Autonomic Architectural Framework for Internet of Brain Controlled Things (IoBCT)

Brain Machine Interface (BMI) involves the acquisition and analysis of brainwave signals and translating them into commands that can be relayed to control devices in order to achieve a desired action. With the wide adoption of smart objects realized by the Internet of Things (IoT) and wearable technology across applications and industries, one can envision how BMI can empower users to control such objects (i.e.: home appliances, alert systems, or assistive robots), via their thoughts. However, the implementation of a practical BMI-based IoT system is faced with several challenges, most importantly being the issue of accurately translating the user’s intention which is derived from the raw brainwave signals. Such translations are often enabled by computationally heavy algorithms which require a larger computing system. Thus, a new strategy and process flow for a concrete and resilient framework over which a BMI-IoT solution is built will be needed. In this paper, a novel system architecture based on Edge computing is proposed for controlling BMI-IoT enabled environments. The proposed simplified and versatile architecture is aimed at helping the designer articulate the key functions and elements of BMI-based IoT system which we call “Internet of Brain Controlled Things (IoBCT).