scholarly journals The Impact of Load Style Variation on Gait Recognition Based on sEMG Images Using a Convolutional Neural Network

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8365
Author(s):  
Xianfu Zhang ◽  
Yuping Hu ◽  
Ruimin Luo ◽  
Chao Li ◽  
Zhichuan Tang
Keyword(s):  
Neural Network ◽  
Control System ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Lower Limb ◽  
Gait Recognition ◽  
Training Set ◽  
Lower Limb Exoskeleton ◽  
The Impact ◽  
Semg Signals

Surface electromyogram (sEMG) signals are widely employed as a neural control source for lower-limb exoskeletons, in which gait recognition based on sEMG is particularly important. Many scholars have taken measures to improve the accuracy of gait recognition, but several real-time limitations affect its applicability, of which variation in the load styles is obvious. The purposes of this study are to (1) investigate the impact of different load styles on gait recognition; (2) study whether good gait recognition performance can be obtained when a convolutional neural network (CNN) is used to deal with the sEMG image from sparse multichannel sEMG (SMC-sEMG); and (3) explore whether the control system of the lower-limb exoskeleton trained by sEMG from part of the load styles still works efficiently in a real-time environment where multiload styles are required. In addition, we discuss an effective method to improve gait recognition at the levels of the load styles. In our experiment, fifteen able-bodied male graduate students with load (20% of body weight) and using three load styles (SBP = backpack, SCS = cross shoulder, SSS = straight shoulder) were asked to walk uniformly on a treadmill. Each subject performed 50 continuous gait cycles under three speeds (V3 = 3 km/h, V5 = 5 km/h, and V7 = 7 km/h). A CNN was employed to deal with sEMG images from sEMG signals for gait recognition, and back propagation neural networks (BPNNs) and support vector machines (SVMs) were used for comparison by dealing with the same sEMG signal. The results indicated that (1) different load styles had remarkable impact on the gait recognition at three speeds under three load styles (p < 0.001); (2) the performance of gait recognition from the CNN was better than that from the SVM and BPNN at each speed (84.83%, 81.63%, and 83.76% at V3; 93.40%, 88.48%, and 92.36% at V5; and 90.1%, 86.32%, and 85.42% at V7, respectively); and (3) when all the data from three load styles were pooled as testing sets at each speed, more load styles were included in the training set, better performance was obtained, and the statistical analysis suggested that the kinds of load styles included in training set had a significant effect on gait recognition (p = 0.002), from which it can be concluded that the control system of a lower-limb exoskeleton trained by sEMG using only some load styles is not sufficient in a real-time environment.

scholarly journals Impact of Load Variation on the Accuracy of Gait Recognition from Surface EMG Signals

2018 ◽  
Vol 8 (9) ◽  
pp. 1462 ◽  
Author(s):  
Xianfu Zhang ◽  
Shouqian Sun ◽  
Chao Li ◽  
Zhichuan Tang
Keyword(s):  
Control System ◽  
Lower Limb ◽  
Gait Recognition ◽  
Training Data ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Real Time Control ◽  
Lower Limb Exoskeleton ◽  
Load Variation ◽  
Significant Difference

As lower-limb exoskeleton and prostheses are developed to become smarter and to deploy man–machine collaboration, accurate gait recognition is crucial, as it contributes to the realization of real-time control. Many researchers choose surface electromyogram (sEMG) signals to recognize the gait and control the lower-limb exoskeleton (or prostheses). However, several factors still affect its applicability, of which variation in the loads is an essential one. This study aims to (1) investigate the effect of load variation on gait recognition; and to (2) discuss whether a lower-limb exoskeleton control system trained by sEMG from different loads works well in multi-load applications. In our experiment, 10 male college students were selected to walk on a treadmill at three different speeds (V3 = 3 km/h, V5 = 5 km/h, and V7 = 7 km/h) with four different loads (L0 = 0, L20 = 20%, L30 = 30%, L40 = 40% of body weight, respectively), and 50 gait cycles were performed. Back propagation neural networks (BPNNs) were used for gait recognition, and a support vector machine (SVM) and k-nearest neighbor (k-NN) were used for comparison. The result showed that (1) load variation has significant effects on the accuracy of gait recognition (p < 0.05) under the three speeds when the loads range in L0, L20, L30, or L40, but no significant impact is found when the loads range in L0, L20, or L30. The least significant difference (LSD) post hoc, which can explore all possible pair-wise comparisons of means that comprise a factor using the equivalent of multiple t-tests, reveals that there is a significant difference between the L40 load and the other three loads (L0, L20, L30), but no significant difference was found among the L0, L20, and L30 loads. The total mean accuracy of gait recognition of the intra-loads and inter-loads was 91.81%, and 69.42%, respectively. (2) When the training data was taken from more types of loads, a higher accuracy in gait recognition was obtained at each speed, and the statistical analysis shows that there was a substantial influence for the kinds of loads in the training set on the gait recognition accuracy (p < 0.001). It can be concluded that an exoskeleton (or prosthesis) control system that is trained in a single load or the parts of loads is insufficient in the face of multi-load applications.

scholarly journals Real-Time EEG–EMG Human–Machine Interface-Based Control System for a Lower-Limb Exoskeleton

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 84070-84081 ◽  
Author(s):  
Susanna Yu. Gordleeva ◽  
Sergey A. Lobov ◽  
Nikita A. Grigorev ◽  
Andrey O. Savosenkov ◽  
Maxim O. Shamshin ◽  
...  
Keyword(s):  
Control System ◽  
Real Time ◽  
Lower Limb ◽  
Human Machine Interface ◽  
Lower Limb Exoskeleton ◽  
Machine Interface

scholarly journals Bearing Intelligent Fault Diagnosis Based on Wavelet Transform and Convolutional Neural Network

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Junfeng Guo ◽  
Xingyu Liu ◽  
Shuangxue Li ◽  
Zhiming Wang
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Wavelet Transform ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Rolling Bearing ◽  
Mechanical Equipment ◽  
Time Frequency ◽  
The Impact

As one of the important parts of modern mechanical equipment, the accurate real-time diagnosis of rolling bearing is particularly important. Traditional fault diagnosis methods have some disadvantages, such as low diagnostic accuracy and difficult fault feature extraction. In this paper, a method combining Wavelet transform (WT) and Deformable Convolutional Neural Network (D-CNN) is proposed to realize accurate real-time fault diagnosis of end-to-end rolling bearing. The vibration signal of rolling bearing is taken as the monitoring target. Firstly, the Orthogonal Matching Pursuit (OMP) algorithm is used to remove the harmonic signal and retain the impact signal and noise. Secondly, the time-frequency map of the signal is obtained by time-frequency transform using Wavelet analysis. Finally, the D-CNN is used for feature extraction and classification. The experimental results show that the accuracy of the method can reach 99.9% under various fault modes, and it can accurately identify the fault of rolling bearing.

scholarly journals Estimation of the Continuous Walking Angle of Knee and Ankle (Talocrural Joint, Subtalar Joint) of a Lower-Limb Exoskeleton Robot Using a Neural Network

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2807
Author(s):  
Taehoon Lee ◽  
Inwoo Kim ◽  
Soo-Hong Lee
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Lower Limb ◽  
Subtalar Joint ◽  
Walking Speed ◽  
Knee Angle ◽  
Talocrural Joint ◽  
Angle Estimation ◽  
Lower Limb Exoskeleton ◽  
Exoskeleton Robot

A lower-limb exoskeleton robot identifies the wearer′s walking intention and assists the walking movement through mechanical force; thus, it is important to be able to identify the wearer′s movement in real-time. Measurement of the angle of the knee and ankle can be difficult in the case of patients who cannot move the lower-limb joint properly. Therefore, in this study, the knee angle as well as the angles of the talocrural and subtalar joints of the ankle were estimated during walking by applying the neural network to two inertial measurement unit (IMU) sensors attached to the thigh and shank. First, for angle estimation, the gyroscope and accelerometer data of the IMU sensor were obtained while walking at a treadmill speed of 1 to 2.5 km/h while wearing an exoskeleton robot. The weights according to each walking speed were calculated using a neural network algorithm programmed in MATLAB software. Second, an appropriate weight was selected according to the walking speed through the IMU data, and the knee angle and the angles of the talocrural and subtalar joints of the ankle were estimated in real-time during walking through a feedforward neural network using the IMU data received in real-time. We confirmed that the angle estimation error was accurately estimated as 1.69° ± 1.43 (mean absolute error (MAE) ± standard deviation (SD)) for the knee joint, 1.29° ± 1.01 for the talocrural joint, and 0.82° ± 0.69 for the subtalar joint. Therefore, the proposed algorithm has potential for gait rehabilitation as it addresses the difficulty of estimating angles of lower extremity patients using torque and EMG sensors.

scholarly journals A Sensorless Control System for an Implantable Heart Pump using a Real-time Deep Convolutional Neural Network

2021 ◽  
Author(s):  
Masoud Fetanat ◽  
Michael Stevens ◽  
Christopher Hayward ◽  
Nigel H. Lovell
Keyword(s):  
Neural Network ◽  
Control System ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Sensorless Control ◽  
Left Ventricular ◽  
Deep Convolutional Neural Network ◽  
Ventricular Assist Devices ◽  
Physiological Control ◽  
Flow Measurements

Left ventricular assist devices (LVADs) are mechanical pumps, which can be used to support heart failure (HF) patients as bridge to transplant and destination therapy. To automatically adjust the LVAD speed, a physiological control system needs to be designed to respond to variations of patient hemodynamics across a variety of clinical scenarios. These control systems require pressure feedback signals from the cardiovascular system. However, there are no suitable long-term implantable sensors available. In this study, a novel real-time deep convolutional neural network (CNN) for estimation of preload based on the LVAD flow was proposed. A new sensorless adaptive physiological control system for an LVAD pump was developed using the full dynamic form of model free adaptive control (FFDL-MFAC) and the proposed preload estimator to maintain the patient conditions in safe physiological ranges. The CNN model for preload estimation was trained and evaluated through 10-fold cross validation on 100 different patient conditions and the proposed sensorless control system was assessed on a new testing set of 30 different patient conditions across six different patient scenarios. The proposed preload estimator was extremely accurate with a correlation coefficient of 0.97, root mean squared error of 0.84 mmHg, reproducibility coefficient of 1.56 mmHg, coefficient of variation of 14.44 %, and bias of 0.29 mmHg for the testing dataset. The results also indicate that the proposed sensorless physiological controller works similarly to the preload-based physiological control system for LVAD using measured preload to prevent ventricular suction and pulmonary congestion. This study shows that the LVADs can respond appropriately to changing patient states and physiological demands without the need for additional pressure or flow measurements.

scholarly journals A Sensorless Control System for an Implantable Heart Pump using a Real-time Deep Convolutional Neural Network

2021 ◽  
Author(s):  
Masoud Fetanat ◽  
Michael Stevens ◽  
Christopher Hayward ◽  
Nigel H. Lovell
Keyword(s):  
Neural Network ◽  
Control System ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Sensorless Control ◽  
Left Ventricular ◽  
Deep Convolutional Neural Network ◽  
Ventricular Assist Devices ◽  
Physiological Control ◽  
Flow Measurements

Left ventricular assist devices (LVADs) are mechanical pumps, which can be used to support heart failure (HF) patients as bridge to transplant and destination therapy. To automatically adjust the LVAD speed, a physiological control system needs to be designed to respond to variations of patient hemodynamics across a variety of clinical scenarios. These control systems require pressure feedback signals from the cardiovascular system. However, there are no suitable long-term implantable sensors available. In this study, a novel real-time deep convolutional neural network (CNN) for estimation of preload based on the LVAD flow was proposed. A new sensorless adaptive physiological control system for an LVAD pump was developed using the full dynamic form of model free adaptive control (FFDL-MFAC) and the proposed preload estimator to maintain the patient conditions in safe physiological ranges. The CNN model for preload estimation was trained and evaluated through 10-fold cross validation on 100 different patient conditions and the proposed sensorless control system was assessed on a new testing set of 30 different patient conditions across six different patient scenarios. The proposed preload estimator was extremely accurate with a correlation coefficient of 0.97, root mean squared error of 0.84 mmHg, reproducibility coefficient of 1.56 mmHg, coefficient of variation of 14.44 %, and bias of 0.29 mmHg for the testing dataset. The results also indicate that the proposed sensorless physiological controller works similarly to the preload-based physiological control system for LVAD using measured preload to prevent ventricular suction and pulmonary congestion. This study shows that the LVADs can respond appropriately to changing patient states and physiological demands without the need for additional pressure or flow measurements.

scholarly journals Geometric property-based convolutional neural network for indoor object detection

2021 ◽  
Vol 18 (1) ◽  
pp. 172988142199332
Author(s):  
Xintao Ding ◽  
Boquan Li ◽  
Jinbao Wang
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Geometric Property ◽  
Ground Truth ◽  
Geometric Constraints ◽  
Depth Information ◽  
Training Set ◽  
Object Knowledge ◽  
The Mean

Indoor object detection is a very demanding and important task for robot applications. Object knowledge, such as two-dimensional (2D) shape and depth information, may be helpful for detection. In this article, we focus on region-based convolutional neural network (CNN) detector and propose a geometric property-based Faster R-CNN method (GP-Faster) for indoor object detection. GP-Faster incorporates geometric property in Faster R-CNN to improve the detection performance. In detail, we first use mesh grids that are the intersections of direct and inverse proportion functions to generate appropriate anchors for indoor objects. After the anchors are regressed to the regions of interest produced by a region proposal network (RPN-RoIs), we then use 2D geometric constraints to refine the RPN-RoIs, in which the 2D constraint of every classification is a convex hull region enclosing the width and height coordinates of the ground-truth boxes on the training set. Comparison experiments are implemented on two indoor datasets SUN2012 and NYUv2. Since the depth information is available in NYUv2, we involve depth constraints in GP-Faster and propose 3D geometric property-based Faster R-CNN (DGP-Faster) on NYUv2. The experimental results show that both GP-Faster and DGP-Faster increase the performance of the mean average precision.

Sign in / Sign up

Export Citation Format

Share Document