An innovative P300 speller brain–computer interface design: Easy screen

• Published in: Biomedical signal processing and control 2022-05, Vol.75, p.103593, Article 103593
• Main Authors: Bilal Aygün, Abdullah, Reşit Kavsaoğlu, Ahmet
• Format: Article
• Language: English
• Subjects: Brain–computer interface; Electroencephalogram (EEG); Event related potential; P300 speller; Visual stimulus; Word-typing paradigm
• ISSN: 1746-8094; 1746-8108
• DOI: 10.1016/j.bspc.2022.103593

•An innovative 7x7 size visual stimulus matrix with alphabetic characters and shortcut characters was designed.•Subjects were monitored during 25 runs to generate a classifier model during the offline analysis, which subjects focused on each area of the interface’s matrix.•In the online study on 30 healthy subjects, an average of 28.37 correct characters out of 30 were identified.•After the first detected alphabetic character, one of the 20 words suggested can be directly printed on the screen.•Each of the 30 subjects was able to correctly print 10 words directly on the screen. P300 spellers are brain–computer interfaces (BCIs) that display desired characters, once at a time, on a screen through the detection of P300 event-related potentials (ERPs) generated in response to flashing visual stimuli using classification methods to determine desired outcomes. Individual words can also be displayed, rather than the letter-by-letter display typical of P300 spellers. An innovative interface using a 7 × 7 letters visual stimulus matrix was designed, as the Easy Screen P300 Speller. In addition to alphabetic characters, 20 shortcut elements (E1–E20) can be used to display words directly on the screen. After first one or more letters of a desired word are determined, 20 words are formed in the word list. If the selection of a shortcut element is detected, the word corresponding to that element is displayed on the screen. An innovative P300 speller BCI was tested for 19 men and 11 women. Offline, online, and word typing studies were performed using the designed interface. During online analysis, on average, each subject focused on 28.37 of 30 characters. Each subject was asked to display 10 words pre-selected according to the subjects' wishes using the Easy Screen P300 Speller. The same word could be displayed in an average of 1.31 min using the Easy Screen P300 Speller compared with 4.53 min using a conventional P300 speller. This paper uncovers upper results in terms of character detection accuracy and Output Characters per Minute (OCM) value across word-typing interfaces than state-of-the-art.