Bio-Inspired Filter Banks for SSVEP-based Brain-Computer Interfaces

TL;DR

This paper presents bio-inspired filter banks that enhance SSVEP frequency detection in brain-computer interfaces by tuning filter parameters based on biological response characteristics, improving accuracy and command options.

Contribution

It introduces a novel bio-inspired filter bank approach that incorporates harmonic responses and frequency-specific tuning for better SSVEP detection in BCIs.

Findings

Improved accuracy over traditional methods

Increased number of usable stimuli frequencies

Validated on online datasets with promising results

Abstract

Brain-computer interfaces (BCI) have the potential to play a vital role in future healthcare technologies by providing an alternative way of communication and control. More specifically, steady-state visual evoked potential (SSVEP) based BCIs have the advantage of higher accuracy and higher information transfer rate (ITR). In order to fully exploit the capabilities of such devices, it is necessary to understand the features of SSVEP and design the system considering its biological characteristics. This paper introduces bio-inspired filter banks (BIFB) for a novel SSVEP frequency detection method. It is known that SSVEP response to a flickering visual stimulus is frequency selective and gets weaker as the frequency of the stimuli increases. In the proposed approach, the gain and bandwidth of the filters are designed and tuned based on these characteristics while also incorporating harmonic SSVEP responses. This method not only improves the accuracy but also increases the available number of commands by allowing the use of stimuli frequencies elicit weak SSVEP responses. The BIFB method achieved reliable performance when tested on datasets available online and compared with two well-known SSVEP frequency detection methods, power spectral density analysis (PSDA) and canonical correlation analysis (CCA). The results show the potential of bio-inspired design which will be extended to include further SSVEP characteristic (e.g. time-domain waveform) for future SSVEP based BCIs.