EEG-based Brain-Computer Interfaces (BCIs): A Survey of Recent Studies on Signal Sensing Technologies and Computational Intelligence Approaches and their Applications

Brain-Computer Interface (BCI) is a powerful communication tool between users\nand systems, which enhances the capability of the human brain in communicating\nand interacting with the environment directly. Advances in neuroscience and\ncomputer science in the past decades have led to exciting developments in BCI,\nthereby making BCI a top interdisciplinary research area in computational\nneuroscience and intelligence. Recent technological advances such as wearable\nsensing devices, real-time data streaming, machine learning, and deep learning\napproaches have increased interest in electroencephalographic (EEG) based BCI\nfor translational and healthcare applications. Many people benefit from\nEEG-based BCIs, which facilitate continuous monitoring of fluctuations in\ncognitive states under monotonous tasks in the workplace or at home. In this\nstudy, we survey the recent literature of EEG signal sensing technologies and\ncomputational intelligence approaches in BCI applications, compensated for the\ngaps in the systematic summary of the past five years (2015-2019). In specific,\nwe first review the current status of BCI and its significant obstacles. Then,\nwe present advanced signal sensing and enhancement technologies to collect and\nclean EEG signals, respectively. Furthermore, we demonstrate state-of-art\ncomputational intelligence techniques, including interpretable fuzzy models,\ntransfer learning, deep learning, and combinations, to monitor, maintain, or\ntrack human cognitive states and operating performance in prevalent\napplications. Finally, we deliver a couple of innovative BCI-inspired\nhealthcare applications and discuss some future research directions in\nEEG-based BCIs.\n