Detection Of Movement Intention Research Articles

Preparatory movement state enhances premovement EEG representations for brain–computer interfaces

Objective. Motor-related brain–computer interface (BCI) have a broad range of applications, with the detection of premovement intentions being a prominent use case. However, the electroencephalography (EEG) features during the premovement phase are not distinctly evident and are susceptible to attentional influences. These limitations impede the enhancement of performance in motor-based BCI. The objective of this study is to establish a premovement BCI encoding paradigm that integrates the preparatory movement state and validates its feasibility in improving the detection of movement intentions. Methods. Two button tasks were designed to induce subjects into a preparation state for two movement intentions (left and right) based on visual guidance, in contrast to spontaneous premovement. The low frequency movement-related cortical potentials (MRCPs) and high frequency event-related desynchronization (ERD) EEG data of 14 subjects were recorded. Extracted features were fused and classified using task related common spatial patterns (CSP) and CSP algorithms. Differences between prepared premovement and spontaneous premovement were compared in terms of time domain, frequency domain, and classification accuracy. Results. In the time domain, MRCPs features reveal that prepared premovement induce lower amplitude and earlier latency on both contralateral and ipsilateral motor cortex compared to spontaneous premovement, with susceptibility to the dominant hand’s influence. Frequency domain ERD features indicate that prepared premovement induce lower ERD values bilaterally, and the ERD recovery speed after button press is the fastest. By using the fusion approach, the classification accuracy increased from 78.92% for spontaneous premovement to 83.59% for prepared premovement (p < 0.05). Along with the 4.67% improvement in classification accuracy, the standard deviation decreased by 0.95. Significance. The research findings confirm that incorporating a preparatory state into premovement enhances neural representations related to movement. This encoding enhancement paradigm effectively improves the performance of motor-based BCI. Additionally, this concept has the potential to broaden the range of decodable movement intentions and related information in motor-related BCI.

A systematic investigation of detectors for low signal-to-noise ratio EMG signals.

Active participation of stroke survivors during robot-assisted movement therapy is essential for sensorimotor recovery. Robot-assisted therapy contingent on movement intention is an effective way to encourage patients' active engagement. For severely impaired stroke patients with no residual movements, a surface electromyogram (EMG) has been shown to be a viable option for detecting movement intention. Although numerous algorithms for EMG detection exist, the detector with the highest accuracy and lowest latency for low signal-to-noise ratio (SNR) remains unknown. This study, therefore, investigates the performance of 13 existing EMG detection algorithms on simulated low SNR (0dB and -3dB) EMG signals generated using three different EMG signal models: Gaussian, Laplacian, and biophysical model. The detector performance was quantified using the false positive rate (FPR), false negative rate (FNR), and detection latency. Any detector that consistently showed FPR and FNR of no more than 20%, and latency of no more than 50ms, was considered an appropriate detector for use in robot-assisted therapy. The results indicate that the Modified Hodges detector - a simplified version of the threshold-based Hodges detector introduced in the current study - was the most consistent detector across the different signal models and SNRs. It consistently performed for ~90% and ~40% of the tested trials for 0dB and -3dB SNR, respectively. The two statistical detectors (Gaussian and Laplacian Approximate Generalized Likelihood Ratio) and the Fuzzy Entropy detectors have a slightly lower performance than Modified Hodges. Overall, the Modified Hodges, Gaussian and Laplacian Approximate Generalized Likelihood Ratio, and the Fuzzy Entropy detectors were identified as the potential candidates that warrant further investigation with real surface EMG data since they had consistent detection performance on low SNR EMG data.

EEG generation mechanism of lower limb active movement intention and its virtual reality induction enhancement: a preliminary study.

Active rehabilitation requires active neurological participation when users use rehabilitation equipment. A brain-computer interface (BCI) is a direct communication channel for detecting changes in the nervous system. Individuals with dyskinesia have unclear intentions to initiate movement due to physical or psychological factors, which is not conducive to detection. Virtual reality (VR) technology can be a potential tool to enhance the movement intention from pre-movement neural signals in clinical exercise therapy. However, its effect on electroencephalogram (EEG) signals is not yet known. Therefore, the objective of this paper is to construct a model of the EEG signal generation mechanism of lower limb active movement intention and then investigate whether VR induction could improve movement intention detection based on EEG. Firstly, a neural dynamic model of lower limb active movement intention generation was established from the perspective of signal transmission and information processing. Secondly, the movement-related EEG signal was calculated based on the model, and the effect of VR induction was simulated. Movement-related cortical potential (MRCP) and event-related desynchronization (ERD) features were extracted to analyze the enhancement of movement intention. Finally, we recorded EEG signals of 12 subjects in normal and VR environments to verify the effectiveness and feasibility of the above model and VR induction enhancement of lower limb active movement intention for individuals with dyskinesia. Simulation and experimental results show that VR induction can effectively enhance the EEG features of subjects and improve the detectability of movement intention. The proposed model can simulate the EEG signal of lower limb active movement intention, and VR induction can enhance the early and accurate detectability of lower limb active movement intention. It lays the foundation for further robot control based on the actual needs of users.

A systematic investigation of detectors for low signal-to-noise ratio EMG signals

Background Active participation of stroke survivors during robot-assisted movement therapy is essential for sensorimotor recovery. Robot-assisted therapy contingent on movement intention is an effective way to encourage patients’ active engagement. For severely impaired stroke patients with no residual movements, a surface electromyogram (EMG) has been shown to be a viable option for detecting movement intention. Although numerous algorithms for EMG detection exist, the detector with the highest accuracy and lowest latency for low signal-to-noise ratio (SNR) remains unknown. Methods This study, therefore, investigates the performance of 13 existing EMG detection algorithms on simulated low SNR (0dB and -3dB) EMG signals generated using three different EMG signal models: Gaussian, Laplacian, and biophysical model. The detector performance was quantified using the false positive rate (FPR), false negative rate (FNR), and detection latency. Any detector that consistently showed FPR and FNR of no more than 20%, and latency of no more than 50ms, was considered an appropriate detector for use in robot-assisted therapy. Results The results indicate that the Modified Hodges detector – a simplified version of the threshold-based Hodges detector introduced in the current study – was the most consistent detector across the different signal models and SNRs. It consistently performed for ~90% and ~40% of the tested trials for 0dB and -3dB SNR, respectively. The two statistical detectors (Gaussian and Laplacian Approximate Generalized Likelihood Ratio) and the Fuzzy Entropy detectors have a slightly lower performance than Modified Hodges. Conclusions Overall, the Modified Hodges, Gaussian and Laplacian Approximate Generalized Likelihood Ratio, and the Fuzzy Entropy detectors were identified as the potential candidates that warrant further investigation with real surface EMG data since they had consistent detection performance on low SNR EMG data.

A cascade fuzzy adaptive based interaction torque control of a pneumatically actuated forearm rehabilitation robot under disturbance effects

In this study, an intelligent adaptive interaction torque control for a pneumatically actuated forearm rehabilitation robot has been proposed. The main objective is to provide a haptic environment that ensures stable interaction torque fields at changing levels. To achieve this goal, a cascade fuzzy adaptive controller, that is specifically tailored to handle varying levels of interaction torque and ensure stability throughout the rehabilitation process, has been designed. To improve the efficiency of the controller, non-linear friction torque identification of the pneumatic actuator based on changing operating conditions has been conducted. Parallel to this, a user motion intention detection algorithm has been designed to provide compliant, safe and suitable human-robot interactions. The disturbance cases have been considered to make the system robust to unknown conditions. Stability analysis has been performed, specifically focusing on the boundary-input boundary-output (BIBO) stability conditions. In order to demonstrate the superior performance of the proposed cascade fuzzy adaptive algorithm, a cascade PID algorithm has also been meticulously designed for comparison. Numerous experimental validation tests involving a healthy user were conducted in a Hardware-in-the-Loop environment, focusing on torque trajectory tracking performance. The proposed control technique exhibited improved convergence dynamics compared to the cascade PID algorithm, yielding mean absolute error levels of 0.0218 Nm and 0.099 Nm for target interaction torque under disturbance-free and disturbed conditions, respectively.

Rhythmic temporal prediction enhances neural representations of movement intention for brain–computer interface

Objective. Detecting movement intention is a typical use of brain–computer interfaces (BCI). However, as an endogenous electroencephalography (EEG) feature, the neural representation of movement is insufficient for improving motor-based BCI. This study aimed to develop a new movement augmentation BCI encoding paradigm by incorporating the cognitive function of rhythmic temporal prediction, and test the feasibility of this new paradigm in optimizing detections of movement intention. Methods. A visual-motion synchronization task was designed with two movement intentions (left vs. right) and three rhythmic temporal prediction conditions (1000 ms vs. 1500 ms vs. no temporal prediction). Behavioural and EEG data of 24 healthy participants were recorded. Event-related potentials (ERPs), event-related spectral perturbation induced by left- and right-finger movements, the common spatial pattern (CSP) and support vector machine, Riemann tangent space algorithm and logistic regression were used and compared across the three temporal prediction conditions, aiming to test the impact of temporal prediction on movement detection. Results. Behavioural results showed significantly smaller deviation time for 1000 ms and 1500 ms conditions. ERP analyses revealed 1000 ms and 1500 ms conditions led to rhythmic oscillations with a time lag in contralateral and ipsilateral areas of movement. Compared with no temporal prediction, 1000 ms condition exhibited greater beta event-related desynchronization (ERD) lateralization in motor area (P< 0.001) and larger beta ERD in frontal area (P< 0.001). 1000 ms condition achieved an averaged left–right decoding accuracy of 89.71% using CSP and 97.30% using Riemann tangent space, both significantly higher than no temporal prediction. Moreover, movement and temporal information can be decoded simultaneously, achieving 88.51% four-classification accuracy. Significance. The results not only confirm the effectiveness of rhythmic temporal prediction in enhancing detection ability of motor-based BCI, but also highlight the dual encodings of movement and temporal information within a single BCI paradigm, which is promising to expand the range of intentions that can be decoded by the BCI.

Adaptive neuro-fuzzy inference system model driven by the non-negative matrix factorization-extracted muscle synergy patterns to estimate lower limb joint movements

Background and objectiveFor patients with movement disorders, the main clinical focus is on exercise rehabilitation to help recover lost motor function, which is achieved by relevant assisted equipment. The basis for seamless control of the assisted equipment is to achieve accurate inference of the user's movement intentions in the human-machine interface. This study proposed a novel movement intention detection technology for estimating lower limb joint continuous kinematic variables following muscle synergy patterns, to develop applications for more efficient assisted rehabilitation training. MethodsThis study recruited 16 healthy males and 16 male patients with symptomatic patellar tendinopathy (VISA-P: 59.1 ± 8.7). The surface electromyography of 12 muscles and lower limb joint kinematic and kinetic data from healthy subjects and patients during step-off landings from 30 cm-high stair steps were collected. We subsequently solved the preprocessed data based on the established recursive model of second-order differential equation to obtain the muscle activation matrix, and then imported it into the non-negative matrix factorization model to obtain the muscle synergy matrix. Finally, the lower limb neuromuscular synergy pattern was then imported into the developed adaptive neuro-fuzzy inference system non-linear regression model to estimate the human movement intention during this movement pattern. ResultsSix muscle synergies were determined to construct the muscle synergy pattern driven ANFIS model. Three fuzzy rules were determined in most estimation cases. Combining the results of the four error indicators across the estimated variables indicates that the current model has excellent estimated performance in estimating lower limb joint movement. The estimation errors between the healthy (Angle: R2=0.98±0.03; Torque: R2=0.96±0.04) and patient (Angle: R2=0.98±0.02; Torque: R2=0.96±0.03) groups are consistent. ConclusionThe proposed model of this study can accurately and reliably estimate lower limb joint movements, and the effectiveness will also be radiated to the patient group. This revealed that our models also have certain advantages in the recognition of motor intentions in patients with relevant movement disorders. Future work from this study can be focused on sports rehabilitation in the clinical field by achieving more flexible and precise movement control of the lower limb assisted equipment to help the rehabilitation of patients.

Machine Learning for Human Motion Intention Detection.

The gait pattern of exoskeleton control conflicting with the human operator's (the pilot) intention may cause awkward maneuvering or even injury. Therefore, it has been the focus of many studies to help decide the proper gait operation. However, the timing for the recognization plays a crucial role in the operation. The delayed detection of the pilot's intent can be equally undesirable to the exoskeleton operation. Instead of recognizing the motion, this study examines the possibility of identifying the transition between gaits to achieve in-time detection. This study used the data from IMU sensors for future mobile applications. Furthermore, we tested using two machine learning networks: a linearfFeedforward neural network and a long short-term memory network. The gait data are from five subjects for training and testing. The study results show that: 1. The network can successfully separate the transition period from the motion periods. 2. The detection of gait change from walking to sitting can be as fast as 0.17 s, which is adequate for future control applications. However, detecting the transition from standing to walking can take as long as 1.2 s. 3. This study also find that the network trained for one person can also detect movement changes for different persons without deteriorating the performance.

Development of a Bioimpedance and sEMG Fusion Sensor for Gait Phase Detection: Validation with a Transtibial Amputee.

Accurate gait phase detection is crucial for safe and efficient robotic prosthesis control in lower limb amputees. Several sensing modalities, including mechanical and biological signals, have been proposed to improve the accuracy of gait phase detection. In this paper, we propose a bioimpedance and sEMG fusion sensor for high-accuracy gait phase detection. We fabricated a wearable band-type sensor for multichannel bioimpedance and sEMG measurement, and we conducted gait experiments with a transtibial amputee to obtain biosignal data. Finally, we trained a deep-learning-based gait phase detection algorithm and evaluated its detection performance. Our results showed that using both bioimpedance and sEMG yielded the highest accuracy of 95.1%. Using only sEMG yielded a higher accuracy (90.9%) than that using only bioimpedance (85.1%). Therefore, we conclude that using both signals simultaneously is beneficial for improving the accuracy of gait phase detection. In addition, the proposed sensor can be applied to several applications by improving the accuracy of motion intention detection.

Decoupling brain activations of muscle-caused activations and mental intention-cause activations using the general linear model: A functional near-infrared spectroscopy study.

Integrating a brain-computer interface into a lower-limb medical rehabilitation assistive device can enhance rehabilitation efficiency. The latest research in the field focuses on the decoding performance of different motions. However, the difference between muscle-caused primitive activation and mental intention-caused activation has not been fully investigated. Thus, our study tried to decouple these two kinds of cerebral activation using a general linear model (GLM). Nine healthy and right-handed subjects were recruited for a two-section experiment. They were asked to extend or flex their knees while seated in the first section of the experiment or standing in the second section. Functional near-infrared spectroscopy (fNIR) was adopted to monitor their hemodynamic changes. Two groups of paradigms (one for circle-wise analysis, the other for full-section analysis) were constructed from the experimental paradigm. Each group consisted of three (the first intention, the second intention, and the muscle activation). The constructed paradigms were fed to the Balloon model for six desired hemodynamic responses (dHRFs). The regressor of GLM consisted of three dHRFs and the corresponding motion artifacts and drifts. The simulated physiological noises were included in the structured background matrix. The results showed that all subjects had similar cerebral activation patterns for the intention to extend or flex knees. The activation during musclecaused activation was less intense than that caused by both intentions. This finding can help further research on more efficient motion intention detection and the possibility of multiple motions decoding.

MCR-ALS-based muscle synergy extraction method combined with LSTM neural network for motion intention detection.

The time-varying and individual variability of surface electromyographic signals (sEMG) can lead to poorer motor intention detection results from different subjects and longer temporal intervals between training and testing datasets. The consistency of using muscle synergy between the same tasks may be beneficial to improve the detection accuracy over long time ranges. However, the conventional muscle synergy extraction methods, such as non-negative matrix factorization (NMF) and principal component analysis (PCA) have some limitations in the field of motor intention detection, especially in the continuous estimation of upper limb joint angles. In this study, we proposed a reliable multivariate curve-resolved-alternating least squares (MCR-ALS) muscle synergy extraction method combined with long-short term memory neural network (LSTM) to estimate continuous elbow joint motion by using the sEMG datasets from different subjects and different days. The pre-processed sEMG signals were then decomposed into muscle synergies by MCR-ALS, NMF and PCA methods, and the decomposed muscle activation matrices were used as sEMG features. The sEMG features and elbow joint angular signals were input to LSTM to establish a neural network model. Finally, the established neural network models were tested by using sEMG dataset from different subjects and different days, and the detection accuracy was measured by correlation coefficient. The detection accuracy of elbow joint angle was more than 85% by using the proposed method. This result was significantly higher than the detection accuracies obtained by using NMF and PCA methods. The results showed that the proposed method can improve the accuracy of motor intention detection results from different subjects and different acquisition timepoints. This study successfully improves the robustness of sEMG signals in neural network applications using an innovative muscle synergy extraction method. It contributes to the application of human physiological signals in human-machine interaction.

A systematic investigation of detectors for low signal-to-noise ratio EMG signals

Background: Active participation of stroke survivors during robot-assisted movement therapy is essential for sensorimotor recovery. Robot-assisted therapy contingent on movement intention is an effective way to encourage patients' active engagement. For severely impaired stroke patients with no residual movements, a surface electromyogram (EMG) has been shown to be a viable option for detecting movement intention. Although numerous algorithms for EMG detection exist, the detector with the highest accuracy and lowest latency for low signal-to-noise ratio (SNR) remains unknown. Methods: This study, therefore, investigates the performance of 13 existing EMG detection algorithms on simulated low SNR (0dB and -3dB) EMG signals generated using three different EMG signal models: gaussian, Laplacian, and biophysical model. The detector performance was quantified using the false positive rate (FPR), false negative rate (FNR), and detection latency. Any detector that consistently showed FPR and FNR of no more than 20%, and latency of no more than 50ms, was considered an appropriate detector for use in robot-assisted therapy. Results: The results indicate that the Modified Hodges detector – a simplified version of the threshold-based Hodges detector introduced in the current study – was the most consistent detector across the different signal models and SNRs. It consistently performed for ~90% and ~40% of the tested trials for 0dB and -3dB SNR, respectively. The two statistical detectors (Gaussian and Laplacian Approximate Generalized Likelihood Ratio) and the Fuzzy Entropy detectors have a slightly lower performance than Modified Hodges. Conclusions: Overall, the Modified Hodges, Gaussian and Laplacian Approximate Generalized Likelihood ratio, and the Fuzzy Entropy detectors were identified as the potential candidates that warrant further investigation with real surface EMG data since they had consistent detection performance on low SNR EMG data.

Learning-Based Motion-Intention Prediction for End-Point Control of Upper-Limb-Assistive Robots

The lack of intuitive and active human-robot interaction makes it difficult to use upper-limb-assistive devices. In this paper, we propose a novel learning-based controller that intuitively uses onset motion to predict the desired end-point position for an assistive robot. A multi-modal sensing system comprising inertial measurement units (IMUs), electromyographic (EMG) sensors, and mechanomyography (MMG) sensors was implemented. This system was used to acquire kinematic and physiological signals during reaching and placing tasks performed by five healthy subjects. The onset motion data of each motion trial were extracted to input into traditional regression models and deep learning models for training and testing. The models can predict the position of the hand in planar space, which is the reference position for low-level position controllers. The results show that using IMU sensor with the proposed prediction model is sufficient for motion intention detection, which can provide almost the same prediction performance compared with adding EMG or MMG. Additionally, recurrent neural network (RNN)-based models can predict target positions over a short onset time window for reaching motions and are suitable for predicting targets over a longer horizon for placing tasks. This study's detailed analysis can improve the usability of the assistive/rehabilitation robots.

Window length insensitive real-time EMG hand gesture classification using entropy calculated from globally parsed histograms

Electromyography (EMG) signal classification is vital to diagnose musculoskeletal abnormalities and control devices by motion intention detection. Machine learning assists both areas by classifying conditions or motion intentions. This paper proposes a novel window length insensitive EMG classification method utilizing the Entropy feature. The main goal of this study is to show that entropy can be used as the only feature for fast real-time classification of EMG signals of hand gestures. The main goal of this study is to show that entropy can be used as the only feature for fast real-time classification of EMG signals of hand gestures. Additionally, the entropy feature can classify feature vectors of different sliding window lengths without including them in the training data. Many kinds of entropy feature succeeded in electroencephalography (EEG) and electrocardiography (ECG) classification research. However, to the best of our knowledge, the Entropy Feature proposed by Shannon stays untested for EMG classification to this day. All the machine learning models are tested on datasets NinaPro DB5 and the newly collected SingleMyo. As an initial analysis to test the entropy feature, classic Machine Learning (ML) models are trained on the NinaPro DB5 dataset. This stage showed that except for the K Nearest Neighbor (kNN) with high inference time, Support Vector Machines (SVM) gave the best validation accuracy. Later, SVM models trained with feature vectors created by 1 s (200 samples) sliding windows are tested on feature vectors created by 250 ms (50 samples) to 1500 ms (300 samples) sliding windows. This experiment resulted in slight accuracy differences through changing window length, indicating that the Entropy feature is insensitive to this parameter. Lastly, Locally Parsed Histogram (LPH), typical in standard entropy functions, makes learning hard for ML methods. Globally Parsed Histogram (GPH) was proposed, and classification accuracy increased from 60.35% to 89.06% while window length insensitivity is preserved. This study shows that Shannon’s entropy is a compelling feature with low window length sensitivity for EMG hand gesture classification. The effect of the GPH approach against an easy-to-make mistake LPH is shown. A real-time classification algorithm for the entropy features is tested on the newly created SingleMyo dataset.

Detection of Motor Cerebral Activity After Median Nerve Stimulation During General Anesthesia (STIM-MOTANA): Protocol for a Prospective Interventional Study.

Accidental awareness during general anesthesia (AAGA) is defined as an unexpected awareness of the patient during general anesthesia. This phenomenon occurs in 1%-2% of high-risk practice patients and can cause physical suffering and psychological after-effects, called posttraumatic stress disorder. In fact, no monitoring techniques are satisfactory enough to effectively prevent AAGA; therefore, new alternatives are needed. Because the first reflex for a patient during an AAGA is to move, but cannot do so because of the neuromuscular blockers, we believe that it is possible to design a brain-computer interface (BCI) based on the detection of movement intention to warn the anesthetist. To do this, we propose to describe and detect the changes in terms of motor cortex oscillations during general anesthesia with propofol, while a median nerve stimulation is performed. We believe that our results could enable the design of a BCI based on median nerve stimulation, which could prevent AAGA. To our knowledge, no published studies have investigated the detection of electroencephalographic (EEG) patterns in relation to peripheral nerve stimulation over the sensorimotor cortex during general anesthesia. The main objective of this study is to describe the changes in terms of event-related desynchronization and event-related synchronization modulations, in the EEG signal over the motor cortex during general anesthesia with propofol while a median nerve stimulation is performed. STIM-MOTANA is an interventional and prospective study conducted with patients scheduled for surgery under general anesthesia, involving EEG measurements and median nerve stimulation at two different times: (1) when the patient is awake before surgery (2) and under general anesthesia. A total of 30 patients will receive surgery under complete intravenous anesthesia with a target-controlled infusion pump of propofol. The changes in event-related desynchronization and event-related synchronization during median nerve stimulation according to the various propofol concentrations for 30 patients will be analyzed. In addition, we will apply 4 different offline machine learning algorithms to detect the median nerve stimulation at the cerebral level. Recruitment began in December 2022. Data collection is expected to conclude in June 2024. STIM-MOTANA will be the first protocol to investigate median nerve stimulation cerebral motor effect during general anesthesia for the detection of intraoperative awareness. Based on strong practical and theoretical scientific reasoning from our previous studies, our innovative median nerve stimulation-based BCI would provide a way to detect intraoperative awareness during general anesthesia. Clinicaltrials.gov NCT05272202; https://clinicaltrials.gov/ct2/show/NCT05272202. PRR1-10.2196/43870.

An active and passive upper limb rehabilitation training system based on a hybrid brain–computer interface

Movement function rehabilitation of patients with craniocerebral injuries is an important issue facing neurorehabilitation science. The use of brain–computer interface technology in rehabilitation training systems can allow patients to actively participate in the rehabilitation training process and use the brain’s neuroplasticity to enhance the effects from rehabilitation training. At present, the brain–computer interface-based rehabilitation training system still has problems such as insufficient active participation of patients, resulting in slowed motor neural circuit repair or low action execution accuracy. In response to the above problems, this paper designed an active and passive upper limb rehabilitation training system based on a hybrid brain–computer interface of steady-state visual evoked potentials (SSVEP) and movement-related cortical potentials (MRCPs). The system includes six parts: task setting and training guidance module, EEG signal acquisition module, EEG signal preprocessing and recognition module, rehabilitation training module, training completion evaluation module, and communication module. The system drives the rehabilitation robot to complete the training actions by identifying the participant’s SSVEP and evaluates the completion of the rehabilitation training based on the patient’s movement intention recognition results. In this study, 12 participants were recruited. In the online test, the system achieved an average action execution accuracy of 99.3%. The movement intention detection based on MRCPs reached an average accuracy of 82.7%. The participants’ average completion rate was 0.91. The experimental results show that the system can achieve a high rate of execution accuracy. In addition, it can evaluate the active participation level of patients in rehabilitation training based on the movement intention detection results, accelerate the reconstruction of motor neural circuits, improve the effects of training, and provide more effective ways of thinking for the study of upper limb rehabilitation training systems for patients with craniocerebral injuries.

A Variational Bayesian Gaussian Mixture-Nonnegative Matrix Factorization Model to Extract Movement Primitives for Robust Control

Nonnegative matrix factorization (NMF) is a powerful tool for parameter estimation applied in numerous robotics applications, such as path planning, motion trajectory prediction, and motion intention detection. In particular, NMF has been successfully used to extract simplified and organized movement primitives from myoelectric signal (MES) for robust control of multi-degree of freedom humanoid robots. However, MES is typically contaminated by complex noise sources. The system performance often degrades due to the simplified Gaussian assumption of the noise distribution in existing NMF methods. Furthermore, most existing NMF models are unable to automatically determine the rank of the latent matrices. To address these issues, this article presents a hybrid variational Bayesian Gaussian mixture and NMF (GMNMF) model with a finite Gaussian mixture model adopted to fit the mixed noise density function of MES. In addition, the automatic relevant determination criterion is applied to automatically infer the number of movement primitives. The coordinate descent update rules for the proposed model are formulated by mean-field variational Bayesian inference. We assess the model performance on five synthetic noise distribution functions and an experimental MES dataset to perform six wrist movements. The results demonstrate that GMNMF yields low error and high robustness in extracting the movement primitives over four competitive methods for robust cybernetic control.

Transfer learning in hand movement intention detection based on surface electromyography signals.

Over the past several years, electromyography (EMG) signals have been used as a natural interface to interact with computers and machines. Recently, deep learning algorithms such as Convolutional Neural Networks (CNNs) have gained interest for decoding the hand movement intention from EMG signals. However, deep networks require a large dataset to train appropriately. Creating such a database for a single subject could be very time-consuming. In this study, we addressed this issue from two perspectives: (i) we proposed a subject-transfer framework to use the knowledge learned from other subjects to compensate for a target subject's limited data; (ii) we proposed a task-transfer framework in which the knowledge learned from a set of basic hand movements is used to classify more complex movements, which include a combination of mentioned basic movements. We introduced two CNN-based architectures for hand movement intention detection and a subject-transfer learning approach. Classifiers are tested on the Nearlab dataset, a sEMG hand/wrist movement dataset including 8 movements and 11 subjects, along with their combination, and on open-source hand sEMG dataset "NinaPro DataBase 2 (DB2)." For the Nearlab database, the subject-transfer learning approach improved the average classification accuracy of the proposed deep classifier from 92.60 to 93.30% when classifier was utilizing 10 other subjects' data via our proposed framework. For Ninapro DB2 exercise B (17 hand movement classes), this improvement was from 81.43 to 82.87%. Moreover, three stages of analysis in task-transfer approach proved that it is possible to classify combination hand movements using the knowledge learned from a set of basic hand movements with zero, few samples and few seconds of data from the target movement classes. First stage takes advantage of shared muscle synergies to classify combined movements, while second and third stages take advantage of novel algorithms using few-shot learning and fine-tuning to use samples from target domain to further train the classifier trained on the source database. The use of information learned from basic hand movements improved classification accuracy of combined hand movements by 10%.

Multi-user myoelectric pattern recognition for shoulder motion intent detection

Myoelectric interfaces have a large range of applications in rehabilitation and prosthetic fields. The electromyographic signal (EMG) generates different patterns of activations according to a specific motion activity allowing the extraction of task-discriminant features, and leading to an efficient external device control [1]. The application of such methodologies in the motion intention detection (MID) is challenging, since this requires to predict the subjects’ intentions while attempting to generate a certain movement [2]. Despite good results have been obtained for the intra-subject scenario [3], the inter- subject generalization still remains an issue. The aim of this work was to investigate myoelectric interfaces for multi-user application on data relative to the shoulder MID. The dataset was composed by eight subjects performing six shoulder movements [4]. The signals were segmented into 150 ms windows with an overlap of 75 ms and four time-domain features were extracted. The feature matrix was split into a calibration and testing subsets. The spectral regression (SR) was used to reduce the dimension of the feature space and with the canonical correlation analysis (CCA) the reduced feature set was projected into a new space, where data related to different subjects are maximally correlated. The obtained projection coefficients were then used on the testing subset. The SVM classifier was trained on the projected calibration subset of a user A and the projected testing subset of a user B was used for testing. In this way, the classifier was trained on data belonging to a certain subject, and then tested on unseen data of a different person. Outcomes demonstrated that the presented approach boosted the classification performance, even if only one trial was used for the training session, with respect to the case in which neither the SR nor the CCA were applied. Indeed, the F1-score increased from 28% up to 53%. It can be also appreciated that increasing the number of repetitions for the calibration subset, the F1-score was further improved, up to 70% already with two repetitions. The accuracy presented a similar behaviour (Fig. 1). The coupling between SR and CCA proved to be reliable for the multi-user oriented shoulder MID. In MID problems, the movement recognition is performed relying on features extracted from a very short time period and on a transient epoch of the EMG signal, before the movement was fully achieved. For this challenging task, the present architecture proved to be reliable in an inter-subject scenario. Indeed, it provided high classification performances training on one subject and then testing on an unseen one, hence supporting the use of CCA for the development of subject-independent myoelectric interfaces.

Electroencephalogram and surface electromyogram fusion-based precise detection of lower limb voluntary movement using convolution neural network-long short-term memory model.

The electroencephalogram (EEG) and surface electromyogram (sEMG) fusion has been widely used in the detection of human movement intention for human–robot interaction, but the internal relationship of EEG and sEMG signals is not clear, so their fusion still has some shortcomings. A precise fusion method of EEG and sEMG using the CNN-LSTM model was investigated to detect lower limb voluntary movement in this study. At first, the EEG and sEMG signal processing of each stage was analyzed so that the response time difference between EEG and sEMG can be estimated to detect lower limb voluntary movement, and it can be calculated by the symbolic transfer entropy. Second, the data fusion and feature of EEG and sEMG were both used for obtaining a data matrix of the model, and a hybrid CNN-LSTM model was established for the EEG and sEMG-based decoding model of lower limb voluntary movement so that the estimated value of time difference was about 24 ∼ 26 ms, and the calculated value was between 25 and 45 ms. Finally, the offline experimental results showed that the accuracy of data fusion was significantly higher than feature fusion-based accuracy in 5-fold cross-validation, and the average accuracy of EEG and sEMG data fusion was more than 95%; the improved average accuracy for eliminating the response time difference between EEG and sEMG was about 0.7 ± 0.26% in data fusion. In the meantime, the online average accuracy of data fusion-based CNN-LSTM was more than 87% in all subjects. These results demonstrated that the time difference had an influence on the EEG and sEMG fusion to detect lower limb voluntary movement, and the proposed CNN-LSTM model can achieve high performance. This work provides a stable and reliable basis for human–robot interaction of the lower limb exoskeleton.