The neural signal contains rich physiological and pathological information, and its acquisition and intelligent analysis contribute to the development of psychology, biology, cognitive neuroscience, and clinical medicine. As neural signals can be recorded and analyzed using a variety of techniques, traditional versions of the acquisition techniques include the Electroencephalograph (EEG), Magneto-encephalograph (MEG), functional Magnetic Resonance Imaging (fMRI), Computed Tomography (CT), and others. Technological advances have now produced a new generation of devices and systems designed to assist in signal acquisition, signal processing, or provide neural feedback to humans. In addition, extracted brain information is used to understand the mechanisms of brain activities, cognitive functions, and cognitive impairment.
On the other hand, machine deep learning methods are increasingly popular and applied in neuroscience. They have the potential to reveal interactions, hidden patterns of abnormal activity, brain structure and connectivity, and physiological mechanisms of the brain and behavior. A major limitation of intelligent analysis research is associated with the controversy surrounding the use of standards and interpretable analytics of data. Therefore, deep learning framework in neuroscience focus more on interpretability.
This Research Topic aims to build a bridge between two scientific communities, the community of advanced brain signals acquisition method and the community of machine learning, including chief scientists in deep learning and related areas within pattern recognition and artificial intelligence. Interactions between these communities are expected to play the most relevant role in the diagnosis, monitoring, and treatment of neurological disorders, and restore their lost function. Therefore, a special topic is organized to publish original, innovative, and state-of-the-art devices and algorithms in neuroscience.
Topics covered include, but are not limited to:
• Brain signal acquisition and application
• Brain-computer interface
• Neuroimaging
• Cognitive computing
• Physiological measurement
• Artificial intelligence
• Clinical application
The neural signal contains rich physiological and pathological information, and its acquisition and intelligent analysis contribute to the development of psychology, biology, cognitive neuroscience, and clinical medicine. As neural signals can be recorded and analyzed using a variety of techniques, traditional versions of the acquisition techniques include the Electroencephalograph (EEG), Magneto-encephalograph (MEG), functional Magnetic Resonance Imaging (fMRI), Computed Tomography (CT), and others. Technological advances have now produced a new generation of devices and systems designed to assist in signal acquisition, signal processing, or provide neural feedback to humans. In addition, extracted brain information is used to understand the mechanisms of brain activities, cognitive functions, and cognitive impairment.
On the other hand, machine deep learning methods are increasingly popular and applied in neuroscience. They have the potential to reveal interactions, hidden patterns of abnormal activity, brain structure and connectivity, and physiological mechanisms of the brain and behavior. A major limitation of intelligent analysis research is associated with the controversy surrounding the use of standards and interpretable analytics of data. Therefore, deep learning framework in neuroscience focus more on interpretability.
This Research Topic aims to build a bridge between two scientific communities, the community of advanced brain signals acquisition method and the community of machine learning, including chief scientists in deep learning and related areas within pattern recognition and artificial intelligence. Interactions between these communities are expected to play the most relevant role in the diagnosis, monitoring, and treatment of neurological disorders, and restore their lost function. Therefore, a special topic is organized to publish original, innovative, and state-of-the-art devices and algorithms in neuroscience.
Topics covered include, but are not limited to:
• Brain signal acquisition and application
• Brain-computer interface
• Neuroimaging
• Cognitive computing
• Physiological measurement
• Artificial intelligence
• Clinical application