P300-Based Asynchronous Brain Computer Interface for Environmental Control System.

Eda Akman Aydin,Omer Faruk Bay,Inan Guler

IEEE journal of biomedical and health informatics（2018）CCF CSCI 2区SCI 1区

Cited 52|Views6

Abstract

An asynchronous brain computer interface (A-BCI) determines whether or not a subject is on control state, and produces control commands only in case of subject's being on control state. In this study, we propose a novel P300-based A-BCI algorithm that distinguishes control state and noncontrol state of users. Furthermore, A-BCI algorithm combined with a dynamic stopping function that enables users to select control command independent from a fixed number of intensification sequence. The proposed P300-based A-BCI algorithm uses classification patterns to determine control state and uses optimal operating point of receiver operating characteristics curve for dynamic stopping function. The proposed A-BCI algorithm is also combined with region-based paradigm (RBP) based stimulus interface. The A-BCI algorithm is tested on an internet-based environmental control system. A total of ten nondisabled subjects were participated voluntarily in the experiments. Two-level approach of the RBP-based stimulus interface improves noncontrol state detection accuracy up to 100%. Besides, ratio of incorrect command selection at control state is reduced significantly. At control state, ratio of correct selections, incorrect selections, and missed selections are 93.27%, 1.09%, and 5.63%, respectively. On the other hand, dynamic stopping function enables command selections at least two intensifications. Mean number of intensification sequences to complete the given tasks is 3.15. Thanks to dynamic stopping function, it provides a significant improvement on information transfer rate. The proposed A-BCI algorithm is important in terms of practical BCI systems.

Translated text

Key words

Asynchronous control,brain computer interface (BCI),control state detection,dynamic stopping,environmental control,P300,region based paradigm (RBP)

Bibtex

AI Read Science

AI Summary

AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.

Example

Background

Key content

Introduction

Methods

Results

Related work

Fund

Key content

Pretraining has recently greatly promoted the development of natural language processing (NLP)
We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance

Try using models to generate summary,it takes about 60s

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper