Single-trial detection of motor related potentials for use in a direct brain interface for persons with severe disabilities

点击翻译按钮获取中文摘要

The ultimate goal of this research is to create an advanced personal control interface that will allow an individual with a high-level disability to control a device such as a robotic arm or a computer with signals recorded directly from their brain. This type of Brain-Computer Interface (BCI) will allow individuals with even the highest levels of disability to use existing and emerging technical aids, thus increasing their independence and leading to an improved quality of life and reduced social costs.   The concept of a BCI has emerged over the last two decades. In our approach, a user generates a control signal by consciously changing his or her cognitive state when he or she wants to control the device. The change in cognitive state is measured as a specific pattern in electrical activity on the user's scalp. The BCI system monitors the user's brain signals, detects the presence of control signals, decides which control signal was generated by the user and then forwards the control instruction on to the device being controlled.     Work to date on this approach to a BCI switch has produced promising results. Our findings suggest that individuals with high-level spinal-cord injuries and able-bodied people can control the switch, although there are many outstanding issues that need to be addressed. We will study methods to improve the switch activation accuracy through new signal processing and switch customization methods, expand the bandwidth and functionality of our switch, and explore methods to reduce contaminating signals that interfere with the performance.