Adaptive Methods Exploiting the Time Structure in EEG for Self-paced Brain-Computer Interfaces
نویسندگان
چکیده
Although self-paced Brain-Computer Interface (BCI) is desirable from the users’ point of view, it brings about great technological challenges. This thesis aims to provide novel solutions to several important aspects in developing a realistic self-paced Electroencephalogram (EEG) based BCI. A Sequential Floating Forward Search (SFFS) based method is developed for feature selection, followed by two novel multi-objective optimization approaches to tackle the channel selection problem. The problem of non-stationarity of EEG data is handled by a novel unsupervised adaptive Gaussian Mixture Model (GMM). The method involves a new unsupervised classification scheme for GMM that proved to be particularly useful for the onset detection problem in online BCIs. These new techniques were employed in a novel user interface especially designed to be a testbed for adaptive BCIs. Conditional Random Fields (CRF) are suggested as a novel probabilistic approach that can model the embedded temporal information in EEG. The new method is tested on a large set of 3-class synchronous BCI data. The temporal information in self-paced data are also modeled with three different methods based on CRF and Hidden Markov Model (HMM), leading to significant performance improvement over non-temporal methods.
منابع مشابه
EEG Based Brain Computer Interface Hand Grasp Control: Feature Extraction Method MTCSP
Brain-Computer Interfaces (BCIs) are communication systems, which enable users to send commands to computers by using brain activity only; this activity being generally measured by Electroencephalography (EEG). BCIs are generally designed according to a pattern recognition approach, i.e., by extracting features from EEG signals, and by using a classifier to identify the user’s mental state from...
متن کاملEEG Based Brain Computer Interface Hand Grasp Control: Feature Extraction Method MTCSP
Brain-Computer Interfaces (BCIs) are communication systems, which enable users to send commands to computers by using brain activity only; this activity being generally measured by Electroencephalography (EEG). BCIs are generally designed according to a pattern recognition approach, i.e., by extracting features from EEG signals, and by using a classifier to identify the user’s mental state from...
متن کاملA hybrid NIRS-EEG system for self-paced brain computer interface with online motor imagery.
BACKGROUND For a self-paced motor imagery based brain-computer interface (BCI), the system should be able to recognize the occurrence of a motor imagery, as well as the type of the motor imagery. However, because of the difficulty of detecting the occurrence of a motor imagery, general motor imagery based BCI studies have been focusing on the cued motor imagery paradigm. NEW METHOD In this pa...
متن کاملA self-paced motor imagery based brain-computer interface for robotic wheelchair control.
This paper presents a simple self-paced motor imagery based brain-computer interface (BCI) to control a robotic wheelchair. An innovative control protocol is proposed to enable a 2-class self-paced BCI for wheelchair control, in which the user makes path planning and fully controls the wheelchair except for the automatic obstacle avoidance based on a laser range finder when necessary. In order ...
متن کاملBCI Competition IV – Data Set I: Learning Discriminative Patterns for Self-Paced EEG-Based Motor Imagery Detection
Detecting motor imagery activities versus non-control in brain signals is the basis of self-paced brain-computer interfaces (BCIs), but also poses a considerable challenge to signal processing due to the complex and non-stationary characteristics of motor imagery as well as non-control. This paper presents a self-paced BCI based on a robust learning mechanism that extracts and selects spatio-sp...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2010