A platform-independent open-source feedback framework for BCI systems

Abstract

This paper introduces the Pythonic Feedback Framework which provides a platform independent framework to develop BCI feedback applications in Python. It was designed to make the development of feedback applications as easy as possible. Existing solutions have either been implemented in C++, which makes the programming task rather tedious, especially for non-computer-scientists, or in Matlab, which is not well suited for more advanced visual (flickering is inavoidable which is unconfortable for the user and has side effects in the EEG) or auditory feedback applications. This framework solves this problem by moving the feedback implementations to a general purpose, and easy to learn language like Python. Python provides many so called bindings to other libraries, which allow it to develop high quality multimedia feedback applications, with little effort. The framework communicates with the rest of the BCI system via a standardized communication protocol using UDP and XML and is therefore suitable to be used with any BCI system that may be adapted to send its control signal via UDP in the specified format. Having such a general feedback framework will also foster a vivid exchange of feedback applications between BCI groups, even if individual system for processing and classification are used.