scholarly journals A Control and Posture Recognition Strategy for Upper-Limb Rehabilitation of Stroke Patients

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Xian Yu ◽  
Bo Xiao ◽  
Ye Tian ◽  
Zihao Wu ◽  
Qi Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Data Acquisition ◽  
Network Model ◽  
Upper Limb ◽  
Recognition Performance ◽  
Recognition Rate ◽  
Upper Limb Rehabilitation ◽  
Human Posture ◽  
Posture Recognition ◽  
Limb Posture

At present, the study of upper-limb posture recognition is still in the primary stage; due to the diversity of the objective environment and the complexity of the human body posture, the upper-limb posture has no public dataset. In this paper, an upper extremity data acquisition system is designed, with a three-channel data acquisition mode, collect acceleration signal, and gyroscope signal as sample data. The datasets were preprocessed with deweighting, interpolation, and feature extraction. With the goal of recognizing human posture, experiments with KNN, logistic regression, and random gradient descent algorithms were conducted. In order to verify the superiority of each algorithm, the data window was adjusted to compare the recognition speed, computation time, and accuracy of each classifier. For the problem of improving the accuracy of human posture recognition, a neural network model based on full connectivity is developed. In addition, this paper proposes a finite state machine- (FSM-) based FES control model for controlling the upper limb to perform a range of functional tasks. In the process of constructing the network model, the effects of different hidden layers, activation functions, and optimizers on the recognition rate were experimental for the comparative analysis; the softplus activation function with better recognition performance and the adagrad optimizer are selected. Finally, by comparing the comprehensive recognition accuracy and time efficiency with other classification models, the fully connected neural network is verified in the human posture superiority in identification.

DYNAMIC RECURRENT NEURAL NETWORK BASED CLASSIFICATION SCHEME FOR MYOELECTRIC CONTROL OF UPPER LIMB REHABILITATION ROBOT

2014 ◽  
Vol 14 (06) ◽  
pp. 1440017 ◽  
Author(s):  
YUDING CUI ◽  
CAIHUA XIONG
Keyword(s):  
Neural Network ◽  
Upper Limb ◽  
Recurrent Neural Network ◽  
Classification Scheme ◽  
Majority Vote ◽  
Upper Limb Rehabilitation ◽  
Linear Discriminant ◽  
Structure Selection ◽  
Post Process ◽  
Limb Rehabilitation

This paper proposes and evaluates the application of a modular dynamic recurrent neural network (DRNN) to classify upper limb motion using myoelectric signals. The DRNN algorithmic issues, including the structure selection, the segmentation of the data and various feature sets such as time-domain features and frequency features, were evaluated experimentally in order to actualize the optimization and configuration of this classification scheme. This was achieved by using a majority vote technique to post-process the output decision stream. The DRNN-based approach was then been compared with two commonly used classification methods: multilayer perceptron (MLP) neural network and linear discriminant analysis (LDA). The DRNN-based motion classification system demonstrated exceptional accuracy and a low computational load for the classification of robust limb motion. The DRNN may also display utility for online training and controlling rehabilitation robots.

An Identification Method of Library Identifiers Based on Computer Vision

2013 ◽  
Vol 380-384 ◽  
pp. 3534-3537
Author(s):  
Li Ya Liu
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Network Model ◽  
Neural Network Model ◽  
Recognition Rate ◽  
Computation Time ◽  
Principal Component ◽  
Structural Features ◽  
Traditional Methods ◽  
Quantum Neural Network

For traditional methods of library identifies based on the two-dimensional code characteristics, these methods are time consuming and a lot of prior experience is required. A method of library identifies based on computer vision technology is proposed. In this method, a preprocessing, such as image equalization, binarization and wavelet change, is first performed on the acquired library label images. Then on the basis of the structural features of the character, the features of library identifiers are obtained by applying PCA for a principal component analysis. A quantum neural network model is designed to have an optimization analysis and calculation on the extracted features, to avoid the drawbacks which need a lot of prior knowledge for the traditional methods. At the same time, an optimization is carried out for the neural network model saving a large amount of computation time. The experimental results show that a recognition rate, up to 98.13%, is obtained by using this method. With a high recognition speed, the method can meet the actual needs to be applied in a practical system.

scholarly journals A Resource Constrained Neural Network for the Design of Embedded Human Posture Recognition Systems

2021 ◽  
Vol 11 (11) ◽  
pp. 4752
Author(s):  
Gian Domenico Licciardo ◽  
Alessandro Russo ◽  
Alessandro Naddeo ◽  
Nicola Cappetti ◽  
Luigi Di Benedetto ◽  
...  
Keyword(s):  
Neural Network ◽  
Power Dissipation ◽  
Pressure Sensors ◽  
Quantization Scheme ◽  
Sitting Posture ◽  
Human Posture ◽  
Computing Paradigm ◽  
Low Power Dissipation ◽  
Posture Recognition ◽  
Public Dataset

A custom HW design of a Fully Convolutional Neural Network (FCN) is presented in this paper to implement an embeddable Human Posture Recognition (HPR) system capable of very high accuracy both for laying and sitting posture recognition. The FCN exploits a new base-2 quantization scheme for weight and binarized activations to meet the optimal trade-off between low power dissipation, a very reduced set of instantiated physical resources and state-of-the-art accuracy to classify human postures. By using a limited number of pressure sensors only, the optimized HW implementation allows keeping the computation close to the data sources according to the edge computing paradigm and enables the design of embedded HP systems. The FCN can be simply reconfigured to be used for laying and sitting posture recognition. Tested on a public dataset for in-bed posture classification, the proposed FCN obtains a mean accuracy value of 96.77% to recognize 17 different postures, while a small custom dataset has been used for training and testing for sitting posture recognition, where the FCN achieves 98.88% accuracy to recognize eight positions. The FCN has been prototyped on a Xilinx Artix 7 FPGA where it exhibits a dynamic power dissipation lower than 11 mW and 7 mW for laying and sitting posture recognition, respectively, and a maximum operation frequency of 47.64 MHz and 26.6 MHz, corresponding to an Output Data Rate (ODR) of the sensors of 16.50 kHz and 9.13 kHz, respectively. Furthermore, synthesis results with a CMOS 130 nm technology have been reported, to give an estimation about the possibility of an in-sensor circuital implementation.

Sign in / Sign up

Export Citation Format

Share Document