Journal
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
Volume 28, Issue 12, Pages 2660-2670Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNSRE.2020.3040264
Keywords
Electrodes; Electroencephalography; Scalp; Visualization; Steady-state; Task analysis; Signal to noise ratio; Electroencephalography (EEG); artifact removal; constrained independent component analysis (cICA); online learning; ambulatory environment
Categories
Funding
- Institute for Information & Communications Technology Planning & Evaluation (IITP) - Korea Government (MSIT) [20170-00451, 2015-0-00185, 2019-0-00079]
Ask authors/readers for more resources
Recently, practical brain-computer interfaces (BCIs) have been widely investigated for detecting human intentions in real world. However, performance differences still exist between the laboratory and the real world environments. One of the main reasons for such differences comes from the user's unstable physical states (e.g., human movements are not strictly controlled), which produce unexpected signal artifacts. Hence, to minimize the performance degradation of electroencephalography (EEG)-based BCIs, we present a novel artifact removal method named constrained independent component analysis with online learning (cIOL). The cIOL can find and reject the noise-like components related to human body movements (i.e., movement artifacts) in the EEG signals. To obtain movement information, isolated electrodes are used to block electrical signals from the brain using high-resistance materials. We estimate artifacts with movement information using constrained independent component analysis from EEG signals and then extract artifact-free signals using online learning in each sample. In addition, the cIOL is evaluated by signal processing under 16 different experimental conditions (two types of EEG devices x two BCI paradigms x four different walking speeds). The experimental results show that the cIOL has the highest accuracy in both scalp- and ear-EEG, and has the highest signal-to-noise ratio in scalp-EEG among the state-of-the-art methods, except for the case of steady-state visual evoked potential at 2.0 m/s with superposition problem.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available