Multimodal Human-Exoskeleton Interface for Lower Limb Movement Prediction Through a Dense Co-Attention Symmetric Mechanism

Shi, Kecheng; Mu, Fengjun; Huang, Rui; Huang, Ke; Peng, Zhinan; Zou, Chaobin; Yang, Xiao Li; Cheng, Hong

doi:10.3389/fnins.2022.796290

Cited by 8 publications

(5 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Robotic rehabilitation with the use of exoskeletons undoubtedly offers greater therapeutic possibilities than current treatment options, including increased and more precise control of the dose of therapy [39][40][41]. Personalized 3D-printed exoskeletons extend these possibilities even further.…”

Section: Future Research Directionsmentioning

confidence: 99%

Specificity of 3D Printing and AI-Based Optimization of Medical Devices Using the Example of a Group of Exoskeletons

et al. 2023

View full text Add to dashboard Cite

Three-dimensional-printed medical devices are a separate group of medical devices necessary for the development of personalized medicine. The present article discusses a modern and specific group of medical devices and exoskeletons, which aims to present our own experiences in the selection of materials, design, artificial-intelligence optimization, production, and testing of several generations of various upper limb exoskeletons when considering the Medical Devices Regulation (MDR) and the ISO 13485 and ISO 10993 standards. Work is underway to maintain the methodological rigor inherent in medical devices and to develop new business models to achieve cost-effectiveness so that inadequate legislation does not stop the development of this group of technologies (3D scanning, 3D printing, and reverse engineering) in the healthcare system. The gap between research and engineering practice and clinical 3D printing should be bridged as quickly and as carefully as possible. This measure will ensure the transfer of proven solutions into clinical practice. The growing maturity of 3D printing technology will increasingly impact everyday clinical practice, so it is necessary to prepare medical specialists and strategic and organizational changes to realize the correct implementation based on the needs of patients and clinicians.

show abstract

Section: Future Research Directionsmentioning

confidence: 99%

Specificity of 3D Printing and AI-Based Optimization of Medical Devices Using the Example of a Group of Exoskeletons

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Sensor Model Accuracy (%) [21] 7 IMU LSTM-CNN 97.78 [22] 4 IMU DDLMI 97.64 [40] IMU EMG BP 93.76 [41] EEG sEMG EDMEFNet 88.44 [42] 8 sEMG GA-DANN 94.89 [37] 5 IMU LSTM >95 Tis paper 1 IMU MCN 96.08…”

Section: Referencesmentioning

confidence: 99%

Human Activity Recognition Based on a Modified Capsule Network

Zhu

Chen

Liu

et al. 2023

Mobile Information Systems

View full text Add to dashboard Cite

Human activity recognition (HAR) has attracted considerable research attention in the past decade with the development of wearable sensor technology and deep learning algorithms. However, most of the existing HAR methods ignored the spatial relationship of features, which may lead to recognition errors. In this paper, a novel model based on a modified capsule network (MCN) is proposed to accurately recognize various human activities. This novel model is composed of a convolution block and a capsule block, which can achieve end-to-end intelligent recognition. In the meantime, the spatial information among features is preserved through a dynamic routing process. To validate the effectiveness of the model, a human activity dataset is constructed by placing an inertial measurement unit (IMU) on the calf of the volunteers to collect their activity data in daily life, including walking, jogging, upstairs, downstairs, up-ramps, and down-ramps. The recognition accuracy of this novel approach can reach 96.08%, which performs better than the convolutional neural network (CNN) with an accuracy of 91.62%. In addition, it is evaluated on two public datasets named WISDM and UCI-HAR, and the accuracies achieve 98.21% and 95.28%, respectively, which presents higher accuracy than the reported results obtained from benchmark algorithms like CNN. The experimental results show that the proposed model has better activity detection capability and achieves outstanding performance for HAR.

show abstract

“…Some neural network-based approaches are useful for estimating human motor intent [18], such as artificial neural networks (ANN) [9,19,20] and convolutional neural networks (CNN) [21][22][23]. In [20], through combining wavelets theory with a neural network, Eslamy et al leveraged thigh and shank angles to predict knee and ankle angles.…”

Section: Deep Learningmentioning

confidence: 99%

“…In [20], through combining wavelets theory with a neural network, Eslamy et al leveraged thigh and shank angles to predict knee and ankle angles. In [23], Shi et al designed a DMEFNet composing of CNNs, EEGNet, and MCSNet to make lower-limb movement predictions in hemiplegia rehabilitation training.…”

Section: Deep Learningmentioning

confidence: 99%

Transferable multi-modal fusion in knee angles and gait phases for their continuous prediction

Guo

Zheng

et al. 2023

J. Neural Eng.

View full text Add to dashboard Cite

Objective.The gait phase and joint angle are two essential and complementary components of kinematics during normal walking, whose accurate prediction is critical for lower-limb rehabilitation, such as controlling the exoskeleton robots. Multi-modal signals have been used to promote the prediction performance of the gait phase or joint angle separately, but it is still few reports to examine how these signals can be used to predict both simultaneously. Approach.To address this problem, we propose a new method named transferable multi-modal fusion (TMMF) to perform a continuous prediction of knee angles and corresponding gait phases by fusing multi-modal signals. Specifically, TMMF consists of a multi-modal signal fusion block, a time series feature extractor, a regressor, and a classifier. The multi-modal signal fusion block leverages the Maximum Mean Discrepancy to reduce the distribution discrepancy across different modals in the latent space, achieving the goal of transferable multi-modal fusion. Subsequently, by using the long short-term memory-based network, we obtain the feature representation from time series data to predict the knee angles and gait phases simultaneously. To validate our proposal, we design an experimental paradigm with random walking and resting to collect data containing multi-modal biomedical signals from electromyography, gyroscopes, and virtual reality.Main results.Comprehensive experiments on our constructed dataset demonstrate the effectiveness of the proposed method. TMMF achieves a root mean square error of 0.090±0.022 s in knee angle prediction and a precision of 83.7±7.7\% in gait phase prediction.Significance.We demonstrate the feasibility and validity of using TMMF to predict lower-limb kinematics continuously from multi-modal biomedical signals. This proposed method represents application potential in predicting the motor intent of patients with different pathologies.

show abstract

Multimodal Human-Exoskeleton Interface for Lower Limb Movement Prediction Through a Dense Co-Attention Symmetric Mechanism

Cited by 8 publications

References 43 publications

Specificity of 3D Printing and AI-Based Optimization of Medical Devices Using the Example of a Group of Exoskeletons

Specificity of 3D Printing and AI-Based Optimization of Medical Devices Using the Example of a Group of Exoskeletons

Human Activity Recognition Based on a Modified Capsule Network

Transferable multi-modal fusion in knee angles and gait phases for their continuous prediction

Contact Info

Product

Resources

About