Adaptive and Neural Network-based Control Methods Comparison using different Human Torque Synthesis for Upper-limb Robotic Exoskeletons

Hybrid exoskeletons are a recent development, combining electrically controlled actuation with functional electrical stimulation, which potentially offers great benefits for muscular rehabilitation. This chapter presents a review on the state of the art of upper-limb hybrid exoskeletons with a particular focus on stroke rehabilitation. The current needs of the stroke rehabilitation field are discussed and the ability of hybrid exoskeletons to provide a solution to some of the gaps in this field is explored. Due to the early stage of development which most hybrid exoskeletons are in, little research has yet been done in control methods used for them. In particular, more investigation is needed with regards to the potential benefit of hybrid exoskeletons as a patient-monitoring and rehabilitation assist-as-need tool.

Download Full-text

Using Morphological-Linear Neural Network for Upper Limb Movement Intention Recognition from EEG Signals

Lecture Notes in Computer Science - Pattern Recognition ◽

10.1007/978-3-030-21077-9_36 ◽

2019 ◽

pp. 389-397

Author(s):

Gerardo Hernández ◽

Luis G. Hernández ◽

Erik Zamora ◽

Humberto Sossa ◽

Javier M. Antelis ◽

...

Keyword(s):

Neural Network ◽

Upper Limb ◽

Limb Movement ◽

Eeg Signals ◽

Intention Recognition ◽

Linear Neural Network ◽

Movement Intention

Download Full-text

A design framework for optimizing forming processing parameters based on matrix cellular automaton and neural network-based model predictive control methods

Applied Mathematical Modelling ◽

10.1016/j.apm.2019.07.023 ◽

2019 ◽

Vol 76 ◽

pp. 918-937 ◽

Cited By ~ 7

Author(s):

Dong-Dong Chen ◽

Y.C. Lin ◽

Fan Wu

Keyword(s):

Neural Network ◽

Model Predictive Control ◽

Cellular Automaton ◽

Predictive Control ◽

Processing Parameters ◽

Design Framework ◽

Control Methods

Download Full-text

Artificial Neural Network Prediction Using Accelerometers to Control Upper Limb FES During Reaching and Grasping Following Stroke

2006 International Conference of the IEEE Engineering in Medicine and Biology Society ◽

10.1109/iembs.2006.260447 ◽

2006 ◽

Cited By ~ 5

Author(s):

Phil Tresadern ◽

Sibylle Thies ◽

Laurence Kenney ◽

David Howard ◽

John Y. Goulermas

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Upper Limb ◽

Neural Network Prediction ◽

Network Prediction ◽

Artificial Neural

Download Full-text

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

Journal of Mechanics in Medicine and Biology ◽

10.1142/s021951941440017x ◽

2014 ◽

Vol 14 (06) ◽

pp. 1440017 ◽

Cited By ~ 1

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.

Download Full-text