Classification of Motor Imaginary Signals for Machine Commmunication - A Novel Approach for Brain Machine Interface Design

ABSTRACTMost daily tasks require simultaneous control of both hands. Here we demonstrate simultaneous classification of gestures in both hands using multi-unit activity recorded from bilateral motor and somatosensory cortices of a tetraplegic participant. Attempted gestures were classified using hierarchical linear discriminant models trained separately for each hand. In an online experiment, gestures were continuously classified and used to control two robotic arms in a center-out movement task. Bimanual trials that required keeping one hand still resulted in the best performance (70.6%), followed by symmetric movement trials (50%) and asymmetric movement trials (22.7%). Our results indicate that gestures can be simultaneously decoded in both hands using two independently trained hand models concurrently, but online control using this approach becomes more difficult with increased complexity of bimanual gesture combinations. This study demonstrates the potential for restoring simultaneous control of both hands using a bilateral intracortical brain-machine interface.

Download Full-text

Robust Brain-Machine Interface Design Using Optimal Feedback Control Modeling and Adaptive Point Process Filtering

PLoS Computational Biology ◽

10.1371/journal.pcbi.1004730 ◽

2016 ◽

Vol 12 (4) ◽

pp. e1004730 ◽

Cited By ~ 56

Author(s):

Maryam M. Shanechi ◽

Amy L. Orsborn ◽

Jose M. Carmena

Keyword(s):

Feedback Control ◽

Point Process ◽

Interface Design ◽

Optimal Feedback Control ◽

Brain Machine Interface ◽

Optimal Feedback ◽

Machine Interface ◽

Control Modeling

Download Full-text

A Novel Approach to Shadow Boundary Detection Based on an Adaptive Direction-Tracking Filter for Brain-Machine Interface Applications

Applied Sciences ◽

10.3390/app10196761 ◽

2020 ◽

Vol 10 (19) ◽

pp. 6761

Author(s):

Ziyi Ju ◽

Li Gun ◽

Amir Hussain ◽

Mufti Mahmud ◽

Cosimo Ieracitano

Keyword(s):

Support Vector ◽

Brain Machine Interface ◽

Shadow Boundary ◽

Reporting Accuracy ◽

Novel Approach ◽

Machine Interface ◽

Feature Information ◽

Comparative Results ◽

Tracking Filter ◽

Accuracy Rates

In this paper, a Brain-Machine Interface (BMI) system is proposed to automatically control the navigation of wheelchairs by detecting the shadows on their route. In this context, a new algorithm to detect shadows in a single image is proposed. Specifically, a novel adaptive direction tracking filter (ADT) is developed to extract feature information along the direction of shadow boundaries. The proposed algorithm avoids extraction of features around all directions of pixels, which significantly improves the efficiency and accuracy of shadow features extraction. Higher-order statistics (HOS) features such as skewness and kurtosis in addition to other optical features are used as input to different Machine Learning (ML) based classifiers, specifically, a Multilayer Perceptron (MLP), Autoencoder (AE), 1D-Convolutional Neural Network (1D-CNN) and Support Vector Machine (SVM), to perform the shadow boundaries detection task. Comparative results demonstrate that the proposed MLP-based system outperforms all the other state-of-the-art approaches, reporting accuracy rates up to 84.63%.

Download Full-text