BrainForm: a Serious Game for BCI Training and Data Collection

TL;DR

BrainForm addresses the calibration and variability barriers in ERP-based BCIs by delivering a gamified, scalable training and data-collection platform built on consumer hardware. Through two parallel tasks and a within-subject design, the study evaluates how BCI control skills evolve over repeated sessions and whether two stimulation textures differentially affect performance or fatigue. Findings show clear learning across runs and similar performance across textures, though ocular irritation increases with repeated exposure, and engagement remains high as evidenced by GEQ scores. This work demonstrates BrainForm’s potential as an accessible research tool for large-scale BCI data collection and provides design guidance for sustaining engagement while mitigating training fatigue.

Abstract

$\textit{BrainForm}$ is a gamified Brain-Computer Interface (BCI) training system designed for scalable data collection using consumer hardware and a minimal setup. We investigated (1) how users develop BCI control skills across repeated sessions and (2) perceptual and performance effects of two visual stimulation textures. Game Experience Questionnaire (GEQ) scores for Flow, Positive Affect, Competence and Challenge were strongly positive, indicating sustained engagement. A within-subject study with multiple runs, two task complexities, and post-session questionnaires revealed no significant performance differences between textures but increased ocular irritation over time. Online metrics$\unicode{x2013}$Task Accuracy, Task Time, and Information Transfer Rate$\unicode{x2013}$improved across sessions, confirming learning effects for symbol spelling, even under pressure conditions. Our results highlight the potential of $\textit{BrainForm}$ as a scalable, user-friendly BCI research tool and offer guidance for sustained engagement and reduced training fatigue.

Figures (5)

• Figure 1: An example of ERPs from the calibration sessions of a subject playing BrainForm. Calibrations trials are averaged across the session and highlighted in red:Target and blue:Non-Target.
• Figure 2: The experimental protocol of BrainForm. Runs included in the statistical analysis are highlighted in green. The numbers in white boxes represents the amount of flickering targets in the task.
• Figure 3: A) A participant taking part into the BrainForm experiment. B) Left: an example of the Complex Task; right: an example of the Speller Task. The color of the target is represented by the small symbol in the middle of the alien ships. The green outline provides real-time feedback on the spelled symbol. Targets flash sequentially for 100ms each.
• Figure 4: Results from post-session questionnaires: (a) Session questionnaires outcome and (b) In-Game GEQ scores.
• Figure 5: Trends of the ITR for repetition of Complex Task and repetitions of the Speller Task; $*$ marks $p_{smaller}$ than the reference run, as per Table \ref{['tbl:stat_results_4runs']}.