To train or not to train? A survey on training of feature extraction methods for SSVEP-based BCIs

Objective. Despite the vast research aimed at improving the performance of steady-state visually evoked potential (SSVEP)-based brain-computer interfaces (BCIs), several limitations exist that restrict the use of such applications for long-term users in the real-world. One of the main challenges has been to reduce training time while maintaining good BCI performance. In view of this challenge, this survey identifies and compares the different training requirements of feature extraction methods for SSVEP-based BCIs. Approach. This paper reviews the various state-of-the-art SSVEP feature extraction methods that have been developed and are most widely used in the literature. Main results. The main contributions compared to existing reviews are the following: (i) a detailed summary, including a brief mathematical description of each feature extraction algorithm, providing a guide to the basic concepts of the state-of-the-art techniques for SSVEP-based BCIs found in literature; (ii) a categorisation of the training requirements of SSVEP-based methods into three categories, defined as training-free methods, subject-specific and subject-independent training methods; (iii) a comparative review of the training requirements of SSVEP feature extraction methods, providing a reference for future work on SSVEP-based BCIs. Significance. This review highlights the strengths and weaknesses of the three categories of SSVEP training methods. Training-free systems are more practical but their performance is limited due to inter-subject variability resulting from the complex EEG activity. Feature extraction methods that incorporate some training data address this issue and in fact have outperformed training-free methods: subject-specific BCIs are tuned to the individual yielding the best performance at the cost of long, tiring training sessions making these methods unsuitable for everyday use; subject-independent BCIs that make use of training data from various subjects offer a good trade-off between training effort and performance, making these BCIs better suited for practical use.