Validating a Meditation-based Mind Wandering BCI: A Pilot Study

Abstract

Brain-computer interfaces (BCI) have become a burgeoning field of research as computers become embedded in everyday life. Electroencephalography (EEG) is the preferred brain measurement device used in BCIs, though research- and medical-grade devices are prohibitively expensive. EEGs such as the Unicorn Hybrid Black (UHB) have entered the market as low-cost alternatives, albeit with electrode arrays of diminished density. The present study aims to assess the feasibility and usability of the UHB in BCI research and how it can or cannot be utilized as an accessible learning tool in academic, commercial, and public spheres. This was done by creating a BCI using the UHB and UHB Python API to assess various machine learning algorithms’ classification accuracy of a meditation paradigms that uses self-caught experience sampling to capture mind wandering. Key findings suggest that the UHB is a demonstrably effective tool within research and academic spheres; however, its feasibility within consumer-grade BCIs may be limited. The machine learning classification accuracy was deemed acceptable with the ridge classifier emerging as the algorithm of optimal performance.