A Review on Signal Processing Approaches to Reduce Calibration Time in EEG-Based Brain–Computer Interface

Abstract

In an electroencephalogram- (EEG-) based brain–computer interface (BCI), a subject can directly communicate with an electronic device using his EEG signals in a safe and convenient way. However, the sensitivity to noise/artifact and the non-stationarity of EEG signals result in high inter-subject/session variability. Therefore, each subject usually spends long and tedious calibration time in building a subject-specific classifier. To solve this problem, we review existing signal processing approaches, including transfer learning (TL), semi-supervised learning (SSL), and a combination of TL and SSL. Cross-subject TL can transfer amounts of labeled samples from different source subjects for the target subject. Moreover, Cross-session/task/device TL can reduce the calibration time of the subject for the target session, task, or device by importing the labeled samples from the source sessions, tasks, or devices. SSL simultaneously utilizes the labeled and unlabeled samples from the target subject. The combination of TL and SSL can take advantage of each other. For each kind of signal processing approaches, we introduce their concepts and representative methods. The experimental results show that TL, SSL, and their combination can obtain good classification performance by effectively utilizing the samples available. In the end, we draw a conclusion and point to research directions in the future.

Identifying Thematics in a Brain‐Computer Interface Research

“…Interestingly, 2017 saw a blush of terms associated with software and hardware with keyword terms such as “affective computing” [ 54 ], “BCI hardware” [ 4 , 5 ], “BCI software” [ 4 , 5 ], “classification accuracy” [ 61 ], “covariance matrix” [ 6 ], and “Riemannian geometry” [ 6 ]. In contrast, the 2018 onward period saw a shift toward technological development to exploit the early research with terms such as “learning” [ 55 , 97 ], “robotics” [ 83 ], and “speller” [ 87 ].…”

“…EEG has two applications: (1) in medicine with the provision of enhanced monitoring, assessment, and diagnosis of psychiatric and neurological disorders such as autism, depression, and schizophrenia [ 54 ] and (2) in entertainment, design of traffic safety systems and gaming through understanding emotional feedback assisting in product design and development [ 54 ]. Research has focused on the level of individual variability and reducing can lead to long tedious calibration times to ensure task determination accuracy [ 55 ].…”

A Novel Deep Learning Method Based on an Overlapping Time Window Strategy for Brain–Computer Interface-Based Stroke Rehabilitation

“…It is difficult to compare different BCI systems since there are many aspects that can influence the performance of BCI, such as input, preprocessing, and outputs. The ITR is a widely and generally accepted standard by which the performance of different BCI systems can be compared [ 35 ]. Figure 6 illustrates the distribution of ITRs for the sessions.…”

Error-related Potential Variability: Exploring the Effects on Classification and Transferability

“…The constant variation in observed brain signals leads to the difficult problem, often seen in machine learning, of nonstationarity. To further reduce this problem, BCI applica-tions usually entail tedious calibration periods where subjectspecific classifiers are created [20]. In order to create these subject-specific classifiers, ideally, before any real experiment begins, the target task is used to generate data for the initial training of the classifier.…”