A Robust Driver Assessment Method for the Brain-computer Interface

Brain-computer interfaces (BCI) are a valuable proposition for the long-term vision of the automotive human-machine interfaces and for increasing the personal mobility of users with physical disabilities. In this work, we do not attempt to improve the vehicle control through a BCI. Instead, we focus on assessing the driver’s fatigue using a non-invasive BCI technology, a mobile electroencephalograph (EEG). Noninvasive EEG-based approaches for driver assessment often rely on the independent components analysis (ICA) and measure the relative power of specific EEG frequency bands. In the case of wireless and mobile EEG devices, especially outside the domain of medical-grade electronics, a higher number of artifacts and lower channel count can be expected. Main priorities for such devices are ergonomics and usability, with signal quality and robustness on the second place. Such devices significantly simplify experiment design and data collection in automobile simulators and real test-drives. This work presents a robust two-step EEG signal processing method for driver assessment for a consumer-grade EEG BCI, which collects artifact-rich data using a limited number of low-quality saline-pad electrodes. We demonstrate that a reliable assessment of driver state in such conditions is possible, if the independent component analysis is extended through an expert system-based assessment of reliable signal components in a specific region-of-interest on the brain surface. The method additionally eliminates the need for manual artifact removal. We show that the lower sensor count, lower sensor quality and mechanical vibrations can be offset through additional signal processing. We additionally show that the data collected by the BCI provides additional value to the driver assistance, meaning that BCIs can serve both as a human-machine interface and a driver assistance system.