Intelligent neural interface (NI) seeks to establish a direct communication pathway between the neural system and external devices by incorporating a variety of techniques in bioelectronics, biomechanics, biomaterials, and biosignal processing. It provides new perspectives to expand the application space of next-generation neurotechnology. For example, neural signal processing or decoding has been extensively investigated to enhance human-machine interaction for a variety of assistive devices including prosthetics and exoskeleton robotics. Such advances can aid people experiencing motor, sensory, or cognitive impairments due to disease, injury, or advanced aging. By helping regain their physical, psychological, or social functions, intelligent NI shows great promise in significantly improving the quality of life.
Despite considerable progress in NI in the last decades, there are still unmet challenges in its long-term clinical application. Typical issues include frequent model re-calibration, low signal-to-noise ratio, heavy computation load, poor portability, etc., which have drawn considerable attention in recent years due to their significant impacts on system accuracy, robustness, and generalization. Breakthroughs in the closed-loop NI are also urged to enhance the capability to assist, evolve, and grow with the user. Additionally, the comprehensive merging of domain knowledge in rehabilitation engineering and the biomedical sciences is essential. More recently, cutting-edge techniques have emerged in NI as the result of advances in artificial intelligence (AI). For instance, the combination of AI and NI has proved to be able to better decode electroencephalography (EEG) and electromyography (EMG) signals for intent recognition, movement control, rehabilitation evaluation, etc. Moreover, advances in mechatronics and materials, such as flexible sensors and soft robotics, will also benefit the application of NI in daily life.
This Research Topic focuses on theoretical and applied research on the neural interface that adopts innovations in bioelectronics, biomechanics, biomaterials, biosignal processing, etc. It aims to promote the development and application of human-machine interaction in both healthcare and rehabilitation. The Research Topic solicits the submission of different types of articles (e.g., Original Research, Brief Report, Review, Mini Review, Opinion, Perspective, etc.). Areas of interest for this Research Topic include, but are not limited to:
• Research on bioelectronics, biomechanics, and biomaterials in neural interfaces, such as innovations in biomedical circuits, sensing systems, prostheses, and exoskeleton robotics.
• Theoretical derivations, mathematical modeling, and algorithms for biosignal processing and robotic control.
• Design and application of neural interfaces for disease prediction, diagnosis, and prognosis.
• Multi-modal fusion strategies for precise analysis of neural information.
• Advanced approaches for rehabilitation quantification and evaluation, and techniques for objective outcome measures.
Intelligent neural interface (NI) seeks to establish a direct communication pathway between the neural system and external devices by incorporating a variety of techniques in bioelectronics, biomechanics, biomaterials, and biosignal processing. It provides new perspectives to expand the application space of next-generation neurotechnology. For example, neural signal processing or decoding has been extensively investigated to enhance human-machine interaction for a variety of assistive devices including prosthetics and exoskeleton robotics. Such advances can aid people experiencing motor, sensory, or cognitive impairments due to disease, injury, or advanced aging. By helping regain their physical, psychological, or social functions, intelligent NI shows great promise in significantly improving the quality of life.
Despite considerable progress in NI in the last decades, there are still unmet challenges in its long-term clinical application. Typical issues include frequent model re-calibration, low signal-to-noise ratio, heavy computation load, poor portability, etc., which have drawn considerable attention in recent years due to their significant impacts on system accuracy, robustness, and generalization. Breakthroughs in the closed-loop NI are also urged to enhance the capability to assist, evolve, and grow with the user. Additionally, the comprehensive merging of domain knowledge in rehabilitation engineering and the biomedical sciences is essential. More recently, cutting-edge techniques have emerged in NI as the result of advances in artificial intelligence (AI). For instance, the combination of AI and NI has proved to be able to better decode electroencephalography (EEG) and electromyography (EMG) signals for intent recognition, movement control, rehabilitation evaluation, etc. Moreover, advances in mechatronics and materials, such as flexible sensors and soft robotics, will also benefit the application of NI in daily life.
This Research Topic focuses on theoretical and applied research on the neural interface that adopts innovations in bioelectronics, biomechanics, biomaterials, biosignal processing, etc. It aims to promote the development and application of human-machine interaction in both healthcare and rehabilitation. The Research Topic solicits the submission of different types of articles (e.g., Original Research, Brief Report, Review, Mini Review, Opinion, Perspective, etc.). Areas of interest for this Research Topic include, but are not limited to:
• Research on bioelectronics, biomechanics, and biomaterials in neural interfaces, such as innovations in biomedical circuits, sensing systems, prostheses, and exoskeleton robotics.
• Theoretical derivations, mathematical modeling, and algorithms for biosignal processing and robotic control.
• Design and application of neural interfaces for disease prediction, diagnosis, and prognosis.
• Multi-modal fusion strategies for precise analysis of neural information.
• Advanced approaches for rehabilitation quantification and evaluation, and techniques for objective outcome measures.