Design and Implementation of a Decision Making System for Controlling a Hand Exoskeleton Based on EEG/EMG Signals
Zolanvari, A.; Arfaee, M.; Menhaj, M. B.; DeFeo, V.; Abolfathi, N.; Jahangiri, F.; Sohrabi, A.; Sajedin, A.
Show abstract
This paper presents an approach of combining Electroencephalography (EEG) and Electromyography (EMG) signals to create a hybrid Brain Interface Computer (BCI) device for controlling a hand exoskeleton through classifying the flexion attempt and resting states of the subjects. We analyzed data of 51 healthy and patients with brain lesions that involved the motor cortex and different hand movement disorders. Their EMG and EEG activity were recorded while the subjects attempted to move their index finger. The signals are analyzed through deep neural network, restricted Boltzmann machine and LDA classifier methods to access a reliable accuracy. Further, to evaluate the proposed approach, we designed and implemented a robotic system for rehabilitation of the hand movement to show that it is able to derive assistive control, by detecting flexion movement from the signals as a command and send it to robot. The system is combined with control signals that determine the information of flexion according to measured EMG signals.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- EEG in game user analysis: A framework for expertise classification during gameplay 96%
- Validation of two-dimensional video-based inference of finger kinematics with pose estimation 95%
- Filter bank common spatial pattern and envelope-based features in multimodal EEG-fTCD brain-computer interfaces 95%
Similar papers in this journal
Similar papers in this journal
- Deep Learning-Based Approaches for Decoding Motor Intent from Peripheral Nerve Signals 97%
- Artificial cerebellum on FPGA: Realistic real-time cerebellar spiking neural network model capable of real-world adaptive motor control 95%
- Low-Density EEG for Neural Activity Reconstruction Using Multivariate Empirical Mode Decomposition 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.