Profiling a Raspberry Pi-Based Motor Imagery Classification to Facilitate At-Home BCI for Children with Disabilities

There has been incremental progress in moving BCI out of the laboratory environment and into the homes of those who would benefit most, especially children living with severe physical disabilities. Practical issues, such as available computational resources and long calibration times, have slowed down the adoption of such systems. To develop an efficient and scalable machine learning framework consistent with early approaches that facilitate at-home BCI use, this study provides valuable insights into measuring the behavioral characteristics of a Raspberry Pi 4 (RPi4) during the operation and execution of standard BCI processes, including the training and evaluation of classifier models. The results, which evaluated ten standard classifiers, including the Riemannian Geometry (RG) framework and more advanced deep learning approaches like Artificial Neural Network (ANN), were profiled on RPi4. These were compared to Desktop and MacBook computations for metrics such as training time, inference time, peak memory, and incremental memory usage, with computational bottlenecks identified. Our assessment revealed comparable performance metrics (84.3% of accuracy, recall, and f1_score, and 84.7% precision) for the neural network models despite the lower computational resources. Profiling results, including 1.74 sec training time, 0.405 sec inference time, 1154.9 MiB peak memory, and 405.2 MiB incremental memory usage, also demonstrated that the RPi4 is a potentially viable device for low-cost BCI systems. However, high-resource demanding classifiers such as ANN may need to be carefully considered in their implementation, which, in turn, will scale down the potential cost and complexity of adopting practical, impactful at-home BCI systems.