scholarly journals A Simple Convolutional Neural Network for Accurate P300 Detection and Character Spelling in Brain Computer Interface

2018 ◽  
Author(s):  
Hongchang Shan ◽  
Yu Liu ◽  
Todor Stefanov
Keyword(s):  
Signal Detection ◽  
Spatial Information ◽  
Brain Computer Interface ◽  
Computer Interface ◽  
Detection Accuracy ◽  
Signal Recognition ◽  
Human Beings ◽  
Feature Representations ◽  
Machine Learning Methods ◽  
Benchmark Datasets

A Brain Computer Interface (BCI) character speller allows human-beings to directly spell characters using eye-gazes, thereby building communication between the human brain and a computer. Convolutional Neural Networks (CNNs) have shown better performance than traditional machine learning methods for BCI signal recognition and its application to the character speller. However, current CNN architectures limit further accuracy improvements of signal detection and character spelling and also need high complexity to achieve competitive accuracy, thereby preventing the use of CNNs in portable BCIs. To address these issues, we propose a novel and simple CNN which effectively learns feature representations from both raw temporal information and raw spatial information. The complexity of the proposed CNN is significantly reduced compared with state-of-the-art CNNs for BCI signal detection. We perform experiments on three benchmark datasets and compare our results with those in previous research works which report the best results. The comparison shows that our proposed CNN can increase the signal detection accuracy by up to 15.61% and the character spelling accuracy by up to 19.35%.

scholarly journals A magnetoencephalography dataset for motor and cognitive imagery-based brain-computer interface

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Dheeraj Rathee ◽  
Haider Raza ◽  
Sujit Roy ◽  
Girijesh Prasad
Keyword(s):  
Scientific Community ◽  
Brain Computer Interface ◽  
Sampling Frequency ◽  
Computer Interface ◽  
Word Generation ◽  
Machine Learning Methods ◽  
Computer Interfaces ◽  
Signal Processing Algorithms ◽  
Processing Algorithms ◽  
Healthy Participants

AbstractRecent advancements in magnetoencephalography (MEG)-based brain-computer interfaces (BCIs) have shown great potential. However, the performance of current MEG-BCI systems is still inadequate and one of the main reasons for this is the unavailability of open-source MEG-BCI datasets. MEG systems are expensive and hence MEG datasets are not readily available for researchers to develop effective and efficient BCI-related signal processing algorithms. In this work, we release a 306-channel MEG-BCI data recorded at 1KHz sampling frequency during four mental imagery tasks (i.e. hand imagery, feet imagery, subtraction imagery, and word generation imagery). The dataset contains two sessions of MEG recordings performed on separate days from 17 healthy participants using a typical BCI imagery paradigm. The current dataset will be the only publicly available MEG imagery BCI dataset as per our knowledge. The dataset can be used by the scientific community towards the development of novel pattern recognition machine learning methods to detect brain activities related to motor imagery and cognitive imagery tasks using MEG signals.

scholarly journals Residual Invertible Spatio-Temporal Network for Video Super-Resolution

2019 ◽  
Vol 33 ◽  
pp. 5981-5988 ◽  
Author(s):  
Xiaobin Zhu ◽  
Zhuangzi Li ◽  
Xiao-Yu Zhang ◽  
Changsheng Li ◽  
Yaqi Liu ◽  
...  
Keyword(s):  
Spatial Information ◽  
Super Resolution ◽  
Temporal Consistency ◽  
Temporal Network ◽  
Convolutional Network ◽  
Feature Representations ◽  
Video Frames ◽  
Temporal Features ◽  
Benchmark Datasets ◽  
Spatio Temporal

Video super-resolution is a challenging task, which has attracted great attention in research and industry communities. In this paper, we propose a novel end-to-end architecture, called Residual Invertible Spatio-Temporal Network (RISTN) for video super-resolution. The RISTN can sufficiently exploit the spatial information from low-resolution to high-resolution, and effectively models the temporal consistency from consecutive video frames. Compared with existing recurrent convolutional network based approaches, RISTN is much deeper but more efficient. It consists of three major components: In the spatial component, a lightweight residual invertible block is designed to reduce information loss during feature transformation and provide robust feature representations. In the temporal component, a novel recurrent convolutional model with residual dense connections is proposed to construct deeper network and avoid feature degradation. In the reconstruction component, a new fusion method based on the sparse strategy is proposed to integrate the spatial and temporal features. Experiments on public benchmark datasets demonstrate that RISTN outperforms the state-ofthe-art methods.

scholarly journals A P300 Brain-Computer Interface Paradigm Based on Electric and Vibration Simple Command Tactile Stimulation

2021 ◽  
Vol 15 ◽  
Author(s):  
Chenxi Chu ◽  
Jingjing Luo ◽  
Xiwei Tian ◽  
Xiangke Han ◽  
Shijie Guo
Keyword(s):  
Spatial Information ◽  
Brain Computer Interface ◽  
Learning Ability ◽  
Computer Interface ◽  
New Paradigm ◽  
Common Spatial Pattern ◽  
Frequency Information ◽  
Tactile Stimuli ◽  
Average Accuracy ◽  
Electrical Stimuli

This paper proposed a novel tactile-stimuli P300 paradigm for Brain-Computer Interface (BCI), which potentially targeted at people with less learning ability or difficulty in maintaining attention. The new paradigm using only two types of stimuli was designed, and different targets were distinguished by frequency and spatial information. The classification algorithm was developed by introducing filters for frequency bands selection and conducting optimization with common spatial pattern (CSP) on the tactile evoked EEG signals. It features a combination of spatial and frequency information, with the spatial information distinguishing the sites of stimuli and frequency information identifying target stimuli and disturbances. We investigated both electrical stimuli and vibration stimuli, in which only one target site was stimulated in each block. The results demonstrated an average accuracy of 94.88% for electrical stimuli and 95.21% for vibration stimuli, respectively.

scholarly journals Research on How Human Intelligence, Consciousness, and Cognitive Computing Affect the Development of Artificial Intelligence

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Yanyan Dong ◽  
Jie Hou ◽  
Ning Zhang ◽  
Maocong Zhang
Keyword(s):  
Artificial Intelligence ◽  
Human Brain ◽  
Tacit Knowledge ◽  
Brain Computer Interface ◽  
Computer Interface ◽  
Human Intelligence ◽  
Cognitive Computing ◽  
Human Beings ◽  
Intelligent Machines ◽  
Value Rationality

Artificial intelligence (AI) is essentially the simulation of human intelligence. Today’s AI can only simulate, replace, extend, or expand part of human intelligence. In the future, the research and development of cutting-edge technologies such as brain-computer interface (BCI) together with the development of the human brain will eventually usher in a strong AI era, when AI can simulate and replace human’s imagination, emotion, intuition, potential, tacit knowledge, and other kinds of personalized intelligence. Breakthroughs in algorithms represented by cognitive computing promote the continuous penetration of AI into fields such as education, commerce, and medical treatment to build up AI service space. As to human concern, namely, who controls whom between humankind and intelligent machines, the answer is that AI can only become a service provider for human beings, demonstrating the value rationality of following ethics.

A Novel Neural Network for P300 Brain-Computer Interface Signal Recognition

2021 ◽  
Author(s):  
Jingrou Xu ◽  
Zhaoqian Jia ◽  
Wenchao Wang ◽  
Chunyu Wang ◽  
Guangqiang Yin
Keyword(s):  
Neural Network ◽  
Brain Computer Interface ◽  
Computer Interface ◽  
Signal Recognition

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.

scholarly journals Machine Learning Methods of the Berlin Brain-Computer Interface

2015 ◽  
Vol 48 (20) ◽  
pp. 447-452 ◽  
Author(s):  
Carmen Vidaurre ◽  
Claudia Sannelli ◽  
Wojciech Samek ◽  
Sven Dähne ◽  
Klaus-Robert Müller
Keyword(s):  
Machine Learning ◽  
Brain Computer Interface ◽  
Computer Interface ◽  
Learning Methods ◽  
Machine Learning Methods
Sign in / Sign up

Export Citation Format

Share Document