scholarly journals Brain-Computer Interface for Clinical Purposes: Cognitive Assessment and Rehabilitation

2017 ◽  
Vol 2017 ◽  
pp. 1-11 ◽  
Author(s):  
Laura Carelli ◽  
Federica Solca ◽  
Andrea Faini ◽  
Paolo Meriggi ◽  
Davide Sangalli ◽  
...  
Keyword(s):  
Neural Plasticity ◽  
Cognitive Assessment ◽  
Developmental Disorders ◽  
Neurological Diseases ◽  
Brain Computer Interface ◽  
Autism Spectrum ◽  
Computer Interface ◽  
Elderly Subjects ◽  
Severe Motor ◽  
And Training

Alongside the best-known applications of brain-computer interface (BCI) technology for restoring communication abilities and controlling external devices, we present the state of the art of BCI use for cognitive assessment and training purposes. We first describe some preliminary attempts to develop verbal-motor free BCI-based tests for evaluating specific or multiple cognitive domains in patients with Amyotrophic Lateral Sclerosis, disorders of consciousness, and other neurological diseases. Then we present the more heterogeneous and advanced field of BCI-based cognitive training, which has its roots in the context of neurofeedback therapy and addresses patients with neurological developmental disorders (autism spectrum disorder and attention-deficit/hyperactivity disorder), stroke patients, and elderly subjects. We discuss some advantages of BCI for both assessment and training purposes, the former concerning the possibility of longitudinally and reliably evaluating cognitive functions in patients with severe motor disabilities, the latter regarding the possibility of enhancing patients’ motivation and engagement for improving neural plasticity. Finally, we discuss some present and future challenges in the BCI use for the described purposes.

scholarly journals The 2019 yearbook of Neurorestoratology

2020 ◽  
Vol 08 (01) ◽  
pp. 1-11
Author(s):  
Hongyun Huang
Keyword(s):  
Clinical Practice ◽  
Neurological Diseases ◽  
Brain Computer Interface ◽  
Computer Interface ◽  
Cell Therapies ◽  
Recent Advances

Time is infinite movement in constant motion. We are glad to see that Neurorestoratology, a new discipline, has grown into a rich field involving many global researchers in recent years. In this 2019 yearbook of Neurorestoratology, we introduce the most recent advances and achievements in this field, including findings on the pathogenesis of neurological diseases, neurorestorative mechanisms, and clinical therapeutic achievements globally. Many patients have benefited from treatments involving cell therapies, neurostimulation/neuromodulation, brain–computer interface, neurorestorative surgery or pharmacy, and many others. Clinical physicians can refer to this yearbook with the latest knowledge and apply it to clinical practice.

A Closed-Loop Brain–Computer Interface Triggering an Active Ankle–Foot Orthosis for Inducing Cortical Neural Plasticity

2014 ◽  
Vol 61 (7) ◽  
pp. 2092-2101 ◽  
Author(s):  
Ren Xu ◽  
Ning Jiang ◽  
Natalie Mrachacz-Kersting ◽  
Chuang Lin ◽  
Guillermo Asin Prieto ◽  
...  
Keyword(s):  
Neural Plasticity ◽  
Closed Loop ◽  
Brain Computer Interface ◽  
Computer Interface ◽  
Ankle Foot Orthosis ◽  
Foot Orthosis

scholarly journals User Specific Efficiency Parameters for Brain Computer Interface (BCI) based Upper Limb Stroke Rehabilitation System

2021 ◽  
Vol 9 (4) ◽  
pp. 524-528
Keyword(s):  
Neural Plasticity ◽  
Stroke Rehabilitation ◽  
Brain Computer Interface ◽  
Large Population ◽  
Computer Interface ◽  
Computer Gaming ◽  
Middle Income ◽  
Middle Income Countries ◽  
Overall Efficiency ◽  
Low And Middle Income

Rehabilitation after stroke through conventional manner is not quite successful due to a number of patient related issues including lack of interest in lengthy exercises, cost of therapy and dependency on healthcare professionals. In addition, around 50% of stroke survivors worldwide belong to the low and middle income countries that are unable to afford expensive rehabilitation systems. Advancements in Brain Computer Interface (BCI) technology enabling the researchers to design and develop BCI based strokerehabilitation systems by exploiting neural plasticity. This is achieved via Electroencephalogram (EEG) based computer gaming rehabilitation exercises through Motor Imagery (MI) to achieve successful neural plasticity. However, current research is largelybased on expensive bio-signal amplifiers and processing hardware that are beyond the affordability of a large population of stroke patients living in low and middle-income countries. Moreover, the efficiency of BCI based stroke rehabilitation systems thatare generally considered as the accuracy of EEG signal classifications is not the only parameter to rate the efficiency.Since the requirements of BCI based rehabilitation therapy are highly subject specific, efficiency of such systems also depends on many user specific features related to cost and performance.This paper describes a research that proposes a number of parameters for cost and efficiency along with their weightage set by the domestic users to determine the overall efficiency of the system.Inputs from different groups of users were obtained that are classified as deserving class, middle class and rich class. Results indicated that the users of different groups are giving different weights to different performance and cost parameters. The overall efficiency requirements are therefore having different meanings for different classes of users

A Robust P300-Speller Brain-Computer Interface Based on Kernel PCA

2013 ◽  
Vol 300-301 ◽  
pp. 721-724 ◽  
Author(s):  
Yi Hung Liu ◽  
Jui Tsung Weng ◽  
Han Pang Huang ◽  
Jyh Tong Teng
Keyword(s):  
Brain Activity ◽  
Brain Computer Interface ◽  
Principal Component ◽  
Computer Interface ◽  
Kernel Principal Component Analysis ◽  
Support Vector ◽  
Detection Accuracy ◽  
Motor Disabilities ◽  
P300 Speller ◽  
Severe Motor

P300 speller is a well-known brain-computer interface (BCI), which allows patients with severe motor disabilities to spell words through the recognition on patients’ brain activity measured by electroencephalography (EEG). The brain-activity recognition is essentially a task of detecting of P300 responses in EEG signals. Support vector machine (SVM) has been a widely-used P300 detector in existing works. However, SVM is computationally expensive, greatly reducing the usability of the speller BCI for practical use. To address this issue, we propose in this paper a novel P300 detector, which is based on the kernel principal component analysis (KPCA). The proposed detector has a lower computational complexity, and can measure the belongingness of an input EEG to P300 class by the construction of EEG in nonlinear eigenspaces. Results carried out on subjects show that the proposed method is able to significantly shorten offline training sessions of the speller BCI while achieving high online P300-detection accuracy.

Sign in / Sign up

Export Citation Format

Share Document