriveTM Sense3 for Muscle Activity Monitoring During the Squat Exercise

Background: Recent innovations in surface electromyographic (sEMG) technology have enabled the measurement of muscle activity using smart textiles. Objective: In this study, the StriveTM Sense3 performance monitoring system is evaluated against a research-grade system, NoraxonTM, in measuring activity during the back squat exercise. Method: Seventeen participants performed three total trials of the squat exercise with a progressive load for individual trials equal to 30%, 60%, and 80% of their estimated maximum 1RM (one-repetition maximum). sEMG measurements from the rectus femoris were captured for the left and right leg by both systems. Pearson product-moment correlation coefficient (r) and intraclass correlation coefficient (ICC) values were computed for each trial to assess concurrent validity and interrater reliability of the StriveTM Sense3 device. Additionally, five coaches at the collegiate- and professional-level of Men’s Basketball speak from an autoethnographic frame to the findings from this study. Results: Results ranged from “Poor” to “Excellent” validity and “Poor to Moderate” to “Excellent” reliability, with a majority of trials achieving “Good” or better results across all loads [93% trials: r >= 0.7; 87% trials: lower ICC 95% CI bound >= 0.75 (absolute sEMG); 98% trials: lower ICC 95% CI bound >= 0.75 (normalized sEMG)]. Higher validity and reliability for medium and heavy loads were observed in comparison to the light load, and several outliers indicate the need for coaches to lubricate sensors and ensure proper fit to collect accurate data. Conclusion: Examining results alongside practitioner feedback indicate the StriveTM Sense3 system is capable of tracking sEMG activity in comparison to a research-grade system.

SEMG-Based Human-in-the-Loop Control of Elbow Assistive Robots for Physical Tasks and Muscle Strength Training

In this letter we present a sEMG-driven human-in-the-loop (HITL) control designed to allow an assistive robot produce proper support forces for both muscular effort compensations, i.e. for assistance in physical tasks, and muscular effort generations, i.e. for the application in muscle strength training exercises related to the elbow joint. By employing our control strategy based on a Double Threshold Strategy (DTS) with a standard PID regulator, we report that our approach can be successfully used to achieve a target, quantifiable muscle activity assistance. In this relation, an experimental concept validation was carried out involving four healthy subjects in physical and muscle strength training tasks, reporting with single-subject and global results that the proposed sEMG-driven control strategy was able to successfully limit the elbow muscular activity to an arbitrary level for effort compensation objectives, and to impose a lower bound to the sEMG signals during effort generation goals. Also, a subjective qualitative evaluation of the robotic assistance was carried out by means of a questionnaire. The obtained results open future possibilities for a simplified usage of the sEMG measurements to obtain a target, quantitatively defined, robot assistance for human joints and muscles.

Ankle bracing’s effects during a modified agility task: analysis of sEMG, impulse, and time to complete using a crossover, repeated measures design

ABSTRACT This study explored the effects of no braces, softshell (AE), and semi-rigid (T1) ankle braces on time to complete a modified agility task, as well as lower extremity muscle activity and impulse during the change of direction component of the task. Thirty-nine healthy, active individuals completed a modified agility task under the three brace conditions. Time to complete the modified agility task, along with mean surface electromyographic activity (sEMG) and impulse during the deceleration and propulsive phases of the task were measured. There were no significant differences across conditions with respect to sEMG or impulse measures during the deceleration or propulsive phases. There was a significant change in time to complete the modified agility task, F(2,76) = 17.242, p< 0.001, ηp2 = 0.312. Post-hoc analysis revealed a significant increase in time to complete the modified agility task when wearing the AE (0.16 (95% CI, 0.062 to 0.265) seconds, p< 0.001) and T1 (0.20 (95% CI, 0.113 to 0.286) seconds, p< 0.001) ankle braces compared to no braces. It appears that performance on a modified agility task may be diminished when wearing ankle braces, although sEMG activity and impulse are unaffected.

A sEMG-Driven Soft ExoSuit Based on Twisted String Actuators for Elbow Assistive Applications

The scope of this letter is to show the applicability of the Twisted String Actuators (TSAs) for lightweight, wearable and assistive robotic applications. To this aim, we have developed a novel surface electromyography (sEMG)-driven soft ExoSuit using the TSAs to perform both single and dual-arm elbow assistive applications. The proposed ExoSuit, with an overall weight of 1650 g, uses a pair of TSAs mounted in the back of the user, connected via tendons to the user's forearms to actuate each arm independently for supporting external loads. We confirm this new light-weight and customizable wearable solution via multiple user studies based on the biceps and tricep' sEMG measurements. We demonstrate that user's muscles can automatically activate and regulate the TSAs and compensate for the user's effort: by using our controller based on a Double Threshold Strategy (DTS) with a standard PID regulator, we report that the system was able to limit the biceps' sEMG activity under an arbitrary target threshold, compensating a muscular activity equal to 220% (related to a single arm 3 kg load) and 110% (related to a dual arm 4 kg load) of the threshold value itself. Moreover, the triceps' sEMG signal detects the external load and, depending on the threshold, returns the system to the initial state where it requires no assistance from the ExoSuit. The experimental results show the proposed ExoSuit's capabilities in both single and dual-arm load compensation tasks. Therefore, the applicability of the TSAs is experimentally demonstrated for a real-case assistive device, fostering future studies and developments of this kind of actuation strategy for wearable robotic systems.

Torque Estimation Using Neural Drive for a Concentric Contraction.

The scope and relevance of wearable robotics spans across a number of research fields with a variety of applications. A challenge across these research areas is improving user-interface control. One established approach is using neural control interfaces derived from surface electromyography (sEMG). Although there has been some success with sEMG controlled prosthetics, the coarse nature of traditional sEMG processing has limited the development of fully functional prosthetics and wearable robotics. To solve this problem, blind source separation (BSS) techniques have been implemented to extract the user's movement intent from high-density sEMG (HDsEMG) measurements; however, current methods have only been well validated during static, low-level muscle contractions, and it is unclear how they will perform during movement. In this paper we present a neural drive based method for predicting output torque during a constant force, concentric contraction. This was achieved by modifying an existing HDsEMG decomposition algorithm to decompose 1 sec. overlapping windows. The neural drive profile was computed using both rate coding and kernel smoothing. Neither rate coding nor kernel smoothing performed as well as HDsEMG amplitude estimation, indicating that there are still significant limitations in adapting current methods to decompose dynamic contractions, and that sEMG amplitude estimation methods still remain highly reliable estimators.

Neural Respiratory Drive Estimation in Respiratory sEMG with Cardiac Arrhythmias.

Neural respiratory drive as measured by the electromyography allows the study of the imbalance between the load on respiratory muscles and its capacity. Surface respiratory electromyography (sEMG) is a non-invasive tool used for indirectly assessment of NRD. It also provides a way to evaluate the level and pattern of respiratory muscle activation. The prevalence of electrocardiographic activity (ECG) in respiratory sEMG signals hinders its proper evaluation. Moreover, the occurrence of abnormal heartbeats or cardiac arrhythmias in respiratory sEMG measures can make even more challenging the NRD estimation. Respiratory sEMG can be evaluated using the fixed sample entropy (fSampEn), a technique which is less affected by cardiac artefacts. The aim of this work was to investigate the performance of the fSampEn, the root mean square (RMS) and the average rectified value (ARV) on respiratory sEMG signals with supraventricular arrhythmias (SVA) for NRD estimation. fSampEn, ARV and RMS parameters increased as the inspiratory load increased during the test. fSampEn was less influenced by ECG with SVAs for the NRD estimation showing a greater response to respiratory sEMG, reflected with a higher percentage increase with increasing load (228 % total increase, compared to 142 % and 135 % for ARV and RMS, respectively).

The Prognostic Value of the Surface Electromyographic Assessment of Pelvic Floor Muscles in Women with Stress Urinary Incontinence.

Background: The use of surface electromyography (sEMG) measurements to evaluate the bioelectrical activity of the pelvic floor muscle (PFM) during therapeutic intervention is now well established. This study investigates the diagnostic possibilities of sEMG in women with stress urinary incontinence (SUI). The aim of this study was to carry out objective assessments of the bioelectrical activity of the PFM in women after menopause and determine the prognostic value of sEMG for assessing the PFM in patients with SUI. Methods: This was a prospective, observational study that evaluated the bioelectrical activity of the PFM in postmenopausal women with or without SUI (SUI group, n = 89 vs. non-SUI group, n = 62). The study was carried out between January 2013 and December 2018 at the Clinic of Urology (Wroclaw, Poland). The protocol for all sEMG measurements of PFM activity consisted of following elements: “baseline”, “quick flicks”, “contractions”, “static hold”, and “rest tone”; we then compared these results between groups. To determine the optimal cutoff level for sEMG activation of the PFM to detect the occurrence of SUI, we performed receiver operating characteristic (ROC) curve analysis (with Youden’s index). Results: Significantly lower results were obtained for all PFM measurements in women with SUI. The optimum diagnostic cutoff for “baseline” was 3.7 μV (area under curve (AUC), 0.63), “quick flicks” was 9.15 μV (AUC, 0.84), “contractions” was 11.33 μV (AUC, 0.80), “static hold” was 9.94 μV (AUC, 0.84), and “rest” was 3.89 μV (AUC, 0.63). Conclusions: Measuring sEMG activity in the PFM may be a useful diagnostic tool to confirm the absence of SUI. We can expect that the sEMG activity of subjects with SUI will be lower than that of healthy people. In order to determine appropriate reference values for assessing sEMG activity data in the PFM, it is now necessary to conduct multicenter studies.

Neuromuscular, Perceptual, and Temporal Determinants of Movement Patterns in Wheelchair Fencing: Preliminary Study.

The objective of the present study was to determine the structure of the movement pattern performed during a wheelchair fencing lunge that is executed in response to visual and sensory stimuli. In addition, a comparison was made between fencers in the categories A and B of disability. In addition, the analysis involved the correlation between the duration of the sensorimotor response and the value of the bioelectric signal recorded in selected muscles. Seven Paralympic team athletes specializing in wheelchair fencing (3 in category A and 4 in category B) participated in the research. The fencers perform at international level competitions and are multiple medalists of the Paralympic Games. In the study, a wireless system for sEMG and accelerometer signal measurement was employed to test the intervals between the initiation of the lunge attack and its termination defined by the touch of the weapon on the coach's torso. The electrodes were placed on 9 key muscles responsible for the effectiveness of the executed attack: DEL, TRI, BC, ECR FCR, LD, and EAO. The significant intergroup difference in the muscle activation was found to be 0.333 s for category A fencers and 0.522 s for category A fencers at p = 0.039 applies to the latissimus dorsi (LD LT) muscle, which demonstrates its significance as a postural muscle in the structure of the examined movement pattern. In terms of the values of EMG, a tendency for higher MVC (%) values in most muscles for category A competitors was recorded. The latissimus dorsi (DL RT) muscle with an intergroup difference of MVC-114.63 for cat. A and 67.50 for cat. B at p = 0.039 turned out to play a significant role. The results prove the role of postural muscles: external abdominal oblique and latissimus dorsi on the effectiveness of the attacks executed in wheelchair fencing.

Surface Electromyography Normalization Affects the Interpretation of Muscle Activity and Coactivation in Children With Cerebral Palsy During Walking.

Investigating muscle activity and coactivation with surface electromyography (sEMG) gives insight into pathological muscle function during activities like walking in people with neuromuscular impairments, such as children with cerebral palsy (CP). There is large variation in the amount of coactivation reported during walking in children with CP, possibly due to the inconsistent handling of sEMG and in calculating the coactivation index. The aim of this study was to evaluate how different approaches of handling sEMG may affect the interpretation of muscle activity and coactivation, by looking at both absolute and normalized sEMG. Twenty-three ambulatory children with CP and 11 typically developing (TD) children participated. We conducted a three-dimensional gait analysis (3DGA) with concurrent sEMG measurements of tibialis anterior, soleus, gastrocnemius medialis, rectus femoris, and hamstring medialis. They walked barefoot at a self-selected, comfortable speed back and forth a 7-m walkway. The gait cycle extracted from the 3DGA was divided into six phases, and for each phase, root mean square sEMG amplitude was calculated (sEMG-RMS-abs), and also normalized to peak amplitude of the linear envelope (50-ms running RMS window) during the gait cycle (sEMG-RMS-norm). The coactivation index was calculated using sEMG-RMS-abs and sEMG-RMS-norm values and by using two different indices. Differences between TD children's legs and the affected legs of children with CP were tested with a mixed model. The between-subject muscle activity variability was more evenly distributed using sEMG-RMS-norm; however, potential physiological variability was eliminated as a result of normalization. Differences between groups in one gait phase using sEMG-RMS-abs showed opposite differences in another phase using sEMG-RMS-norm for three of the five muscles investigated. The CP group showed an increased coactivation index in two out of three muscle pairs using sEMG-RMS-abs and in all three muscle pairs using sEMG-RMS-norm. These results were independent of index calculation method. Moreover, the increased coactivation indices could be explained by either reduced agonist activity or increased antagonist activity. Thus, differences in muscle activity and coactivation index between the groups change after normalization. However, because we do not know the truth, we cannot conclude whether to normalize and recommend incorporating both.

Use of Surface Electromyography to Measure Muscle Fatigue in Patients in an Acute Care Hospital.

Functional outcomes with early rehabilitation in the acute care setting have improved; however, an improved understanding of muscle fatigue using surface electromyography (sEMG) is warranted to better guide patient-centered exercise prescription. The objectives of this study were to assess the safety and feasibility of collecting sEMG at the acute care bedside and to determine differences in muscle fatigue during isometric and dynamic submaximal contractions among patients in the hospital, healthy younger participants, and healthy older participants. The study used an observational cohort design. There were 37 participants. Median frequency (Fmed) of the myoelectric signal of the quadriceps femoris muscles and time to task failure (TTTF) were measured using sEMG during an isometric and dynamic fatiguing contraction. Primary analysis compared TTTF between groups for both types of contractions. Secondary analysis compared Fmed at initiation and termination of fatiguing contraction. High-quality sEMG measures were safe and feasible to collect at the acute care bedside with no adverse events. There was a statistically significant difference in TTTF between groups after isometric and dynamic contractions; hospitalized patients fatigued faster than healthy younger and healthy older participants after both contractions. With the exception of the vastus lateralis during a dynamic contraction in healthy younger and hospitalized patients, there was a statistically significant difference between Fmed at initiation and termination of contraction, indicating that subjects' muscles did truly fatigue. A limitation of the study was the small sample size of patients who were hospitalized without matched controls. sEMG is a lab quantitative technique that was found to be safe and feasible to assess muscle fatigue in the acute care environment. The protocol yielded similar results to previously published literature for healthy younger and healthy older people. Further research is needed to better understand how to integrate sEMG findings into patient-centered exercise prescriptions.

Biofeedback-Assisted Relaxation Therapy on Women with Breast Cancer after Mastectomy: Effects of EMG-HRV Biofeedback on Psychological Symptoms

Abstract Introduction: Breast cancer patients usually react to mastectomy surgery by increased levels of stress, anxiety and depression which requires effective interventions. The aim of present research was to investigate the effects of an Electromyography (EMG) and heart rate variability (HRV) biofeedback-assisted relaxation training to alleviate the psychological symptoms of mastectomy breast cancer women. Method: In a randomized controlled trial design about 14 mastectomy women were randomly chosen and divided into two groups and measures of Depression Anxiety Stress Scale were gathered for them. The experimental group received biofeedback-assisted relaxation training, whereas no intervention administered on the control group. All subjects again completed the DASS scales afterwards. Indices of smooth artifact free surface Electromyography (sEMG) and HRV biofeedback recorded using a Biofeedback 2000 x-pert system Version 4. Data were analyzed by a General Linear Model: Multivariate Analysis of Variance statistical analysis. Results: Depression, anxiety, and stress average scores showed a significant difference after biofeedback intervention. Significant differences were observed in the sEMG and Heart Rate Variability-Index (HRV-Index) measures of the two groups with better results for the experimental subjects as well. Conclusion: The biofeedback-assisted relaxation training could effectively decrease negative psychological symptoms of the mastectomy breast cancer patients due to sEMG and HRV positive changes and is then recommended for these patients in the course of their treatment.

Detection of relevant information in intrinsic mode functions

The empirical mode decomposition (EMD) decomposes a local and adaptive time series into a finite set of intrinsic mode functions (IMF), AM-FM signals that allow to represent a non-linear and non-stationary model with the advantage of not losing the underlying meaning. This study examines time series of sEMG measurements for a case study of healthy individuals with carpal tunnel syndrome. Due to the amount of multiple levels of detail, all around a central frequency and evoked by the number of IMFs obtained through EMD, the informational contribution of each at the intermodal and interindividual level is studied through Shannon entropy to establish a general framework of spectral study given Hilbert Huang's (HHT) transformation to remarkable degrees of information. The results show that the latest IMFs have more disordered states even when they engage in apparently regular behavior, agglomerate more time-frequency information, and in the same way, concentrate more differentiable characteristics for a process of individualization of patterns.

Neck/Shoulder Muscle Fatigue of Military Vehicle Drivers Exposed to Whole-Body Vibration on Field Terrain Road

A driver of a military vehicle is exposed to whole-body vibration when driving in field terrain conditions, and the driver’s muscles become tired. Muscle fatigue occurs most strongly near both shoulders, which must be used to steer the vehicle in the target direction. The degree of a muscle fatigue is predicted to correlate with the exposure amount of the human body to vibration. In this study, the vibration driving a military vehicle on a field terrain test road was simulated using a 6-degree-of-freedom (DOF) exciter, and the muscle fatigue was analyzed by measuring electromyography (EMG) signals from subjects before and after the vibration exposure. Surface EMG (sEMG) measurements were taken at the deltoid and trapezius muscles of subjects for the muscle fatigue analysis. Before and after the vibration exposure, the Maximal Voluntary Contraction (MVC) state was determined. The change of the median frequency of the sEMG signal was measured in this state and analyzed. The output values of the sEMG signal at MVC decreased after the vibration exposure, suggesting reduced muscle activation. The change of the median frequency value after the vibration exposure was sharply reduced, which means that the muscles are fatigued more rapidly with the same load.

Surface EMG-based Estimation of Breathing Effort for Neurally Adjusted Ventilation Control

In assisted mechanical ventilation, it is of critical importance to monitor the patient’s own effort to breathe. Methods currently available are either invasive (esophageal electromyography and esophageal pressure) or rely heavily on intermittent occlusion maneuvers to identify the properties of the respiratory muscles. In this article, we propose a novel, non-invasive method to identify the patient’s respiratory mechanics and estimate the pressure generated by the patient, based on surface electromyographic (sEMG) measurements of the respiratory muscles. Our method is computationally efficient, real-time capable, and can be run continuously during normal ventilation. A numerical comparison with esophageal pressure measurements using three clinical data sets demonstrates the estimation procedure’s good performance. Clinically, monitoring a patient’s respiratory effort is of high intrinsic, diagnostic value, while also enabling a whole range of new, adaptive control algorithms for assisted mechanical ventilation.

SEMG Measurement Position and Feature Optimization Strategy for Gesture Recognition Based on ANOVA and Neural Networks

Surface electromyography (sEMG) signals are widely used in the recognition of hand gestures. Nowadays, researchers usually increase the number of sEMG signal measurement positions and extract multiple features to improve the recognition accuracy. In this paper, we propose a sEMG measurement position and feature optimization strategy for gesture recognition based on Analysis of Variance (ANOVA) and neural networks. Firstly, four channels of raw sEMG signals are acquired, and four time-domain features are extracted. Then different neural networks are trained and tested by using different data sets which are obtained based on the combination of different measurement positions and features. Finally, ANOVA and Tukey HSD testing are conducted based on the gesture recognition results of different neural networks. We obtain the optimal measurement position sets for gesture recognition when different feature sets are used, and similarly, the optimal feature sets when different measurement position sets are used. Our experimental results show that the feature set of zero crossing and integrated sEMG provides the highest gesture recognition accuracy, which is 94.83%, when four channels of sEMG signals are used; the optimal measurement position set when four sEMG signal features are used for hand gesture recognition is P1+P3+P4, which provides an accuracy of 94.6%.