Control Of Lower Limb Prostheses Research Articles

Electromyography-Based Control of Lower Limb Prostheses: A Systematic Review.

Most amputations occur in lower limbs and despite improvements in prosthetic technology, no commercially available prosthetic leg uses electromyography (EMG) information as an input for control. Efforts to integrate EMG signals as part of the control strategy have increased in the last decade. In this systematic review, we summarize the research in the field of lower limb prosthetic control using EMG. Four different online databases were searched until June 2022: Web of Science, Scopus, PubMed, and Science Direct. We included articles that reported systems for controlling a prosthetic leg (with an ankle and/or knee actuator) by decoding gait intent using EMG signals alone or in combination with other sensors. A total of 1,331 papers were initially assessed and 121 were finally included in this systematic review. The literature showed that despite the burgeoning interest in research, controlling a leg prosthesis using EMG signals remains challenging. Specifically, regarding EMG signal quality and stability, electrode placement, prosthetic hardware, and control algorithms, all of which need to be more robust for everyday use. In the studies that were investigated, large variations were found between the control methodologies, type of research participant, recording protocols, assessments, and prosthetic hardware.

Deep learning with an attention mechanism for continuous biomechanical motion estimation across varied activities.

Reliable estimation of desired motion trajectories plays a crucial part in the continuous control of lower extremity assistance devices such as prostheses and orthoses. Moreover, reliable estimation methods are also required to predict hard-to-measure biomechanical quantities (e.g., joint contact moment/force) for use in sports injury science. Recognising that human locomotion is an inherently time-sequential and limb-synergetic behaviour, this study investigates models and learning algorithms for predicting the motion of a subject's leg from the motion of complementary limbs. The novel deep learning model architectures proposed are based on the Long Short-Term Memory approach with the addition of an attention mechanism. A dataset comprising Inertial Measurement Unit signals from 21 subjects traversing varied terrains was used, including stair ascent/descent, ramp ascent/descent, stopped, level-ground walking and the transitions between these conditions. Fourier Analysis is deployed to evaluate the model robustness, in addition to assessing time-based prediction errors. The experiment on three unseen test participants suggests that the branched neural network structure is preferred to tackle the multioutput problem, and the inclusion of an attention mechanism demonstrates improved performance in terms of accuracy, robustness and network size. An experimental comparison found that 57% of the model parameters were not needed after adding attention layers meanwhile the prediction error is lower than the LSTM model without attention mechanism. The attention model has errors of 9.06% and 7.64% (normalised root mean square error) for ankle and hip acceleration prediction respectively. Also, less high-frequency noise is present in the attention model predictions. We conclude that the internal structure of the proposed deep learning model is justified, principally the benefit of using an attention mechanism. Experimental results for biomechanical motion estimation are obtained, showing greater accuracy than only with LSTM. The trained attention model can be used throughout despite transitioning between terrain types. Such a model will be useful in, for example, the control of lower-limb prostheses, instead of the need to identify and switch between different trajectory generators for different walking modes.

Locomotion Prediction for Lower Limb Prostheses in Complex Environments via sEMG and Inertial Sensors

Previous studies have shown that the motion intention recognition for lower limb prosthesis mainly focused on the identification of performed gait. However, the bionic prosthesis needs to know the next movement at the beginning of a new gait, especially in complex operation environments. In this paper, an upcoming locomotion prediction scheme via multilevel classifier fusion was proposed for the complex operation. At first, two motion states, including steady state and transient state, were defined. Steady-state recognition was backtracking of a completed gait, which would be used as prior knowledge of motion prediction. In steady-state recognition, surface electromyographic (sEMG) and inertial sensors were fused to improve recognition accuracy; five typical locomotion modes were recognized by random forest classifier with over 97.8% accuracy. The transient state was defined as an observation period at the initial stage of upcoming movement, in which only the sEMG signal was recorded due to the limitation of sliding window length. LightGBM classifier was validated to outperform other methods in the accuracy and prediction time of transient-state recognition. Finally, a simplified HMM model based on prior knowledge and observation result was constructed to predict upcoming locomotion. The results indicated that the locomotion prediction was over 91% accuracy. The proposed scheme implements the locomotion prediction at the initial stage of each gait and provides critical information for the gait control of lower limb prosthesis.

Estimation of Ankle Joint Power during Walking Using Two Inertial Sensors.

(1) Background: Ankle joint power, as an indicator of the ability to control lower limbs, is of great relevance for clinical diagnosis of gait impairment and control of lower limb prosthesis. However, the majority of available techniques for estimating joint power are based on inverse dynamics methods, which require performing a biomechanical analysis of the foot and using a highly instrumented environment to tune the parameters of the resulting biomechanical model. Such techniques are not generally applicable to real-world scenarios in which gait monitoring outside of the clinical setting is desired. This paper proposes a viable alternative to such techniques by using machine learning algorithms to estimate ankle joint power from data collected by two miniature inertial measurement units (IMUs) on the foot and shank, (2) Methods: Nine participants walked on a force-plate-instrumented treadmill wearing two IMUs. The data from the IMUs were processed to train and test a random forest model to estimate ankle joint power. The performance of the model was then evaluated by comparing the estimated power values to the reference values provided by the motion tracking system and the force-plate-instrumented treadmill. (3) Results: The proposed method achieved a high accuracy with the correlation coefficient, root mean square error, and normalized root mean square error of 0.98, 0.06 w/kg, and 1.05% in the intra-subject test, and 0.92, 0.13 w/kg, and 2.37% in inter-subject test, respectively. The difference between the predicted and true peak power values was 0.01 w/kg and 0.14 w/kg with a delay of 0.4% and 0.4% of gait cycle duration for the intra- and inter-subject testing, respectively. (4) Conclusions: The results of this study demonstrate the feasibility of using only two IMUs to estimate ankle joint power. The proposed technique provides a basis for developing a portable and compact gait monitoring system that can potentially offer monitoring and reporting on ankle joint power in real-time during activities of daily living.

Environmental Features Recognition for Lower Limb Prostheses Toward Predictive Walking.

This paper aims to present a robust environmental features recognition system (EFRS) for lower limb prosthesis, which can assist the control of prosthesis by predicting the locomotion modes of amputees and estimating environmental features in the following steps. A depth sensor and an inertial measurement unit are combined to stabilize the point cloud of environments. Subsequently, the 2D point cloud is extracted from origin 3D point cloud and is classified through a neural network. Environmental features, including slope of road, width, and height of stair, were also estimated via the 2D point cloud. Finally, the EFRS is evaluated through classifying and recognizing five kinds of common environments in simulation, indoor experiments, and outdoor experiments by six healthy subjects and three transfemoral amputees, and databases of five healthy subjects and three amputees are used to validate without training. The classification accuracy of five kinds of common environments reach up to 99.3% and 98.5% for the amputees in the indoor and outdoor experiments, respectively. The locomotion modes are predicted at least 0.6 s before the switch of actual locomotion modes. Most estimation errors of indoor and outdoor environments features are lower than 5% and 10%, respectively. The overall process of EFRS takes less than 0.023 s. The promising results demonstrate the robustness and the potential application of the presented EFRS to help the control of lower limb prostheses.

Computational model for the recognition of lower limb movement using wearable gyroscope sensor

Human activity recognition (HAR) using inertial sensors has enabled many applications in different fields, especially healthcare and biomedical engineering. In this regard, an activity recognition system is proposed using the signals of a single gyroscope sensor placed at the shank. Principal component analysis method was utilised to exclude the redundant features from the feature set. Furthermore, different classifiers such as probabilistic neural network, k-nearest neighbour (KNN) and support vector machine (SVM) were used for recognition of walking activities. K-fold cross validation and four performance parameters namely accuracy, sensitivity, specificity, and Matthew's correlation coefficient were used to inspect the performance of the recognition model. The proposed model yielded encouraging recognition accuracy of 98.7% compared to the existing activity recognition systems. It is realised that the proposed system will potentially be utilised in the control of lower limb prosthesis and be useful tool for the gait analysis applications.

Computational model for the recognition of lower limb movement using wearable gyroscope sensor

Human activity recognition (HAR) using inertial sensors has enabled many applications in different fields, especially healthcare and biomedical engineering. In this regard, an activity recognition system is proposed using the signals of a single gyroscope sensor placed at the shank. Principal component analysis method was utilised to exclude the redundant features from the feature set. Furthermore, different classifiers such as probabilistic neural network, k-nearest neighbour (KNN) and support vector machine (SVM) were used for recognition of walking activities. K-fold cross validation and four performance parameters namely accuracy, sensitivity, specificity, and Matthew's correlation coefficient were used to inspect the performance of the recognition model. The proposed model yielded encouraging recognition accuracy of 98.7% compared to the existing activity recognition systems. It is realised that the proposed system will potentially be utilised in the control of lower limb prosthesis and be useful tool for the gait analysis applications.

Characterizing Residual Muscle Properties in Lower Limb Amputees Using High Density EMG Decomposition: A Pilot Study.

As research is progressing towards EMG control of lower limb prostheses, it is vital to understand the neurophysiology of the residual muscles in the amputated limb, which has been largely ignored. Therefore, the goal of this study was to characterize the activation patterns (muscle recruitment and motor unit discharge patterns) of the residual muscles of lower limb amputees. One transtibial amputee subject was recruited for this pilot study. The participant wore three high-density EMG electrode pads (8x8 grid with 64 channels) on each limb (a total of six pads) - one on the tibialis anterior (TA), medial gastrocnemius (MG), and lateral gastrocnemius (LG), respectively. The participant was asked to follow a ramping procedure plateauing at 50% of maximum voluntary contraction (MVC) for both the TA and Gastrocnemius muscles. The EMG signals were then decomposed offline; the firing rate and spatial activation patterns of the muscle were analyzed. Results showed slower and more variable firing rate in motor units of residual muscles than those of intact side. In addition, the spatial pattern of muscle activation differed between residual and intact muscles. These results indicate that surface EMG signals recorded from residual muscles present modified signal features from intact shank muscles, which should be considered when implementing myoelectric control schemes.

Real-time gait event detection for lower limb amputees using a single wearable sensor.

This paper presents a rule-based real-time gait event/phase detection system (R-GEDS) using a shank mounted inertial measurement unit (IMU) for lower limb amputees during the level ground walking. Development of the algorithm is based on the shank angular velocity in the sagittal plane and linear acceleration signal in the shank longitudinal direction. System performance was evaluated with four control subjects (CS) and one transfemoral amputee (TFA) and the results were validated with four FlexiForce footswitches (FSW). The results showed a data latency for initial contact (IC) and toe off (TO) within a range of ± 40 ms for both CS and TFA. A delay of about 3.7 ± 62 ms for a foot-flat start (FFS) and an early detection of -9.4 ± 66 ms for heel-off (HO) was found for CS. Prosthetic side showed an early detection of -105 ± 95 ms for FFS whereas intact side showed a delay of 141 ±73 ms for HO. The difference in the kinematics of the TFA and CS is one of the potential reasons for high variations in the time difference. Overall, detection accuracy was 99.78% for all the events in both groups. Based on the validated results, the proposed system can be used to accurately detect the temporal gait events in real-time that leads to the detection of gait phase system and therefore, can be utilized in gait analysis applications and the control of lower limb prostheses.

Task discrimination for non-weight-bearing movements using muscle synergies.

Myoelectric control of lower limb prostheses requires discrimination of task-specific muscle patterns. In this paper we present a method based on the notion of muscle synergies to discriminate between various non-weight-bearing movements such as knee extension/flexion, femur rotation in/out, tibia rotation in/out and ankle dorsiflexion/plantarflexion. Data is recorded from eight targeted muscle sites on the thigh. Non-negative matrix factorization is used to identify the muscle synergies using multiple features and estimation of electromyographic (EMG) patterns is done using non-negative least squares (NNLS). Classification accuracy for the movements involving the knee joint was higher than the movements involving the ankle joint. The proposed algorithm performs at par with the common machine learning algorithm Linear Discriminant Analysis (LDA) in offline analysis.

Depth Sensing for Improved Control of Lower Limb Prostheses.

Powered lower limb prostheses have potential to improve the quality of life of individuals with amputations by enabling all daily activities. However, seamless ambulation mode recognition is necessary to achieve this goal and is not yet a clinical reality. Current intent recognition systems use mechanical and EMG sensors to estimate prosthesis and user status. We propose to complement these systems by integrating information about the environment obtained through the depth sensing. This paper presents the design, characterization, and the early validation of a novel stair segmentation system based on Microsoft Kinect. Static and dynamic tests were performed. A first experiment showed how the resolution of the depth camera affects the speed and the accuracy of segmentation. A second test proved the robustness of the algorithm to different staircases. Finally, we performed an online walking test with the stair segmentation and related measures recorded online at >5frames/s. Experimental results show that the proposed algorithm allows for an accurate estimate of distance, angle of intersection, number of steps, stair height, and stair depth for a set of stairs in the environment. The online test produced an estimate of whether the individual was approaching stairs in real time with approximately 98.8% accuracy.

Non-weight-bearing neural control of a powered transfemoral prosthesis

Lower limb prostheses have traditionally been mechanically passive devices without electronic control systems. Microprocessor-controlled passive and powered devices have recently received much interest from the clinical and research communities. The control systems for these devices typically use finite-state controllers to interpret data measured from mechanical sensors embedded within the prosthesis. In this paper we investigated a control system that relied on information extracted from myoelectric signals to control a lower limb prosthesis while amputee patients were seated. Sagittal plane motions of the knee and ankle can be accurately (>90%) recognized and controlled in both a virtual environment and on an actuated transfemoral prosthesis using only myoelectric signals measured from nine residual thigh muscles. Patients also demonstrated accurate (~90%) control of both the femoral and tibial rotation degrees of freedom within the virtual environment. A channel subset investigation was completed and the results showed that only five residual thigh muscles are required to achieve accurate control. This research is the first step in our long-term goal of implementing myoelectric control of lower limb prostheses during both weight-bearing and non-weight-bearing activities for individuals with transfemoral amputation.