Batch processing mode is widely used in the training process of human motiun recognition. After training, the motion elassitier usually remains invariable. However, if the classifier is to be expanded, all historical ...Batch processing mode is widely used in the training process of human motiun recognition. After training, the motion elassitier usually remains invariable. However, if the classifier is to be expanded, all historical data must be gathered for retraining. This consumes a huge amount of storage space, and the new training process will be more complicated. In this paper, we use an incremental learning method to model the motion classifier. A weighted decision tree is proposed to help illustrate the process, and the probability sampling method is also used. The resuhs show that with continuous learning, the motion classifier is more precise. The average classification precision for the weighted decision tree was 88.43% in a typical test. Incremental learning consumes much less time than the batch processing mode when the input training data comes continuously.展开更多
Lower limb motion recognition techniques commonly employ Surface Electromyographic Signal(sEMG)as input and apply a machine learning classifier or Back Propagation Neural Network(BPNN)for classification.However,this a...Lower limb motion recognition techniques commonly employ Surface Electromyographic Signal(sEMG)as input and apply a machine learning classifier or Back Propagation Neural Network(BPNN)for classification.However,this artificial feature engineering technique is not generalizable to similar tasks and is heavily reliant on the researcher’s subject expertise.In contrast,neural networks such as Convolutional Neural Network(CNN)and Long Short-term Memory Neural Network(LSTM)can automatically extract features,providing a more generalized and adaptable approach to lower limb motion recognition.Although this approach overcomes the limitations of human feature engineering,it may ignore the potential correlation among the sEMG channels.This paper proposes a spatial–temporal graph neural network model,STGNN-LMR,designed to address the problem of recognizing lower limb motion from multi-channel sEMG.STGNN-LMR transforms multi-channel sEMG into a graph structure and uses graph learning to model spatial–temporal features.An 8-channel sEMG dataset is constructed for the experimental stage,and the results show that the STGNN-LMR model achieves a recognition accuracy of 99.71%.Moreover,this paper simulates two unexpected scenarios,including sEMG sensors affected by sweat noise and sudden failure,and evaluates the testing results using hypothesis testing.According to the experimental results,the STGNN-LMR model exhibits a significant advantage over the control models in noise scenarios and failure scenarios.These experimental results confirm the effectiveness of the STGNN-LMR model for addressing the challenges associated with sEMG-based lower limb motion recognition in practical scenarios.展开更多
For controlling dexterous prosthetic hand with a high number of active Degrees of Freedom (DOF), it is necessary to reliably extract control volitions of finger motions from the human body. In this study, a large va...For controlling dexterous prosthetic hand with a high number of active Degrees of Freedom (DOF), it is necessary to reliably extract control volitions of finger motions from the human body. In this study, a large variety of finger motions are discriminated based on the diversities of the pressure distribution produced by the mechanical actions of muscles on the forearm. The pressure distribution patterns corresponding to the motions were measured by sensor array which is composed of 32 Force Sensitive Resistor (FSR) sensors. In order to map the pressure patterns with different finger motions, a multiclass classifier was designed based on the Support Vector Machine (SVM) algorithm. The multi-subject experiments show that it is possible to identify as many as seventeen different finger motions, including individual finger motions and multi-finger grasping motions, with the accuracy above 99% in the in-session validation. Further, the cross-session validation demonstrates that the performance of the proposed method is robust for use if the FSR array is not reset. The results suggest that the proposed method has great application prospects for the control of multi-DOF dexterous hand prosthesis.展开更多
Based on light field reconstruction and motion recognition technique, a penetrable interactive floating 3D display system is proposed. The system consists of a high-frame-rate projector, a flat directional diffusing s...Based on light field reconstruction and motion recognition technique, a penetrable interactive floating 3D display system is proposed. The system consists of a high-frame-rate projector, a flat directional diffusing screen, a high-speed data transmission module, and a Kinect somatosensory device. The floating occlusioncorrect 3D image could rotate around some axis at different speeds according to user's hand motion. Eight motion directions and speed are detected accurately, and the prototype system operates efficiently with a recognition accuracy of 90% on average.展开更多
Brain-computer interfaces (BCIs) records brain activity using electroencephalogram (EEG) headsets in the form of EEG signals;these signals can berecorded, processed and classified into different hand movements, which...Brain-computer interfaces (BCIs) records brain activity using electroencephalogram (EEG) headsets in the form of EEG signals;these signals can berecorded, processed and classified into different hand movements, which can beused to control other IoT devices. Classification of hand movements will beone step closer to applying these algorithms in real-life situations using EEGheadsets. This paper uses different feature extraction techniques and sophisticatedmachine learning algorithms to classify hand movements from EEG brain signalsto control prosthetic hands for amputated persons. To achieve good classificationaccuracy, denoising and feature extraction of EEG signals is a significant step. Wesaw a considerable increase in all the machine learning models when the movingaverage filter was applied to the raw EEG data. Feature extraction techniques likea fast fourier transform (FFT) and continuous wave transform (CWT) were usedin this study;three types of features were extracted, i.e., FFT Features, CWTCoefficients and CWT scalogram images. We trained and compared differentmachine learning (ML) models like logistic regression, random forest, k-nearestneighbors (KNN), light gradient boosting machine (GBM) and XG boost onFFT and CWT features and deep learning (DL) models like VGG-16, DenseNet201 and ResNet50 trained on CWT scalogram images. XG Boost with FFTfeatures gave the maximum accuracy of 88%.展开更多
A concurrency control mechanism for collaborative work is akey element in a mixed reality environment. However, conventional lockingmechanisms restrict potential tasks or the support of non-owners, thusincreasing the ...A concurrency control mechanism for collaborative work is akey element in a mixed reality environment. However, conventional lockingmechanisms restrict potential tasks or the support of non-owners, thusincreasing the working time because of waiting to avoid conflicts. Herein, wepropose an adaptive concurrency control approach that can reduce conflictsand work time. We classify shared object manipulation in mixed reality intodetailed goals and tasks. Then, we model the relationships among goal,task, and ownership. As the collaborative work progresses, the proposedsystem adapts the different concurrency control mechanisms of shared objectmanipulation according to the modeling of goal–task–ownership. With theproposed concurrency control scheme, users can hold shared objects andmove and rotate together in a mixed reality environment similar to realindustrial sites. Additionally, this system provides MS Hololens and Myosensors to recognize inputs from a user and provides results in a mixed realityenvironment. The proposed method is applied to install an air conditioneras a case study. Experimental results and user studies show that, comparedwith the conventional approach, the proposed method reduced the number ofconflicts, waiting time, and total working time.展开更多
Recognizing and reproducing spatiotemporal motions are necessary when analyzing behaviors andmovements during human-robot interaction. Rigid body motion trajectories are proven as compact and informativeclues in chara...Recognizing and reproducing spatiotemporal motions are necessary when analyzing behaviors andmovements during human-robot interaction. Rigid body motion trajectories are proven as compact and informativeclues in characterizing motions. A flexible dual square-root function (DSRF) descriptor for representing rigid bodymotion trajectories, which can offer robustness in the description over raw data, was proposed in our previousstudy. However, this study focuses on exploring the application of the DSRF descriptor for effective backwardmotion reproduction and motion recognition. Specifically, two DSRF-based reproduction methods are initiallyproposed, including the recursive reconstruction and online optimization. New trajectories with novel situationsand contextual information can be reproduced from a single demonstration while preserving the similarities withthe original demonstration. Furthermore, motion recognition based on DSRF descriptor can be achieved byemploying a template matching method. Finally, the experimental results demonstrate the effectiveness of theproposed method for rigid body motion reproduction and recognition.展开更多
基金partly supported by the National Natural Science Foundation of China under Grant 61573242the Projects from Science and Technology Commission of Shanghai Municipality under Grant No.13511501302,No.14511100300,and No.15511105100+1 种基金Shanghai Pujiang Program under Grant No.14PJ1405000ZTE Industry-Academia-Research Cooperation Funds
文摘Batch processing mode is widely used in the training process of human motiun recognition. After training, the motion elassitier usually remains invariable. However, if the classifier is to be expanded, all historical data must be gathered for retraining. This consumes a huge amount of storage space, and the new training process will be more complicated. In this paper, we use an incremental learning method to model the motion classifier. A weighted decision tree is proposed to help illustrate the process, and the probability sampling method is also used. The resuhs show that with continuous learning, the motion classifier is more precise. The average classification precision for the weighted decision tree was 88.43% in a typical test. Incremental learning consumes much less time than the batch processing mode when the input training data comes continuously.
文摘Lower limb motion recognition techniques commonly employ Surface Electromyographic Signal(sEMG)as input and apply a machine learning classifier or Back Propagation Neural Network(BPNN)for classification.However,this artificial feature engineering technique is not generalizable to similar tasks and is heavily reliant on the researcher’s subject expertise.In contrast,neural networks such as Convolutional Neural Network(CNN)and Long Short-term Memory Neural Network(LSTM)can automatically extract features,providing a more generalized and adaptable approach to lower limb motion recognition.Although this approach overcomes the limitations of human feature engineering,it may ignore the potential correlation among the sEMG channels.This paper proposes a spatial–temporal graph neural network model,STGNN-LMR,designed to address the problem of recognizing lower limb motion from multi-channel sEMG.STGNN-LMR transforms multi-channel sEMG into a graph structure and uses graph learning to model spatial–temporal features.An 8-channel sEMG dataset is constructed for the experimental stage,and the results show that the STGNN-LMR model achieves a recognition accuracy of 99.71%.Moreover,this paper simulates two unexpected scenarios,including sEMG sensors affected by sweat noise and sudden failure,and evaluates the testing results using hypothesis testing.According to the experimental results,the STGNN-LMR model exhibits a significant advantage over the control models in noise scenarios and failure scenarios.These experimental results confirm the effectiveness of the STGNN-LMR model for addressing the challenges associated with sEMG-based lower limb motion recognition in practical scenarios.
文摘For controlling dexterous prosthetic hand with a high number of active Degrees of Freedom (DOF), it is necessary to reliably extract control volitions of finger motions from the human body. In this study, a large variety of finger motions are discriminated based on the diversities of the pressure distribution produced by the mechanical actions of muscles on the forearm. The pressure distribution patterns corresponding to the motions were measured by sensor array which is composed of 32 Force Sensitive Resistor (FSR) sensors. In order to map the pressure patterns with different finger motions, a multiclass classifier was designed based on the Support Vector Machine (SVM) algorithm. The multi-subject experiments show that it is possible to identify as many as seventeen different finger motions, including individual finger motions and multi-finger grasping motions, with the accuracy above 99% in the in-session validation. Further, the cross-session validation demonstrates that the performance of the proposed method is robust for use if the FSR array is not reset. The results suggest that the proposed method has great application prospects for the control of multi-DOF dexterous hand prosthesis.
基金supported by the National Basic Research Program of China(973 Program)(No.2013CB328806)the National High Technology Research and Development Program of China(863 Program)(No.2012AA011902)+1 种基金the National Natural Science Foundation of China(No.61177015)the Research Funds for the Central Universities of China(No.2012XZZX013)
文摘Based on light field reconstruction and motion recognition technique, a penetrable interactive floating 3D display system is proposed. The system consists of a high-frame-rate projector, a flat directional diffusing screen, a high-speed data transmission module, and a Kinect somatosensory device. The floating occlusioncorrect 3D image could rotate around some axis at different speeds according to user's hand motion. Eight motion directions and speed are detected accurately, and the prototype system operates efficiently with a recognition accuracy of 90% on average.
文摘Brain-computer interfaces (BCIs) records brain activity using electroencephalogram (EEG) headsets in the form of EEG signals;these signals can berecorded, processed and classified into different hand movements, which can beused to control other IoT devices. Classification of hand movements will beone step closer to applying these algorithms in real-life situations using EEGheadsets. This paper uses different feature extraction techniques and sophisticatedmachine learning algorithms to classify hand movements from EEG brain signalsto control prosthetic hands for amputated persons. To achieve good classificationaccuracy, denoising and feature extraction of EEG signals is a significant step. Wesaw a considerable increase in all the machine learning models when the movingaverage filter was applied to the raw EEG data. Feature extraction techniques likea fast fourier transform (FFT) and continuous wave transform (CWT) were usedin this study;three types of features were extracted, i.e., FFT Features, CWTCoefficients and CWT scalogram images. We trained and compared differentmachine learning (ML) models like logistic regression, random forest, k-nearestneighbors (KNN), light gradient boosting machine (GBM) and XG boost onFFT and CWT features and deep learning (DL) models like VGG-16, DenseNet201 and ResNet50 trained on CWT scalogram images. XG Boost with FFTfeatures gave the maximum accuracy of 88%.
基金supported by“Regional Innovation Strategy (RIS)”through the National Research Foundation of Korea (NRF)funded by the Ministry of Education (MOE) (2021RIS-004).
文摘A concurrency control mechanism for collaborative work is akey element in a mixed reality environment. However, conventional lockingmechanisms restrict potential tasks or the support of non-owners, thusincreasing the working time because of waiting to avoid conflicts. Herein, wepropose an adaptive concurrency control approach that can reduce conflictsand work time. We classify shared object manipulation in mixed reality intodetailed goals and tasks. Then, we model the relationships among goal,task, and ownership. As the collaborative work progresses, the proposedsystem adapts the different concurrency control mechanisms of shared objectmanipulation according to the modeling of goal–task–ownership. With theproposed concurrency control scheme, users can hold shared objects andmove and rotate together in a mixed reality environment similar to realindustrial sites. Additionally, this system provides MS Hololens and Myosensors to recognize inputs from a user and provides results in a mixed realityenvironment. The proposed method is applied to install an air conditioneras a case study. Experimental results and user studies show that, comparedwith the conventional approach, the proposed method reduced the number ofconflicts, waiting time, and total working time.
基金the Science and Technology Commission of Shanghai Municipality(No.20DZ2220400)the Interdisciplinary Program of Shanghai Jiao Tong University(No.YG2021QN117)。
文摘Recognizing and reproducing spatiotemporal motions are necessary when analyzing behaviors andmovements during human-robot interaction. Rigid body motion trajectories are proven as compact and informativeclues in characterizing motions. A flexible dual square-root function (DSRF) descriptor for representing rigid bodymotion trajectories, which can offer robustness in the description over raw data, was proposed in our previousstudy. However, this study focuses on exploring the application of the DSRF descriptor for effective backwardmotion reproduction and motion recognition. Specifically, two DSRF-based reproduction methods are initiallyproposed, including the recursive reconstruction and online optimization. New trajectories with novel situationsand contextual information can be reproduced from a single demonstration while preserving the similarities withthe original demonstration. Furthermore, motion recognition based on DSRF descriptor can be achieved byemploying a template matching method. Finally, the experimental results demonstrate the effectiveness of theproposed method for rigid body motion reproduction and recognition.
基金supported by Fujian Science&Technology Innovation Laboratory for Optoelectronic Information of China(2021ZZ130)the Natural Science Foundation of Fujian Province,China(2021J01577)。