A novel hybrid paradigm based on steady state visually evoked potential & P300 to enhance information transfer rate. (May 2020)

• Record Type: Journal Article
• Authors: Katyal, Akshay; Singla, Rajesh
• Is Part Of: Biomedical signal processing and control. Volume 59(2020)
• Publication Date: 2020-05
• Subjects: P300 -- SSVEP -- Hybrid BCI -- ITR; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2020.101884
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Classification accuracy: The mean classification accuracy of Novel hBCI with distinct colours was 92.30%. ITR: The average ITR for 10 subjects was highest for SSVEP-P300 hBCI with distinct colours (82.38 bits/min.). FAR: Average FAR was reduced to 2.72 % for the Novel hBCI with distinct colours. Increased number of target tiers resulted in more targets for the same number of frequency as compared to traditional SSVEP BCI. Abstract: Background: Steady-State Visually Evoked Potential (SSVEP) has been one of the most common paradigms for Brain-Computer Interface (BCI) based applications with relatively good accuracy and Information Transfer Rate (ITR). However, limited decision options for a set number of paradigm frequencies, which is the main reason behind low ITR, is a huge hurdle the researchers have been facing in generalising SSVEP based BCI applications. New method: This paper proposes a novel hybrid Brain-Computer Interface (hBCI) stimuli paradigm to improve ITR by increasing the number of decision options available for SSVEP BCI by introducing P300 as a Time Division Multiplexing (TDM) marker. One of the Hybrid BCI's used distinct colours along with distinct flickering frequencies for targets, with an aim to improve the performance of the BCI based on the accuracy of classification, the elevation of ITR and reduction of FAR as compared to traditional BCIs. Results: It was established that the Novel SSVEP-P300 with distinct colours for target frequencies hybrid BCI had average parameters as following: classification accuracy of 92.30 %, ITR of 82.38 bits/min and FAR of 2.72 %. Comparison: A comparative study between the two novel paradigms, traditional SSVEP and P300 paradigms in the same environment was conducted. And a statistical inference was established sussing paired t -tests. Conclusion: The results of the comparative study were conclusive that the hybrid BCI with distinct colours for each target frequency yielded best results and hence can be considered as a viable paradigm option for the development of an Assistive Device.