To see the other types of publications on this topic, follow the link: EMG-based control strategy.
Journal articles on the topic 'EMG-based control strategy'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 34 journal articles for your research on the topic 'EMG-based control strategy.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Secciani, N., M. Bianchi, A. Ridolfi, B. Allotta, F. Gerli, and F. Vannetti. "Development and preliminary testing of an EMG-based control strategy for a hand exoskeleton." Gait & Posture 66 (October 2018): S35. http://dx.doi.org/10.1016/j.gaitpost.2018.07.155.
Full text
2
Li, Shunchong, Jiayuan He, Xinjun Sheng, Honghai Liu, and Xiangyang Zhu. "Synergy-Driven Myoelectric Control for EMG-Based Prosthetic Manipulation: A Case Study." International Journal of Humanoid Robotics 11, no. 02 (2014): 1450013. http://dx.doi.org/10.1142/s0219843614500133.
Full textAbstract:
The paper proposes a synergy-based myoelectric control strategy for prosthetic hands. Synergy is first reviewed in the context of hand movement, then postural synergy-based proportional and simultaneous control has been introduced to prosthetic manipulation via the principal component analysis (PCA) framework. Experiments have been comprehensively carried out on lab-developed prosthetic hand called SJU-5 to evaluate the proposed method. It is evident that the synergy driven myoelectric control achieves the targeted objectives and performs well on the SJU-5 prosthetic hand.
3
Chen, Lingling, Xiaotian Liu, Bokai Xuan, Jie Zhang, Zuojun Liu, and Yan Zhang. "Selection of EMG Sensors Based on Motion Coordinated Analysis." Sensors 21, no. 4 (2021): 1147. http://dx.doi.org/10.3390/s21041147.
Full textAbstract:
The intelligent prosthesis driven by electromyography (EMG) signal provides a solution for the movement of the disabled. The proper position of EMG sensors can improve the prosthesis’s motion recognition ability. To exert the amputee’s action-oriented ability and the prosthesis’ control ability, the EMG spatial distribution and internal connection of the prosthetic wearer is analyzed in three kinds of movement conditions: appropriate angle, excessive angle, and angle too small. Firstly, the correlation characteristics between the EMG channels are analyzed by mutual information to construct a muscle functional network. Secondly, the network’s features of different movement conditions are analyzed by calculating the characteristic of nodes and evaluating the importance of nodes. Finally, the convergent cross-mapping method is applied to construct a directed network, and the critical muscle groups which can reflect the user’s movement intention are determined. Experiment shows that this method can accurately determine the EMG location and simplify the distribution of EMG sensors inside the prosthetic socket. The network characteristics of key muscle groups can distinguish different movements effectively and provide a new strategy for decoding the relationship between limb nerve control and body movement.
4
LIU, JIE, XIAOYAN LI, CHRISTINA MARCINIAK, WILLIAM ZEV RYMER, and PING ZHOU. "EXTRACTION OF NEURAL CONTROL COMMANDS USING MYOELECTRIC PATTERN RECOGNITION: A NOVEL APPLICATION IN ADULTS WITH CEREBRAL PALSY." International Journal of Neural Systems 24, no. 07 (2014): 1450022. http://dx.doi.org/10.1142/s0129065714500221.
Full textAbstract:
This study investigates an electromyogram (EMG)-based neural interface toward hand rehabilitation for patients with cerebral palsy (CP). Forty-eight channels of surface EMG signals were recorded from the forearm of eight adult subjects with CP, while they tried to perform six different hand grasp patterns. A series of myoelectric pattern recognition analyses were performed to identify the movement intention of each subject with different EMG feature sets and classifiers. Our results indicate that across all subjects high accuracies (average overall classification accuracy > 98%) can be achieved in classification of six different hand movements, suggesting that there is substantial motor control information contained in paretic muscles of the CP subjects. Furthermore, with a feature selection analysis, it was found that a small number of ranked EMG features can maintain high classification accuracies comparable to those obtained using all the EMG features (average overall classification accuracy > 96% with 16 selected EMG features). The findings of the study suggest that myoelectric pattern recognition may be a useful control strategy for promoting hand rehabilitation in CP patients.
5
Arora, A. S. "Modified adaptive resonance theory based control strategy for EMG operated prosthesis for below-elbow amputee." Journal of Medical Engineering & Technology 31, no. 3 (2007): 191–201. http://dx.doi.org/10.1080/03091900500481036.
Full text
6
Asai, Yoshiyuki, Shota Tateyama, and Taishin Nomura. "Learning an Intermittent Control Strategy for Postural Balancing Using an EMG-Based Human-Computer Interface." PLoS ONE 8, no. 5 (2013): e62956. http://dx.doi.org/10.1371/journal.pone.0062956.
Full text
7
Sriram, Girish, Alex Jensen, and Steve C. Chiu. "Smart Prosthetic Hand with Object Slippage Detection, Measurement, and Control." International Journal of Handheld Computing Research 5, no. 3 (2014): 25–48. http://dx.doi.org/10.4018/ijhcr.2014070102.
Full textAbstract:
The human hand along with its fingers possess one of the highest numbers of nerve endings in the human body. It thus has the capacity for the richest tactile feedback for positioning capabilities. This article shares a new technique of controlling slippage. The sensing system used for the detection of slippage is a modified force sensing resistor (FSR®). The control system is a fuzzy logic control algorithm with multiple rules that is designed to be processed on a mobile handheld computing platform and integrated/working alongside a traditional Electromyography (EMG) or Electroencephalography (EEG) based control system used for determining position of the fingers. A 5 Degrees of Freedom (DOF) hand, was used to test the slippage control strategy in real time. First a reference EMG signal was used for getting the 5 DOF hand to grasp an object, using position control. Then a slip was introduced to see the slippage control strategy at work. The results based on the plain tactile sensory feedback and the modified sensory feedback are discussed.
8
Meng, Wei, Quan Liu, Zude Zhou, and Qingsong Ai. "Active interaction control applied to a lower limb rehabilitation robot by using EMG recognition and impedance model." Industrial Robot: An International Journal 41, no. 5 (2014): 465–79. http://dx.doi.org/10.1108/ir-04-2014-0327.
Full textAbstract:
Purpose – The purpose of this paper is to propose a seamless active interaction control method integrating electromyography (EMG)-triggered assistance and the adaptive impedance control scheme for parallel robot-assisted lower limb rehabilitation and training. Design/methodology/approach – An active interaction control strategy based on EMG motion recognition and adaptive impedance model is implemented on a six-degrees of freedom parallel robot for lower limb rehabilitation. The autoregressive coefficients of EMG signals integrating with a support vector machine classifier are utilized to predict the movement intention and trigger the robot assistance. An adaptive impedance controller is adopted to influence the robot velocity during the exercise, and in the meantime, the user’s muscle activity level is evaluated online and the robot impedance is adapted in accordance with the recovery conditions. Findings – Experiments on healthy subjects demonstrated that the proposed method was able to drive the robot according to the user’s intention, and the robot impedance can be updated with the muscle conditions. Within the movement sessions, there was a distinct increase in the muscle activity levels for all subjects with the active mode in comparison to the EMG-triggered mode. Originality/value – Both users’ movement intention and voluntary participation are considered, not only triggering the robot when people attempt to move but also changing the robot movement in accordance with user’s efforts. The impedance model here responds directly to velocity changes, and thus allows the exercise along a physiological trajectory. Moreover, the muscle activity level depends on both the normalized EMG signals and the weight coefficients of involved muscles.
9
Zhao, Shumi, Jianxun Liu, Zidan Gong, et al. "Wearable Physiological Monitoring System Based on Electrocardiography and Electromyography for Upper Limb Rehabilitation Training." Sensors 20, no. 17 (2020): 4861. http://dx.doi.org/10.3390/s20174861.
Full textAbstract:
Secondary injuries are common during upper limb rehabilitation training because of uncontrollable physical force and overexciting activities, and long-time training may cause fatigue and reduce the training effect. This study proposes a wearable monitoring device for upper limb rehabilitation by integrating electrocardiogram and electromyogram (ECG/EMG) sensors and using data acquisition boards to obtain accurate signals during robotic glove assisting training. The collected ECG/EMG signals were filtered, amplified, digitized, and then transmitted to a remote receiver (smart phone or laptop) via a low-energy Bluetooth module. A software platform was developed for data analysis to visualize ECG/EMG information, and integrated into the robotic glove control module. In the training progress, various hand activities (i.e., hand closing, forearm pronation, finger flexion, and wrist extension) were monitored by the EMG sensor, and the changes in the physiological status of people (from excited to fatigue) were monitored by the ECG sensor. The functionality and feasibility of the developed physiological monitoring system was demonstrated by the assisting robotic glove with an adaptive strategy for upper limb rehabilitation training improvement. The feasible results provided a novel technique to monitor individual ECG and EMG information holistically and practically, and a technical reference to improve upper limb rehabilitation according to specific treatment conditions and the users’ demands. On the basis of this wearable monitoring system prototype for upper limb rehabilitation, many ECG-/EMG-based mobile healthcare applications could be built avoiding some complicated implementation issues such as sensors management and feature extraction.
10
Meng, Lin, Jun Pang, Ziyao Wang, Rui Xu, and Dong Ming. "The Role of Surface Electromyography in Data Fusion with Inertial Sensors to Enhance Locomotion Recognition and Prediction." Sensors 21, no. 18 (2021): 6291. http://dx.doi.org/10.3390/s21186291.
Full textAbstract:
Locomotion recognition and prediction is essential for real-time human–machine interactive control. The integration of electromyography (EMG) with mechanical sensors could improve the performance of locomotion recognition. However, the potential of EMG in motion prediction is rarely discussed. This paper firstly investigated the effect of surface EMG on the prediction of locomotion while integrated with inertial data. We collected EMG signals of lower limb muscle groups and linear acceleration data of lower limb segments from ten healthy participants in seven locomotion activities. Classification models were built based on four machine learning methods—support vector machine (SVM), k-nearest neighbor (KNN), artificial neural network (ANN), and linear discriminant analysis (LDA)—where a major vote strategy and a content constraint rule were utilized for improving the online performance of the classification decision. We compared four classifiers and further investigated the effect of data fusion on the online locomotion classification. The results showed that the SVM model with a sliding window size of 80 ms achieved the best recognition performance. The fusion of EMG signals does not only improve the recognition accuracy of steady-state locomotion activity from 90% (using acceleration data only) to 98% (using data fusion) but also enables the prediction of the next steady locomotion (∼370 ms). The study demonstrates that the employment of EMG in locomotion recognition could enhance online prediction performance.
11
Farina, Dario, Mauro Fosci, and Roberto Merletti. "Motor unit recruitment strategies investigated by surface EMG variables." Journal of Applied Physiology 92, no. 1 (2002): 235–47. http://dx.doi.org/10.1152/jappl.2002.92.1.235.
Full textAbstract:
During isometric contractions of increasing strength, motor units (MUs) are recruited by the central nervous system in an orderly manner starting with the smallest, with muscle fibers that usually show the lowest conduction velocity (CV). Theory predicts that the higher the velocity of propagation of the action potential, the higher the power at high frequencies of the detected surface signal. These considerations suggest that the power spectral density of the surface detected electromyogram (EMG) signal may give indications about the MU recruitment process. The purpose of this paper is to investigate the potential and limitations of spectral analysis of the surface EMG signal as a technique for the investigation of muscle force control. The study is based on a simulation approach and on an experimental investigation of the properties of surface EMG signals detected from the biceps brachii during isometric linearly increasing torque contractions. Both simulation and experimental data indicate that volume conductor properties play an important role as confounding factors that may mask any relation between EMG spectral variables and estimated CV as a size principle parameter during ramp contractions. The correlation between spectral variables and CV is thus significantly lower when the MU pool is not stable than during constant-torque isometric contractions. Our results do not support the establishment of a general relationship between spectral EMG variables and torque or recruitment strategy.
12
Asogbon, Mojisola Grace, Oluwarotimi Williams Samuel, Yanbing Jiang, et al. "Appropriate Feature Set and Window Parameters Selection for Efficient Motion Intent Characterization towards Intelligently Smart EMG-PR System." Symmetry 12, no. 10 (2020): 1710. http://dx.doi.org/10.3390/sym12101710.
Full textAbstract:
The constantly rising number of limb stroke survivors and amputees has motivated the development of intelligent prosthetic/rehabilitation devices for their arm function restoration. The device often integrates a pattern recognition (PR) algorithm that decodes amputees’ limb movement intent from electromyogram (EMG) signals, characterized by neural information and symmetric distribution. However, the control performance of the prostheses mostly rely on the interrelations among multiple dynamic factors of feature set, windowing parameters, and signal conditioning that have rarely been jointly investigated to date. This study systematically investigated the interaction effects of these dynamic factors on the performance of EMG-PR system towards constructing optimal parameters for accurately robust movement intent decoding in the context of prosthetic control. In this regard, the interaction effects of various features across window lengths (50 ms~300 ms), increments (50 ms~125 ms), robustness to external interferences and sensor channels (2 ch~6 ch), were examined using EMG signals obtained from twelve subjects through a symmetrical movement elicitation protocol. Compared to single features, multiple features consistently achieved minimum decoding error below 10% across optimal windowing parameters of 250 ms/100 ms. Also, the multiple features showed high robustness to additive noise with obvious trade-offs between accuracy and computation time. Consequently, our findings may provide proper insight for appropriate parameter selection in the context of robust PR-based control strategy for intelligent rehabilitation device.
13
Corcos, D. M., G. C. Agarwal, B. P. Flaherty, and G. L. Gottlieb. "Organizing principles for single-joint movements. IV. Implications for isometric contractions." Journal of Neurophysiology 64, no. 3 (1990): 1033–42. http://dx.doi.org/10.1152/jn.1990.64.3.1033.
Full textAbstract:
1. Normal human subjects made isometric pulse and step contractions about the elbow to visually defined target torques of different amplitudes and at different rates. We measured joint torque and electromyograms (EMG) from two agonist and two antagonist muscles. 2. When the task specification requires that the subject explicitly alter the rate at which torque is increased, the rates of rise of the agonist and antagonist EMG bursts covary with the rate of rise of the torque. For pulses of torque the duration of motoneuron excitation varies with the duration of the task-defined contractile event. 3. When a subject is asked to generate torques of different amplitudes without specifying a time interval, torque amplitude is positively correlated with how long, and therefore how high, the EMG rose. Subjects usually proportionately covary the strength of the agonist and antagonist contractions but are not constrained to do so. Some subjects use a strategy of varying the antagonist inversely with the agonist contraction. 4. We extend the organizing principles for the control of movement about a single joint to the control of isometric torque. These rules state that control of torque about a single joint is exercised by one of two strategies: the speed-sensitive strategy modulates the rate at which contraction rises by varying the intensity of motoneuron-pool excitation. The speed-insensitive strategy varies the duration over which contraction rises but does not change the rate. These two respective patterns of torque emerge from pulse-height and pulse-width modulation of motoneuron-pool excitation. 5. The rules defining speed-sensitive and speed-insensitive strategies for movements are broadened for isometric contractions because of the wider range of torque patterns that we observe under these conditions. We propose a step-excitation component for prolonged isometric step contractions and slowly rising ramp patterns of excitation for contractions that develop over several hundreds of milliseconds. 6. The choice of strategies is based on task-specific torque requirements. The same two strategies that control torque to produce movement apply to the control of isometric torque. Unlike movements, however, isometric tasks are more often controlled by a blending of the two patterns. Possible reasons for this are discussed.
14
CHIOU, YING-HAN, JER-JUNN LUH, SHIH-CHING CHEN, JIN-SHIN LAI, and TE-SON KUO. "RESIDUAL CAPABILITIES OF HEMIPLEGIC PATIENTS TO RESTORE HAND FUNCTIONS VIA A NON-INVASIVE FUNCTIONAL ELECTRICAL STIMULATION SYSTEM." Biomedical Engineering: Applications, Basis and Communications 18, no. 05 (2006): 255–63. http://dx.doi.org/10.4015/s1016237206000397.
Full textAbstract:
Control strategies are the chief attraction in the field of rehabilitation engineering, and especially in a functional electrical stimulation (FES) system, a reliable control method is important for paralyzed patients to restore lost their functions. In this paper, we have presented a demonstration of the control strategy, which is based on the patient-driven loop, used in a non-invasive FES system for hand function restoration. With the patient-driven loop control, hemiplegic patients could use their residual capabilities, such as shoulder movements in their sound extremities, the myoelectric signals generated from different muscles, etc, to operate the FES system. Here we have chosen the most common and acceptable signals as the input sources, i.e. electromyographic (EMG) signals, to control a non-invasive FES system, generating the electrical stimuli to excite the paralyzed muscles. In addition, EMG signals recorded by the sensors in the electrical stimulator can serve both as the trigger of the system and as the adjustment of the electrical stimulation parameters, thereby improving the system's performance and reliability. From the experimental results, subjects can successfully use their residual capabilities to control the FES system and restore their lost hand functions as well. On the other hand, from the viewpoints of rehabilitation and psychology, hemiplegics will benefit greatly by using their residual capabilities to regain their lost functions. It is believed that the patient-driven loop control is very useful, not only for the FES system in this study, but also for other assistive devices. By the control strategy proposed in this paper, we deeply hope that patients will benefit greatly and regain their self-confidence.
15
Fu, Zhumu, Aiyun Gao, Xiaohong Wang, and Xiaona Song. "Torque Split Strategy for Parallel Hybrid Electric Vehicles with an Integrated Starter Generator." Discrete Dynamics in Nature and Society 2014 (2014): 1–10. http://dx.doi.org/10.1155/2014/793864.
Full textAbstract:
This paper presents a torque split strategy for parallel hybrid electric vehicles with an integrated starter generator (ISG-PHEV) by using fuzzy logic control. By combining the efficiency map and the optimum torque curve of the internal combustion engine (ICE) with the state of charge (SOC) of the batteries, the torque split strategy is designed, which manages the ICE within its peak efficiency region. Taking the quantified ICE torque, the quantified SOC of the batteries, and the quantified ICE speed as inputs, and regarding the output torque demanded on the ICE as an output, a fuzzy logic controller (FLC) with relevant fuzzy rules has been developed to determine the optimal torque distribution among the ICE, the ISG, and the electric motor/generator (EMG) effectively. The simulation results reveal that, compared with the conventional torque control strategy which uses rule-based controller (RBC) in different driving cycles, the proposed FLC improves the fuel economy of the ISG-PHEV, increases the efficiency of the ICE, and maintains batteries SOC within its operation range more availably.
16
Jacobs, R., and J. M. Macpherson. "Two functional muscle groupings during postural equilibrium tasks in standing cats." Journal of Neurophysiology 76, no. 4 (1996): 2402–11. http://dx.doi.org/10.1152/jn.1996.76.4.2402.
Full textAbstract:
1. This study examined the relation between electromyographic (EMG) activation and the contact force and joint torques of the left hindlimb during postural equilibrium tasks in the standing cat. It is the appropriate application of force by the limbs against the support surface that allows the animal to control its center of mass and maintain equilibrium. 2. Cats were trained to stand quietly on a moveable force platform. During quiet stance, the cat was perturbed by a platform translation in each of 12 directions evenly spaced in the horizontal plane. EMG activity of mono- and biarticular thigh muscles, three-dimensional ground reaction force under the paw (contact force), and kinematics of the hindlimb segments were recorded Net joint torques were computed using inverse dynamics. The analysis focused on the functional organization of the rapid, automatic postural response in relation to the sagittal plane contact force and joint torques. 3. The muscles of the thigh were subdivided into two functional groups, based on the relationship of the evoked response to the various components of the sagittal plane contact force or joint torques. The first group, consisting of the monoarticular and some biarticular muscles, was correlated with the vertical force component, Fz. The second group, consisting of a separate group of biarticular muscles, was correlated with the difference between knee and hip torque. This torque difference is a function of both sagittal plane force components, Fz and Fy, and is related to contact force direction. 4. It is suggested that this subdivision of muscle activations reflects a neural strategy of parallel control of the two muscle groups in relation to their influence on Fz and Fy. Such a control mechanism could be a strategy for simplifying the control of the multisegmented limb in contact force tasks such as maintaining postural equilibrium.
17
Shahid, Talha, Darwin Gouwanda, Surya G. Nurzaman, and Alpha A. Gopalai. "Moving toward Soft Robotics: A Decade Review of the Design of Hand Exoskeletons." Biomimetics 3, no. 3 (2018): 17. http://dx.doi.org/10.3390/biomimetics3030017.
Full textAbstract:
Soft robotics is a branch of robotics that deals with mechatronics and electromechanical systems primarily made of soft materials. This paper presents a summary of a chronicle study of various soft robotic hand exoskeletons, with different electroencephalography (EEG)- and electromyography (EMG)-based instrumentations and controls, for rehabilitation and assistance in activities of daily living. A total of 45 soft robotic hand exoskeletons are reviewed. The study follows two methodological frameworks: a systematic review and a chronological review of the exoskeletons. The first approach summarizes the designs of different soft robotic hand exoskeletons based on their mechanical, electrical and functional attributes, including the degree of freedom, number of fingers, force transmission, actuation mode and control strategy. The second approach discusses the technological trend of soft robotic hand exoskeletons in the past decade. The timeline analysis demonstrates the transformation of the exoskeletons from rigid ferrous materials to soft elastomeric materials. It uncovers recent research, development and integration of their mechanical and electrical components. It also approximates the future of the soft robotic hand exoskeletons and some of their crucial design attributes.
18
Hug, François, Nicolas A. Turpin, Antoine Couturier, and Sylvain Dorel. "Consistency of muscle synergies during pedaling across different mechanical constraints." Journal of Neurophysiology 106, no. 1 (2011): 91–103. http://dx.doi.org/10.1152/jn.01096.2010.
Full textAbstract:
The purpose of the present study was to determine whether muscle synergies are constrained by changes in the mechanics of pedaling. The decomposition algorithm used to identify muscle synergies was based on two components: “muscle synergy vectors,” which represent the relative weighting of each muscle within each synergy, and “synergy activation coefficients,” which represent the relative contribution of muscle synergy to the overall muscle activity pattern. We hypothesized that muscle synergy vectors would remain fixed but that synergy activation coefficients could vary, resulting in observed variations in individual electromyographic (EMG) patterns. Eleven cyclists were tested during a submaximal pedaling exercise and five all-out sprints. The effects of torque, maximal torque-velocity combination, and posture were studied. First, muscle synergies were extracted from each pedaling exercise independently using non-negative matrix factorization. Then, to cross-validate the results, muscle synergies were extracted from the entire data pooled across all conditions, and muscle synergy vectors extracted from the submaximal exercise were used to reconstruct EMG patterns of the five all-out sprints. Whatever the mechanical constraints, three muscle synergies accounted for the majority of variability [mean variance accounted for (VAF) = 93.3 ± 1.6%, VAF muscle > 82.5%] in the EMG signals of 11 lower limb muscles. In addition, there was a robust consistency in the muscle synergy vectors. This high similarity in the composition of the three extracted synergies was accompanied by slight adaptations in their activation coefficients in response to extreme changes in torque and posture. Thus, our results support the hypothesis that these muscle synergies reflect a neural control strategy, with only a few timing adjustments in their activation regarding the mechanical constraints.
19
Weeks, D. L., M. P. Aubert, A. G. Feldman, and M. F. Levin. "One-trial adaptation of movement to changes in load." Journal of Neurophysiology 75, no. 1 (1996): 60–74. http://dx.doi.org/10.1152/jn.1996.75.1.60.
Full textAbstract:
1. We analyzed the rapid adaptation of elbow movement to unexpected changes in external load conditions at the elbow joint. The experimental approach was based on the lambda model, which defines control variables (CVs) setting the positional frames of reference for recruitment of flexor and extensor motoneurons. CVs may be specified by the nervous system independently of the current values of output variable such as electromyographic (EMG) activity, muscle torques, and kinematics. The CV R specifies the referent joint angle (R) at which the transition of flexor to extensor activity or vice versa can be observed during changes in the actual joint angle, theta, elicited by an external force. The other CV, the coactivation (C) command, instead of a single transition angle, defines an angular range in which flexor and extensor muscles may be simultaneously active (if C > 0) or silent (if C < 0). Changes in the R command result in shifts in the equilibrium state of the system, a dynamic process leading to EMG modifications resulting in movement or isometric force production if movement is obstructed. Fast movements are likely produced by combining the R command with a positive C command, which provides movement stability and effective energy dissipation, diminishing oscillations at the end of movement. 2. According to the model, changes in the load characteristic (e.g., from a 0 to a springlike load) influence the system's equilibrium state, leading to a positional error. This error may be corrected by a secondary movement produced by additional changes in R and C commands. In subsequent trials, the system may reproduce the CVs specified after correction in the previous trial. This behavior is called the recurrent strategy. It allows the system to adapt to the new load condition in the subsequent trials without corrections (1-trial adaptation). Alternatively, the system may reproduce the CVs specified before correction (invariant strategy). If the movement was perturbed only in a single trial, the invariant strategy allows the system to reach the target in the subsequent trials without corrections. 3. To test the assumption on the dominant role of the recurrent strategy in rapid adaptation of movement to new load conditions, we performed experiments in which subjects (n = 6) used a pivoting manipulandum and made fast 60 degrees movements to a target. After a random number of trials (5-10) with no load, we introduced opposing (experiment 1), assisting (experiment 2), or randomly varied opposing or assisting loads (experiment 3) for 5-10 trials before unexpectedly switching loads again (14-18 switches in total). The opposing or assisting torque was created by position feedback to a torque motor and was a linear function of the displacement of the manipulandum form the initial position (springlike load). Subjects were instructed to correct positional errors as soon as possible to reach the target. The EMG activity of two elbow flexors (biceps brachii and brachioradialis) and two elbow extensors (triceps brachii and anconeus), elbow position, velocity, and torque were recorded. Kinematic and EMG patterns were compared with those obtained in similar experiments in which subjects were instructed not to correct errors. 4. In 94% of the trials in which a change in the load occurred, the primary movement was in error and was followed by a corrective secondary movement. In primary movements, both the phasic and tonic levels of EMG activity as well as the kinematics were load dependent, implicating reflex and intramuscular mechanisms in the adaptation of muscle forces counteracting external loads. These mechanisms, however, were not sufficient to eliminate positional errors. 5. An undershoot error occurred in trials with an opposing load after those with no load or in trials with no load after those with an assisting load. After adaptation to a new load condition, a sudden return to the previous load condition resulted in an error of the oppo
20
Henry, Sharon M., Joyce Fung, and Fay B. Horak. "Effect of Stance Width on Multidirectional Postural Responses." Journal of Neurophysiology 85, no. 2 (2001): 559–70. http://dx.doi.org/10.1152/jn.2001.85.2.559.
Full textAbstract:
The effect of stance width on postural responses to 12 different directions of surface translations was examined. Postural responses were characterized by recording 11 lower limb and trunk muscles, body kinematics, and forces exerted under each foot of 7 healthy subjects while they were subjected to horizontal surface translations in 12 different, randomly presented directions. A quasi-static approach of force analysis was done, examining force integrals in three different epochs (background, passive, and active periods). The latency and amplitude of muscle responses were quantified for each direction, and muscle tuning curves were used to determine the spatial activation patterns for each muscle. The results demonstrate that the horizontal force constraint exerted at the ground was lessened in the wide, compared with narrow, stance for humans, a similar finding to that reported by Macpherson for cats. Despite more trunk displacement in narrow stance, there were no significant changes in body center of mass (CoM) displacement due to large changes in center of pressure (CoP), especially in response to lateral translations. Electromyographic (EMG) magnitude decreased for all directions in wide stance, particularly for the more proximal muscles, whereas latencies remained the same from narrow to wide stance. Equilibrium control in narrow stance was more of an active postural strategy that included regulating the loading/unloading of the limbs and the direction of horizontal force vectors. In wide stance, equilibrium control relied more on an increase in passive stiffness resulting from changes in limb geometry. The selective latency modulation of the proximal muscles with translation direction suggests that the trunk was being actively controlled in all directions. The similar EMG latencies for both narrow and wide stance, with modulation of only the muscle activation magnitude as stance width changed, suggest that the same postural synergy was only slightly modified for a change in stance width. Nevertheless, the magnitude of the trunk displacement, as well as of CoP displacement, was modified based on the degree of passive stiffness in the musculoskeletal system, which increased with stance width. The change from a more passive to an active horizontal force constraint, to larger EMG magnitudes especially in the trunk muscles and larger trunk and CoP excursions in narrow stance are consistent with a more effortful response for equilibrium control in narrow stance to perturbations in all directions.
21
Stäuber, F., A. Brunner, D. Czepa, et al. "Altersabhängige Ansteuerung der Muskulatur im Stand bei Patienten mit Hämophilie." Hämostaseologie 34, S 01 (2014): S36—S42. http://dx.doi.org/10.5482/hamo-14-02-0015.
Full textAbstract:
SummaryThe haemophilic arthropathy affects the function of the knee joint muscles. The aim of this study was to investigate the myoelectrical signal of knee joint muscles in different age stages during upright standing. Surface EMG (SEMG) amplitudes of quadriceps, hamstrings and gastrocnemii were measured in 191 patients with severe haemophilia A (n=164) and B (n=27) while standing on an even surface. After an age-based classification of patients into the subgroups HA: 17–29 (n = 37), HB: 30–39 (n = 50), HC: 40–49 (n = 61), HD: 50–70 in years (n = 43) the clinical WFH score for the ankle and knee joint was determined. To normalize the SEMG values amplitude ratios (percentage of cumulated activity) were calculated with respect to the specific limb. With increasing age, the patient showed descriptively a deterioration of the joint situation. The extensors of the knee joint reached significantly higher absolute and percentage levels in the muscle activity with increasing age (p < 0.05). The absolute amplitude values of the Mm. gastrocnemii showed no differences in the age groups while the relative levels were decreased.The present study shows that patients with increasing age and degree of haemophilic arthro pathy deve lop a modified control strategy during upright standing, in the form of a shift from the plantar flexors to the extensors of the knee joint.
22
Ghofrani, Masoud, Manijeh Soleimanifar, and Saeed Talebian. "Control of trunk muscles activity while manual material handling symmetrically and asymmetrically, Based on Motor control strategy." Pakistan Journal of Medical and Health Sciences 15, no. 6 (2021): 1736–40. http://dx.doi.org/10.53350/pjmhs211561736.
Full textAbstract:
[Purpose] Although lifting tasks has been recognized as a primary risk factor in low back pain, the concept of lifting asymmetry is relatively new subject. To address trunk function, biomechanical studies generally measure trunk muscle activity using surface electromyography (EMG). But so far, magnitude and similarity index (SI) obtained from EMG have not been studied as indicators of the motor control during lifting task. So, the purpose of this study is to compare the trunk muscles magnitude and SI during symmetric and asymmetric lifting. [Subjects and Methods] A total of 20 healthy male with no history of lumbar spine disorders participated. Surface electromyography data were recorded from the 7 trunk muscles while the participants performed symmetric and asymmetric lifting and lowering different loads. [Results] According to Multivariate ANOVAs the phase of motion (lifting, lowering) and condition (symmetry, asymmetry) have a significant effect on SI and magnitude (p≤0.05). Load changes have no effect on SI (p=0.969) but have a significant effect on magnitude (p≤0.05). The magnitude and SI value is higher in asymmetrical lifting and lowering compare to symmetrical condition. [Conclusion] The findings reveal the SI value is higher in asymmetric conditions. This means that the amount of muscles co-contracture increased during asymmetrical conditions. Increased muscles co-contracture reinforces the hypothesis of exerting more compression on the spine in asymmetrical movement. Keywords: Asymmetrical lifting, Motor control, Electromyography
23
Ting, Lena H., Steven A. Kautz, David A. Brown, and Felix E. Zajac. "Phase Reversal of Biomechanical Functions and Muscle Activity in Backward Pedaling." Journal of Neurophysiology 81, no. 2 (1999): 544–51. http://dx.doi.org/10.1152/jn.1999.81.2.544.
Full textAbstract:
Phase reversal of biomechanical functions and muscle activity in backward pedaling. Computer simulations of pedaling have shown that a wide range of pedaling tasks can be performed if each limb has the capability of executing six biomechanical functions, which are arranged into three pairs of alternating antagonistic functions. An Ext/Flex pair accelerates the limb into extension or flexion, a Plant/Dorsi pair accelerates the foot into plantarflexion or dorsiflexion, and an Ant/Post pair accelerates the foot anteriorly or posteriorly relative to the pelvis. Because each biomechanical function (i.e., Ext, Flex, Plant, Dorsi, Ant, or Post) contributes to crank propulsion during a specific region in the cycle, phasing of a muscle is hypothesized to be a consequence of its ability to contribute to one or more of the biomechanical functions. Analysis of electromyogram (EMG) patterns has shown that this biomechanical framework assists in the interpretation of muscle activity in healthy and hemiparetic subjects during forward pedaling. Simulations show that backward pedaling can be produced with a phase shift of 180° in the Ant/Post pair. No phase shifts in the Ext/Flex and Plant/Dorsi pairs are then necessary. To further test whether this simple yet biomechanically viable strategy may be used by the nervous system, EMGs from 7 muscles in 16 subjects were measured during backward as well as forward pedaling. As predicted, phasing in vastus medialis (VM), tibialis anterior (TA), medial gastrocnemius (MG), and soleus (SL) were unaffected by pedaling direction, with VM and SL contributing to Ext, MG to Plant, and TA to Dorsi. In contrast, phasing in biceps femoris (BF) and semimembranosus (SM) were affected by pedaling direction, as predicted, compatible with their contribution to the directionally sensitive Post function. Phasing of rectus femoris (RF) was also affected by pedaling direction; however, its ability to contribute to the directionally sensitive Ant function may only be expressed in forward pedaling. RF also contributed significantly to the directionally insensitive Ext function in both forward and backward pedaling. Other muscles also appear to have contributed to more than one function, which was especially evident in backward pedaling (i.e., BF, SM, MG, and TA to Flex). We conclude that the phasing of only the Ant and Post biomechanical functions are directionally sensitive. Further, we suggest that task-dependent modulation of the expression of the functions in the motor output provides this biomechanics-based neural control scheme with the capability to execute a variety of lower limb tasks, including walking.
24
sbargoud, Fazia, Mohamed Djeha, Mohamed Guiatni, and Noureddine Ababou. "HYBRID CLASSIFICATION STRATEGY OF EMG SIGNALS FOR ROBOTIC HAND CONTROL." Biomedical Engineering: Applications, Basis and Communications, March 16, 2021, 2150015. http://dx.doi.org/10.4015/s1016237221500150.
Full textAbstract:
Among the different bio-signals modalities, Electromyographic signal (EMG) has been one of the frequently used signals in the bio-robotics applications field. This is due to the fact that the EMG reflects directly the muscle activity of the user following the human motion intention. Consequently, the decoding of this intention is an essential task for controlling devices such as prosthetic hands and exoskeletons, based on EMG signals. This paper deals with the processing of EMG signals of the forearm muscles, in order to control two degrees of freedom (2 DoFs) robotic hand. The main contribution of this paper is the proposal of a hybrid approach that combines a pattern and a non-pattern recognition-based strategy. The proposed approach aims to take advantage of both strategies and overcome their shortcomings leading to a better analysis of the user movement intention. The EMG recorded signals are processed for feature extraction based on a Wavelet Packet Decomposition (WPD) method and classification using an Artificial Neural Network (ANN). Furthermore, we investigate the effect of the various parameters such as the applied force level, the number of the EMG channels and the window length of the EMG signal. The proposed approach is validated experimentally under realistic conditions. Very interesting results have been obtained for user intention decoding.
25
Alkhafaf, Omer Saad, Mousa K. Wali, and Ali H. Al-Timemy. "Improved hand prostheses control for transradial amputees based on hybrid of voice recognition and electromyography." International Journal of Artificial Organs, December 7, 2020, 039139882097665. http://dx.doi.org/10.1177/0391398820976656.
Full textAbstract:
The control of prostheses and their complexities is one of the greatest challenges limiting wide amputees’ use of upper limb prostheses. The main challenges include the difficulty of extracting signals for controlling the prostheses, limited number of degrees of freedom (DoF), and cost-prohibitive for complex controlling systems. In this study, a real-time hybrid control system, based on electromyography (EMG) and voice commands (VC) is designed to render the prosthesis more dexterous with the ability to accomplish amputee’s daily activities proficiently. The voice and EMG systems were combined in three proposed hybrid strategies, each strategy had different number of movements depending on the combination protocol between voice and EMG control systems. Furthermore, the designed control system might serve a large number of amputees with different amputation levels, and since it has a reasonable cost and be easy to use. The performance of the proposed control system, based on hybrid strategies, was tested by intact-limbed and amputee participants for controlling the HANDi hand. The results showed that the proposed hybrid control system was robust, feasible, with an accuracy of 94%, 98%, and 99% for Strategies 1, 2, and 3, respectively. It was possible to specify the grip force applied to the prosthetic hand within three gripping forces. The amputees participated in this study preferred combination Strategy 3 where the voice and EMG are working concurrently, with an accuracy of 99%.
26
Ay, Ayse Nur, and Mustafa Zahid Yildiz. "The effect of attentional focusing strategies on EMG-based classification." Biomedical Engineering / Biomedizinische Technik, October 16, 2020. http://dx.doi.org/10.1515/bmt-2020-0082.
Full textAbstract:
AbstractEarlier studies showed that external focusing enhances motor performance and reduces muscular activity compare to internal one. However, low activity is not always desired especially in case of Human-Machine Interface applications. This study is based on investigating the effects of attentional focusing preferences on EMG based control systems. For the EMG measurements via biceps brachii muscles, 35 subjects were asked to perform weight-lifting under control, external and internal focus conditions. The difference between external and internal focusing was found to be significant and internal focus enabled higher EMG activity. Besides, six statistical features, namely, RMS, maximum, minimum, mean, standard deviation, and variance were extracted from both time and frequency domains to be used as inputs for Artificial Neural Network classifiers. The results found to be 87.54% for ANN1 and 82.69% for ANN2, respectively. These findings showed that one’s focus of attention would be predicted during the performance and unlike the literature, internal focusing could be also useful when it is used as an input for HMI studies. Therefore, attentional focusing might be an important strategy not only for performance improvement to human movement but also for advancing the study of EMG-based control mechanisms.
27
Yihun, Yimesker, Visharath Adhikari, Amirhossein Majidirad, and Jaydip Desai. "Task-Based Knee Rehabilitation With Assist-as-Needed Control Strategy and Recovery Tracking System." Journal of Engineering and Science in Medical Diagnostics and Therapy 3, no. 2 (2020). http://dx.doi.org/10.1115/1.4046400.
Full textAbstract:
Abstract This research aims to design and implement a novel task-based knee rehabilitation strategy through kinematic synthesis, assist-as-needed control strategy, and recovery tracking system. Experimental kinematic data collected through motion capture system are utilized as an input to the mechanism synthesis procedure. Parallel mechanisms with single degree-of-freedom are considered to generate the complex three-dimensional (3D) motions of the lower leg. An exact workspace synthesis approach is utilized, in which the implicit description of the workspace is made to be a function of the structural parameters of the serial chains of the parallel mechanism, making it easy to relate those parameters to the desired trajectory from the motion capture. The synthesis procedure resulted an exoskeleton which can guide the complex motion of the human knee without the need of mimicking the joint by the exoskeleton counterpart. This can potentially reduce the improper alignment problems arising due to the constantly varying axis of rotation of human joint, which is often very difficult to predict. An assist-as-needed control and recovery tracking strategy is outlined based on an electromyography (EMG) signals and force sensing resistors (FSRs) mounted on the user and exoskeleton, respectively. The EMG signal is captured from the user leg and FSRs are applied at the attachment area of the exoskeleton and the leg, this helps to get the amount of force applied by the exoskeleton to the leg as well as for the recovery tracking. The assist-as-needed controller eliminates the need of constant supervision, and hence saves time and reduces cost of the rehabilitation process. Similarly, the real-time progress tracking system will motivate and actively engage users
28
Asai, Yoshiyuki, Shota Tateyama, and Taishin Nomura. "Correction: Learning an Intermittent Control Strategy for Postural Balancing Using an EMG-Based Human-Computer Interface." PLoS ONE 9, no. 1 (2014). http://dx.doi.org/10.1371/annotation/0495873b-830d-498e-8cbd-68af5bb55371.
Full text
29
A, Ameri. "Recent Advances in EMG Pattern Recognition for Prosthetic Control." Journal of Biomedical Physics and Engineering 10, no. 2 (2020). http://dx.doi.org/10.31661/jbpe.v0i0.2002-1076.
Full textAbstract:
Limb loss results in significant debilitation and reduces the quality of life of the affected individuals [ 1 ]. To restore the lost limb’s function, myoelectric systems have been widely used in powered prostheses [ 2 ]. With this approach, the motor intent is estimated from the electromyogram (EMG) signals recorded by electrodes which are placed on the skin surface above the residual muscles [ 1 ]. The principle of commercial myoelectric schemes has not changed in several decades, and is referred to as conventional control [ 2 ]. This technique uses a measure of amplitude (such as mean absolute value over a time window) of the EMG signals recorded by electrodes placed at two control sites, preferably over a pair of antagonist muscles of the residual limb, to control a single motion i.e. degree of freedom (DoF), for example hand opening closing [ 2 ]. To change the DoF, a mode switch is conducted by muscle co-contraction or a hardware switch [ 2 ]. The mode switch, however, results in an unnatural control of multiple DoFs [ 2 ]. To overcome this challenge, a significant body of research has been conducted on pattern recognition techniques [ 3 ]. With this approach, a classifier is trained to discriminate between different DoFs, using patterns from multi-channel EMG input data. Promising results have been achieved in the literature for classification of several DoFs [ 2 ]. Since activities of daily living include simultaneous movements of multiple DoFs, combined motions must be also included as separate classes, and they have to be conducted in the training set [ 4 ]. The limitation of this approach, however, is that it does not allow the DoFs in combined motions to have different magnitudes. As a solution to this problem, regression-based systems have been proposed [ 5 , 6 ], where a regressor is trained to estimate each DoF, using data from single and combined motions. This strategy provides independent simultaneous control, because it does not limit the DoFs to have the same amplitude. Classification and regression based systems are the two categories of pattern recognition methods. Due to the high dimensionality of EMG signals, the EMG instantaneous values are not directly used as the inputs to classifiers/regressors [ 1 ]. Instead, a set of features is extracted from a time window (100-200 ms) of EMG signals [ 7 ]. Feature engineering is the process of design and extraction of features with the highest amount of useful information to maximize the classification/regression accuracy [ 8 ] Among various EMG features proposed in the literature, the Time Domain (TD) set [ 9 ] is the most popular set and includes mean absolute value, waveform length, zero-crossings, and slope sign changes. The past few years have seen the advent of deep learning-based myoelectric control [ 4 , 10 ]. Deep learning can perform classification/regression tasks directly from high-dimensional raw data, without feature engineering [ 8 ]. Convolutional neural network (CNN) [ 11 ] is one of the most widely used deep learning frameworks. The successive convolution layers of CNNs can learn useful features from the EMG data to estimate the motor intent [ 4 ]. As the outcomes of the previous studies [ 4 , 10 ] confirm, CNNs outperform classical models such as support vector machines (SVMs) with engineered feature sets. EMG pattern recognition schemes have yet to be deployed in commercial prostheses. The major challenge is performance degradation due to disturbances such as electrode shift, skin impedance change, muscle size variations, and learning effect [ 2 ]. Recent studies (e.g. [ 12 , 13 ]) have proposed methods to improve the robustness of EMG pattern recognition to such disturbances. These methods as well as new deep learning schemes that eliminate feature engineering, may pave the way for commercial implementation of myoelectric pattern recognition prostheses. Moreover, independent simultaneous control can be achieved by using regression deep learning models. These promising methods have the potential to significantly outperform existing commercial systems. Consequently, the missing functions in people with limb loss can be restored more efficiently by delivering a more natural and intuitive control.
30
Adiputra, Dimas, Ubaidillah Ubaidillah, Saiful Amri Mazlan, Hairi Zamzuri, and Mohd Azizi Abdul Rahman. "FUZZY LOGIC CONTROL FOR ANKLE FOOT ORTHOSES EQUIPPED WITH MAGNETORHEOLOGICAL BRAKE." Jurnal Teknologi 78, no. 11 (2016). http://dx.doi.org/10.11113/.v78.7942.
Full textAbstract:
This study focused on the development of passive control ankle foot orthosis (PICAFO) for a specific purpose such as preventing foot drop in the post-stroke patient. The PICAFO utilized the magnetorheological (MR) brake as the actuator in which the braking torque was controlled by regulating direct current (DC) from current driver. The Fuzzy Logic Controller (FLC) was employed to control output voltage for current driver based on the inputs, i.e. Electromyography (EMG) bio signal and ankle position. Walking experiment to test the controller was carried out on a single subject where the input and output FLC was monitored and logged. The results showed that the output voltage of the FLC was 94.41% of the maximum output (high) on forward ankle position during swing phase and gradually increase from 9.667% to 77.34% of maximum output during stance phase. The FLC successfully controlled the output voltage according to the required needs. According to the experimental results, the FLC strategy was applicable for PICAFO realizing it contributes to prevention of foot drop.
31
Tam, Simon, Mounir Boukadoum, Alexandre Campeau-Lecours, and Benoit Gosselin. "Intuitive real-time control strategy for high-density myoelectric hand prosthesis using deep and transfer learning." Scientific Reports 11, no. 1 (2021). http://dx.doi.org/10.1038/s41598-021-90688-4.
Full textAbstract:
AbstractMyoelectric hand prostheses offer a way for upper-limb amputees to recover gesture and prehensile abilities to ease rehabilitation and daily life activities. However, studies with prosthesis users found that a lack of intuitiveness and ease-of-use in the human-machine control interface are among the main driving factors in the low user acceptance of these devices. This paper proposes a highly intuitive, responsive and reliable real-time myoelectric hand prosthesis control strategy with an emphasis on the demonstration and report of real-time evaluation metrics. The presented solution leverages surface high-density electromyography (HD-EMG) and a convolutional neural network (CNN) to adapt itself to each unique user and his/her specific voluntary muscle contraction patterns. Furthermore, a transfer learning approach is presented to drastically reduce the training time and allow for easy installation and calibration processes. The CNN-based gesture recognition system was evaluated in real-time with a group of 12 able-bodied users. A real-time test for 6 classes/grip modes resulted in mean and median positive predictive values (PPV) of 93.43% and 100%, respectively. Each gesture state is instantly accessible from any other state, with no mode switching required for increased responsiveness and natural seamless control. The system is able to output a correct prediction within less than 116 ms latency. 100% PPV has been attained in many trials and is realistically achievable consistently with user practice and/or employing a thresholded majority vote inference. Using transfer learning, these results are achievable after a sensor installation, data recording and network training/fine-tuning routine taking less than 10 min to complete, a reduction of 89.4% in the setup time of the traditional, non-transfer learning approach.
32
Kisiel-Sajewicz, Katarzyna, Jarosław Marusiak, Mónica Rojas-Martínez, et al. "High-density surface electromyography maps after computer-aided training in individual with congenital transverse deficiency: a case study." BMC Musculoskeletal Disorders 21, no. 1 (2020). http://dx.doi.org/10.1186/s12891-020-03694-4.
Full textAbstract:
Abstract Background The aim of this study was to determine whether computer-aided training (CAT) of motor tasks would increase muscle activity and change its spatial distribution in a patient with a bilateral upper-limb congenital transverse deficiency. We believe that our study makes a significant contribution to the literature because it demonstrates the usefulness of CAT in promoting the neuromuscular adaptation in people with congenital limb deficiencies and altered body image. Case presentation The patient with bilateral upper-limb congenital transverse deficiency and the healthy control subject performed 12 weeks of the CAT. The subject’s task was to imagine reaching and grasping a book with the hand. Subjects were provided a visual animation of that movement and sensory feedback to facilitate the mental engagement to accomplish the task. High-density electromyography (HD-EMG; 64-electrode) were collected from the trapezius muscle during a shrug isometric contraction before and after 4, 8, 12 weeks of the training. After training, we observed in our patient changes in the spatial distribution of the activation, and the increased average intensity of the EMG maps and maximal force. Conclusions These results, although from only one patient, suggest that mental training supported by computer-generated visual and sensory stimuli leads to beneficial changes in muscle strength and activity. The increased muscle activation and changed spatial distribution of the EMG activity after mental training may indicate the training-induced functional plasticity of the motor activation strategy within the trapezius muscle in individual with bilateral upper-limb congenital transverse deficiency. Marked changes in spatial distribution during the submaximal contraction in the patient after training could be associated with changes of the neural drive to the muscle, which corresponds with specific (unfamiliar for patient) motor task. These findings are relevant to neuromuscular functional rehabilitation in patients with a bilateral upper-limb congenital transverse deficiency especially before and after upper limb transplantation and to development of the EMG based prostheses.
33
Krasoulis, Agamemnon, and Kianoush Nazarpour. "Myoelectric digit action decoding with multi-output, multi-class classification: an offline analysis." Scientific Reports 10, no. 1 (2020). http://dx.doi.org/10.1038/s41598-020-72574-7.
Full textAbstract:
Abstract The ultimate goal of machine learning-based myoelectric control is simultaneous and independent control of multiple degrees of freedom (DOFs), including wrist and digit artificial joints. For prosthetic finger control, regression-based methods are typically used to reconstruct position/velocity trajectories from surface electromyogram (EMG) signals. Unfortunately, such methods have thus far met with limited success. In this work, we propose action decoding, a paradigm-shifting approach for independent, multi-digit movement intent prediction based on multi-output, multi-class classification. At each moment in time, our algorithm decodes movement intent for each available DOF into one of three classes: open, close, or stall (i.e., no movement). Despite using a classifier as the decoder, arbitrary hand postures are possible with our approach. We analyse a public dataset previously recorded and published by us, comprising measurements from 10 able-bodied and two transradial amputee participants. We demonstrate the feasibility of using our proposed action decoding paradigm to predict movement action for all five digits as well as rotation of the thumb. We perform a systematic offline analysis by investigating the effect of various algorithmic parameters on decoding performance, such as feature selection and choice of classification algorithm and multi-output strategy. The outcomes of the offline analysis presented in this study will be used to inform the real-time implementation of our algorithm. In the future, we will further evaluate its efficacy with real-time control experiments involving upper-limb amputees.
34
Missiroli, Francesco, Nicola Lotti, Michele Xiloyannis, Lizeth H. Sloot, Robert Riener, and Lorenzo Masia. "Relationship Between Muscular Activity and Assistance Magnitude for a Myoelectric Model Based Controlled Exosuit." Frontiers in Robotics and AI 7 (December 17, 2020). http://dx.doi.org/10.3389/frobt.2020.595844.
Full textAbstract:
The growing field of soft wearable exosuits, is gradually gaining terrain and proposing new complementary solutions in assistive technology, with several advantages in terms of portability, kinematic transparency, ergonomics, and metabolic efficiency. Those are palatable benefits that can be exploited in several applications, ranging from strength and resistance augmentation in industrial scenarios, to assistance or rehabilitation for people with motor impairments. To be effective, however, an exosuit needs to synergistically work with the human and matching specific requirements in terms of both movements kinematics and dynamics: an accurate and timely intention-detection strategy is the paramount aspect which assume a fundamental importance for acceptance and usability of such technology. We previously proposed to tackle this challenge by means of a model-based myoelectric controller, treating the exosuit as an external muscular layer in parallel to the human biomechanics and as such, controlled by the same efferent motor commands of biological muscles. However, previous studies that used classical control methods, demonstrated that the level of device's intervention and effectiveness of task completion are not linearly related: therefore, using a newly implemented EMG-driven controller, we isolated and characterized the relationship between assistance magnitude and muscular benefits, with the goal to find a range of assistance which could make the controller versatile for both dynamic and static tasks. Ten healthy participants performed the experiment resembling functional daily activities living in separate assistance conditions: without the device's active support and with different levels of intervention by the exosuit. Higher assistance levels resulted in larger reductions in the activity of the muscles augmented by the suit actuation and a good performance in motion accuracy, despite involving a decrease of the movement velocities, with respect to the no assistance condition. Moreover, increasing torque magnitude by the exosuit resulted in a significant reduction in the biological torque at the elbow joint and in a progressive effective delay in the onset of muscular fatigue. Thus, contrarily to classical force and proportional myoelectric schemes, the implementation of an opportunely tailored EMG-driven model based controller affords to naturally match user's intention detection and provide an assistance level working symbiotically with the human biomechanics.