Learning across multi-stimulus enhances target recognition methods in SSVEP-based BCIs

[jinglescode]

Paper

Link: https://iopscience.iop.org/article/10.1088/1741-2552/ab2373/pdf
Year: 2020

Summary

• covers a variety of CCAs
• estimate reliable spatial filters and SSVEP templates given small calibration data

Contributions and Distinctions from Previous Works

• canonical correlation analysis [5], the minimum energy combination (MEC) [6], the multivariate synchronization index (MSI) [7] and the task-related component analysis (TRCA) [8]
• extended CCA (eCCA) [10, 11] and the ensemble TRCA (eTRCA) [8] methods equipped with learning from subject’s training data are representative in the midst and have demonstrated excellent performance in target recognition in SSVEP-based BCIs
• but it relies on calibration (calibration trials for each visual stimulus cannot be small for the eCCA method and the eTRCA method; otherwise, their recognition accuracies would decrease dramatically)
• and calibration is time-consuming and tiring

Methods

• learning across multi-stimulus

Results

• lesser calibration (The eCCA and eTRCA, as two representative methods, are extended with the new learning scheme to the socalled multi-stimulus eCCA (ms-eCCA) and multistimulus eTRCA (ms-eTRCA) method, respectively, in this work. A combination of the ms-eCCA and mseTRCA (called ms-eCCA+ms-eTRCA) method is also proposed to include both merits: good ability against the small training data problem and good target recognition performance.)

Objective. Latest target recognition methods that are equipped with learning from the subject's calibration data, represented by the extended canonical correlation analysis (eCCA) and the ensemble task-related component analysis (eTRCA), can achieve extra high performance in the steady-state visual evoked potential (SSVEP)-based brain–computer interfaces (BCIs), however their performance deteriorate drastically if the calibration trials are insufficient. This paper develops a new scheme to learn from limited calibration data. Approach. A learning across multiple stimuli scheme is proposed for the target recognition methods, which applies to learning the data corresponding to not only the target stimulus but also the other stimuli. The resulting optimization problems can be simplified and solved utilizing the prior knowledge and properties of SSVEPs across different stimuli. With the new learning scheme, the eCCA and the eTRCA can be extended to the multi-stimulus eCCA (ms-eCCA) and the multi-stimulus eTRCA (ms-eTRCA), respectively, as well as a combination of them (i.e. ms-eCCA+ms-eTRCA) that incorporates their merits. Main results. Evaluation and comparison using an SSVEP-BCI benchmark dataset with 35 subjects show that the ms-eCCA (or ms-eTRCA) performs significantly better than the eCCA (or eTRCA) method while the ms-eCCA+ms-eTRCA performs the best. With the learning across stimuli scheme, the existing target recognition methods can be further improved in terms of the target recognition performance and the ability against insufficient calibration. Significance. A new learning scheme is proposed towards the efficient use of the calibration data, providing enhanced performance and saving calibration time in the SSVEP-based BCIs.